Search

Cluster randomized trials (CRTs) often enroll large numbers of participants; yet due to resource constraints, only a subset of participants may be selected for outcome assessment, and those sampled may not be representative of all cluster members. Missing data also present a challenge: if sampled individuals with measured outcomes are dissimilar from those with missing outcomes, unadjusted estimates of arm-specific endpoints and the intervention effect may be biased. Further, CRTs often enroll and randomize few clusters, limiting statistical power and raising concerns about finite sample performance. Motivated by SEARCH-TB, a CRT aimed at reducing incident tuberculosis infection, we demonstrate interlocking methods to handle these challenges. First, we extend Two-Stage targeted minimum loss-based estimation to account for three sources of missingness: (i) subsampling; (ii) measurement of baseline status among those sampled; and (iii) measurement of final status among those in the incidence cohort (persons known to be at risk at baseline). Second, we critically evaluate the assumptions under which subunits of the cluster can be considered the conditionally independent unit, improving precision and statistical power but also causing the CRT to behave like an observational study. Our application to SEARCH-TB highlights the real-world impact of different assumptions on measurement and dependence; estimates relying on unrealistic assumptions suggested the intervention increased the incidence of TB infection by 18% (risk ratio [RR]=1.18, 95% confidence interval [CI]: 0.85-1.63), while estimates accounting for the sampling scheme, missingness, and within community dependence found the intervention decreased the incident TB by 27% (RR=0.73, 95% CI: 0.57-0.92).

Leukemia is a form of cancer that affects the bone marrow and lymphatic system, and it requires complex treatment strategies that vary with each subtype. Due to the subtle morphological differences among these types, monitoring gene expressions is crucial for accurate classification. Manual or pathological testing can be time-consuming and expensive. Therefore, data-driven methods and machine learning algorithms offer an efficient alternative for leukemia classification. This study introduced a novel super learning model that leverages heterogeneous machine learning models to analyze gene expression data and classify leukemia cells. The proposed approach incorporates an entropy-based feature importance technique to identify the gene profiles most significant to the labeling process. The strength of this super learning model lies in its final super learner, Random Forest, which effectively classifies cross-validated data from the candidate learners. Validation on a gene expression monitoring dataset demonstrates that this model outperforms other state-of-the-art models in predictive accuracy. The study contributes to the knowledge regarding the use of advanced machine learning techniques to improve the accuracy and reliability of leukemia classification using gene expression data, addressing the challenges of traditional methods that rely on clinical features and morphological examination. [ABSTRACT FROM AUTHOR]

The importance of technology and managerial risk management in banks has increased due to the financial crisis. Banks are the most affected since there are so many of them with poor financial standing. Due to this problem, an unstable and inefficient financial system causes economic stagnation in both the banking sector and overall economy. Data envelopment analysis (DEA) has been used to examine decision-making units (DMUs) performance to enhance efficiency. Currently, with the rapid growth of big data, adding more DMUs will likely require a large amount of memory and CPU time on the computer system, which will be the biggest challenge. As a result, machine learning (ML) approaches have been used to analyze financial institution performance, but many of them have variances in predictions or model stability, making measuring bank efficiency extremely difficult. For this, ensemble learning is commonly used to evaluate the performance of financial institutions in this context. This paper presents a robust super learner ensemble technique for assessing bank efficiency, with four machine learning models serving as base learners. These models are the support vector machine (SVM), K-nearest neighbors (KNN), random forest (RF), and AdaBoost classifier (ADA) which represent the base learners and their results utilized to train the meta-learner. The super learner (SL) approach is an extension of the stacking technique, which generates an ensemble based on cross-validation. One important benefit of this cross-validation theory-based technique is that it can overcome the overfitting issue that plagues most other ensemble approaches. When SL and base learners were compared for their forecasting abilities using different statistical standards, the results showed that the SL is superior to the base learners, where different variable combinations were used. The SL had accuracy (ACC) of 0.8636–0.9545 and F1-score (F1) of 0.9143–0.9714, while the basic learners had ACC of 0.5909–0.8182 and F1 of 0.6897–0.9143. So, SL is highly recommended for improving the accuracy of financial data forecasts, even with limited financial data. [ABSTRACT FROM AUTHOR]

ABSTRACT Aim Innovation Main Conclusions Species distribution models (SDMs) are powerful tools for assessing suitable habitats across large areas and at fine spatial resolution. Yet, the usefulness of SDMs for mapping species' realised distributions is often limited since data biases or missing information on dispersal barriers or biotic interactions hinder them from accurately delineating species' range limits. One way to overcome this limitation is to integrate SDMs with expert range maps, which provide coarse‐scale information on the extent of species' ranges and thereby range limits that are complementary to information offered by SDMs.Here, we propose a new approach for integrating expert range maps in SDMs based on an ensemble method called stacked generalisation. Specifically, our approach relies on training a meta‐learner regression model using predictions from one or more SDM algorithms alongside the distance of training points to expert‐defined ranges as predictor variables. We demonstrate our approach with an occurrence dataset for 49 bat species covering four biodiversity hotspots in the Eastern Mediterranean, Western Asia and Central Asia.Our approach offers a flexible method to integrate expert range maps with any combination of SDM modelling algorithms, thus facilitating the use of algorithm ensembles. In addition, it provides a novel, data‐driven way to account for uncertainty in expert‐defined ranges not requiring prior knowledge about their accuracy, which is often lacking. Integrating expert range maps into SDMs for bats resulted in more realistic predictions of distribution patterns that showed narrower niche breadths and smaller range overlaps between species compared to traditional SDMs. Our approach holds promise to improve assessments of species distributions, while our work highlights the overlooked potential of stacked generalisation as an ensemble method in species distribution modelling. [ABSTRACT FROM AUTHOR]

Cardio Vascular Diseases (CVD) has become a serious concern for humans as fatalities rate due to CVD are increasing at an alarming pace. With the aid of machine learning techniques, heart illnesses can be predicted much earlier, and therapy or dietary changes can prevent deaths. By combining predictions from various individual models, the machine learning technique known as ensemble learning improves forecasting accuracy and resiliency. In this work, a Super Learner Ensemble Model is used where the base learners are a diverse combination of linear, probabilistic, bagging, boosting and stacking models. To improve the performance of the Super Learner Ensemble Model, an Optimized Super Learner Ensemble Model (OSLEM) is proposed, where optimal selection of base learners in the ensemble is done based on the pairwise disagreement accuracy diversity measure of classifiers in each best fitness whale obtained by different iterations of Whale Optimization Algorithm (WOA). ModifiedBoostARoota (MBAR), a wrapper feature selection technique is used to choose the most significant features of six different heart datasets and the proposed OSLEM modelled on the selected features exhibits high performance compared to other existing ensemble models. [ABSTRACT FROM AUTHOR]

Abstract Leukemia is a form of cancer that affects the bone marrow and lymphatic system, and it requires complex treatment strategies that vary with each subtype. Due to the subtle morphological differences among these types, monitoring gene expressions is crucial for accurate classification. Manual or pathological testing can be time-consuming and expensive. Therefore, data-driven methods and machine learning algorithms offer an efficient alternative for leukemia classification. This study introduced a novel super learning model that leverages heterogeneous machine learning models to analyze gene expression data and classify leukemia cells. The proposed approach incorporates an entropy-based feature importance technique to identify the gene profiles most significant to the labeling process. The strength of this super learning model lies in its final super learner, Random Forest, which effectively classifies cross-validated data from the candidate learners. Validation on a gene expression monitoring dataset demonstrates that this model outperforms other state-of-the-art models in predictive accuracy. The study contributes to the knowledge regarding the use of advanced machine learning techniques to improve the accuracy and reliability of leukemia classification using gene expression data, addressing the challenges of traditional methods that rely on clinical features and morphological examination.

BACKGROUND: In suspected myocardial infarction (MI), guidelines recommend using high-sensitivity cardiac troponin (hs-cTn)-based approaches. These require fixed assay-specific thresholds and timepoints, without directly integrating clinical information. Using machine-learning techniques including hs-cTn and clinical routine variables, we aimed to build a digital tool to directly estimate the individual probability of MI, allowing for numerous hs-cTn assays. METHODS: In 2,575 patients presenting to the emergency department with suspected MI, two ensembles of machine-learning models using single or serial concentrations of six different hs-cTn assays were derived to estimate the individual MI probability (ARTEMIS model). Discriminative performance of the models was assessed using area under the receiver operating characteristic curve (AUC) and logLoss. Model performance was validated in an external cohort with 1688 patients and tested for global generalizability in 13 international cohorts with 23,411 patients. RESULTS: Eleven routinely available variables including age, sex, cardiovascular risk factors, electrocardiography, and hs-cTn were included in the ARTEMIS models. In the validation and generalization cohorts, excellent discriminative performance was confirmed, superior to hs-cTn only. For the serial hs-cTn measurement model, AUC ranged from 0.92 to 0.98. Good calibration was observed. Using a single hs-cTn measurement, the ARTEMIS model allowed direct rule-out of MI with very high and similar safety but up to tripled efficiency compared to the guideline-recommended strategy. CONCLUSION: We developed and validated diagnostic models to accurately estimate the individual probability of MI, which allow for variable hs-cTn use and flexible timing of resampling. Their digital application may provide rapid, safe and efficient personalized patient care. TRIAL REGISTRATION NUMBERS: Data of following cohorts were used for this project: BACC ( www. CLINICALTRIALS: gov ; NCT02355457), stenoCardia ( www. CLINICALTRIALS: gov ; NCT03227159), ADAPT-BSN ( www.australianclinicaltrials.gov.au ; ACTRN12611001069943), IMPACT ( www.australianclinicaltrials.gov.au , ACTRN12611000206921), ADAPT-RCT ( www.anzctr.org.au ; ANZCTR12610000766011), EDACS-RCT ( www.anzctr.org.au ; ANZCTR12613000745741); DROP-ACS ( https://www.umin.ac.jp , UMIN000030668); High-STEACS ( www. CLINICALTRIALS: gov ; NCT01852123), LUND ( www. CLINICALTRIALS: gov ; NCT05484544), RAPID-CPU ( www. CLINICALTRIALS: gov ; NCT03111862), ROMI ( www. CLINICALTRIALS: gov ; NCT01994577), SAMIE ( https://anzctr.org.au ; ACTRN12621000053820), SEIGE and SAFETY ( www. CLINICALTRIALS: gov ; NCT04772157), STOP-CP ( www. CLINICALTRIALS: gov ; NCT02984436), UTROPIA ( www. CLINICALTRIALS: gov ; NCT02060760).

Cluster randomized trials (CRTs) randomly assign an intervention to groups of individuals (e.g., clinics or communities) and measure outcomes on individuals in those groups. While offering many advantages, this experimental design introduces challenges that are only partially addressed by existing analytic approaches. First, outcomes are often missing for some individuals within clusters. Failing to appropriately adjust for differential outcome measurement can result in biased estimates and inference. Second, CRTs often randomize limited numbers of clusters, resulting in chance imbalances on baseline outcome predictors between arms. Failing to adaptively adjust for these imbalances and other predictive covariates can result in efficiency losses. To address these methodological gaps, we propose and evaluate a novel two-stage targeted minimum loss-based estimator to adjust for baseline covariates in a manner that optimizes precision, after controlling for baseline and postbaseline causes of missing outcomes. Finite sample simulations illustrate that our approach can nearly eliminate bias due to differential outcome measurement, while existing CRT estimators yield misleading results and inferences. Application to real data from the SEARCH community randomized trial demonstrates the gains in efficiency afforded through adaptive adjustment for baseline covariates, after controlling for missingness on individual-level outcomes.

Abstract Background & aim Cardiovascular disease (CVD) is the most important cause of death in the world and has a potential impact on health care costs, this study aimed to evaluate the performance of machine learning survival models and determine the optimum model for predicting CVD-related mortality. Method In this study, the research population was all participants in Tehran Lipid and Glucose Study (TLGS) aged over 30 years. We used the Gradient Boosting model (GBM), Support Vector Machine (SVM), Super Learner (SL), and Cox proportional hazard (Cox-PH) models to predict the CVD-related mortality using 26 features. The dataset was randomly divided into training (80%) and testing (20%). To evaluate the performance of the methods, we used the Brier Score (BS), Prediction Error (PE), Concordance Index (C-index), and time-dependent Area Under the Curve (TD-AUC) criteria. Four different clinical models were also performed to improve the performance of the methods. Results Out of 9258 participants with a mean age of (SD; range) 43.74 (15.51; 20–91), 56.60% were female. The CVD death proportion was 2.5% (228 participants). The death proportion was significantly higher in men (67.98% M, 32.02% F). Based on predefined selection criteria, the SL method has the best performance in predicting CVD-related mortality (TD-AUC > 93.50%). Among the machine learning (ML) methods, The SVM has the worst performance (TD-AUC = 90.13%). According to the relative effect, age, fasting blood sugar, systolic blood pressure, smoking, taking aspirin, diastolic blood pressure, Type 2 diabetes mellitus, hip circumference, body mss index (BMI), and triglyceride were identified as the most influential variables in predicting CVD-related mortality. Conclusion According to the results of our study, compared to the Cox-PH model, Machine Learning models showed promising and sometimes better performance in predicting CVD-related mortality. This finding is based on the analysis of a large and diverse urban population from Tehran, Iran.

Abstract Background The primary treatment for patients with myocardial infarction (MI) is percutaneous coronary intervention (PCI). Despite this, the incidence of major adverse cardiovascular events (MACEs) remains a significant concern. Our study seeks to optimize PCI predictive modeling by employing an ensemble learning approach to identify the most effective combination of predictive variables. Methods and results We conducted a retrospective, non-interventional analysis of MI patient data from 2018 to 2021, focusing on those who underwent PCI. Our principal metric was the occurrence of 1-year postoperative MACEs. Variable selection was performed using lasso regression, and predictive models were developed using the Super Learner (SL) algorithm. Model performance was appraised by the area under the receiver operating characteristic curve (AUC) and the average precision (AP) score. Our cohort included 3,880 PCI patients, with 475 (12.2%) experiencing MACEs within one year. The SL model exhibited superior discriminative performance, achieving a validated AUC of 0.982 and an AP of 0.971, which markedly surpassed the traditional logistic regression models (AUC: 0.826, AP: 0.626) in the test cohort. Thirteen variables were significantly associated with the occurrence of 1-year MACEs. Conclusion Implementing the Super Learner algorithm has substantially enhanced the predictive accuracy for the risk of MACEs in MI patients. This advancement presents a promising tool for clinicians to craft individualized, data-driven interventions to better patient outcomes.

Recent evidence shows the highest prevalence of multidimensional poverty in the world. To alleviate poverty, Ethiopia is investing in stimulating agricultural commercialization for poverty reduction, driving sustainable economic growth, and creating jobs. Therefore, this study investigated the causal relationship between crop commercialization and multidimensional poverty across Ethiopian rural households using the Ethiopia Socioeconomic Survey 2018/19 data, which included 1129 crop commercialized and 1585 completely subsistence rural households. Moreover, this study also examined the causal effect of crop commercialization on the multidimensional poverty mediated by mobile phone ownership status. The study used the double robust method of the augmented inverse probability of treatment weighted (AIPTW) and targeted maximum likelihood estimation (TMLE) methods. The result showed that crop commercialization has an association with multidimensional poverty. Specifically, the TMLE with a default super learner model estimates were the most precise and suggest that the prevalence of risk of being multidimensionally poor among rural households who were crop commercialized is 12.2 % lower than for those who were completely subsistence households. Thus, it is important to have more robust policies like crop commercialization to target rural multidimensional poverty reduction. Moreover, the controlled direct effect estimation analyses showed that crop-commercialized rural households reduced the adjusted risk of multidimensional poverty by; 12 % for those who owned mobile phones and 7.8 % for those who did not. To ensure sustainable livelihoods for rural multidimensional poor households, it is necessary to have a multidisciplinary policy intervention to promote crop commercialization through the spread of mobile phones in rural areas.

Background & aim: Cardiovascular disease (CVD) is the most important cause of death in the world and has a potential impact on health care costs, this study aimed to evaluate the performance of machine learning survival models and determine the optimum model for predicting CVD-related mortality. Method: In this study, the research population was all participants in Tehran Lipid and Glucose Study (TLGS) aged over 30 years. We used the Gradient Boosting model (GBM), Support Vector Machine (SVM), Super Learner (SL), and Cox proportional hazard (Cox-PH) models to predict the CVD-related mortality using 26 features. The dataset was randomly divided into training (80%) and testing (20%). To evaluate the performance of the methods, we used the Brier Score (BS), Prediction Error (PE), Concordance Index (C-index), and time-dependent Area Under the Curve (TD-AUC) criteria. Four different clinical models were also performed to improve the performance of the methods. Results: Out of 9258 participants with a mean age of (SD; range) 43.74 (15.51; 20–91), 56.60% were female. The CVD death proportion was 2.5% (228 participants). The death proportion was significantly higher in men (67.98% M, 32.02% F). Based on predefined selection criteria, the SL method has the best performance in predicting CVD-related mortality (TD-AUC > 93.50%). Among the machine learning (ML) methods, The SVM has the worst performance (TD-AUC = 90.13%). According to the relative effect, age, fasting blood sugar, systolic blood pressure, smoking, taking aspirin, diastolic blood pressure, Type 2 diabetes mellitus, hip circumference, body mss index (BMI), and triglyceride were identified as the most influential variables in predicting CVD-related mortality. Conclusion: According to the results of our study, compared to the Cox-PH model, Machine Learning models showed promising and sometimes better performance in predicting CVD-related mortality. This finding is based on the analysis of a large and diverse urban population from Tehran, Iran. [ABSTRACT FROM AUTHOR]

Background: The primary treatment for patients with myocardial infarction (MI) is percutaneous coronary intervention (PCI). Despite this, the incidence of major adverse cardiovascular events (MACEs) remains a significant concern. Our study seeks to optimize PCI predictive modeling by employing an ensemble learning approach to identify the most effective combination of predictive variables. Methods and results: We conducted a retrospective, non-interventional analysis of MI patient data from 2018 to 2021, focusing on those who underwent PCI. Our principal metric was the occurrence of 1-year postoperative MACEs. Variable selection was performed using lasso regression, and predictive models were developed using the Super Learner (SL) algorithm. Model performance was appraised by the area under the receiver operating characteristic curve (AUC) and the average precision (AP) score. Our cohort included 3,880 PCI patients, with 475 (12.2%) experiencing MACEs within one year. The SL model exhibited superior discriminative performance, achieving a validated AUC of 0.982 and an AP of 0.971, which markedly surpassed the traditional logistic regression models (AUC: 0.826, AP: 0.626) in the test cohort. Thirteen variables were significantly associated with the occurrence of 1-year MACEs. Conclusion: Implementing the Super Learner algorithm has substantially enhanced the predictive accuracy for the risk of MACEs in MI patients. This advancement presents a promising tool for clinicians to craft individualized, data-driven interventions to better patient outcomes. [ABSTRACT FROM AUTHOR]

Background: Drug overdose persists as a leading cause of death in the United States, but resources to address it remain limited. As a result, health authorities must consider where to allocate scarce resources within their jurisdictions. Machine learning offers a strategy to identify areas with increased future overdose risk to proactively allocate overdose prevention resources. This modeling study is embedded in a randomized trial to measure the effect of proactive resource allocation on statewide overdose rates in Rhode Island (RI). Methods: We used statewide data from RI from 2016 to 2020 to develop an ensemble machine learning model predicting neighborhoodlevel fatal overdose risk. Our ensemble model integrated gradient boosting machine and super learner base models in a moving window framework to make predictions in 6-month intervals. Our performance target, developed a priori with the RI Department of Health, was to identify the 20% of RI neighborhoods containing at least 40% of statewide overdose deaths, including at least one neighborhood per municipality. The model was validated after trial launch. Results: Our model selected priority neighborhoods capturing 40.2% of statewide overdose deaths during the test periods and 44.1% of statewide overdose deaths during validation periods. Our ensemble outperformed the base models during the test periods and performed comparably to the best-performing base model during the validation periods. Conclusions: We demonstrated the capacity for machine learning models to predict neighborhood-level fatal overdose risk to a degree of accuracy suitable for practitioners. Jurisdictions may consider predictive modeling as a tool to guide allocation of scarce resources. [ABSTRACT FROM AUTHOR]

Load-shedding is vital for managing electrical power shortages and avoiding grid collapse. However, excessive electricity demand poses an imminent threat to the overall stability of power grid system (PGS) and its ability to run safely and reliably. Load-shedding strategies can be complicated and inadequate to manage electrical power system efficiently. The study proposed a data-driven load-shedding time series classification (TSC) technique employing a heterogeneous ensemble super learner (eSL) to categorize load-shedding based on contributing features. The model investigated challenges with binary classification while using a multidimensional time series for South Africa’s hourly load-shedding stages in MWcollected from PGS data. Considering that load-shedding is planned and predicted based on contributing features, we use these features as strong indicators to classify expected outcomes for load-shedding or no load-shedding. Validation tests for the suggested technique included the precision recall curve, the confusion matrix, the class likelihood ratio, the Brier skill scores and critical difference factor (CDF). Logistic regression (LR) produced the highest CDF average score, while support vector classifier (SVC) had the highest balanced precision (90.694%). The recursive feature elimination (RFE) model exhibited the most significant true negative and true positive counts, at 50.59% and 40.84%, respectively, and the highest proportion of valid classifications.

Abstract Background Nowadays, the chance of discovering the best antibody candidates for predicting clinical malaria has notably increased due to the availability of multi-sera data. The analysis of these data is typically divided into a feature selection phase followed by a predictive one where several models are constructed for predicting the outcome of interest. A key question in the analysis is to determine which antibodies should be included in the predictive stage and whether they should be included in the original or a transformed scale (i.e. binary/dichotomized). Methods To answer this question, we developed three approaches for antibody selection in the context of predicting clinical malaria: (i) a basic and simple approach based on selecting antibodies via the nonparametric Mann–Whitney-Wilcoxon test; (ii) an optimal dychotomizationdichotomization approach where each antibody was selected according to the optimal cut-off via maximization of the chi-squared (χ2) statistic for two-way tables; (iii) a hybrid parametric/non-parametric approach that integrates Box-Cox transformation followed by a t-test, together with the use of finite mixture models and the Mann–Whitney-Wilcoxon test as a last resort. We illustrated the application of these three approaches with published serological data of 36 Plasmodium falciparum antigens for predicting clinical malaria in 121 Kenyan children. The predictive analysis was based on a Super Learner where predictions from multiple classifiers including the Random Forest were pooled together. Results Our results led to almost similar areas under the Receiver Operating Characteristic curves of 0.72 (95% CI = [0.62, 0.82]), 0.80 (95% CI = [0.71, 0.89]), 0.79 (95% CI = [0.7, 0.88]) for the simple, dichotomization and hybrid approaches, respectively. These approaches were based on 6, 20, and 16 antibodies, respectively. Conclusions The three feature selection strategies provided a better predictive performance of the outcome when compared to the previous results relying on Random Forest including all the 36 antibodies (AUC = 0.68, 95% CI = [0.57;0.79]). Given the similar predictive performance, we recommended that the three strategies should be used in conjunction in the same data set and selected according to their complexity.

The green concretes industry benefits from utilizing gel to replace parts of the cement in concretes. However, measuring the compressive strength of geo-polymer concretes (CSGPoC) needs a significant amount of work and expenditure. Therefore, the best idea is predicting CSGPoC with a high level of accuracy. To do this, the base learner and super learner machine learning models were proposed in this study to anticipate CSGPoC. The decision tree (DT) is applied as base learner, and the random forest and extreme gradient boosting (XGBoost) techniques are used as super learner system. In this regard, a database was provided involving 259 CSGPoC data samples, of which four-fifths of is considered for the training model and one-fifth is selected for the testing models. The values of fly ash, ground-granulated blast-furnace slag (GGBS), Na2SiO3, NaOH, fine aggregate, gravel 4/10 mm, gravel 10/20 mm, water/solids ratio, and NaOH molarity were considered as input of the models to estimate CSGPoC. To evaluate the reliability and performance of the decision tree (DT), XGBoost, and random forest (RF) models, 12 performance evaluation metrics were determined. Based on the obtained results, the highest degree of accuracy is achieved by the XGBoost model with mean absolute error (MAE) of 2.073, mean absolute percentage error (MAPE) of 5.547, Nash–Sutcliffe (NS) of 0.981, correlation coefficient (R) of 0.991, R2 of 0.982, root mean square error (RMSE) of 2.458, Willmott's index (WI) of 0.795, weighted mean absolute percentage error (WMAPE) of 0.046, Bias of 2.073, square index (SI) of 0.054, p of 0.027, mean relative error (MRE) of -0.014, and a20 of 0.983 for the training model and MAE of 2.06, MAPE of 6.553, NS of 0.985, R of 0.993, R2 of 0.986, RMSE of 2.307, WI of 0.818, WMAPE of 0.05, Bias of 2.06, SI of 0.056, p of 0.028, MRE of -0.015, and a20 of 0.949 for the testing model. By importing the testing set into trained models, values of 0.8969, 0.9857, and 0.9424 for R2 were obtained for DT, XGBoost, and RF, respectively, which show the superiority of the XGBoost model in CSGPoC estimation. In conclusion, the XGBoost model is capable of more accurately predicting CSGPoC than DT and RF models.

Accurate reference evapotranspiration (ET0) estimation has an effective role in reducing water losses and raising the efficiency of irrigation water management. The complicated nature of the evapotranspiration process is illustrated in the amount of meteorological variables required to estimate ET0. Incomplete meteorological data is the most significant challenge that confronts ET0 estimation. For this reason, different machine learning techniques have been employed to predict ET0, but the complicated structures and architectures of many of them make ET0 estimation very difficult. For these challenges, ensemble learning techniques are frequently employed for estimating ET0, particularly when there is a shortage of meteorological data. This paper introduces a powerful super learner ensemble technique for ET0 estimation, where four machine learning models: Extra Tree Regressor, Support Vector Regressor, K-Nearest Neighbor and AdaBoost Regression represent the base learners and their outcomes used as training data for the meta learner. Overcoming the overfitting problem that affects most other ensemble methods is a significant advantage of this cross-validation theory-based approach. Super learner performances were compared with the base learners for their forecasting capabilities through different statistical standards, where the results revealed that the super learner has better accuracy than the base learners, where different combinations of variables have been used whereas Coefficient of Determination (R2) ranged from 0.9279 to 0.9994 and Mean Squared Error (MSE) ranged from 0.0026 to 0.3289 mm/day but for the base learners R2 ranged from 0.5592 to 0.9977, and MSE ranged from 0.0896 to 2.0118 mm/day therefore, super learner is highly recommended for ET0 prediction with limited meteorological data. [ABSTRACT FROM AUTHOR]

Background: Nowadays, the chance of discovering the best antibody candidates for predicting clinical malaria has notably increased due to the availability of multi-sera data. The analysis of these data is typically divided into a feature selection phase followed by a predictive one where several models are constructed for predicting the outcome of interest. A key question in the analysis is to determine which antibodies should be included in the predictive stage and whether they should be included in the original or a transformed scale (i.e. binary/dichotomized). Methods: To answer this question, we developed three approaches for antibody selection in the context of predicting clinical malaria: (i) a basic and simple approach based on selecting antibodies via the nonparametric Mann–Whitney-Wilcoxon test; (ii) an optimal dychotomizationdichotomization approach where each antibody was selected according to the optimal cut-off via maximization of the chi-squared (χ2) statistic for two-way tables; (iii) a hybrid parametric/non-parametric approach that integrates Box-Cox transformation followed by a t-test, together with the use of finite mixture models and the Mann–Whitney-Wilcoxon test as a last resort. We illustrated the application of these three approaches with published serological data of 36 Plasmodium falciparum antigens for predicting clinical malaria in 121 Kenyan children. The predictive analysis was based on a Super Learner where predictions from multiple classifiers including the Random Forest were pooled together. Results: Our results led to almost similar areas under the Receiver Operating Characteristic curves of 0.72 (95% CI = [0.62, 0.82]), 0.80 (95% CI = [0.71, 0.89]), 0.79 (95% CI = [0.7, 0.88]) for the simple, dichotomization and hybrid approaches, respectively. These approaches were based on 6, 20, and 16 antibodies, respectively. Conclusions: The three feature selection strategies provided a better predictive performance of the outcome when compared to the previous results relying on Random Forest including all the 36 antibodies (AUC = 0.68, 95% CI = [0.57;0.79]). Given the similar predictive performance, we recommended that the three strategies should be used in conjunction in the same data set and selected according to their complexity. [ABSTRACT FROM AUTHOR]

The 21st Century Cures Act of 2016 includes a provision for the U.S. Food and Drug Administration10.13039/100000038 (FDA) to evaluate the potential use of Real-World Evidence (RWE) to support new indications for use for previously approved drugs, and to satisfy post-approval study requirements. Extracting reliable evidence from Real-World Data (RWD) is often complicated by a lack of treatment randomization, potential intercurrent events, and informative loss to follow-up. Targeted Learning (TL) is a sub-field of statistics that provides a rigorous framework to help address these challenges. The TL Roadmap offers a step-by-step guide to generating valid evidence and assessing its reliability. Following these steps produces an extensive amount of information for assessing whether the study provides reliable scientific evidence, including in support of regulatory decision-making. This article presents two case studies that illustrate the utility of following the roadmap. We used targeted minimum loss-based estimation combined with super learning to estimate causal effects. We also compared these findings with those obtained from an unadjusted analysis, propensity score matching, and inverse probability weighting. Nonparametric sensitivity analyses illuminate how departures from (untestable) causal assumptions affect point estimates and confidence interval bounds that would impact the substantive conclusion drawn from the study. TL's thorough approach to learning from data provides transparency, allowing trust in RWE to be earned whenever it is warranted. [ABSTRACT FROM AUTHOR]

Purpose: High‐dimensional propensity score (hdPS) is a semiautomated method that leverages a vast number of covariates available in healthcare databases to improve confounding adjustment. A novel combined Super Learner (SL)‐hdPS approach was proposed to assist with selecting the number of covariates for propensity score inclusion, and was found in plasmode simulation studies to improve bias reduction and precision compared to hdPS alone. However, the approach has not been examined in the applied setting. Methods: We compared SL‐hdPS's performance with that of several hdPS models, each with prespecified covariates and a different number of empirically‐identified covariates, using a cohort study comparing real‐world bleeding rates between ibrutinib‐ and bendamustine‐rituximab (BR)‐treated individuals with chronic lymphocytic leukemia in Optum's de‐identified Clinformatics® Data Mart commercial claims database (2013–2020). We used inverse probability of treatment weighting for confounding adjustment and Cox proportional hazards regression to estimate hazard ratios (HRs) for bleeding outcomes. Parameters of interest included prespecified and empirically‐identified covariate balance (absolute standardized difference [ASD] thresholds of <0.10 and <0.05) and outcome HR precision (95% confidence intervals). Results: We identified 2423 ibrutinib‐ and 1102 BR‐treated individuals. Including >200 empirically‐identified covariates in the hdPS model compromised covariate balance at both ASD thresholds. SL‐hdPS balanced more covariates than all individual hdPS models at both ASD thresholds. The bleeding HR 95% confidence intervals were generally narrower with SL‐hdPS than with individual hdPS models. Conclusion: In a real‐world application, hdPS was sensitive to the number of covariates included, while use of SL for covariate selection resulted in improved covariate balance and possibly improved precision. [ABSTRACT FROM AUTHOR]

As the size and complexity of projects grows, estimates are increasingly used, especially in the agile community. Software development cannot begin without first conducting thorough planning and estimation. Estimating how much work a project will take is a common first step in the software development life cycle. By employing ensemble techniques, we integrate multiple learning algorithms to build a more accurate predictive model. The core elements of our proposed stacked ensemble strategy include Decision Tree, Principal Components Regression, Random Forest, NeuralNet, GLMNET, XGBoost, Earth, and Support Vector Machine. Moreover, we augment the model's performance by incorporating a blend of these foundational algorithms with other ensemble regression methods. Extensive testing in the suggested research work with a number of Super Learners demonstrates that Regression is the best technique for judging effort. The evaluation of the different estimators involved the use of various metrics, including Mean Absolute Error, Root Mean Squared Error, Mean Squared Error, Percentage of Close Approximations within 25% of the True Values (PRED (25)), R-Squared Coefficients, Precision, Recall, and F1-Score. The proposed method yields more trustworthy predicted performance than either single-model approaches or stacked ensembles. Effort estimation serves as the foundation for the rest of the project management process. [ABSTRACT FROM AUTHOR]

We consider the problem of optimizing treatment allocation for statistical efficiency in randomized clinical trials. Optimal allocation has been studied previously for simple treatment effect estimators such as the sample mean difference, which are not fully efficient in the presence of baseline covariates. More efficient estimators can be obtained by incorporating covariate information, and modern machine learning methods make it increasingly feasible to approach full efficiency. Accordingly, we derive the optimal allocation ratio by maximizing the design efficiency of a randomized trial, assuming that an efficient estimator will be used for analysis. We then expand the scope of optimization by considering covariate‐dependent randomization (CDR), which has some flavor of an observational study but provides the same level of scientific rigor as a standard randomized trial. We describe treatment effect estimators that are consistent, asymptotically normal, and (nearly) efficient under CDR, and derive the optimal propensity score by maximizing the design efficiency of a CDR trial (under the assumption that an efficient estimator will be used for analysis). Our optimality results translate into optimal designs that improve upon standard practice. Real‐world examples and simulation results demonstrate that the proposed designs can produce substantial efficiency improvements in realistic settings. [ABSTRACT FROM AUTHOR]

Nuclear receptors (NRs) are important biological targets of endocrine-disrupting chemicals (EDCs). Identifying chemicals that can act as EDCs and modulate the function of NRs is difficult because of the time and cost of in vitro and in vivo screening to determine the potential hazards of the 100 000s of chemicals that humans are exposed to. Hence, there is a need for computational approaches to prioritize chemicals for biological testing. Machine learning (ML) techniques are alternative methods that can quickly screen millions of chemicals and identify those that may be an EDC. Computational models of chemical binding to multiple NRs have begun to emerge. Recently, a Nuclear Receptor Activity (NuRA) dataset, describing experimentally derived small-molecule activity against various NRs has been created. We have used the NuRA dataset to develop an ensemble of ML-based models to predict the agonism, antagonism, binding and effector binding of small molecules to nine different human NRs. We defined the applicability domain of the ML models as a measure of Tanimoto similarity to the molecules in the training set, which enhanced the performance of the developed classifiers. We further developed a user-friendly web server named 'NR-ToxPred' to predict the binding of chemicals to the nine NRs using the best-performing models for each receptor. This web server is freely accessible at http://nr-toxpred.cchem.berkeley.edu. Users can upload individual chemicals using Simplified Molecular-Input Line-Entry System, CAS numbers or sketch the molecule in the provided space to predict the compound's activity against the different NRs and predict the binding mode for each.

There has been growing interest in using nonparametric machine learning approaches for propensity score estimation in order to foster robustness against misspecification of the propensity score model. However, the vast majority of studies focused on single‐level data settings, and research on nonparametric propensity score estimation in clustered data settings is scarce. In this article, we extend existing research by describing a general algorithm for incorporating random effects into a machine learning model, which we implemented for generalized boosted modeling (GBM). In a simulation study, we investigated the performance of logistic regression, GBM, and Bayesian additive regression trees for inverse probability of treatment weighting (IPW) when the data are clustered, the treatment exposure mechanism is nonlinear, and unmeasured cluster‐level confounding is present. For each approach, we compared fixed and random effects propensity score models to single‐level models and evaluated their use in both marginal and clustered IPW. We additionally investigated the performance of the standard Super Learner and the balance Super Learner. The results showed that when there was no unmeasured confounding, logistic regression resulted in moderate bias in both marginal and clustered IPW, whereas the nonparametric approaches were unbiased. In presence of cluster‐level confounding, fixed and random effects models greatly reduced bias compared to single‐level models in marginal IPW, with fixed effects GBM and fixed effects logistic regression performing best. Finally, clustered IPW was overall preferable to marginal IPW and the balance Super Learner outperformed the standard Super Learner, though neither worked as well as their best candidate model. [ABSTRACT FROM AUTHOR]

In single-arm clinical trials with external controls, usually the estimand of interest is defined as the average treatment effect on the treated (ATT), and external controls are leveraged to provide an estimator of the estimand. Recently, virtual control approaches have been proposed to predict the outcomes for experimental study subjects as if they were receiving the control treatment, resulting in so-called “virtual controls” for comparison with their observed outcomes under the experimental intervention. We consider the virtual control approaches within the causal inference framework, discussing the properties of the vanilla virtual control approach and the targeted virtual control approach. We illustrate via simulation that the targeted virtual control approach is doubly robust, whereas the vanilla virtual control approach is not. We demonstrate the targeted virtual control approach is the same as the targeted maximum likelihood estimator (TMLE) when targeted at the ATT estimand. Therefore, through the notion of virtual controls, we offer a tangible way to understand and interpret TMLE when targeted at the ATT estimand. [ABSTRACT FROM AUTHOR]

In this issue, Naimi et al. (Am J Epidemiol. 2023;192(9):1536–1544) discuss a critical topic in public health and beyond: obtaining valid statistical inference when using machine learning in causal research. In doing so, the authors review recent prominent methodological work and recommend: 1) doubly robust estimators, such as targeted maximum likelihood estimation (TMLE); 2) ensemble methods, such as Super Learner, to combine predictions from a diverse library of algorithms; and 3) sample splitting to reduce bias and improve inference. We largely agree with these recommendations. In this commentary, we highlight the critical importance of the Super Learner library. Specifically, in both simulation settings considered by the authors, we demonstrate that reductions in bias and improvements in confidence-interval coverage can be achieved using TMLE without sample splitting and with a Super Learner library that excludes tree-based methods but includes regression splines. Whether extremely data-adaptive algorithms and sample splitting are needed depends on the specific problem and should be informed by simulations reflecting the specific application. More research is needed on practical recommendations for selecting among these options in common situations arising in epidemiology. [ABSTRACT FROM AUTHOR]

Common tasks encountered in epidemiology, including disease incidence estimation and causal inference, rely on predictive modelling. Constructing a predictive model can be thought of as learning a prediction function (a function that takes as input covariate data and outputs a predicted value). Many strategies for learning prediction functions from data (learners) are available, from parametric regressions to machine learning algorithms. It can be challenging to choose a learner, as it is impossible to know in advance which one is the most suitable for a particular dataset and prediction task. The super learner (SL) is an algorithm that alleviates concerns over selecting the one 'right' learner by providing the freedom to consider many, such as those recommended by collaborators, used in related research or specified by subject-matter experts. Also known as stacking, SL is an entirely prespecified and flexible approach for predictive modelling. To ensure the SL is well specified for learning the desired prediction function, the analyst does need to make a few important choices. In this educational article, we provide step-by-step guidelines for making these decisions, walking the reader through each of them and providing intuition along the way. In doing so, we aim to empower the analyst to tailor the SL specification to their prediction task, thereby ensuring their SL performs as well as possible. A flowchart provides a concise, easy-to-follow summary of key suggestions and heuristics, based on our accumulated experience and guided by SL optimality theory. [ABSTRACT FROM AUTHOR]

Gaussian graphical models (GGMs) are a popular form of network model in which nodes represent features in multivariate normal data and edges reflect conditional dependencies between these features. GGM estimation is an active area of research. Currently available tools for GGM estimation require investigators to make several choices regarding algorithms, scoring criteria, and tuning parameters. An estimated GGM may be highly sensitive to these choices, and the accuracy of each method can vary based on structural characteristics of the network such as topology, degree distribution, and density. Because these characteristics are a priori unknown, it is not straightforward to establish universal guidelines for choosing a GGM estimation method. We address this problem by introducing SpiderLearner, an ensemble method that constructs a consensus network from multiple estimated GGMs. Given a set of candidate methods, SpiderLearner estimates the optimal convex combination of results from each method using a likelihood‐based loss function. K$$ K $$‐fold cross‐validation is applied in this process, reducing the risk of overfitting. In simulations, SpiderLearner performs better than or comparably to the best candidate methods according to a variety of metrics, including relative Frobenius norm and out‐of‐sample likelihood. We apply SpiderLearner to publicly available ovarian cancer gene expression data including 2013 participants from 13 diverse studies, demonstrating our tool's potential to identify biomarkers of complex disease. SpiderLearner is implemented as flexible, extensible, open‐source code in the R package ensembleGGM at https://github.com/katehoffshutta/ensembleGGM. [ABSTRACT FROM AUTHOR]

BackgroundPopulation-level estimates of disease prevalence and control are needed to assess prevention and treatment strategies. However, available data often suffer from differential missingness. For example, population-level HIV viral suppression is the proportion of all HIV-positive persons with suppressed viral replication. Individuals with measured HIV status, and among HIV-positive individuals those with measured viral suppression, likely differ from those without such measurements.MethodsWe discuss three sets of assumptions to identify population-level suppression in the intervention arm of the SEARCH Study (NCT01864603), a community randomized trial in rural Kenya and Uganda (2013-2017). Using data on nearly 100,000 participants, we compare estimates from (1) an unadjusted approach assuming data are missing-completely-at-random (MCAR); (2) stratification on age group, sex, and community; and (3) targeted maximum likelihood estimation to adjust for a larger set of baseline and time-updated variables.ResultsDespite high measurement coverage, estimates of population-level viral suppression varied by identification assumption. Unadjusted estimates were most optimistic: 50% (95% confidence interval [CI] = 46%, 54%) of HIV-positive persons suppressed at baseline, 80% (95% CI = 78%, 82%) at year 1, 85% (95% CI = 83%, 86%) at year 2, and 85% (95% CI = 83%, 87%) at year 3. Stratifying on baseline predictors yielded slightly lower estimates, and full adjustment reduced estimates meaningfully: 42% (95% CI = 37%, 46%) of HIV-positive persons suppressed at baseline, 71% (95% CI = 69%, 73%) at year 1, 76% (95% CI = 74%, 78%) at year 2, and 79% (95% CI = 77%, 81%) at year 3.ConclusionsEstimation of population-level disease burden and control requires appropriate adjustment for missing data. Even in large studies with limited missingness, estimates relying on the MCAR assumption or baseline stratification should be interpreted cautiously.

Because the proportion between the compressive strength of high‐performance concrete (HPC) and its composition is highly nonlinear, more advanced regression methods are demanded to obtain better results. Super learner models, which are based on several ensemble methods including random forest regression (RFR), an adaptive boosting (AdaBoost), gradient boosting machine (GBM), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), categorical gradient Boosting (CatBoost), are used to solve this complicated problem. A grid search method is employed to determine the best set of hyper‐parameters of each ensemble algorithm. Two super learner models, which combine all six models or select the top three effective ones as the base learners, are then proposed to develop an accurate approach to estimate the compressive strength of HPC. The results on four popular datasets show significant improvement of the proposed super learner models in terms of prediction accuracy. It also reveals that their trained models always perform better than other methods since their errors (MAE, MSE, RMSE) are always much lower and values of R2 are higher than those of the previous studies. The proposed super learner models can be used to provide a reliable tool for mixture design optimization of the HPC. [ABSTRACT FROM AUTHOR]

Diabetes mellitus has become a rapidly growing chronic health problem worldwide. There has been a noticeable increase in diabetes cases in the last two decades. Recent advances in ensemble machine learning methods play an important role in the early detection of diabetes mellitus. These methods are both faster and less costly than traditional methods. This study aims to propose a new super ensemble learning model to enable an early diagnosis of diabetes mellitus. Super learner is a cross-validation-based approach that makes better predictions by combining prediction results of more than one machine learning algorithm. The proposed super learner model was created with four base-learners (logistic regression, decision tree, random forest, gradient boosting) and a meta learner (support vector machines) as a result of a case study. Three different dataset were used to measure the robustness of the proposed model. Chi-square was determined as an optimal feature selection technique from five different techniques, and also hyper-parameter settings were made with GridSearch. Finally, the proposed new super learner model achieved to obtain the best accuracy results in the detection of Diabetes mellitus compared to the base-learners for the early-stage diabetes risk prediction (99.6%), PIMA (92%), and diabetes 130-US hospitals (98%) dataset, respectively. This study revealed that super learner algorithms can be effectively used in the detection of diabetes mellitus. Also, obtaining of the high and convincing statistical scores shows the robustness of the proposed super learner model. [ABSTRACT FROM AUTHOR]

Multi-parametric MRI (mpMRI) is a critical tool in prostate cancer (PCa) diagnosis and management. To further advance the use of mpMRI in patient care, computer aided diagnostic methods are under continuous development for supporting/supplanting standard radiological interpretation. While voxel-wise PCa classification models are the gold standard, few if any approaches have incorporated the inherent structure of the mpMRI data, such as spatial heterogeneity and between-voxel correlation, into PCa classification. We propose a machine learning-based method to fill in this gap. Our method uses an ensemble learning approach to capture regional heterogeneity in the data, where classifiers are developed at multiple resolutions and combined using the super learner algorithm, and further account for between-voxel correlation through a Gaussian kernel smoother. It allows any type of classifier to be the base learner and can be extended to further classify PCa sub-categories. We introduce the algorithms for binary PCa classification, as well as for classifying the ordinal clinical significance of PCa for which a weighted likelihood approach is implemented to improve the detection of less prevalent cancer categories. The proposed method has shown important advantages over conventional modeling and machine learning approaches in simulations and application to our motivating patient data. [ABSTRACT FROM AUTHOR]

Causal inference under the potential outcome framework relies on the strongly ignorable treatment assumption. This assumption is usually questionable in observational studies, and the unmeasured confounding is one of the fundamental challenges in causal inference. To this end, we propose a new sensitivity analysis method to evaluate the impact of the unmeasured confounder by leveraging ideas of doubly robust estimators, the exponential tilt method, and the super learner algorithm. Compared to other existing methods of sensitivity analysis that parameterize the unmeasured confounder as a latent variable in the working models, the exponential tilting method does not impose any restrictions on the structure or models of the unmeasured confounders. In addition, in order to reduce the modeling bias of traditional parametric methods, we propose incorporating the super learner machine learning algorithm to perform nonparametric model estimation and the corresponding sensitivity analysis. Furthermore, most existing sensitivity analysis methods require multivariate sensitivity parameters, which make its choice difficult and subjective in practice. In comparison, the new method has a univariate sensitivity parameter with a nice and simple interpretation of log-odds ratios for binary outcomes, which makes its choice and the application of the new sensitivity analysis method very easy for practitioners. [ABSTRACT FROM AUTHOR]

We often seek to estimate the impact of an exposure naturally occurring or randomly assigned at the cluster-level. For example, the literature on neighborhood determinants of health continues to grow. Likewise, community randomized trials are applied to learn about real-world implementation, sustainability, and population effects of interventions with proven individual-level efficacy. In these settings, individual-level outcomes are correlated due to shared cluster-level factors, including the exposure, as well as social or biological interactions between individuals. To flexibly and efficiently estimate the effect of a cluster-level exposure, we present two targeted maximum likelihood estimators (TMLEs). The first TMLE is developed under a non-parametric causal model, which allows for arbitrary interactions between individuals within a cluster. These interactions include direct transmission of the outcome (i.e. contagion) and influence of one individual's covariates on another's outcome (i.e. covariate interference). The second TMLE is developed under a causal sub-model assuming the cluster-level and individual-specific covariates are sufficient to control for confounding. Simulations compare the alternative estimators and illustrate the potential gains from pairing individual-level risk factors and outcomes during estimation, while avoiding unwarranted assumptions. Our results suggest that estimation under the sub-model can result in bias and misleading inference in an observational setting. Incorporating working assumptions during estimation is more robust than assuming they hold in the underlying causal model. We illustrate our approach with an application to HIV prevention and treatment.

Using cross validation to select the best model from a library is standard practice in machine learning. Similarly, meta learning is a widely used technique where models previously developed are combined (mainly linearly) with the expectation of improving performance with respect to individual models. In this article we consider the Conditional Super Learner (CSL), an algorithm that selects the best model candidate from a library of models conditional on the covariates. The CSL expands the idea of using cross validation to select the best model and merges it with meta learning. We propose an optimization algorithm that finds a local minimum to the problem posed and proves that it converges at a rate faster than $O_p(n^{-1/4})$ O p (n - 1 / 4) . We offer empirical evidence that: (1) CSL is an excellent candidate to substitute stacking and (2) CLS is suitable for the analysis of Hierarchical problems. Additionally, implications for global interpretability are emphasized. [ABSTRACT FROM AUTHOR]

Binary classification problems are ubiquitous in health and social sciences. In many cases, one wishes to balance two competing optimality considerations for a binary classifier. For instance, in resource-limited settings, an human immunodeficiency virus prevention program based on offering pre-exposure prophylaxis (PrEP) to select high-risk individuals must balance the sensitivity of the binary classifier in detecting future seroconverters (and hence offering them PrEP regimens) with the total number of PrEP regimens that is financially and logistically feasible for the program. In this article, we consider a general class of constrained binary classification problems wherein the objective function and the constraint are both monotonic with respect to a threshold. These include the minimization of the rate of positive predictions subject to a minimum sensitivity, the maximization of sensitivity subject to a maximum rate of positive predictions, and the Neyman-Pearson paradigm, which minimizes the type II error subject to an upper bound on the type I error. We propose an ensemble approach to these binary classification problems based on the Super Learner methodology. This approach linearly combines a user-supplied library of scoring algorithms, with combination weights and a discriminating threshold chosen to minimize the constrained optimality criterion. We then illustrate the application of the proposed classifier to develop an individualized PrEP targeting strategy in a resource-limited setting, with the goal of minimizing the number of PrEP offerings while achieving a minimum required sensitivity. This proof of concept data analysis uses baseline data from the ongoing Sustainable East Africa Research in Community Health study. Copyright © 2017 John Wiley & Sons, Ltd.

Crop yield prediction is critical for investigating the yield gap and potential adaptations to environmental and management factors in arid regions. Crop models (CMs) are powerful tools for predicting yield and water use, but they still have some limitations and uncertainties; therefore, combining them with machine learning algorithms (MLs) could improve predictions and reduce uncertainty. To that end, the DSSAT-CERES-maize model was calibrated in one location and validated in others across Egypt with varying agro-climatic zones. Following that, the dynamic model (CERES-Maize) was used for long-term simulation (1990–2020) of maize grain yield (GY) and evapotranspiration (ET) under a wide range of management and environmental factors. Detailed outputs from three growing seasons of field experiments in Egypt, as well as CERES-maize outputs, were used to train and test six machine learning algorithms (linear regression, ridge regression, lasso regression, K-nearest neighbors, random forest, and XGBoost), resulting in more than 1.5 million simulated yield and evapotranspiration scenarios. Seven warming years (i.e., 1991, 1998, 2002, 2005, 2010, 2013, and 2020) were chosen from a 31-year dataset to test MLs, while the remaining 23 years were used to train the models. The Ensemble model (super learner) and XGBoost outperform other models in predicting GY and ET for maize, as evidenced by R2 values greater than 0.82 and RRMSE less than 9%. The broad range of management practices, when averaged across all locations and 31 years of simulation, not only reduced the hazard impact of environmental factors but also increased GY and reduced ET. Moving beyond prediction and interpreting the outputs from Lasso and XGBoost, and using global and local SHAP values, we found that the most important features for predicting GY and ET are maximum temperatures, minimum temperature, available water content, soil organic carbon, irrigation, cultivars, soil texture, solar radiation, and planting date. Determining the most important features is critical for assisting farmers and agronomists in prioritizing such features over other factors in order to increase yield and resource efficiency values. The combination of CMs and ML algorithms is a powerful tool for predicting yield and water use in arid regions, which are particularly vulnerable to climate change and water scarcity. [ABSTRACT FROM AUTHOR]

Longitudinal data sources offer new opportunities for the evaluation of sequential interventions. To adjust for time-dependent confounding in these settings, longitudinal targeted maximum likelihood based estimation (TMLE), a doubly robust method that can be coupled with machine learning, has been proposed. This paper provides a tutorial in applying longitudinal TMLE, in contrast to inverse probability of treatment weighting and g-computation based on iterative conditional expectations. We apply these methods to estimate the causal effect of nutritional interventions on clinical outcomes among critically ill children in a United Kingdom study (Control of Hyperglycemia in Paediatric Intensive Care, 2008-2011). We estimate the probability of a child's being discharged alive from the pediatric intensive care unit by a given day, under a range of static and dynamic feeding regimes. We find that before adjustment, patients who follow the static regime "never feed" are discharged by the end of the fifth day with a probability of 0.88 (95% confidence interval: 0.87, 0.90), while for the patients who follow the regime "feed from day 3," the probability of discharge is 0.64 (95% confidence interval: 0.62, 0.66). After adjustment for time-dependent confounding, most of this difference disappears, and the statistical methods produce similar results. TMLE offers a flexible estimation approach; hence, we provide practical guidance on implementation to encourage its wider use.

Soil texture is a key soil property driving physical, chemical, biological, and hydrological processes in soils. The rapid development of remote sensing techniques shows great potential for mapping soil properties. This study highlights the effectiveness of multitemporal remote sensing data in identifying soil textural class by using retrieved vegetation properties as proxies of soil properties. The impacts of sensors, modeling resolutions, and modeling techniques on the accuracy of soil texture classification were explored. Multitemporal Landsat-8 and Sentinel-2 images were individually acquired at the same time periods. Three satellite-based experiments with different inputs, i.e., Landsat-8 data, Sentinel-2 data (excluding red-edge parameters), and Sentinel-2 data (including red-edge parameters) were conducted. Modeling was carried out at three spatial resolutions (10, 30, 60 m) using five machine-learning (ML) methods: random forest, support vector machine, gradient-boosting decision tree, categorical boosting, and super learner that combined the four former classifiers based on the stacking concept. In addition, a novel SHapley Addictive Explanation (SHAP) technique was introduced to explain the outputs of the ML model. The results showed that the sensors, modeling resolutions, and modeling techniques significantly affected the prediction accuracy. The models using Sentinel-2 data with red-edge parameters performed consistently best. The models usually gave better results at fine (10 m) and medium (30 m) modeling resolutions than at a coarse (60 m) resolution. The super learner provided higher accuracies than other modeling techniques and gave the highest values of overall accuracy (0.8429), kappa (0.7611), precision (0.8378), recall rate (0.8393), and F1-score (0.8398) at 30 m with Sentinel-2 data involving red-edge parameters. The SHAP technique quantified the contribution of each variable for different soil textural classes, revealing the critical roles of red-edge parameters in separating loamy soils. This study provides comprehensive insights into the effective modeling of soil properties on various scales using multitemporal optical images. [ABSTRACT FROM AUTHOR]

Objective: Several prognostic models of suicide risk have been published; however, few have been implemented in Japan using longitudinal cohort data. The aim of this study was to identify suicide risk factors for suicidal ideation in the Japanese population and to develop a machine-learning model to predict suicide risk in Japan. Materials and methods: Data was obtained from Wave1 Time 1 (November 2016) and Time 2 (March 2017) of the National Survey for Stress and Health in Japan, were incorporated into a suicide risk prediction machine-learning model, trained using 65 items related to trauma and stress. The study included 3,090 and 2,163 survey respondents >18 years old at Time 1 and Time 2, respectively. The mean (standard deviation, SD) age was 44.9 (10.9) years at Time 1 and 46.0 (10.7) years at Time 2. We analyzed the participants with increased suicide risk at Time 2 survey. Model performance, including the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity, were also analyzed. Results: The model showed a good performance (AUC = 0.830, 95% confidence interval = 0.795-0.866). Overall, the model achieved an accuracy of 78.8%, sensitivity of 75.4%, specificity of 80.4%, positive predictive value of 63.4%, and negative predictive value of 87.9%. The most important risk factor for suicide risk was the participants' Suicidal Ideation Attributes Scale score, followed by the Sheehan Disability Scale score, Patient Health Questionnaire-9 scores, Cross-Cutting Symptom Measure (CCSM-suicidal ideation domain, Dissociation Experience Scale score, history of self-harm, Generalized Anxiety Disorder-7 score, Post-Traumatic Stress Disorder check list-5 score, CCSM-dissociation domain, and Impact of Event Scale-Revised scores at Time 1. Conclusions: This prognostic study suggests the ability to identify patients at a high risk of suicide using an online survey method. In addition to confirming several well-known risk factors of suicide, new riskmeasures related to trauma and trauma-related experiences were also identified, which may help guide future clinical assessments and early intervention approaches. [ABSTRACT FROM AUTHOR]

The use of machine learning algorithms in magnesium (Mg) alloys has evolved a scientific innovation for lightweight. The dataset was compiled by collecting data from the experiment and utilizing machine learning (ML) models to predict the mechanical properties of 348 Mg alloys. The proportion between the predicted and experimental results produced by different ML models demands more advanced regression methods to obtain better results. Utilizing Mg alloy descriptors as input variables and mechanical properties as output variables, four different ML models were employed namely (i.e.) Random Forest (RF), Extra Tree (ET), Gradient Boost (GB), and Extreme Gradient Boost (XGBoost) to resolve this difficult problem. Each single algorithm aimed to predict the mechanical properties of Mg alloy i.e. Ultimate Tensile Strength (UTS), Yield Strength (YS), and Elongation (EL). Subsequently, the data-driven intelligent prediction modeling technique called scaled Super Learner (SL) was employed to integrate the single models into the stacked model approach to enhance prediction accuracy. The results obtained using scaled Super Learner demonstrated enhanced prediction accuracy for UTS, YS, and EL. The findings further demonstrate enhanced prediction ability by outperforming other approaches as demonstrated by lower Root Mean Squared Error (RMSE) and higher R-Squared (R2) compared to previous studies. The reason for choosing Scaled Super Learner is because of its robustness and resistance to overfitting. Scaled Super Learner is also widely known for its better scalability, simplicity, and ability to handle noisy. The scaled Super Learner is an optimal approach for predicting the properties of Mg alloys. The proposed scaled Super learner serves as a tool for predicting Mg alloy properties. • An intelligent predictive algorithm is proposed for the mechanical properties of Mg-rare earth alloys through the use of ML algorithms. • Perform examination of the significance contribution of different features in predicting the mechanical properties of Mg-rare earth alloys. • Validating the effectiveness of the ML model by comparing its predictions with experimental outcomes. • Employ the SHAP and SL to derive practical insights for designing and optimizing Magnesium alloys respectively. [ABSTRACT FROM AUTHOR]

The exclusion of high-motion participants can reduce the impact of motion in functional Magnetic Resonance Imaging (fMRI) data. However, the exclusion of high-motion participants may change the distribution of clinically relevant variables in the study sample, and the resulting sample may not be representative of the population. Our goals are two-fold: 1) to document the biases introduced by common motion exclusion practices in functional connectivity research and 2) to introduce a framework to address these biases by treating excluded scans as a missing data problem. We use a study of autism spectrum disorder in children without an intellectual disability to illustrate the problem and the potential solution. We aggregated data from 545 children (8–13 years old) who participated in resting-state fMRI studies at Kennedy Krieger Institute (173 autistic and 372 typically developing) between 2007 and 2020. We found that autistic children were more likely to be excluded than typically developing children, with 28.5% and 16.1% of autistic and typically developing children excluded, respectively, using a lenient criterion and 81.0% and 60.1% with a stricter criterion. The resulting sample of autistic children with usable data tended to be older, have milder social deficits, better motor control, and higher intellectual ability than the original sample. These measures were also related to functional connectivity strength among children with usable data. This suggests that the generalizability of previous studies reporting naïve analyses (i.e., based only on participants with usable data) may be limited by the selection of older children with less severe clinical profiles because these children are better able to remain still during an rs-fMRI scan. We adapt doubly robust targeted minimum loss based estimation with an ensemble of machine learning algorithms to address these data losses and the resulting biases. The proposed approach selects more edges that differ in functional connectivity between autistic and typically developing children than the naïve approach, supporting this as a promising solution to improve the study of heterogeneous populations in which motion is common.

Sound classification has obtained considerable attention in recent years due to its wide range of applications in various fields, such as speech recognition, sound surveillance, music analysis, and environmental monitoring. Because of its success, audio classification can also be employed in medical applications. Coughing is the most common disease symptom, and cough sounds might be used to diagnose them. This research focuses on identifying observable features of cough and classifying them into positive, negative, or symptomatic categories. A novel ensemble learning model based on the super learner (SL) is proposed to diagnose the disease using cough sounds utilizing various audio features such as Frequency Distribution, Time Domain Features, Spectral Features, and Time–Frequency Features. The SL method is a cross-validated approach to stacked generalization, and it can select an optimal learner from a set of learners and improve performance by selecting and merging models using cross-validation. The proposed SL model comprises DT, RF, LR, SVM, ET, and k-NN algorithms. We use the public Coughvid dataset, and the proposed model achieves a correct classification rate for symptomatic cases, which was 90.90%, and the positive predictive value for COVID-19 cases was 84.50%. The SL3 model attains 72%, 78%, 73%, 74.4%, and 78.85% precision, recall, f1-score, accuracy, and average AUC values, respectively. The numerical results show that the proposed model might be implemented to diagnose various other diseases that can be determined from respiratory sounds. • A novel SL-based EL model is proposed to diagnose the COVID-19 on cough sounds. • Various audio features are utilized. • The proposed model evaluated on Coughvid dataset. • The numerical results show that SL model achieved promising results. [ABSTRACT FROM AUTHOR]

Objectives: To illustrate the use of machine learning methods to search for heterogeneous effects of a target modifiable risk factor on suicide in observational studies. The illustration focuses on secondary analysis of a matched case‐control study of vitamin D deficiency predicting subsequent suicide. Methods: We describe a variety of machine learning methods to search for prescriptive predictors; that is, predictors of significant variation in the association between a target risk factor and subsequent suicide. In each case, the purpose is to evaluate the potential value of selective intervention on the target risk factor to prevent the outcome based on the provisional assumption that the target risk factor is causal. The approaches illustrated include risk modeling based on the super learner ensemble machine learning method, Least Absolute Shrinkage and Selection Operator (Lasso) penalized regression, and the causal forest algorithm. Results: The logic of estimating heterogeneous intervention effects is exposited along with the illustration of some widely used methods for implementing this logic. Conclusions: In addition to describing best practices in using the machine learning methods considered here, we close with a discussion of broader design and analysis issues in planning an observational study to investigate heterogeneous effects of a modifiable risk factor. [ABSTRACT FROM AUTHOR]

Background: We sought to investigate the effect of public masking mandates in US states on COVID-19 at the national level in Fall 2020. Specifically, we aimed to evaluate how the relative growth of COVID-19 cases and deaths would have differed if all states had issued a mandate to mask in public by 1 September 2020 versus if all states had delayed issuing such a mandate. Methods: We applied the Causal Roadmap, a formal framework for causal and statistical inference. We defined the outcome as the state-specific relative increase in cumulative cases and in cumulative deaths 21, 30, 45, and 60 days after 1 September. Despite the natural experiment occurring at the state-level, the causal effect of masking policies on COVID-19 outcomes was not identifiable. Nonetheless, we specified the target statistical parameter as the adjusted rate ratio (aRR): the expected outcome with early implementation divided by the expected outcome with delayed implementation, after adjusting for state-level confounders. To minimize strong estimation assumptions, primary analyses used targeted maximum likelihood estimation with Super Learner. Results: After 60 days and at a national level, early implementation was associated with a 9% reduction in new COVID-19 cases (aRR = 0.91 [95% CI = 0.88, 0.95]) and a 16% reduction in new COVID-19 deaths (aRR = 0.84 [95% CI = 0.76, 0.93]). Conclusions: Although lack of identifiability prohibited causal interpretations, application of the Causal Roadmap facilitated estimation and inference of statistical associations, providing timely answers to pressing questions in the COVID-19 response. [ABSTRACT FROM AUTHOR]

A growing number of studies in the spatial estimation of geological features use machine learning (ML) models, as these models promise to provide efficient solutions for estimation especially in non-Gaussian, non-stationary and complex cases. However, these models have two major limitations: (1) the data are considered to be independent and identically distributed (or spatially uncorrelated), and (2) the data are not reproduced at their locations. Kriging, on the other hand, has a long history of generating unbiased estimates with minimum error variance at unsampled locations. Kriging assumes stationarity and linearity. This study proposes a methodology that combines kriging and ML models to mitigate the disadvantages of each method and obtain more accurate estimates. In the proposed methodology, a stacked ensemble model, which is also referred to as the super learner (SL) model, is applied for ML modeling. We have shown how the estimates generated by the SL model and estimates obtained from kriging can be combined through a weighting function based on a kriging variance. The weights are optimized using the sequential quadratic programming. The proposed methodology is demonstrated in two synthetic case studies containing data with non-stationarity and non-Gaussian features; a real case study using a dataset from an oilsands deposit is also presented. The performance of the combined model is compared with the SL model and kriging using the coefficient of determination (R-squared), root mean squared error, and mean absolute error criteria. The combined model appears to yield more accurate estimates than the ones generated by SL model and kriging in all cases. [ABSTRACT FROM AUTHOR]

Abstract Background The identification of acutely ill patients at high risk for venous thromboembolism (VTE) may be determined clinically or by use of integer‐based scoring systems. These scores demonstrated modest performance in external data sets. Objectives To evaluate the performance of machine learning models compared to the IMPROVE score. Methods The APEX trial randomized 7513 acutely medically ill patients to extended duration betrixaban vs. enoxaparin. Including 68 variables, a super learner model (ML) was built to predict VTE by combining estimates from 5 families of candidate models. A “reduced” model (rML) was also developed using 16 variables that were thought, a priori, to be associated with VTE. The IMPROVE score was calculated for each patient. Model performance was assessed by discrimination and calibration to predict a composite VTE end point. The frequency of predicted risks of VTE were plotted and divided into tertiles. VTE risks were compared across tertiles. Results The ML and rML algorithms outperformed the IMPROVE score in predicting VTE (c‐statistic: 0.69, 0.68 and 0.59, respectively). The Hosmer‐Lemeshow goodness‐of‐fit P‐value was 0.06 for ML, 0.44 for rML, and

Background: Postacute sequelae of COVID-19 (PASC), also known as long COVID, is a broad grouping of a range of long-term symptoms following acute COVID-19. These symptoms can occur across a range of biological systems, leading to challenges in determining risk factors for PASC and the causal etiology of this disorder. An understanding of characteristics that are predictive of future PASC is valuable, as this can inform the identification of high-risk individuals and future preventative efforts. However, current knowledge regarding PASC risk factors is limited., Objective: Using a sample of 55,257 patients (at a ratio of 1 patient with PASC to 4 matched controls) from the National COVID Cohort Collaborative, as part of the National Institutes of Health Long COVID Computational Challenge, we sought to predict individual risk of PASC diagnosis from a curated set of clinically informed covariates. The National COVID Cohort Collaborative includes electronic health records for more than 22 million patients from 84 sites across the United States., Methods: We predicted individual PASC status, given covariate information, using Super Learner (an ensemble machine learning algorithm also known as stacking) to learn the optimal combination of gradient boosting and random forest algorithms to maximize the area under the receiver operator curve. We evaluated variable importance (Shapley values) based on 3 levels: individual features, temporal windows, and clinical domains. We externally validated these findings using a holdout set of randomly selected study sites., Results: We were able to predict individual PASC diagnoses accurately (area under the curve 0.874). The individual features of the length of observation period, number of health care interactions during acute COVID-19, and viral lower respiratory infection were the most predictive of subsequent PASC diagnosis. Temporally, we found that baseline characteristics were the most predictive of future PASC diagnosis, compared with characteristics immediately before, during, or after acute COVID-19. We found that the clinical domains of health care use, demographics or anthropometry, and respiratory factors were the most predictive of PASC diagnosis., Conclusions: The methods outlined here provide an open-source, applied example of using Super Learner to predict PASC status using electronic health record data, which can be replicated across a variety of settings. Across individual predictors and clinical domains, we consistently found that factors related to health care use were the strongest predictors of PASC diagnosis. This indicates that any observational studies using PASC diagnosis as a primary outcome must rigorously account for heterogeneous health care use. Our temporal findings support the hypothesis that clinicians may be able to accurately assess the risk of PASC in patients before acute COVID-19 diagnosis, which could improve early interventions and preventive care. Our findings also highlight the importance of respiratory characteristics in PASC risk assessment., International Registered Report Identifier (irrid): RR2-10.1101/2023.07.27.23293272., (©Zachary Butzin-Dozier, Yunwen Ji, Haodong Li, Jeremy Coyle, Junming Shi, Rachael V Phillips, Andrew N Mertens, Romain Pirracchio, Mark J van der Laan, Rena C Patel, John M Colford, Alan E Hubbard, The National COVID Cohort Collaborative (N3C) Consortium. Originally published in JMIR Public Health and Surveillance (https://publichealth.jmir.org), 15.08.2024.)