Search

In insurance, proposing an accurate premium that is adjusted to the insured risk profile allows companies to better manage their portfolios and to be more competitive. Machine learning methods have recently been adopted for various improvements in insurance ratemaking, especially in the automobile industry. These models are specifically used to mine potential data information and to build a predictive model for a variable of interest using explanatory variables. In this paper, we aim to provide a pricing method for ratemaking individual healthcare insurance contracts using machine learning algorithms that are applied to a Tunisian healthcare insurance portfolio. We start with a simple Classification and Regression Tree, and we work toward more advanced methods that are Random Forest, Extreme gradient boosting, Support Vector Regression, and Artificial Neural network regression model. The predictive performance of these non-parametric methods is compared with the standard generalized linear model. Our results showed the applicability of machine learning in the healthcare insurance market and that the XGBoost algorithm outperforms the predictive capacity of the classical generalized linear model. [ABSTRACT FROM AUTHOR]

Background: Metabolic dysfunction-associated steatotic liver disease (MASLD) represents a significant global health burden without established curative therapies. Early detection and preventive strategies are crucial for effective MASLD management. This study aimed to develop and validate machine-learning (ML) algorithms for accurate MASLD screening in a geographically diverse, large-scale population. Methods: Data from the prospective Fasa Cohort Study, initiated in rural Fars province, Iran (March 2014), were employed for this purpose. The required data were collected using blood tests, questionnaires, liver ultrasonography, and physical examinations. A two-step approach identified key predictors from over 100 variables: (1) statistical selection using mean decrease Gini in random forest and (2) incorporation of clinical expertise for alignment with known MASLD risk factors. The hold-out validation approach (with a 70/30 train/validation split) was utilized, along with 5-fold cross-validation on the validation set. Logistic regression, Naïve Bayes, support vector machine, and light gradient-boosting machine (LightGBM) algorithms were compared for model construction with the same input variables based on area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy. Results: A total of 6,180 adults (52.7% female) were included in the study, categorized into 4816 non-MASLD and 1364 MASLD cases with a mean age (± standard deviation [SD]) of 48.12 (± 9.61) and 49.47 (± 9.15) years, respectively. Logistic regression outperformed other ML algorithms, achieving an accuracy of 0.88 (95% confidence interval [CI]: 0.86-0.89) and an AUC of 0.92 (95% CI: 0.90-0.93). Among more than 100 variables, the key predictors included waist circumference, body mass index (BMI), hip circumference, wrist circumference, alanine aminotransferase levels, cholesterol, glucose, high-density lipoprotein, and blood pressure. Conclusion: Integration of ML in MASLD management holds significant promise, particularly in resource-limited rural settings. Additionally, the relative importance assigned to each predictor, particularly prominent contributors such as waist circumference and BMI, offers valuable insights into MASLD prevention, diagnosis, and treatment strategies. [ABSTRACT FROM AUTHOR]

Background: Hepatocellular carcinoma (HCC) recurrence following surgical resection remains a significant clinical challenge, necessitating reliable predictive models to guide personalised interventions. In this study, we sought to harness the power of artificial intelligence (AI) to develop a robust predictive model for HCC recurrence using comprehensive clinical datasets. Methods: Leveraging data from 958 patients across multiple centres in Australia and Hong Kong, we employed a multilayer perceptron (MLP) as the optimal classifier for model generation. Results: Through rigorous internal cross‐validation, including a cohort from the Chinese University of Hong Kong (CUHK), our AI model successfully identified specific pre‐surgical risk factors associated with HCC recurrence. These factors encompassed hepatic synthetic function, liver disease aetiology, ethnicity and modifiable metabolic risk factors, collectively contributing to the predictive synergy of our model. Notably, our model exhibited high accuracy during cross‐validation (.857 ±.023) and testing on the CUHK cohort (.835), with a notable degree of confidence in predicting HCC recurrence within accurately classified patient cohorts. To facilitate clinical application, we developed an online AI digital tool capable of real‐time prediction of HCC recurrence risk, demonstrating acceptable accuracy at the individual patient level. Conclusion: Our findings underscore the potential of AI‐driven predictive models in facilitating personalised risk stratification and targeted interventions to mitigate HCC recurrence by identifying modifiable risk factors unique to each patient. This model aims to aid clinicians in devising strategies to disrupt the underlying carcinogenic network driving recurrence. [ABSTRACT FROM AUTHOR]

Objectives: This study investigated the impact of social activities on cognitive functioning and psychopathological symptoms. Methods: Participants aged 55 or older were enrolled through communities. Initial measures assessed demographic data, neuropsychological functioning, psychopathological state, and happiness. Social activities were evaluated using a modified 12-item tool, with 3–4 activities as the cutoff. Follow-up after 6–9 months included Mini-Mental State Examination (MMSE), Beck Depression Inventory – II (BDI-II), Beck Anxiety Inventory (BAI), Health Assessment Questionnaire (HAQ), and Patient Health Questionnaire-15 (PHQ-15) measurements. Predictive models for psychiatric and cognitive statuses were built using multiple linear regression, adjusting for baseline conditions. Results: Initially, 516 older individuals enrolled, with 403 undergoing follow-up. During follow-up, the low participation group reported lower MMSE scores, higher BAI scores, and increased PHQ-15 risk. Negative correlations between social activity numbers and PHQ-15 results were found. Engagement in social clubs correlated positively with higher MMSE scores, while regular interactions with one's adult child(ren) were linked to decreased BAI scores. Conclusions: The quantity of social activities was associated with lower somatic distress. Social club engagement positively influenced cognition, and regular interactions with one's adult child(ren) mitigated anxiety among older individuals. Clinical implications: Enough types of social activities, participating in social clubs, and adequate interactions with children protected against psychopathologies. [ABSTRACT FROM AUTHOR]

Cucumbers (Cucumis sativus) are known for their high water content and nutritional value, making them a valuable addition to a balanced diet. The objective of this study was to evaluate the physicochemical quality (color, moisture, water activity, and texture), and antioxidant/antiradical properties of freshly packed greenhouse-cultivated cucumbers over a 28-day storage period, utilizing a combination of high-throughput analytical techniques, including attenuated total reflectance–Fourier transform infrared (ATR-FTIR) spectroscopy, instrumental analysis, image analysis, and chemometrics. The key findings indicated that the cucumbers underwent a significant loss of moisture during the storage period, with a concomitant decrease in firmness. Color analysis revealed an increase in the yellowness of both the peel and flesh, while image analysis demonstrated increasing dissimilarity and textural disorder, particularly evident by the 13th day of storage. The spectrophotometric and spectroscopic findings demonstrated that the quality of the cucumbers was maintained during the storage period. Meanwhile, regression and discriminant analyses were employed to interpret the collected data. Predictive models were developed with high accuracy to estimate the actual storage days and flesh quality attributes based on textural and color features derived from image analysis. Overall, this study highlights the importance of controlled storage conditions in maintaining cucumber quality and provides a comprehensive approach to monitoring post-harvest changes. [ABSTRACT FROM AUTHOR]

Background and Purpose Methods Results Conclusions Delirium is a common mental disorder after adult cardiovascular surgery. Fifteen to 23% of patients undergoing cardiovascular surgery and cardiomyopathy experience delirium, and the efficacy of treatment interventions for delirium has been consistently unsatisfactory.A total of 729 patients who underwent cardiovascular surgery were randomly allocated into a training set and a validation set. A nomogram was developed using a logistic regression model to predict the incidence of delirium following cardiovascular surgery. The validity of the model was assessed by determining the receiver operating characteristic (ROC) curve, calculating the area under the ROC curve (AUROC), performing a calibration plot, and executing a decision curve analysis. This model was internally validated using the bootstrap method.Postoperative delirium (POD) occurred in 165 cases (22.6%) among the 729 patients. Predictors included age, transient ischemic attack, length of preoperative stay, preoperative left ventricular injection fraction and N‐terminal pro‐B‐type natriuretic peptide level, and intraoperative infusion of dexmedetomidine and human fibrinogen. The nomogram showed sufficient differentiation and calibration (AUROC = 0.754, 95% confidence interval = 0.703–0.804). The calibration graphs showed that the predictive values of the nomogram were in agreement with the actual values. The analysis of the training and validation sets suggested that the model possessed specific clinical significance.In summary, the predictive model consists of seven factors that can roughly predict the occurrence of POD in patients who undergo cardiovascular surgery. [ABSTRACT FROM AUTHOR]

Introduction: This study aimed to establish efficient, cost-effective, and early predictive models for adverse pregnancy outcomes based on the combinations of a minimum number of miRNA biomarkers, whose altered expression was observed in specific pregnancy-related complications and selected maternal clinical characteristics. Methods: This retrospective study included singleton pregnancies with gestational hypertension (GH, n = 83), preeclampsia (PE, n = 66), HELLP syndrome (n = 14), fetal growth restriction (FGR, n = 82), small for gestational age (SGA, n = 37), gestational diabetes mellitus (GDM, n = 121), preterm birth in the absence of other complications (n = 106), late miscarriage (n = 34), stillbirth (n = 24), and 80 normal term pregnancies. MiRNA gene expression profiling was performed on the whole peripheral venous blood samples collected between 10 and 13 weeks of gestation using real-time reverse transcription polymerase chain reaction (RT-PCR). Results: Most pregnancies with adverse outcomes were identified using the proposed approach (the combinations of selected miRNAs and appropriate maternal clinical characteristics) (GH, 69.88%; PE, 83.33%; HELLP, 92.86%; FGR, 73.17%; SGA, 81.08%; GDM on therapy, 89.47%; and late miscarriage, 84.85%). In the case of stillbirth, no addition of maternal clinical characteristics to the predictive model was necessary because a high detection rate was achieved by a combination of miRNA biomarkers only [91.67% cases at 10.0% false positive rate (FPR)]. Conclusion: The proposed models based on the combinations of selected cardiovascular disease-associated miRNAs and maternal clinical variables have a high predictive potential for identifying women at increased risk of adverse pregnancy outcomes; this can be incorporated into routine first-trimester screening programs. Preventive programs can be initiated based on these models to lower cardiovascular risk and prevent the development of metabolic/cardiovascular/cerebrovascular diseases because timely implementation of beneficial lifestyle strategies may reverse the dysregulation of miRNAs maintaining and controlling the cardiovascular system. [ABSTRACT FROM AUTHOR]

Bitter peptides are small molecular peptides produced by the hydrolysis of proteins under acidic, alkaline, or enzymatic conditions. These peptides can enhance food flavor and offer various health benefits, with attributes such as antihypertensive, antidiabetic, antioxidant, antibacterial, and immune-regulating properties. They show significant potential in the development of functional foods and the prevention and treatment of diseases. This review introduces the diverse sources of bitter peptides and discusses the mechanisms of bitterness generation and their physiological functions in the taste system. Additionally, it emphasizes the application of bioinformatics in bitter peptide research, including the establishment and improvement of bitter peptide databases, the use of quantitative structure–activity relationship (QSAR) models to predict bitterness thresholds, and the latest advancements in classification prediction models built using machine learning and deep learning algorithms for bitter peptide identification. Future research directions include enhancing databases, diversifying models, and applying generative models to advance bitter peptide research towards deepening and discovering more practical applications. [ABSTRACT FROM AUTHOR]

Backgrounds: Although allogeneic hematopoietic stem cell transplantation (allo-HSCT) is a potentially curative therapy for hematological malignancies, it can be associated with relevant post-transplant complications. Several reports have shown that polymorphisms in immune system genes are correlated with the development of post-transplant complications. Within this context, this work focuses on identifying novel polymorphisms in cytokine genes and developing predictive models to anticipate the risk of developing graft-versus-host disease (GVHD), transplantation-related mortality (TRM), relapse and overall survival (OS). Methods: Our group developed a 132-cytokine gene panel which was tested in 90 patients who underwent an HLA-identical sibling-donor allo-HSCT. Bayesian logistic regression (BLR) models were used to select the most relevant variables. Based on the cut-off points selected for each model, patients were classified as being at high or low-risk for each of the post-transplant complications (aGVHD II-IV, aGVHD III-IV, cGVHD, mod-sev cGVHD, TRM, relapse and OS). Results: A total of 737 polymorphisms were selected from the custom panel genes. Of these, 41 polymorphisms were included in the predictive models in 30 cytokine genes were selected (17 interleukins and 13 chemokines). Of these polymorphisms, 5 (12.2%) were located in coding regions, and 36 (87.8%) in noncoding regions. All models had a statistical significance of p<0.0001. Conclusion: Overall, genomic polymorphisms in cytokine genes make it possible to anticipate the development all complications studied following allo-HSCT and, consequently, to optimize the clinical management of patients. [ABSTRACT FROM AUTHOR]

Background: Bipolar disorder (BD) involves significant mood and energy shifts reflected in speech patterns. Detecting these patterns is crucial for diagnosis and monitoring, currently assessed subjectively. Advances in natural language processing offer opportunities to objectively analyze them. Aims: To (i) correlate speech features with manic-depressive symptom severity in BD, (ii) develop predictive models for diagnostic and treatment outcomes, and (iii) determine the most relevant speech features and tasks for these analyses. Methods: This naturalistic, observational study involved longitudinal audio recordings of BD patients at euthymia, during acute manic/depressive phases, and after-response. Patients participated in clinical evaluations, cognitive tasks, standard text readings, and storytelling. After automatic diarization and transcription, speech features, including acoustics, content, formal aspects, and emotionality, will be extracted. Statistical analyses will (i) correlate speech features with clinical scales, (ii) use lasso logistic regression to develop predictive models, and (iii) identify relevant speech features. Results: Audio recordings from 76 patients (24 manic, 21 depressed, 31 euthymic) were collected. The mean age was 46.0 ± 14.4 years, with 63.2% female. The mean YMRS score for manic patients was 22.9 ± 7.1, reducing to 5.3 ± 5.3 post-response. Depressed patients had a mean HDRS-17 score of 17.1 ± 4.4, decreasing to 3.3 ± 2.8 post-response. Euthymic patients had mean YMRS and HDRS-17 scores of 0.97 ± 1.4 and 3.9 ± 2.9, respectively. Following data pre-processing, including noise reduction and feature extraction, comprehensive statistical analyses will be conducted to explore correlations and develop predictive models. Conclusions: Automated speech analysis in BD could provide objective markers for psychopathological alterations, improving diagnosis, monitoring, and response prediction. This technology could identify subtle alterations, signaling early signs of relapse. Establishing standardized protocols is crucial for creating a global speech cohort, fostering collaboration, and advancing BD understanding. [ABSTRACT FROM AUTHOR]

Computational modeling is a new approach to optimize Young’s modulus of scaffolds by performing a minimal number of experiments. However, presenting a modeling algorithm to predict Young’s modulus and characterize the governing parameters is a challenging task. Here, a novel modeling approach has been proposed to estimate Young’s modulus of scaffolds, considering particle agglomeration and interphase interactions. Employing the characteristic parameters of these two phenomena, we modified the Maxwell model using a simple three-step algorithm to determine the optimal value of these parameters and predict Young’s modulus. Interestingly, the model provides a precision of more than 95% for all the studied cases and presents a remarkably better performance compared to the two other models. For instance, the proposed model has reduced the average absolute relative error of Young’s modulus of poly (3-hydroxybutyrate)-keratin/hydroxyapatite nanorods from 25.1% to 0.08%, demonstrating the high efficiency of this model in predicting Young’s modulus of scaffolds. The results of this study could lighten the way of fabricating nanobiocomposites with optimal mechanical properties, spending lower cost and energy. [ABSTRACT FROM AUTHOR]

Investigating the transition between the secondary and the tertiary levels is a main theme in mathematics and science education. More so, this paper considers the transition that intersects with the after-effects of COVID-19, or the transition together with an educational context dominated by sociocultural differences and educational disadvantages. With this knowledge in mind, we investigated the effects of predictive mathematical models (multiple regression, logistic regression, and decision trees) to predict at-risk students at three time intervals (weeks one, three, and seven) in the semester. The idea was implemented with a first-year life science class of 130 students. Variables from an academic readiness questionnaire along with early assessment grades were used to build these models. Through a Monte Carlo cross validation method, the performance of the executed predictive models was assessed, and limitations were reported. We argue that the results obtained from predictive models can support both lecturers and students in the transition phase. The idea can be expanded to other courses in STEM fields and other educational contexts. [ABSTRACT FROM AUTHOR]

While the use of machine learning (ML) in automated real estate valuation is growing, research on stacking ML models into ensembles remains limited. In this paper, we propose a stacked ensemble model for valuing residential properties. By applying our models to a comprehensive dataset of residential real estate transactions from Jeju Island, spanning 2012 to 2021, we demonstrate that the predictive power of ML-based models can be enhanced. Our findings indicate that the stacked ensemble model, which combines predictions using ridge regression, outperforms all individual algorithms across multiple metrics. This model not only minimizes prediction errors but also provides the most stable and consistent results, as evidenced by the lowest standard deviation in both absolute errors and absolute percentage errors. Additionally, we employed the decision tree method to analyze the conditions under which specific features yield more accurate results or less reliable outcomes. It was observed that both the size and age of an apartment significantly impact prediction performance, with smaller and older complexes exhibiting lower accuracy and higher error rates. [ABSTRACT FROM AUTHOR]

Background/Objectives: Managing blood glucose levels effectively remains a significant challenge for individuals with diabetes. Traditional methods often lack the flexibility needed for personalized care. This study explores the potential of reinforcement learning-based approaches, which mimic human learning and adapt strategies through ongoing interactions, in creating dynamic and personalized blood glucose management plans. Methods: We developed a mathematical model specifically for patients with type IVP diabetes, validated with data from 10 patients and 17 key parameters. The model includes continuous glucose monitoring (CGM) noise and random carbohydrate intake to simulate real-life conditions. A closed-loop system was designed to enable the application of reinforcement learning algorithms. Results: By implementing a Policy Optimization (PPO) branch, we achieved an average Time in Range (TIR) metric of 73%, indicating improved blood glucose control. Conclusions: This study presents a personalized insulin therapy solution using reinforcement learning. Our closed-loop model offers a promising approach for improving blood glucose regulation, with potential applications in personalized diabetes management. [ABSTRACT FROM AUTHOR]

Building energy consumption prediction models are powerful tools for optimizing energy management. Among various methods, artificial neural networks (ANNs) have become increasingly popular. This paper reviews studies since 2015 on using ANNs to predict building energy use and demand, focusing on the characteristics of different ANN structures and their applications across building phases—design, operation, and retrofitting. It also provides guidance on selecting the most appropriate ANN structures for each phase. Finally, this paper explores future developments in ANN-based predictions, including improving data processing techniques for greater accuracy, refining parameterization to better capture building features, optimizing algorithms for faster computation, and integrating ANNs with other machine learning methods, such as ensemble learning and hybrid models, to enhance predictive performance. [ABSTRACT FROM AUTHOR]

It is generally recognized that accurate and timely prediction of future traffic flow information is one of the important conditions for improving the utilization rate of road networks and relieving traffic congestion. Since long short-term memory (LSTM) networks have obvious advantages in dealing with time series data, LSTM-based prediction models, as well as the improved and hybrid models based on LSTM, have been widely used in the field of traffic flow prediction and have achieved a series of important results. However, although some existing reviews have provided a comprehensive summary of and prospects for traffic flow prediction methods, there is no recent review specifically summarizing the traffic flow prediction methods based on LSTM. Therefore, this article presents a comprehensive review of LSTM-based methods for traffic flow prediction. First, we briefly introduce the development history of traffic flow prediction, the advantages of using LSTM for traffic flow prediction, and the basic principles of LSTM. Then, the representative model structures, training methods, public datasets, attractive results, the advantages and disadvantages of different LSTM-based methods are presented and analyzed in detail. Furthermore, to illustrate the performance of various refinements and hybrid models based on LSTM for traffic flow prediction, we meticulously select several representative approaches to conduct comparative experiments and quantitative analysis. Finally, we discuss the current limitations and challenges of LSTM and traffic flow prediction and present potential areas of future research interest to the readers. [ABSTRACT FROM AUTHOR]

Amidst the growing challenges of water and energy scarcity, the following research presents an innovative solar desalination system that integrates predictive models with advanced thermal energy storage (TES) to optimize freshwater production. The system adjusts feed water flow dynamically, ensuring consistent and continuous top feed water temperature (TBT). Comprehensive mathematical modeling and simulations reveal significant enhancements in system performance, with an optimized TES tank volume of 500 m3 and a solar collector area of 4245 m2. The economic analysis indicates the system is cost-effective, with a production cost of approximately USD 5.86 million, competitive with conventional methods. Additionally, the system achieved an average daily feed water flow rate of 10 kg/s, ensuring stable operation even under fluctuating solar radiation. The system also achieved a global warming potential (GWP) of 2.24 kg CO2-eq per cubic meter, a favorable and environmentally sustainable measure. This study stresses the potential for scalable, sustainable desalination solutions to enhance water security in arid and remote regions. [ABSTRACT FROM AUTHOR]

The increasing prevalence of omics data sources is pushing the study of regulatory mechanisms underlying complex diseases such as cancer. However, the vast quantities of molecular features produced and the inherent interplay between them lead to a level of complexity that hampers both descriptive and predictive tasks, requiring custom‐built algorithms that can extract relevant information from these sources of data. We propose a transformation that moves data centered on molecules (e.g., transcripts and proteins) to a new data space focused on putative regulatory modules given by statistically relevant co‐expression patterns. To this end, the proposed transformation extracts patterns from the data through biclustering and uses them to create new variables with guarantees of interpretability and discriminative power. The transformation is shown to achieve dimensionality reductions of up to 99% and increase predictive performance of various classifiers across multiple omics layers. Results suggest that omics data transformations from gene‐centric to pattern‐centric data supports both prediction tasks and human interpretation, notably contributing to precision medicine applications. [ABSTRACT FROM AUTHOR]

Abstract Loss to follow-up (LTFU) in tuberculosis (TB) management increases morbidity and mortality, challenging effective control strategies. This study aims to develop and evaluate machine learning models to predict loss to follow-up in TB patients, improving treatment adherence and outcomes. Retrospective data encompassing tuberculosis patients who underwent treatment or registration at the National Center for Clinical Medical Research on Infectious Diseases from January 2017 to December 2021 were compiled. Employing machine learning techniques, namely SVM, RF, XGBoost, and logistic regression, the study aimed to prognosticate LTFU. A comprehensive cohort of 24,265 tuberculosis patients underwent scrutiny, revealing a LTFU prevalence of 12.51% (n = 3036). Education level, history of hospitalization, alcohol consumption, outpatient admission, and prior tuberculosis history emerged as precursors for pre-treatment LTFU. Employment status, outpatient admission, presence of chronic hepatitis/cirrhosis, drug adverse reactions, alternative contact availability, and health insurance coverage exerted substantial influence on treatment-phase LTFU. XGBoost consistently surpassed alternative models, boasting superior discriminative ability with an average AUC of 0.921 for pre-treatment LTFU and 0.825 for in-treatment LTFU. Our study demonstrates that the XGBoost model provides superior predictive performance in identifying LTFU risk among tuberculosis patients. The identification of key risk factors highlights the importance of targeted interventions, which could lead to significant improvements in treatment adherence and patient outcomes.

[Objective] The influence of different storage temperatures on the quality and total number of microbial colonies of Premna microphylla Turez jelly was studied, and the shelf-life prediction model based on quality indexes and the total number of colonies were established. [Methods] P. microphylla Turez jelly were stored at temperatures of 1, 4, 10, 15, 20 and 25 ℃, and the hardness, adhesiveness, springiness, chewiness, water holding capacity and total number of colonies were regularly measured. The influence of different temperatures on the quality indexes and the total number of colonies were discussed, and the fitting equations of each monitoring index were determined. According to the quality indexes and total number of colonies of P. microphylla Turez jelly, P. microphylla Turez jelly's shelf-life prediction model was established by combining the Arrhenius model and Belehradck model. [Results] The results show that the different storage temperature has no significant change in springiness, while the storage temperature has a significant effect on the hardness, adhesiveness, chewiness, water-holding capacity, and total number of colonies. The zero-level response equation was the best fit for the change in water holding capacity of P. microphylla Turez jelly, with an average fit of 0.978. On the influence of hardness, viscosity, and chewability, the first-order reaction had the best fitting, and the average fitting degree was 0.967, 0.904, and 0.977, respectively. The Logistics equation had the best fitting effect on the total number of colonies of P. microphylla Turez jelly, and the average fitting was 0.992. Five shelf-life prediction models were validated under the storage temperature of 3 ℃. The relative errors between the measured and predicted values were 7.50%, 8.13%, 4.38%, 5.00%, and 3.75%, respectively, with good prediction results. [Conclusion] The models can effectively predict the shelf life of P. microphylla Turez jelly under storage conditions from 1 ℃ to 25 ℃.

Rock hardness and abrasivity are among the most crucial properties that can significantly impact the interaction between rocks and mechanical tools in different parts of geoengineering projects. Accurate estimation of these properties is essential for a better understanding and optimization of geoengineering operations. Hence, the main aim of this study was to develop different machine learning (ML) models based on the geochemical measurements for predicting rock hardness and abrasivity. To do this, 159 rock samples were collected from a gold mine, and portable X-ray fluorescence spectrometry (pXRF), Leeb rebound hardness (LRH), and Cerchar abrasivity index (CAI) tests were performed on the collected rock samples. Three different ML algorithms, including random forest regressor (RFR), support vector regression, and gradient boosting regressor, were applied to develop predictive models for LRH and CAI separately. Considering the fact that the geochemical data are of the compositional type, two scenarios were followed: developing predictive models based on the original data obtained from the pXRF and the centered log-ratio (Clr) transformed data, resulting in the development of six predictive models for LRH and CAI. The performance assessment of the developed predictive models showed that RFR models outperformed the other two ML algorithms in predicting LRH and CAI. In addition, the developed models based on the original data demonstrated a better performance in both cases of LRH and CAI than the trained model based on Clr data. The result indicates that integrated pXRF measurements and RFR technique have strong potential to be used for practical and efficient rock materials characterization during exploration and extraction processes. [ABSTRACT FROM AUTHOR]

Abstract With the rapid spread of the novel coronavirus (COVID-19), a sustained global pandemic has emerged. Globally, the cumulative death toll is in the millions. The rising number of COVID-19 infections and deaths has severely impacted the lives of people worldwide, healthcare systems, and economic development. We conducted a retrospective analysis of the characteristics of COVID-19 patients. This analysis includes clinical features upon initial hospital admission, relevant laboratory test results, and imaging findings. We aimed to identify risk factors for severe illness and to construct a predictive model for assessing the risk of severe COVID-19. We collected and analyzed electronic medical records of confirmed COVID-19 patients admitted to the Affiliated Hospital of Jiangsu University (Zhenjiang, China) between December 18, 2022, and February 28, 2023. According to the WHO diagnostic criteria for the novel coronavirus, we divided the patients into two groups: severe and non-severe, and compared their clinical, laboratory, and imaging data. Logistic regression analysis, the least absolute shrinkage and selection operator (LASSO) regression, and receiver operating characteristic (ROC) curve analysis were used to identify the relevant risk factors for severe COVID-19 patients. Patients were divided into a training cohort and a validation cohort. A nomogram model was constructed using the “rms” package in R software. Among the 346 patients, the severe group exhibited significantly higher respiratory rates, breathlessness, altered consciousness, neutrophil-to-lymphocyte ratio (NLR), and lactate dehydrogenase (LDH) levels compared to the non-severe group. Imaging findings indicated that the severe group had a higher proportion of bilateral pulmonary inflammation and ground-glass opacities compared to the non-severe group. NLR and LDH were identified as independent risk factors for severe patients. The diagnostic performance was maximized when NLR, respiratory rate (RR), and LDH were combined. Based on the statistical analysis results, we developed a COVID-19 severity risk prediction model. The total score is calculated by adding up the scores for each of the twelve independent variables. By mapping the total score to the lowest scale, we can estimate the risk of COVID-19 severity. In addition, the calibration plots and DCA analysis showed that the nomogram had better discrimination power for predicting the severity of COVID-19. Our results showed that the development and validation of the predictive nomogram had good predictive value for severe COVID-19.

Quality control of programs for detection of significant prostate cancer (sPCa) could be defined by the correlation between observed and reference 95% confidence intervals (CIs) for Prostate Imaging-Reporting and Data System (PI-RADS) categories. We used the area under the receiver operating characteristic curve (AUC) for the Barcelona magnetic resonance imaging (MRI) predictive model to screen the quality of ten participant centers in the sPCa opportunistic early detection program in Catalonia. We set an AUC of 3.0 ng/ml and/or a suspicious digital rectal examination who underwent multiparametric MRI and two- to four-core targeted biopsies of PI-RADS ≥3 lesions and/or 12-core systematic biopsy, AUC values ranged from 0.527 to 0.914 and were

Objectives: Coronavirus disease 2019 (COVID-19) emerged as a global pandemic during 2019 to 2022. The gold standard method of detecting this disease is reverse transcription-polymerase chain reaction (RT-PCR). However, RT-PCR has a number of shortcomings. Hence, the objective is to propose a cheap and effective method of detecting COVID-19 infection by using machine learning (ML) techniques, which encompasses five basic parameters as an alternative to the costly RT-PCR. Materials and Methods: Two machine learning-based predictive models, namely, Artificial Neural Network (ANN) and Multivariate Adaptive Regression Splines (MARS), are designed for predicting COVID-19 infection as a cheaper and simpler alternative to RT-PCR utilizing five basic parameters [i.e., age, total leucocyte count, red blood cell count, platelet count, C-reactive protein (CRP)]. Each of these parameters was studied, and correlation is drawn with COVID-19 diagnosis and progression. These laboratory parameters were evaluated in 171 patients who presented with symptoms suspicious of COVID-19 in a hospital at Kharagpur, India, from April to August 2022. Out of a total of 171 patients, 88 and 83 were found to be COVID-19-negative and COVID-19-positive, respectively. Results: The accuracies of the predicted class are found to be 97.06% and 91.18% for ANN and MARS, respectively. CRP is found to be the most significant input parameter. Finally, two predictive mathematical equations for each ML model are provided, which can be quite useful to detect the COVID-19 infection easily. Conclusion: It is expected that the present study will be useful to the medical practitioners for predicting the COVID-19 infection in patients based on only five very basic parameters.

As global climates undergo changes, the frequency of water-related disasters rises, leading to significant economic losses and safety hazards. During flood events, river water levels exhibit unpredictable fluctuations, introducing considerable noise that poses challenges for accurate prediction. A prediction of water level by using existing water level data makes a major contribution to forecasting flood. Enhanced least-squares support vector machine (ELSSVM) is utilized by integrating an additional extra bias error control term. In this study, least-squares support vector machine (LSSVM) and ELSSVM optimized by the genetic algorithm (GA) were chosen to be compared with the help of data decomposition methods to improve daily water level prediction accuracy. Double empirical mode decomposition (DEMD) will be integrated with LSSVM and ELSSVM. Thus, the models are named LSSVM-GA, ELSSVM-GA, empirical mode decomposition (EMD)-LSSVM-GA, EMD-ELSSVM-GA, DEMD-LSSVM-GA, and DEMD-ELSSVM-GA. The proposed models are used in forecasting the water level of Klang River in Sri Muda, Malaysia. The behavior proposed models are investigated and compared based on several performance metrics. The results demonstrated that the DEMD-ELSSVM-GA model outperformed the other models based on the performance analysis in forecasting the water level with RMSE = 0.2536 m and R2 = 0.8596 for testing data that indicate the forecasting accuracy. HIGHLIGHTS Klang River in Malaysia was chosen as the case study.; Data decomposition methods are integrated to mitigate high-frequency noise data.; Enhanced least-squares support vector machine (LSSVM) by adding extra bias error control term.; Hybrid double empirical mode decomposition is proposed to decompose water level data.; LSSVM and enhanced LSSVM models have been optimized by genetic algorithm.;

In order to effectively predict the changing trend of operating parameters in the pump unit and carry out fault diagnosis and alarm processes, a trend prediction model is proposed in this paper based on PCA-based multi-task learning (MTL) and an attention mechanism (AM). The multi-task learning method based on PCA was used to process the operating data of the pump unit to make full use of the historical data to extract the key common features reflecting the operating state of the pump unit. The attention mechanism (AM) is introduced to dynamically allocate the weight coefficient of common feature mapping for highlighting the key common features and improving the prediction accuracy of the model when predicting the trend of data change for new working conditions. The model is tested with the actual operating data of a pumping station unit, and the calculation results of different models are compared and analyzed. The results show that the introduction of multi-task learning and attention mechanisms can improve the stability and accuracy of the trend prediction model compared with traditional single-task learning and static common feature mapping weights. According to the threshold analysis of the monitoring statistical parameters of the model, a multi-stage alarm model of pump unit operation condition monitoring can be established, which provides a theoretical basis for optimizing operation and maintenance management strategy in the process of pump station management. [ABSTRACT FROM AUTHOR]

Systems vaccinology is an emerging field that integrates structural biology and immunology to revolutionize vaccine development and evaluation. By leveraging high-throughput omics technologies, computational biology, and bioinformatics, systems vaccinology offers comprehensive insights into the molecular and cellular mechanisms underlying immune responses. This holistic approach enables the identification of novel biomarkers, the prediction of vaccine efficacy, and an understanding of adverse reactions. Recent applications in infectious diseases, cancer immunotherapy, and personalized vaccines have demonstrated the potential of systems vaccinology to enhance vaccine design and optimize immunization strategies. Trends highlight the integration of multi-omics data, machine learning algorithms, and big data analytics to create predictive models of vaccine responses. The application of systems vaccinology has led to the discovery of correlates of protection, aiding in the rational design of next-generation vaccines. Despite these advancements, challenges remain, including data integration, standardization, and the need for interdisciplinary collaboration. Future perspectives focus on the development of universally accepted vaccines, rapid-response systems for emerging pathogens, and the incorporation of artificial intelligence to accelerate vaccine discovery. Systems vaccinology stands at the forefront of transforming public health by providing robust tools to combat infectious diseases and enhance global immunization programs. [ABSTRACT FROM AUTHOR]

In view of the problem of high failure efficiency of IGBT (Insulated Gate Bipolar Transistor) modules in inverters, which are most prone to damage and aging, and the device degradation process is difficult to predict, a neural network prediction model combining LSTM (Long Short Term Memory) and chaotic sparrow is proposed. By introducing the two dimensional Pearson correlation coefficient method to obtain the combined degradation features, the LSTM-based voltage degradation prediction model is constructed. The model is used to adaptively extract the internal correlations of degradation features to realize the screening of key information and digging deep degradation features. In the feasible domain of sparrow search algorithm, Gaussian random numbers with normal distribution and chaotic sequence corresponding to Tent mapping are introduced to improve the accuracy and stability of prediction. The learning rate, number of neurons and batch size of the model are optimized to find the optimal value to match the network topology. The LSTM with the optimal structural parameters is used to predict each original data separately and obtain the final degradation prediction value. The accelerated degradation data set of NANS experimental center is analyzed and compared with the conventional prediction algorithm to verify the effectiveness and accuracy of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Currently, FEA software such as ABAQUS uses empirical models to predict the sound absorption coefficient of poroelastic materials. However, based on a recent review of the literature it was found that the current sound absorption empirical models are inadequate for accurate prediction of thin (t < 20 mm), low-density materials (ρB < 50 kg/m³). Therefore, the predictions of the sound pressure levels in vehicle cabins, using such software, will be inaccurate since the trim materials are thin and have a low density. Thus, this research aimed to develop an empirical model that can accurately predict the sound absorption coefficient of these materials. Hence, polypropylene fibres consisting of four different diameters were manufactured and converted into nonwovens. Thereafter, airflow resistivity and impedance tube experimental testing were performed on the specimens. Subsequently, statistical analysis of the data was performed using SAS software. SAS was used to identify which independent variables should be included in the models to be developed. The empirical models were developed using the regression analysis toolbox in Microsoft Excel. Once the models were developed, various checks were performed to validate the assumptions of linear regression. The software NumXL was used to perform Cook's distance tests. Thereafter, the models were validated against the validation dataset, where it was found that the developed exponential model performed best. Finally, the exponential model was compared to existing models using two data sets i.e. an internal dataset, and an external dataset derived from the literature. The developed model outperformed all the historic models on both datasets. [ABSTRACT FROM AUTHOR]

The consumption of fresh and fresh‐cut fruits and vegetables, such as carrots, has increased for the last decades for a healthy life and an adequate diet, but concerns regarding the microbial safety of them have been raised. The present study was conducted to develop predictive models for Salmonella spp. in grated carrots. The results showed that Salmonella spp. did not display growth at 5°C, but it grew in grated carrots at other temperatures (10, 15, 20, 25, and 37°C) for both inoculum levels. Also, the inoculum levels affected the growth of this pathogen in grated carrots when the storage temperatures ranged from 15 to 25°C. The theoretical minimum temperatures calculated using the Huang model were 3.48 and 5.79°C for inoculum levels of 101 and 102 CFU/g, respectively. The primary and secondary models performed well in terms of agreement between experimental and estimated values. Furthermore, compared to the Ratkowsky model, the theoretical minimum temperature was given a more reasonable value using the Huang model. The models developed in the present study will be a useful input for future quantitative microbial risk assessment to appraise the proliferation of Salmonella spp. in grated carrots throughout the production process, storage, and distribution. [ABSTRACT FROM AUTHOR]

Chemical mechanical planarization (CMP) is vital for ensuring chip fabrication uniformity at nanometer scales. The emergence of a series of phenomenological CMP process models (Stine et al., 1997; Gbondo-Tugbawa, 2002; Xie, 2007; Vasilev, 2011) suggests that the existing model upgrade approach is largely based on a change in phenomenological model assumptions, demanding deep insights into complex process mechanisms and protracted period for accuracy improvements. To tackle this issue, this paper proposes a decoupling regression strategy for model upgrades. This strategy employs a data-driven approach to enhance the coupling relationships within the model, facilitating continuous improvement of simulation accuracy based on the existing model. It is capable of achieving improvements in model accuracy even in scenarios where modelers lack insight into complex process mechanisms. We validate our method by upgrading the Density Step Height (DSH) model to the Extend-DSH model to address poor erosion predictions at the 28nm node. Comparing model predictions with silicon data reveals that the Extend-DSH model aligns better with the measured data, reducing the root mean square error from 159.31Å to 6.89Å and increasing the coefficient of determination from -0.83561 to 0.6058, showcasing the effectiveness of the proposed chip-level CMP model upgrade method grounded in the decoupling regression strategy. [ABSTRACT FROM AUTHOR]

It is known that the determination of the good-dice-in-bad-neighborhoods (GDBNs) has been regarded as an effective technique to reduce the value of the defect parts per million (DPPM) by identifying and rejecting the suspicious dice even though they are good in testing. Instead of examining eight immediate neighbors in a small-sized $3\times 3$ window or exploiting simple linear regression, a large-sized window can be used to recognize the broad-sighted neighborhoods and accurately infer the suspiciousness level for any given die. In this paper, the artificial neural networks (ANN)-based method can be proposed to solve the GDBN identification. Furthermore, two enhanced techniques can be further presented to improve the inference accuracy of the original ANN-based method by considering the variation of the time-dependent wafer patterns and the wafer-to-wafer relationship between two adjacent wafers. After applying the two enhanced techniques, the business profits can be improved in the new ANN-based method. Various experiments on two datasets clearly reveal the superiority of the proposed ANN-based method over the other existing methods. In addition to the reduction of the DPPM value, the new ANN-based method can achieve the 1.5X–2X better reduction in the cost of the return merchandise authorization (RMA). On the other hand, the experimental results show that the similar result can also be obtained in the other lower-yield products. By using the new ANN-based method, the relationships on bad dice cross wafers can be captured and the highly-accurate inference results can be simultaneously maintained. [ABSTRACT FROM AUTHOR]

The primary objectives of this research study are to provide a detailed description of machine learning (ML) technology when applied to assessing innovation and to design a model that allows predicting an institution’s degree of innovation. Machine learning technology lacks assumptions or preconceptions and is capable of processing a large amount of data and variables. After data processing, the ML model is built using variables associated with educational context, training is performed, and a web is built to predict the degree of innovation of an educational institution. This model provides an innovation accuracy prediction of 66% and allows assessing the influence of the variables analyzed when predicting the use of active methodologies at a given institution. In conclusion, this approach can open new data analysis techniques supported by ML that complement traditional statistically based approaches. [ABSTRACT FROM AUTHOR]

Greenery initiatives, such as green infrastructures (GIs), create sustainable and climate-resilient environments. However, they can also have unintended consequences, such as displacement and gentrification in low-income areas. This paper proposes an integrated machine learning (ML) approach that combines both unsupervised and supervised ML algorithms. First, 35 indicators that contribute to green gentrification were identified and categorised into 7 categories: social, economic, demographic, housing, household, amenities, and GIs. Second, data was collected for all census tracts in New York City. Third, the green gentrification susceptibility was modelled into 6 levels using k-means clustering analysis, which is an unsupervised ML model. Fourth, the Technique for Order of Preference by Similarity to the Ideal Solution (TOPSIS) was used to map the census tracts to their green gentrification susceptibility level. Finally, different supervised ML algorithms were trained and tested to predict the green gentrification susceptibility. The results showed that the artificial neural network (ANN) model is the most accurate in classifying and predicting the green gentrification susceptibility with an overall accuracy of 96%. Moreover, the outcomes showed that the Normal Difference Vegetation Index (NDVI), the proximity to GIs, the GIs frequency, and the total area of GIs were identified as the most important indicators to predict green gentrification susceptibility. Ultimately, the proposed approach allows practitioners and researchers to perform micro-level (i.e. on the census-tracts level) predictions and inferences about green gentrification susceptibility. This allows more focused and targeted mitigation actions to be designed and implemented in the most affected communities, thus promoting environmental justice. [ABSTRACT FROM AUTHOR]

Background: Thyroid cancer is the most common malignancy of the endocrine system. PANoptosis is a specific form of inflammatory cell death. It mainly includes pyroptosis, apoptosis and necrotic apoptosis. There is increasing evidence that PANoptosis plays a crucial role in tumour development. However, no pathogenic mechanism associated with PANoptosis in thyroid cancer has been identified. Methods: Based on the currently identified PANoptosis genes, a dataset of thyroid cancer patients from the GEO database was analysed. To screen the common differentially expressed genes of thyroid cancer and PANoptosis. To analyse the functional characteristics of PANoptosis-related genes (PRGs) and screen key expression pathways. The prognostic model was established by LASSO regression and key genes were identified. The association between hub genes and immune cells was evaluated based on the CIBERSORT algorithm. Predictive models were validated by validation datasets, immunohistochemistry as well as drug-gene interactions were explored. Results: The results showed that eight key genes (NUAK2, TNFRSF10B, TNFRSF10C, TNFRSF12A, UNC5B, and PMAIP1) exhibited good diagnostic performance in differentiating between thyroid cancer patients and controls. These key genes were associated with macrophages, CD4+ T cells and neutrophils. In addition, PRGs were mainly enriched in the immunomodulatory pathway and TNF signalling pathway. The predictive performance of the model was confirmed in the validation dataset. The DGIdb database reveals 36 potential therapeutic target drugs for thyroid cancer. Conclusion: Our study suggests that PANoptosis may be involved in immune dysregulation in thyroid cancer by regulating macrophages, CD4+ T cells and activated T and B cells and TNF signalling pathways. This study suggests potential targets and mechanisms for thyroid cancer development. [ABSTRACT FROM AUTHOR]

Holocellulose, a term encompassing both cellulose and hemicellulose, constitutes a crucial component of plant cell walls. Traditional wet chemistry methods (WCMs) for measuring holocellulose content have been criticized for their environmental unfriendliness and low efficiency. In the southern part of China, Chinese fir plantations play a significant role as a resource for wood, paper, and bioenergy. This study proposes the use of Raman signals, along with various algorithms, to predict the holocellulose content of Chinese fir as an alternative to traditional WCMs. The results indicate the successful development of a reliable predictive model by carefully selecting the most suitable internal standard peak and algorithm. Furthermore, transfer learning is demonstrated to enhance the accuracy and efficiency of the model. Consequently, the establishment of such predictive models is recommended for consideration in similar endeavors aiming to be a complementary method to WCMs. [ABSTRACT FROM AUTHOR]

Biochar is crucial for agricultural output and plays a significant role in effectively eliminating heavy metals (HMs) from the soil, which is essential for maintaining a soil–plant environment. This work aimed to assess machine learning models to analyze the impact of soil parameters on the transformation of HMs in biochar–soil–plant environments, considering the intricate non-linear relationships involved. A total of 211 datasets from pot or field experiments were evaluated. Fourteen factors were taken into account to assess the efficiency and bioavailability of HM–biochar amendment immobilization. Four predictive models, namely linear regression (LR), partial least squares (PLS), support vector regression (SVR), and random forest (RF), were compared to predict the immobilization efficiency of biochar-HM. The findings revealed that the RF model was created using 5-fold cross-validation, which exhibited a more reliable prediction performance. The results indicated that soil features accounted for 79.7% of the absorption of HM by crops, followed by biochar properties at 17.1% and crop properties at 3.2%. The main elements that influenced the result have been determined as the characteristics of the soil (including the presence of different HM species and the amount of clay) and the quantity and attributes of the biochar (such as the temperature at which it was produced by pyrolysis). Furthermore, the RF model was further developed to predict bioaccumulation factors (BAF) and variations in crop uptake (CCU). The R2 values were found to be 0.7338 and 0.6997, respectively. Thus, machine learning (ML) models could be useful in understanding the behavior of HMs in soil–plant ecosystems by employing biochar additions. [ABSTRACT FROM AUTHOR]

Medical deep neural networks (DNNs) trained upon coarse image inputs are inherently insensible to fine-grained anatomic features. To enhance DNN perception on delicate microvascular structures, we proposed using a straightforward angiographic mobile-dense hybrid network (AMDenseNet) in tandem with a flexible input split, suppression, and swap perturbation (InSSS-P) framework to perform explainable diagnostics for microvascular diseases. Mechanistically, InSSS-P and AMDenseNet conjointly (1) decompose complex anatomy inputs into LEGO-like blocks, then (2) distill plexus-wise vascular block significance from the rearranged anatomy input-output samplings. To validate the robustness of the proposed model, we trained AMDenseNet to detect blind-threatening retina exudative age-related macular degeneration (exAMD) from the micrometer-scaled optic coherence tomographic angiography (OCTA), wherein our AMDenseNet annotated triple-specific (plexus, branch, and exudate activity) neovascular (NV) features at a diagnostic precision that is comparable to the gold standard dye-based angiography. Interestingly, when we applied plexus-wise InSSS-P to the AMDenseNet predictions, the permutate results demonstrated that input perturbation at deep capillary plexus (DCP) layer abrogated model-awared exAMD features and resulted in false-negative exAMD impressions. On the contrary, choroid capillary (CC) input perturbations contributed to false-positive exAMD characterization. Notably, the AMDenseNet triple-specific NV annotation functionality was disrupted by either DCP or CC input perturbations, indicating the significance of DCP and CC in the task of exAMD characterization. In sum, this study employed anatomy decomposition approaches to distill plexus-wise microvascular significance and highlighted the analytic potential of leveraging an anatomy-sensible model to discover novel disease biomarkers. [ABSTRACT FROM AUTHOR]

BACKGROUND: Brain age model, including estimated brain age and brain-predicted age difference (brain-PAD), has shown great potentials for serving as imaging markers for monitoring normal ageing, as well as for identifying the individuals in the pre-diagnostic phase of neurodegenerative diseases. PURPOSE: This study aimed to investigate the brain age models in normal ageing and mild cognitive impairments (MCI) converters and their values in classifying MCI conversion. METHODS: Pre-trained brain age model was constructed using the structural magnetic resonance imaging (MRI) data from the Cambridge Centre for Ageing and Neuroscience (Cam-CAN) project (N = 609). The tested brain age model was built using the baseline, 1-year and 3-year follow-up MRI data from normal ageing (NA) adults (n = 32) and MCI converters (n = 22) drew from the Open Access Series of Imaging Studies (OASIS-2). The quantitative measures of morphometry included total intracranial volume (TIV), gray matter volume (GMV) and cortical thickness. Brain age models were calculated based on the individual's morphometric features using the support vector machine (SVM) algorithm. RESULTS: With comparable chronological age, MCI converters showed significant increased TIV-based (Baseline: P = 0.021; 1-year follow-up: P = 0.037; 3-year follow-up: P = 0.001) and left GMV-based brain age than NA adults at all time points. Higher brain-PAD scores were associated with worse global cognition. Acceptable classification performance of TIV-based (AUC = 0.698) and left GMV-based brain age (AUC = 0.703) was found, which could differentiate the MCI converters from NA adults at the baseline. CONCLUSIONS: This is the first demonstration that MRI-informed brain age models exhibit feature-specific patterns. The greater GMV-based brain age observed in MCI converters may provide new evidence for identifying the individuals at the early stage of neurodegeneration. Our findings added value to existing quantitative imaging markers and might help to improve disease monitoring and accelerate personalized treatments in clinical practice. Plain Language Summary: Based on individual's MRI scans, brain age model has shown great potentials for serving as imaging markers for monitoring normal ageing (NA), as well as for identifying the ones in the pre-diagnostic phase of age-related neurodegenerative diseases. In this study, we investigated the brain age models in normal ageing and mild cognitive impairments (MCI) converters and their values in classifying MCI conversion. Pre-trained brain age model was constructed using the quantitative measures of morphometry included total intracranial volume (TIV), gray matter volume (GMV) and cortical thickness. With comparable chronological age, MCI converters showed significant increased brain age than NA adults at all time points. Higher brain age were associated with worse global cognition. This is the first demonstration that MRI-informed brain age models exhibit feature-specific patterns. The greater GMV-based brain age observed in MCI converters may provide new evidence for identifying the individuals at the early stage of neurodegeneration. Our findings added value to existing quantitative imaging markers and might help to improve disease monitoring and accelerate personalized treatments in clinical practice. [ABSTRACT FROM AUTHOR]

The diagnosis of oral lichen planus (OLP) poses many challenges due to its nonspecific clinical symptoms and histopathological features. Therefore, the diagnostic process should include a thorough clinical history, immunological tests, and histopathology. Our study aimed to enhance the diagnostic accuracy of OLP by integrating direct immunofluorescence (DIF) results with clinical data to develop a multivariate predictive model based on the Artificial Neural Network. Eighty patients were assessed using DIF for various markers (immunoglobulins of classes G, A, and M; complement 3; fibrinogen type 1 and 2) and clinical characteristics such as age, gender, and lesion location. Statistical analysis was performed using machine learning techniques in Statistica 13. The following variables were assessed: gender, age on the day of lesion onset, results of direct immunofluorescence, location of white patches, locations of erosions, treatment history, medications and dietary supplement intake, dental status, smoking status, flossing, and using mouthwash. Four statistically significant variables were selected for machine learning after the initial assessment. The final predictive model, based on neural networks, achieved 85% in the testing sample and 71% accuracy in the validation sample. Significant predictors included stress at onset, white patches under the tongue, and erosions on the mandibular gingiva. In conclusion, while the model shows promise, larger datasets and more comprehensive variables are needed to improve diagnostic accuracy for OLP, highlighting the need for further research and collaborative data collection efforts. [ABSTRACT FROM AUTHOR]

(1) Background: Evidence regarding Non-Alcoholic Fatty Liver Disease (NAFLD) diagnosis is limited in the context of patients with gallstone disease (GD). This study aimed to assess the predictive potential of conventional clinical and biochemical variables as combined models for diagnosing NAFLD in patients with GD. (2) Methods: A cross-sectional study including 239 patients with GD and NAFLD diagnosed by ultrasonography who underwent laparoscopic cholecystectomy and liver biopsy was conducted. Previous clinical indices were also determined. Predictive models for the presence of NAFLD stratified by biological sex were obtained through binary logistic regression and sensitivity analyses were performed. (3) Results: For women, the model included total cholesterol (TC), age and alanine aminotransferase (ALT) and showed an area under receiver operating characteristic curve (AUC) of 0.727 (p < 0.001), sensitivity of 0.831 and a specificity of 0.517. For men, the model included TC, body mass index (BMI) and aspartate aminotransferase (AST), had an AUC of 0.898 (p < 0.001), sensitivity of 0.917 and specificity of 0.818. In both sexes, the diagnostic performance of the designed equations was superior to the previous indices. (4) Conclusions: These models have the potential to offer valuable guidance to healthcare providers in clinical decision-making, enabling them to achieve optimal outcomes for each patient. [ABSTRACT FROM AUTHOR]

This review article explores the transformative impact of Artificial Intelligence (AI) and Machine Learning (ML) in cancer research. It focuses on the critical role of AI in medical imaging for cancer detection, exploring deep learning algorithms for image recognition and feature extraction. The study also examines the challenges and considerations in implementing AI for image analysis in cancer diagnosis. AI is also utilized for mining and analyzing large-scale omics data, such as genomics and proteomics. It is used to decipher complex genetic mutations and signaling pathways in cancer, integrating clinical and molecular data for more accurate diagnosis and treatment planning. The review also discusses AI applications in drug discovery, target identification and drug repurposing for cancer. AI-driven algorithms are used to predict drug responses and identify novel therapeutic targets, with case studies illustrating successful applications. The review evaluates the impact of AI on clinical decision-making and patient care, highlighting the challenges and opportunities in translating AI research into clinical practice. The review concludes with future directions and innovations, exploring emerging trends and potential advancements in AI-driven cancer research. [ABSTRACT FROM AUTHOR]

This research addresses the gap in comprehensive predictive models for construction project success rating by exploring the potential of regression models to evaluate project success rating. By analyzing 130 datasets from the National Capital Region, the study utilizes Support Vector Regression (SVR), Multiple Linear Regression (MLR), and Artificial Neural Network (ANN) with a 22-30-1 configuration (22 input neurons, 30 neurons in a single hidden layer, and 1 output neuron). The input variables represent critical success factors rated on a scale of 1-5, while the output variable represents the predicted project success percentage rating. Various statistical tools, including ANOVA, Lasso Regression, R², MAE, and MSE, are utilized for evaluation. The findings reveal that SVR achieved the highest accuracy (R² = 0.881, MAE = 2.172, MSE = 7.054), followed closely by MLR (R² = 0.874, MAE = 2.180, MSE = 7.470), while ANN (R² = 0.743, MAE = 3.076, MSE = 15.239) may require refinement. Lasso Regression identified 22 critical success factors, with Financial Condition, Effectiveness in Decision-Making, and Compliance to Quality Standards ranking as the top three. This research contributes to the advancement of construction predictive analytics, which can lead to improved decision-making and more efficient, effective, and ethical construction practices. [ABSTRACT FROM AUTHOR]

Background: The application of posttransplant predictive models is limited by their poor statistical performance. Neglecting the dynamic evolution of demographics and medical practice over time may be a key issue. Objectives: Our objective was to develop and validate era‐specific predictive models to assess whether these models could improve risk stratification compared to non–era‐specific models. Methods: We analyzed the United Network for Organ Sharing (UNOS) database including first noncombined heart transplantations (2001–2018, divided into four transplant eras: 2001–2005, 2006–2010, 2011–2015, 2016–2018). The endpoint was death or retransplantation during the 1st‐year posttransplant. We analyzed the dynamic evolution of major predictive variables over time and developed era‐specific models using logistic regression. We then performed a multiparametric evaluation of the statistical performance of era‐specific models and compared them to non–era‐specific models in 1000 bootstrap samples (derivation set, 2/3; test set, 1/3). Results: A total of 34 738 patients were included, 3670 patients (10.5%) met the composite endpoint. We found a significant impact of transplant era on baseline characteristics of donors and recipients, medical practice, and posttransplant predictive models, including significant interaction between transplant year and major predictive variables (total serum bilirubin, recipient age, recipient diabetes, previous cardiac surgery). Although the discrimination of all models remained low, era‐specific models significantly outperformed the statistical performance of non–era‐specific models in most samples, particularly concerning discrimination and calibration. Conclusions: Era‐specific models achieved better statistical performance than non–era‐specific models. A regular update of predictive models may be considered if they were to be applied for clinical decision‐making and allograft allocation. [ABSTRACT FROM AUTHOR]

Objectives: Coronavirus disease 2019 (COVID-19) emerged as a global pandemic during 2019 to 2022. The gold standard method of detecting this disease is reverse transcription-polymerase chain reaction (RT-PCR). However, RT-PCR has a number of shortcomings. Hence, the objective is to propose a cheap and effective method of detecting COVID-19 infection by using machine learning (ML) techniques, which encompasses five basic parameters as an alternative to the costly RT-PCR. Materials and Methods: Two machine learning-based predictive models, namely, Artificial Neural Network (ANN) and Multivariate Adaptive Regression Splines (MARS), are designed for predicting COVID-19 infection as a cheaper and simpler alternative to RT-PCR utilizing five basic parameters [i.e., age, total leucocyte count, red blood cell count, platelet count, C-reactive protein (CRP)]. Each of these parameters was studied, and correlation is drawn with COVID-19 diagnosis and progression. These laboratory parameters were evaluated in 171 patients who presented with symptoms suspicious of COVID-19 in a hospital at Kharagpur, India, from April to August 2022. Out of a total of 171 patients, 88 and 83 were found to be COVID-19-negative and COVID-19-positive, respectively. Results: The accuracies of the predicted class are found to be 97.06% and 91.18% for ANN and MARS, respectively. CRP is found to be the most significant input parameter. Finally, two predictive mathematical equations for each ML model are provided, which can be quite useful to detect the COVID-19 infection easily. Conclusion: It is expected that the present study will be useful to the medical practitioners for predicting the COVID-19 infection in patients based on only five very basic parameters. [ABSTRACT FROM AUTHOR]

BACKGROUND: Nasopharyngeal carcinoma (NC) is one of the prevalent malignancies of the head and neck region with poor prognosis. OBJECTIVE: The aim of this study is to establish a predictive model for assessing NC prognosis based on clinical and MR radiomics data, subsequently to develop a nomogram for practical application. METHODS: Retrospective analysis was conducted on clinical and imaging data collected between May 2010 and August 2018, involving 211 patients diagnosed with histologically confirmed NC who received concurrent chemoradiotherapy or radical surgery in Xiangyang No. 1 People's Hospital. According to 5–10 years of follow-up results, the patients were divided into two groups: the study group (n = 76), which experienced recurrence, metastasis, or death, and the control group (n = 135), characterized by normal survival. Training and testing subsets were established at a 7:3 ratio, with a predefined time cutoff. In the training set, three prediction models were established: a clinical data model, an imaging model, and a combined model using the integrated variation in clinical characteristics along with MR radiomics parameters (Delta-Radscore) observed before and after concurrent chemoradiotherapy. Model performance was compared using Delong's test, and net clinical benefit was assessed via decision curve analysis (DCA). Then, external validation was conducted on the test set, and finally a nomogram predicting NC prognosis was created. RESULTS: Univariate analysis identified that the risk factors impacting the prognosis of NC included gender, pathological type, neutrophil to lymphocyte ratio (NLR), degree of tumor differentiation, MR enhancement pattern, and Delta-Radscore (P < 0.05). The combined model established based on the abovementioned factors exhibited significantly higher predictive performance [AUC: 0.874, 95% CI (0.810–0.923)] than that of the clinical data model [AUC: 0.650, 95% CI (0.568–0.727)] and imaging model [AUC: 0.824, 95% CI (0.753–0.882)]. DCA also demonstrated superior clinical net benefit in the combined model, a finding further verified by results from the test set. The developed nomogram, based on the combined model, exhibited promising performance in clinical applications. CONCLUSION: The Delta-Radscore derived from MR radiomics data before and after concurrent chemoradiotherapy helps enhance the performance of the NC prognostic model. The combined model and resultant nomogram provide valuable support for clinical decision-making in NC treatment, ultimately contributing to an improved survival rate. [ABSTRACT FROM AUTHOR]

The increasing popularity of LLM-based chatbots combined with their reliance on power-hungry GPU infrastructure forms a critical challenge for providers: minimizing energy consumption under Service-Level Objectives (SLOs) that ensure optimal user experience. Traditional energy optimization methods fall short for LLM inference due to their autoregressive architecture, which renders them incapable of meeting a predefined SLO without energy overprovisioning. This autoregressive nature however, allows for iteration-level adjustments, enabling continuous fine-tuning of the system throughout the inference process. In this letter, we propose a solution based on iteration-level GPU Dynamic Voltage Frequency Scaling (DVFS), aiming to reduce the energy impact of LLM serving, an approach that has the potential for more than 22.8% and up to 45.5% energy gains when tested in real world situations under varying SLO constraints. Our approach works on top of existing LLM hosting services, requires minimal profiling and no intervention to the inference serving system. [ABSTRACT FROM AUTHOR]