Search

BACKGROUND: Both defects in mismatch repair (dMMR) and high microsatellite instability (MSI-H) have been recognised as crucial biomarkers that guide treatment strategies and disease management in colorectal cancer (CRC). As MMR and MSI tests are being widely conducted, an increasing number of MSI-H tumours have been identified in CRCs with mismatch repair proficiency (pMMR). The objective of this study was to assess the clinical features of patients with pMMR/MSI-H CRC and elucidate the underlying molecular mechanism in these cases. METHODS: From January 2015 to December 2018, 1684 cases of pMMR and 401 dMMR CRCs were enrolled. Of those patients, 93 pMMR/MSI-H were identified. The clinical phenotypes and prognosis were analysed. Frozen and paraffin-embedded tissue were available in 35 patients with pMMR/MSI-H, for which comprehensive genomic and transcriptomic analyses were performed. FINDINGS: In comparison to pMMR/MSS CRCs, pMMR/MSI-H CRCs exhibited significantly less tumour progression and better long-term prognosis. The pMMR/MSI-H cohorts displayed a higher presence of CD8+ T cells and NK cells when compared to the pMMR/MSS group. Mutational signature analysis revealed that nearly all samples exhibited deficiencies in MMR genes, and we also identified deleterious mutations in MSH3-K383fs. INTERPRETATION: This study revealed pMMR/MSI-H CRC as a distinct subgroup within CRC, which manifests diverse clinicopathological features and long-term prognostic outcomes. Distinct features in the tumour immune-microenvironment were observed in pMMR/MSI-H CRCs. Pathogenic deleterious mutations in MSH3-K383fs were frequently detected, suggesting another potential biomarker for identifying MSI-H. FUNDING: This work was supported by the Science and Technology Commission of Shanghai Municipality (20DZ1100101).

Data has become a high-value commodity in manufacturing. There is a growing realisation that the data-driven applications could become strong differentiators of manufacturing enterprises. To guide the developments in digitisation, a widely accepted framework is needed. In the absence of the universal framework, the components making a digital enterprise are captured in an example framework that is introduced in the paper. The adoption of new technology and software solutions has increased complexity of manufacturing systems. In addition, new product introductions have become more frequent and the demand more variable. A digital space enables optimisation and simulation of decisions before their realisation in the physical space. Predictive modelling with its time dimension is a valuable actor in the digital space. Three challenges of predictive modelling such as model complexity, model interpretability, and model reuse are identified in this paper. The coverage of each challenge in the literature is illustrated with the recently published papers. The main aspects of these challenges and the synthesis of the developments in digital manufacturing are articulated in the form of eight observations that could guide the future research. [ABSTRACT FROM AUTHOR]

Diapause is a vital survival strategy for insects, enabling them to conserve energy and endure adverse conditions. Understanding how diapause affects insect phenology and population dynamics is crucial for the effective management of insect pests. Predictive pest phenological models can be invaluable tools for providing essential information to support management strategies. This study presents a modelling framework to incorporate diapause into phenological models when biological information on variables regulating and functions describing diapause induction and termination are lacking or limited. In our framework, insect phenology is divided into a set of phases characterized by specific events (diapause induction and termination) and processes (development of diapausing and post‐diapausing biological stages). The phenology is simulated by a stage‐structured model based on the Kolmogorov equation, and the temperature‐dependent development rate functions are described by the Brière functional form. Our modelling framework was tested on a case study involving the prediction of the phenology of the codling moth, (Cydia pomonella L. 1758). Model calibration and validation were performed using four time‐series adult trap catch data collected in the Emilia Romagna Region from 2021 to 2023. The calibration procedure allowed obtaining realistic parameters related to the temperature threshold triggering diapause termination and the development rate function of post‐diapausing larvae and pupae. Model validation proved successful in simulating both the initial emergence and the overall phenological patterns of adults across the three observed generations. The methodological framework proposed here aims to facilitate the introduction of diapause in phenological models improving also their predictive abilities. The model may serve as an accurate and knowledge‐based tool for planning and implementing pest monitoring and control actions based on the realistic predictions provided by the model on the phenological status of the pest. [ABSTRACT FROM AUTHOR]

Preserving the archaeological heritage of North Africa is challenging due to unique anthropic and environmental processes. This study introduces a Bayesian network approach to model and evaluates the impact of regional anthropogenic actions and environmental conditions on the gradual disappearance of endangered archaeological heritage in the Marmarica region (northeastern Libya/northwestern Egypt). The predictive model quantifies the complex relationship among human–environment interactions involved in such processes, specifically addressing the nonlinear vulnerability of archaeological heritage to the convergence of different threats, such as climate change, urban development, or natural erosion. This model also enables us to explore patterns of association between anthropic remains (e.g. settlements, productive places, mobility structures, etc.) and environmental factors (e.g. topography, climate, hydrology, etc.), considering different co-occurring agents in these dynamics. Furthermore, the model can be applied to study such processes in other regions, enabling wider effective risk management and heritage preservation efforts. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) uses sophisticated algorithms to “learn” from large volumes of data. This could be used to optimise recruitment of blood donors through predictive modelling of future blood supply, based on previous donation and transfusion demand. We sought to assess utilisation of predictive modelling and AI blood establishments (BE) and conducted predictive modelling to illustrate its use. A BE survey of data modelling and AI was disseminated to the International Society of Blood transfusion members. Additional anonymzed data were obtained from Italy, Singapore and the United States (US) to build predictive models for each region, using January 2018 through August 2019 data to determine likelihood of donation within a prescribed number of months. Donations were from March 2020 to June 2021. Ninety ISBT members responded to the survey. Predictive modelling was used by 33 (36.7%) respondents and 12 (13.3%) reported AI use. Forty‐four (48.9%) indicated their institutions do not utilise predictive modelling nor AI to predict transfusion demand or optimise donor recruitment. In the predictive modelling case study involving three sites, the most important variable for predicting donor return was number of previous donations for Italy and the US, and donation frequency for Singapore. Donation rates declined in each region during COVID‐19. Throughout the observation period the predictive model was able to consistently identify those individuals who were most likely to return to donate blood. The majority of BE do not use predictive modelling and AI. The effectiveness of predictive model in determining likelihood of donor return was validated; implementation of this method could prove useful for BE operations. [ABSTRACT FROM AUTHOR]

Aim Location Taxa Time Period Methods Results Conclusions Shifting climates are reshaping ecosystems globally and are projected to intensify over the coming century. Understanding how biodiversity will respond to these shifts is crucial for developing effective climate adaptation measures. We generate predictive models built from long‐term data to hindcast historic fluctuations in small mammal abundances as they have responded to shifting rainfall and fire conditions. This data set serves as the basis for predicting historical variations (hindcasting) in small mammal abundances, allowing us to examine their responses to decadal changes in fire and rainfall conditions within our study landscape.Australia (Victoria).Small mammals (Mammalia).1970–2022.Small mammal abundance was surveyed at 36 long‐term trapping sites and modelled against coinciding fire history, vegetation productivity and rainfall using generalized additive mixed models. Six species were then used in predictive modelling against these variables for the decades preceding our monitoring programme (1970–2007).All species abundances increased with higher rainfall. Time since fire was also an important variable in all but one species model, with species displaying varying responses to time since fire. Hindcasting predictions for small mammal abundances varied with some species showing marked declines over time. Clear trends emerged, indicating more volatile population fluctuations in response to intensified fire and rainfall extremes in the 21st century. This suggests that periods of higher rainfall and less frequent fire events in the decades preceding our monitoring period supported higher and more stable small mammal abundances.Native species show distinct sensitivity to the combined effects of drought and fire, which has occurred in recent times. Intensification of these drivers has caused increased volatility in small mammal abundances with low abundance extremes occurring more frequently. [ABSTRACT FROM AUTHOR]

The convergence of artificial intelligence (AI), big data (DB), and Internet of Things (IoT) in Society 5.0, has given rise to Marketing 5.0, revolutionizing personalized customer experiences. In this study, a systematic literature review was conducted to examine the integration of predictive modelling and sentiment analysis within the Marketing 5.0 domain. Unlike previous research, this study addresses both aspects within a single context, emphasizing the need for a sentiment-based predictive approach to the buyers' journey. This review explores how predictive and sentiment models enhance customer experience, inform business decisions, and optimize marketing processes. This study contributes to the literature by identifying areas of improvement in predictive modelling and emphasizes the role of a sentiment-based approach in Marketing 5.0. The sentiment-based model assists businesses in understanding customer preferences, offering personalized products, and enabling customers to receive relevant advertisements during their purchase journey. The paper's structure covers the evolution of traditional marketing to digital marketing, AI's role in digital marketing, predictive modelling in marketing, and the significance of analyzing customer sentiments in their reviews. The Prisma-P methodology, research questions, and suggestions for future work and limitations provide a comprehensive overview of the scope and contributions of this review. [ABSTRACT FROM AUTHOR]

Background Older adults (≥65 years) account for a disproportionately high proportion of hospitalization and in-hospital mortality, some of which may be avoidable. Although machine learning (ML) models have already been built and validated for predicting hospitalization and mortality, there remains a significant need to optimize ML models further. Accurately predicting hospitalization may tremendously affect the clinical care of older adults as preventative measures can be implemented to improve clinical outcomes for the patient. Methods In this retrospective cohort study, a data set of 14 198 community-dwelling older adults (≥65 years) with complex care needs from the International Resident Assessment Instrument-Home Care database was used to develop and optimize 3 ML models to predict 30-day hospitalization. The models developed and optimized were Random Forest (RF), XGBoost (XGB), and Logistic Regression (LR). Variable importance plots were generated for all 3 models to identify key predictors of 30-day hospitalization. Results The area under the receiver-operating characteristics curve for the RF, XGB, and LR models were 0.97, 0.90, and 0.72, respectively. Variable importance plots identified the Drug Burden Index and alcohol consumption as important, immediately potentially modifiable variables in predicting 30-day hospitalization. Conclusions Identifying immediately potentially modifiable risk factors such as the Drug Burden Index and alcohol consumption is of high clinical relevance. If clinicians can influence these variables, they could proactively lower the risk of 30-day hospitalization. ML holds promise to improve the clinical care of older adults. It is crucial that these models undergo extensive validation through large-scale clinical studies before being utilized in the clinical setting. [ABSTRACT FROM AUTHOR]

Medication harm affects between 5 and 15% of hospitalised patients, with approximately half of the harm events considered preventable through timely intervention. The Adverse Inpatient Medication Event (AIME) risk prediction model was previously developed to guide a systematic approach to patient prioritisation for targeted clinician review, but frailty was not tested as a candidate predictor variable. To evaluate the predictive performance of an updated AIME model, incorporating a measure of frailty, when applied to a new multisite cohort of hospitalised adult inpatients. A retrospective cohort study was conducted at two tertiary Australian hospitals on patients discharged between 1st January and April 31, 2020. Data were extracted from electronic medical records (EMRs) and clinical coding databases. Medication harm was identified using ICD-10 Y-codes and confirmed by senior pharmacist review of medical records. The Hospital Frailty Risk Score (HFRS) was calculated for each patient. Logistic regression analysis was used to construct a modified AIME model. Candidate variables of the original AIME model, together with new variables including HFRS were tested. Performance of the final model was reported using area under the curve (AUC) and decision curve analysis (DCA). A total of 4089 patient admissions were included, with a mean age ± standard deviation (SD) of 64 years (±19 years), 2050 patients (50%) were males, and mean HFRS was 6.2 (±5.9). 184 patients (4.5%) experienced one or more medication harm events during hospitalisation. The new AIME-Frail risk model incorporated 5 of the original variables: length of stay (LOS), anti-psychotics, antiarrhythmics, immunosuppressants, and INR greater than 3, as well as 5 new variables: HFRS, anticoagulants, antibiotics, insulin, and opioid use. The AUC was 0.79 (95% CI: 0.76–0.83) which was superior to the original model (AUC = 0.70, 95% CI: 0.65–0.74) with a sensitivity of 69%, specificity of 81%, positive predictive value of 0.14 (95% CI: 0.10–0.17) and negative predictive value of 0.98 (95% CI: 0.97–0.99). The DCA identified the model as having potential clinical utility between the probability thresholds of 0.05–0.4. The inclusion of a frailty measure improved the predictive performance of the AIME model. Screening inpatients using the AIME-Frail tool could identify more patients at high-risk of medication harm who warrant timely clinician review. [ABSTRACT FROM AUTHOR]

The freshwater zooplankton of New Zealand-Aotearoa are species-poor with only two indigenous Daphnia species: D. thomsoni, and D. tewaipounamu. Over the last two decades, two species of invasive non-indigenous Daphnia, D. pulicaria/pulex and D. galeata, have become well established in many lakes in New Zealand-Aotearoa and their distribution appears to be rapidly increasing. We report the current distribution of these two invasive species in approximately 300 lakes throughout New Zealand-Aotearoa and test the hypothesis that the distribution and establishment of these invaders is more closely related to human access to a lake than to any environmental attributes of a lake's water or biota and consider potential implications of our findings for lake management. Boosted regression tree analysis identified total nitrogen and distance from the coast (D. pulicaria) and annual lake temperature (D. galeata) as key variables explaining current distributions. Inclusion of spatial autocorrelation overwhelmed other explanatory variables, highlighting the greater likelihood of spread from known source locations. Proximity to a road was an important predictor for D. pulicaria, and when tested separately both invasive Daphnia occurred significantly more often in lakes within 200 m of a road. Critically, D. galeata's realised niche completely envelopes D. thomsoni's, which could force the native species to become extinct through competitive exclusion. These results suggest that the spread of D. pulicaria and D. galeata to lakes where they do not yet occur is unlikely to be prevented unless public access to these waterways is denied or strictly controlled. [ABSTRACT FROM AUTHOR]

Cardiovascular disease (CVD) has become a significant cause of death around the world, with heart-related problems being a major contributor to this trend. It's crucial to identify the signs and symptoms of potential health problems before they become severe. To address this issue, an IoT-based prototype has been proposed. This prototype utilizes an ML-based prediction model to provide precautionary measures for heart-related issues. It includes an IoT device that gathers real-time data from the user's body, such as heart rate and ECG. This data is utilized to create an ML-based prediction model for heart-related problems. The model can alert the user of any potential heart-related risks. The proposed prototype is designed to offer a practical solution for the early detection of heart-related issues, therefore achieving a greater accuracy of 98.3% in lowering the death rate from heart disease than current methods. The results demonstrate that the suggested IoT-based prototype is useful for detecting various heart diseases and predicting future mortality rates compared to other existing machine-learning methods. [ABSTRACT FROM AUTHOR]

Climate change is leading to advanced snowmelt date in alpine regions. Consequently, alpine plant species and ecosystems experience substantial changes due to prolonged phenological seasons, while the responses, mechanisms and implications remain widely unclear. In this 3‐year study, we investigated the effects of advancing snowmelt on the phenology of alpine snowbed species. We related microclimatic drivers to species and ecosystem phenology using in situ monitoring and phenocams. We further used predictive modelling to determine whether early snowmelt sites could be used as sentinels for future conditions. Temperature during the snow‐free period primarily influenced flowering phenology, followed by snowmelt timing. Salix herbacea and Gnaphalium supinum showed the most opportunistic phenology, while annual Euphrasia minima struggled to complete its phenology in short growing seasons. Phenological responses varied more between years than sites, indicating potential local long‐term adaptations and suggesting these species' potential to track future earlier melting dates. Phenocams captured ecosystem‐level phenology (start, peak and end of phenological season) but failed to explain species‐level variance. Our findings highlight species‐specific responses to advancing snowmelt, with snowbed species responding highly opportunistically to changes in snowmelt timings while following species‐specific developmental programs. While species from surrounding grasslands may benefit from extended growing seasons, snowbed species may become outcompeted due to internal‐clock‐driven, non‐opportunistic senescence, despite displaying a high level of phenological plasticity. [ABSTRACT FROM AUTHOR]

Data leakage is a common issue that can lead to misleading generalisation error estimation and incorrect hyperparameter tuning. However, its mechanisms are not always well understood. In this work, we consider the case of clustered data and investigate the distribution of the number of elements in leakage when the data set is uniformly split. For both the validation and test sets, the first and second moments of the number of elements in leakage are derived analytically. Modelling consequences are investigated and exemplified on simulated data. In addition, the case of an actual agronomic feasibility study is presented. We demonstrate how data leakage can distort model performance estimation when an inadequate data splitting strategy is used. We provide an understanding of data leakage in the context of clustered data by quantifying its role in predictive modelling. This sheds light on related challenges that may impact the practice in agronomy and beyond. [ABSTRACT FROM AUTHOR]

There are over 100 types of human cancer, accounting for millions of deaths every year. Lung cancer alone claims over 1.8 million lives per year and is expected to surpass 3.2 million by 2050, which underscores the urgent need for rapid drug development and repurposing initiatives. The application of AI emerges as a pivotal solution to developing anti-cancer therapeutics. This state-of-the-art review aims to explore the various applications of AI in lung cancer therapeutics. Predictive models can analyse large datasets, including clinical data, genetic information, and treatment outcomes, for novel drug design and to generate personalised treatment recommendations, potentially optimising therapeutic strategies, enhancing treatment efficacy, and minimising adverse effects. A thorough literature review study was conducted based on articles indexed in PubMed and Scopus. We compiled the use of various machine learning approaches, including CNN, RNN, GAN, VAEs, and other AI techniques, enhancing efficiency with accuracy exceeding 95%, which is validated through a computer-aided drug design process. AI can revolutionise lung cancer therapeutics, streamlining processes and saving biological scientists' time and effort—however, further research is needed to overcome challenges and fully unlock AI's potential in Lung Cancer Therapeutics. [ABSTRACT FROM AUTHOR]

Summary: This research aimed to explore the influence of nutritional adjustments and storage stability on a functional, reduced‐calorie guava jam incorporating Aloe vera. Over two months, comprehensive analysis assessed physicochemical properties, sensory traits, microbial stability, and shelf‐life. The addition of Aloe vera gel resulted in significant improvements in pH (3.00 to 3.65), total soluble solids (40.10 to 42.20°Brix), antioxidant activity (36.85% to 81.09%), moisture content (29.48% to 38.82%), water activity (0.78 to 0.84), ash content (0.29% to 0.45%), fat content (0.14% to 0.19%), fibre content (1.05% to 1.86%), and the colour values. Moreover, b* scores for colour indication improved from 15.09 to 18.86. Texture attributes of cohesiveness and firmness improved significantly. Sensory evaluation favoured the T2 variant (20% Aloe vera gel), suggesting it as the optimal formulation. Furthermore, artificial neural networks (ANNs), a technique of machine learning, were utilised to predict guava jam behaviour, with 99% accuracy. The study discovered substantial changes in pH, total soluble solids, antioxidant activity, moisture content, and textural qualities, indicating that Aloe vera supplementation could improve guava jam quality and shelf‐life. The results of ANN predictions about antioxidants and cohesiveness provide information about the product's performance during storage. [ABSTRACT FROM AUTHOR]

Aim: Hypertension and diabetes mellitus (DM) are major causes of morbidity and mortality, with growing burdens in low‐income countries where they are underdiagnosed and undertreated. Advances in machine learning may provide opportunities to enhance diagnostics in settings with limited medical infrastructure. Materials and Methods: A non‐interventional study was conducted to develop and validate a machine learning algorithm to estimate cardiovascular clinical and laboratory parameters. At two sites in Kenya, digital retinal fundus photographs were collected alongside blood pressure (BP), laboratory measures and medical history. The performance of machine learning models, originally trained using data from the UK Biobank, were evaluated for their ability to estimate BP, glycated haemoglobin, estimated glomerular filtration rate and diagnoses from fundus images. Results: In total, 301 participants were enrolled. Compared with the UK Biobank population used for algorithm development, participants from Kenya were younger and would probably report Black/African ethnicity, with a higher body mass index and prevalence of DM and hypertension. The mean absolute error was comparable or slightly greater for systolic BP, diastolic BP, glycated haemoglobin and estimated glomerular filtration rate. The model trained to identify DM had an area under the receiver operating curve of 0.762 (0.818 in the UK Biobank) and the hypertension model had an area under the receiver operating curve of 0.765 (0.738 in the UK Biobank). Conclusions: In a Kenyan population, machine learning models estimated cardiovascular parameters with comparable or slightly lower accuracy than in the population where they were trained, suggesting model recalibration may be appropriate. This study represents an incremental step toward leveraging machine learning to make early cardiovascular screening more accessible, particularly in resource‐limited settings. [ABSTRACT FROM AUTHOR]

Desertification, a formidable environmental challenge with broad implications for ecosystems and communities, is examined within Jahun Local Government Area in Jigawa State, Nigeria. This study uses a Cellular Automata Markov Chain Analysis model to visualize and predict the associated environmental risks. Objectives include assessing the extent and rate of desertification in the region and forecasting the process until 2080. Utilizing a multidisciplinary approach, the research integrates unsupervised classification of Landsat images, Land Use Land Cover (LUCC) analysis using MODIS data, Maximum Likelihood classification, and cubic trend analysis. The outcomes yield a comprehensive understanding of desertification dynamics in Jahun Local Government Area, identifying susceptible areas for environmental degradation. The study revealed significant changes in various land cover types within the research area. Urban areas experienced a substantial annual increase of 6.3030 km2, suggesting dynamic transformations within urban landscapes, possibly driven by shifts in population density, infrastructure development, or land use patterns. Conversely, vegetation exhibited a higher rate of change, with an annual decrease of 9.3787 km2, indicating variations in vegetative cover. Waterbodies displayed minimal changes, with a slight reduction rate of 0.2723 km²/year. In contrast, bare lands demonstrated a notable increase, expanding at a rate of 15.9541 km²/year, underscoring significant alterations in these regions. The observed variations in rates of change emphasize the dynamic nature of land cover in the study region and underscore the importance of understanding these changes for effective environmental management and policymaking. The study's predictions up to 2080 offers crucial insights for stakeholders and policymakers, facilitating the formulation of proactive monitoring and management strategies to effectively combat desertification and mitigate its adverse effects on ecosystems and livelihoods. [ABSTRACT FROM AUTHOR]

The machining learning-based predictive model of double disc chemo-magnetorheological finishing process of silicon was proposed in the present manuscript. Six different methods such as CatBoost Regressor, XGBoost, Random Forest Regressor, Gradient Boosting Regressor, Linear Regression, and AdaBoost Regressor were used to predict the surface roughness. The models were trained by the experimental data of surface roughness of silicon wafer polished at combination of different set of parameters. The gradient boosting algorithm was introduced to train the dataset of the models for the surface roughness of the silicon wafer. The robustness of the models was verified with K-fold cross method. The models were verified with the condition monitoring data collected by experimental results. The models were also developed for ultrasonic assistance during the double disc chemo-magnetorheological finishing process. The CatBoost approach outperformed the other models. The accuracy of the CatBoost model was 99.92% and 98.35% for the experimental data without and with ultrasonic vibration assistance. The optimised values from the predicted model were 4.21 nm and 3.4 nm without and with the assistance of vibration for the chemo-magnetorheological finishing process and have good agreement with the experimental results. The acquired experimental findings indicate that the suggested data-driven predictive modelling methodology can accurately forecast the surface roughness of polished silicon wafers. [ABSTRACT FROM AUTHOR]

This research paper investigates the efficacy of various machine learning algorithms in predicting stress levels. By employing a diverse set of algorithms, including [List of Algorithms], we aim to identify the most accurate and reliable model for stress prediction. The study utilizes [Dataset Information] to train and test the algorithms, evaluating their performance based on metrics such as accuracy, precision, recall, and F1 score. The findings will contribute to the development of more effective stress prediction models, with potential applications in healthcare, workplace wellness, and personal well-being. [ABSTRACT FROM AUTHOR]

Deep learning (DL) is increasingly recognized for its effectiveness in analyzing and forecasting complex economic systems, particularly in the context of Pakistan's evolving economy. This paper investigates DL's transformative role in managing and interpreting increasing volumes of intricate economic data, leading to more nuanced insights. DL models show a marked improvement in predictive accuracy and depth over traditional methods across various economic domains and policymaking scenarios. Applications include demand forecasting, risk evaluation, market trend analysis, and resource allocation optimization. These processes utilize extensive datasets and advanced algorithms to identify patterns those traditional methods cannot detect. Nonetheless, DL's broader application in economic research faces challenges like limited data availability, complexity of economic interactions, interpretability of model outputs, and significant computational power requirements. The paper outlines strategies to overcome these barriers, such as enhancing model interpretability, employing federated learning for better data privacy, and integrating behavioral and social economic theories. It concludes by stressing the importance of targeted research and ethical considerations in maximizing DL's impact on economic insights and innovation, particularly in Pakistan and globally. [ABSTRACT FROM AUTHOR]

Type II diabetes mellitus (T2DM) is a rising global health burden due to its rapidly increasing prevalence worldwide, and can result in serious complications. Therefore, it is of utmost importance to identify individuals at risk as early as possible to avoid long-term T2DM complications. In this study, we developed an interpretable machine learning model leveraging baseline levels of biomarkers of oxidative stress (OS), inflammation, and mitochondrial dysfunction (MD) for identifying individuals at risk of developing T2DM. In particular, Isolation Forest (iForest) was applied as an anomaly detection algorithm to address class imbalance. iForest was trained on the control group data to detect cases of high risk for T2DM development as outliers. Two iForest models were trained and evaluated through ten-fold cross-validation, the first on traditional biomarkers (BMI, blood glucose levels (BGL) and triglycerides) alone and the second including the additional aforementioned biomarkers. The second model outperformed the first across all evaluation metrics, particularly for F1 score and recall, which were increased from 0.61 ± 0.05 to 0.81 ± 0.05 and 0.57 ± 0.06 to 0.81 ± 0.08, respectively. The feature importance scores identified a novel combination of biomarkers, including interleukin-10 (IL-10), 8-isoprostane, humanin (HN), and oxidized glutathione (GSSG), which were revealed to be more influential than the traditional biomarkers in the outcome prediction. These results reveal a promising method for simultaneously predicting and understanding the risk of T2DM development and suggest possible pharmacological intervention to address inflammation and OS early in disease progression. [ABSTRACT FROM AUTHOR]

Objective: Previous research on psychotherapy treatment response has mainly focused on outpatients or clinical trial data which may have low ecological validity regarding naturalistic inpatient samples. To reduce treatment failures by proactively screening for patients at risk of low treatment response, gain more knowledge about risk factors and to evaluate treatments, accurate insights about predictors of treatment response in naturalistic inpatient samples are needed. Methods: We compared the performance of different machine learning algorithms in predicting treatment response, operationalized as a substantial reduction in symptom severity as expressed in the Patient Health Questionnaire Anxiety and Depression Scale. To achieve this goal, we used different sets of variables--(a) demographics, (b) physical indicators, (c) psychological indicators and (d) treatment- related variables-- in a naturalistic inpatient sample (N = 723) to specify their joint and unique contribution to treatment success. Results: There was a strong link between symptom severity at baseline and post- treatment (R2 = .32). When using all available variables, both machine learning algorithms outperformed the linear regressions and led to an increment in predictive performance of R2 = .12. Treatment- related variables were the most predictive, followed psychological indicators. Physical indicators and demographics were negligible. Conclusions: Treatment response in naturalistic inpatient settings can be predicted to a considerable degree by using baseline indicators. Regularization via machine learning algorithms leads to higher predictive performances as opposed to including nonlinear and interaction effects. Heterogenous aspects of mental health have incremental predictive value and should be considered as prognostic markers when modelling treatment processes. [ABSTRACT FROM AUTHOR]

The production processes in open cast mining activities are primarily associated with rock blasting operations, which trigger blast-induced ground vibrations causing significant damages to the surrounding surface structures. Regular monitoring of the ground vibration levels serves as crucial input to the regulatory authorities and policymakers for designing and developing an efficient blasting system to control the extent of damages caused by the same. Thus, the present study aimed to monitor the field practiced blasting events in active open cast chromite mines in the Sukinda valley of the Indian state of Odisha to develop a new site-specific model for predicting blast-induced ground vibration. The investigation has proposed a new ground vibration prediction model using multivariate statistical analysis. The validation of the model-predicted results against the field recorded data suggests the reliable performance of the proposed model having R2, RMSE, MAE and MAPE values of 0.8, 2.8, 1.925 and 0.5, respectively. Whereas, the comparison of the field recorded data with the universally employed USBM model exhibits R2, RMSE, MAE and MAPE values of 0.28, 8.13, 4.72 and 0.68, respectively suggesting the better predictive capabilities of the proposed model. Hence, the present study suggests the applicability of a newly proposed predictive model for blast-induced ground vibration in the chromite mining region of Sukinda valley. Finally, one such design parameter, namely the maximum explosive charge per delay, has been optimized for different distances by limiting the PPV value within the legislative limits as per guidelines formulated by the regulatory authority of India. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNN) have become a central method in ecology. To build and train DNNs in deep learning (DL) applications, most users rely on one of the major deep learning frameworks, in particular PyTorch or TensorFlow. Using these frameworks, however, requires substantial experience and time. Here, we present 'cito', a user‐friendly R package for DL that allows specifying DNNs in the familiar formula syntax used by many R packages. To fit the models, 'cito' takes advantage of the numerically optimized 'torch' library, including the ability to switch between training models on the CPU or the graphics processing unit (GPU) which allows the efficient training of large DNNs. Moreover, 'cito' includes many user‐friendly functions for model plotting and analysis, including explainable AI (xAI) metrics for effect sizes and variable importance. All xAI metrics as well as predictions can optionally be bootstrapped to generate confidence intervals, including p‐values. To showcase a typical analysis pipeline using 'cito', with its built‐in xAI features, we built a species distribution model of the African elephant. We hope that by providing a user‐friendly R framework to specify, deploy and interpret DNNs, 'cito' will make this interesting class of models more accessible to ecological data analysis. A stable version of 'cito' can be installed from the comprehensive R archive network (CRAN). [ABSTRACT FROM AUTHOR]

Copyright of Arthroskopie is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Natural protected areas (NPAs) in the Yucatan Peninsula favour the conservation of mangrove forests, which are valuable ecosystems for their provision of ecosystem services. However, mangroves are vulnerable to destruction due to natural and anthropogenic pressures. Therefore, it is important to assess their spatial and temporal dynamics and the potential for deforestation and recovery of cover. In this study, we analyse and model mangrove forest cover change in six NPAs of the Yucatan Peninsula by 2025. Predictions were made using the cellular automata method (CA-Markov) based on attributes that drive rates of change (obtained Kappa coefficients between 0.78 and 0.91). Anthropogenic development was the most dominant potential driver of land use and land cover change in all NPAs except the Flora and Fauna Protection Area-Yum Balam. During the period 2005–2015, the Biosphere Reserves-Petenes and Celestún showed the greatest mangrove loss, followed by the Flora and Fauna Protection Area-Nichupté. These processes changed for the simulated period (2015–2025), where an increase in mangrove cover is projected in these protected areas. Flora and Fauna Protection Area-Términos is the only protected area where a projected transition of mangroves to anthropogenic development has been identified. Therefore, it should be considered an area vulnerable to mangrove transformation and loss. [ABSTRACT FROM AUTHOR]

In this study, we introduce a predictive model leveraging the scaled Dirichlet mixture model (SDMM). This data-driven approach offers enhanced accuracy in predictions, especially with a limited training dataset, surpassing traditional point estimation methods. Recent research has highlighted the flexibility of the Dirichlet distribution in modelling multivariate proportional data. Our research extends this by employing a scaled Dirichlet distribution, which incorporates additional parameters, to construct our predictive model. Furthermore, we address the challenge of data imbalance through a novel approach centred on data spread rate, effectively balancing the dataset to optimize model performance. Empirical evaluations demonstrate the model's efficacy with both synthetic and real datasets, particularly in estimating occupancy in smart buildings. [ABSTRACT FROM AUTHOR]

Measure while drilling (MWD) refers to the acquisition of real-time data associated with the drilling process, including information related to the geological characteristics encountered in hard-rock mining. The availability of large quantities of low-cost MWD data from blast holes compared to expensive and sparsely collected orebody knowledge (OBK) data from exploration drill holes make the former more desirable for characterizing pre-excavation subsurface conditions. Machine learning (ML) plays a critical role in the real-time or near-real-time analysis of MWD data to enable timely enhancement of OBK for operational purposes. Applications can be categorized into three areas, focused on the mechanical properties of the rock mass, the lithology of the rock, as well as, related to that, the estimation of the geochemical species in the rock mass. From a review of the open literature, the following can be concluded: (i) The most important MWD metrics are the rate of penetration (rop), torque (tor), weight on bit (wob), bit air pressure (bap), and drill rotation speed (rpm). (ii) Multilayer perceptron analysis has mostly been used, followed by Gaussian processes and other methods, mainly to identify rock types. (iii) Recent advances in deep learning methods designed to deal with unstructured data, such as borehole images and vibrational signals, have not yet been fully exploited, although this is an emerging trend. (iv) Significant recent developments in explainable artificial intelligence could also be used to better advantage in understanding the association between MWD metrics and the mechanical and geochemical structure and properties of drilled rock. [ABSTRACT FROM AUTHOR]

This study brings about an innovative approach as rainfall forecast predominantly Boolean calculation is reviewed overall for 6 major cities of Pakistan for the time span of last quarter century. The study is aimed at improving the accuracy and the reliability of rainfall forecasting by making use of the capabilities of Artificial Intelligence (AI). This research investigates the efficacy of various machine learning models, including Naive Bayes, Logistic Regression, Support Vector Machines (SVM), K Nearest Neighbors (KNN), Gradient Boosting, and time series forecasting model ARIMA (Autoregressive Integrated Moving Average), for rainfall prediction. The model gets trained using 20 years of pakistan historical data performance where improving precision is the objective. With a highly scientific evaluation against real-world datasets, the new approach shows remarkable improvements in the accuracy of rainfall prediction compared to other conventional methods. Machine learning model KNN and time series forecasting model ARIM provide the good result in term of higher accuracy and lower RMSE. This results in the combination of environmental data science for innovation of the meteorological forecasting of this polarized area where the judgments are not so accurate.

Abstract Remote sensing has been increasingly used in precision agriculture. Buoyed by the developments in the miniaturization of sensors and platforms, contemporary remote sensing offers data at resolutions finer enough to respond to within-farm variations. LiDAR point cloud, offers features amenable to modelling structural parameters of crops. Early prediction of crop growth parameters helps farmers and other stakeholders dynamically manage farming activities. The objective of this work is the development and application of a deep learning framework to predict plant-level crop height and crown area at different growth stages for vegetable crops. LiDAR point clouds were acquired using a terrestrial laser scanner on five dates during the growth cycles of tomato, eggplant and cabbage on the experimental research farms of the University of Agricultural Sciences, Bengaluru, India. We implemented a hybrid deep learning framework combining distinct features of long-term short memory (LSTM) and Gated Recurrent Unit (GRU) for the predictions of plant height and crown area. The predictions are validated with reference ground truth measurements. These predictions were validated against ground truth measurements. The findings demonstrate that plant-level structural parameters can be predicted well ahead of crop growth stages with around 80% accuracy. Notably, the LSTM and the GRU models exhibited limitations in capturing variations in structural parameters. Conversely, the hybrid model offered significantly improved predictions, particularly for crown area, with error rates for height prediction ranging from 5 to 12%, with deviations exhibiting a more balanced distribution between overestimation and underestimation This approach effectively captured the inherent temporal growth pattern of the crops, highlighting the potential of deep learning for precision agriculture applications. However, the prediction quality is relatively low at the advanced growth stage, closer to the harvest. In contrast, the prediction quality is stable across the three different crops. The results indicate the presence of a robust relationship between the features of the LiDAR point cloud and the auto-feature map of the deep learning methods adapted for plant-level crop structural characterization. This approach effectively captured the inherent temporal growth pattern of the crops, highlighting the potential of deep learning for precision agriculture applications.

Abstract Type II diabetes mellitus (T2DM) is a rising global health burden due to its rapidly increasing prevalence worldwide, and can result in serious complications. Therefore, it is of utmost importance to identify individuals at risk as early as possible to avoid long-term T2DM complications. In this study, we developed an interpretable machine learning model leveraging baseline levels of biomarkers of oxidative stress (OS), inflammation, and mitochondrial dysfunction (MD) for identifying individuals at risk of developing T2DM. In particular, Isolation Forest (iForest) was applied as an anomaly detection algorithm to address class imbalance. iForest was trained on the control group data to detect cases of high risk for T2DM development as outliers. Two iForest models were trained and evaluated through ten-fold cross-validation, the first on traditional biomarkers (BMI, blood glucose levels (BGL) and triglycerides) alone and the second including the additional aforementioned biomarkers. The second model outperformed the first across all evaluation metrics, particularly for F1 score and recall, which were increased from 0.61 ± 0.05 to 0.81 ± 0.05 and 0.57 ± 0.06 to 0.81 ± 0.08, respectively. The feature importance scores identified a novel combination of biomarkers, including interleukin-10 (IL-10), 8-isoprostane, humanin (HN), and oxidized glutathione (GSSG), which were revealed to be more influential than the traditional biomarkers in the outcome prediction. These results reveal a promising method for simultaneously predicting and understanding the risk of T2DM development and suggest possible pharmacological intervention to address inflammation and OS early in disease progression.

Background: A quantitative approach to predict expected muscle activity and mandibular movement from non‐invasive hard tissue assessments remains unexplored. Objectives: This study investigated the predictive potential of normalised muscle activity during various jaw movements combined with temporomandibular joint (TMJ) vibration analyses to predict expected maximum lateral deviation during mouth opening. Method: Sixty‐six participants underwent electrognathography (EGN), surface electromyography (EMG) and joint vibration analyses (JVA). They performed maximum mouth opening, lateral excursion and anterior protrusion as jaw movement activities in a single session. Multiple predictive models were trained from synthetic observations generated from the 66 human observations. Muscle function intensity and activity duration were normalised and a decision support system with branching logic was developed to predict lateral deviation. Performance of the models in predicting temporalis, masseter and digastric muscle activity from hard tissue data was evaluated through root mean squared error (RMSE) and mean absolute error. Results: Temporalis muscle intensity ranged from 0.135 ± 0.056, masseter from 0.111 ± 0.053 and digastric from 0.120 ± 0.051. Muscle activity duration varied with temporalis at 112.23 ± 126.81 ms, masseter at 101.02 ± 121.34 ms and digastric at 168.13 ± 222.82 ms. XGBoost predicted muscle intensity and activity duration and scored an RMSE of 0.03–0.05. Jaw deviations were successfully predicted with a MAE of 0.9 mm. Conclusion: Applying deep learning to EGN, EMG and JVA data can establish a quantifiable relationship between muscles and hard tissue movement within the TMJ complex and can predict jaw deviations. [ABSTRACT FROM AUTHOR]

Abstract Mycotoxin contamination of agricultural commodities is a global public health problem that has remained elusive to various mitigation approaches, particularly in developing countries. Climate change and its impact exacerbates South Africa’s vulnerability to mycotoxin contamination, and significantly threatens its’s food systems, public health, and agro-economic development. Herein we analyse sixteen years (2005/2006–2020/2021) of annual national meteorological data on South Africa which reveals both systematic and erratic variability in critical climatic factors known to influence mycotoxin contamination in crops. Within the same study period, data on fumonisin (FB) monitoring show clear climate-dependent trends. The strongest positive warming trend is observed between 2018/2019 and 2019/2020 (0.51 °C/year), and a strong positive correlation is likewise established between FB contamination and temperature (r ranging from 0.6 to 0.9). Four machine learning models, viz support vector machines, eXtreme gradient boosting, random forest, and orthogonal partial least squares, are generalized on the historical data with suitable performance (RMSE as low as 0.00). All the adopted models are able to predict future FB contamination patterns with reasonable precision (R2 ranging from 0.34 to 1.00). The most important model feature for predicting average FB contamination (YA) is the historical pattern of average FB contamination in maize within the region (ΣFBs_avg). The two most significant features in modelling maximum FB contamination (YM) are minimum temperature from the CMIP6 data (Pro_tempMIN) and observed precipitation from the CRU data (O_prep). Our study provides strong evidence of the impact of climate change on FB in South Africa and reiterates the significance of machine learning modelling in predicting mycotoxin contamination in light of changing climatic conditions, which could facilitate early warnings and the adoption of relevant mitigation measures that could help in mycotoxin risk management and control.

A growing challenge in canola (Brassica napus L.) production globally is the management of aphid pests, particularly species that are resistant to insecticides. Aphid pests of canola damage plants through direct feeding and virus transmission, with turnip yellows virus being particularly economically damaging. Integrated Pest Management, a strategy now employed by many growers to reduce the risk of insecticide resistance, requires forward planning and monitoring. Improved risk predictions can be used to help growers limit insecticide spraying by targeting high‐risk regions and/or periods. Within Australia, autumnal aphid flights coincide with the critical risk period for virus infestations in canola. In this study, we used an extensive database accumulated from 6 years of surveys collected from more than 200 canola fields across southern Australia with supervised machine learning models to predict aphid movements in autumn‐early winter as a function of environmental factors. We found: (i) our models achieve very high predictive accuracy when validated on untrained data; (ii) aphid movements are influenced by a combination of daily temperature and wind regimes as well as ‘green bridge’ effects mediated by summer rainfall patterns; and (iii) higher aphid capture rates in sticky traps are correlated with a higher probability of the aphids being carriers of turnip yellows virus. Taken together these results suggest that growers can use the outputs from predictive models to forecast aphid outbreaks in the early growing season and derive useful rules of thumb around the environmental conditions during which canola crops are at a greater risk of turnip yellows virus transmission. [ABSTRACT FROM AUTHOR]

Mycotoxin contamination of agricultural commodities is a global public health problem that has remained elusive to various mitigation approaches, particularly in developing countries. Climate change and its impact exacerbates South Africa's vulnerability to mycotoxin contamination, and significantly threatens its's food systems, public health, and agro-economic development. Herein we analyse sixteen years (2005/2006–2020/2021) of annual national meteorological data on South Africa which reveals both systematic and erratic variability in critical climatic factors known to influence mycotoxin contamination in crops. Within the same study period, data on fumonisin (FB) monitoring show clear climate-dependent trends. The strongest positive warming trend is observed between 2018/2019 and 2019/2020 (0.51 °C/year), and a strong positive correlation is likewise established between FB contamination and temperature (r ranging from 0.6 to 0.9). Four machine learning models, viz support vector machines, eXtreme gradient boosting, random forest, and orthogonal partial least squares, are generalized on the historical data with suitable performance (RMSE as low as 0.00). All the adopted models are able to predict future FB contamination patterns with reasonable precision (R2 ranging from 0.34 to 1.00). The most important model feature for predicting average FB contamination (YA) is the historical pattern of average FB contamination in maize within the region (ΣFBs_avg). The two most significant features in modelling maximum FB contamination (YM) are minimum temperature from the CMIP6 data (Pro_tempMIN) and observed precipitation from the CRU data (O_prep). Our study provides strong evidence of the impact of climate change on FB in South Africa and reiterates the significance of machine learning modelling in predicting mycotoxin contamination in light of changing climatic conditions, which could facilitate early warnings and the adoption of relevant mitigation measures that could help in mycotoxin risk management and control. [ABSTRACT FROM AUTHOR]

This study employs a systematic and predictive modelling approach to investigate the structure and properties of multi-component borate glasses. In particular, this work is focused on understanding the individual and interaction effects of multiple constituents on several material properties. By leveraging advanced modeling techniques, this work examines how the inclusion and variation of B2O3, CaF2, TiO2, ZnO, and Na2CO3 influence the glass network, with particular attention to modifier fractions ≥ 30 mol%. This research addresses the gap in knowledge regarding the complex behavior of borate glasses in this high modifier fraction range, known as the borate anomaly, where prediction of glass structure and properties becomes particularly challenging. The use of a design of mixtures (DoM) approach facilitated the generation of polynomial equations indicating the influence of mixture components on various responses, enabling the prediction and optimization of glass properties over broad compositional ranges despite being within the anomalous region. This methodical approach not only advances our understanding of borate glass systems but also underscores the importance of predictive modelling in the accelerated design and development of novel glass materials for diverse applications. [ABSTRACT FROM AUTHOR]