A Hybrid Framework for Sustainable Ecosystem Management Through Robust Litterfall Prediction Under Data Scarcity

The goal of this work is to show how machine learning models, such as the random forest, neural network, gradient boosting, and AdaBoost models, can be used to forecast the fatigue life (N) of plain concrete under uniaxial compression. Here, we developed our final machine learning model by generating the following three data files from the original data used in the work of Zhang et al.: (a) grouped data with the same input variable value and different output variable logN value, (b) data excluding outliers selected by three or more outlier detection methods; (c) average data excluding outliers, created by averaging the grouped data after excluding outliers from among the grouped data. Excluding the sustained strength of the concrete variable, originally treated as the seventh input variable in the work of Zhang et al., resulted in improving the determination coefficient (R2) values. Moreover, the gradient boosting model showed a high R2 value at 0.753, indicating a high accuracy in predicting outcomes. Further analysis using data excluding outliers shows that the R2 value increased to 0.803. Moreover, the average data excluding outliers provided the best R2 value at 0.915. Finally, a permutation feature importance (PFI) analysis was carried out to determine the strength of the relationship between the feature and the target value for the gradient boosting model. The analysis results showed that the maximum stress level (Smax) and loading frequency (f) were the most significant input variables, followed by compressive strength (f′c) and maximum to minimum stress ratio (R). Shape and height to width ratio (h/w) were the features with a non-significant influence on the model. This trend was previously confirmed by a Pearson and Spearman correlation analysis.

Permeability is a crucial parameter in reservoir engineering, as it determines how easily fluids can flow through subsurface rocks. Traditional methods of measuring permeability are expensive, error-prone and time-consuming, which has led to the development of machine learning models that can predict permeability based on well-log data. This study aims to determine the most effective machine learning models for predicting permeability based on available well-log data. The study covers a detailed explanation of the data-gathering and pre-processing techniques used. Four input features were used in the models, namely gamma ray (GR), bulk density (RHOB), neutron porosity (NPHI), and resistivity (RT). Six different models were trained and evaluated based on their performance, namely linear regression, support vector machine, decision trees, gradient boosting, multi-layer perceptron, and random forest models. The models were evaluated based on their Mean Squared Error and RSquare values. Our results showed that the random forest model outperformed the other models, achieving a Mean Squared Error (MSE) value of 0.88. The multi-layer perceptron and gradient boosting models also showed promising results, achieving MSE values of 0.81 each. These findings suggest that machine learning models can be a powerful tool for predicting permeability from well-log data, and the random forest model, in particular, holds great promise for future modelling efforts in this area.

Background: Maternal depression and anxiety are significant public health concerns that play an important role in the health and well-being of mothers and children. The COVID-19 pandemic, the consequential lockdowns and related safety restrictions worldwide negatively affected the mental health of pregnant and postpartum women. Methods: This regional study aimed to develop a machine learning (ML) model for the prediction of maternal depression and anxiety. The study used a dataset collected from five Arab countries during the COVID-19 pandemic between July to December 2020. The population sample included 3569 women (1939 pregnant and 1630 postpartum) from five countries (Jordan, Palestine, Lebanon, Saudi Arabia, and Bahrain). The performance of seven machine learning algorithms was assessed for the prediction of depression and anxiety symptoms. Results: The Gradient Boosting (GB) and Random Forest (RF) models outperformed other studied ML algorithms with accuracy values of 83.3% and 83.2% for depression, respectively, and values of 82.9% and 81.3% for anxiety, respectively. The Mathew's Correlation Coefficient was evaluated for the ML models; the Naïve Bayes (NB) and GB models presented the highest performance measures (0.63 and 0.59) for depression and (0.74 and 0.73) for anxiety, respectively. The features' importance ranking was evaluated, the results showed that stress during pregnancy, family support, financial issues, income, and social support were the most significant values in predicting anxiety and depression. Conclusion: Overall, the study evidenced the power of ML models in predicting maternal depression and anxiety and proved to be an efficient tool for identifying and predicting the associated risk factors that influence maternal mental health. The deployment of machine learning models for screening and early detection of depression and anxiety among pregnant and postpartum women might facilitate the development of health prevention and intervention programs that will enhance maternal and child health in low- and middle-income countries.

BackgroundAcute upper gastrointestinal bleeding (AUGIB) is one of the most common critical diseases encountered in the intensive care unit (ICU), with a mortality rate ranging from 15 to 20%. Accurate stratification of acute gastrointestinal bleeding into acute variceal gastrointestinal bleeding (AVGIB) and acute non-variceal gastrointestinal bleeding (ANGIB) subtypes is clinically essential as distinct entities require markedly different therapeutic approaches and even divergent prognostic implications. AUGIB characterized by hemorrhagic shock, hypotension, multiple organ dysfunction (MODS), and even circulatory failure is life-threatening. Machine learning (ML) prediction model can be an effective tool for mortality prediction, enabling the timely identification of high-risk patients and improving outcomes.MethodsA total of 3,050 acute upper gastrointestinal bleeding (AUGIB) patients were included in our research from the MIMIC-IV database, among which 625 patients were classified as AVGIB and 2,425 patients were categorized as ANGIB. Patients’ clinical features, intervention methods, vital signs, scores, and important laboratory results were collected. The Synthetic Minority Over-sampling Technique-Edited Nearest Neighbors (SMOTE-ENN) and Adaptive Synthetic Sampling (ADASYN) were adopted to address the imbalance of the dataset. As many as 12 machine learning (ML) algorithms, namely, logistic regression (LR), decision tree (DT), random forest (RF), gradient boosting (GB), AdaBoost, XGBoost, Naive Bayes (NB), support vector machine (SVM), light gradient-boosting machine (LightGBM), K-nearest neighbors (KNN), extremely randomized trees (ET), and voting classifier (VC), were performed. The model performance was evaluated using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). Shapley Additive exPlanations (SHAP) analysis was conducted to identify the most influential features contributing to mortality prediction.ResultsIn terms of AVGIB patients, extremely randomized trees model demonstrated excellent predictive value among other ML models, with the AUC of 0.996 ± 0.007, accuracy of 0.996 ± 0.009, precision of 0.957 ± 0.024, recall of 0.988 ± 0.012, and F1 score of 0.972 ± 0.007. The top 10 primary feature variables of ET model were whether combined with acute kidney failure, transfusion of albumin, vasoactive drugs, transfusion of plasma, transfusion of platelet, the max of international normalized ratio (INR), the max of prothrombin time (PT), and the max of activated partial thromboplastin time (APTT). In case of ANGIB patients, gradient boosting model proven to be the optimal machine learning models, with the AUC of 0.985 ± 0.002, accuracy of 0.948 ± 0.009, precision of 0.949 ± 0.009, recall of 0.968 ± 0.009, and F1 score of 0.959 ± 0.007. Similarly, the top 10 feature variables of GB model were Glasgow Coma Scale (GCS) score, vasoactive drugs, acute kidney failure, AIMS65 score, APACHE-II score, mechanical ventilation, the minimum of lactate, chronic liver disease, and the minimum and maximum of APTT. The SHAP visualization shows the weights of two ML models feature variables and the average sharp values of variables. Meanwhile, SHAP waterfall outputs the model prediction process with true positive and negative patients. Most importantly, two website prognostic prediction platforms were developed to enhance clinical accessibility: the ET model for AVGIB patients available at https://10zr656do5281.vicp.fun while the GB model for ANGIB patients accessible at http://10zr656do5281.vicp.fun.ConclusionThe ET model provides a reliable prognostic tool for AVGIB patients, while the GB model serves as a robust tool for ANGIB patients in predicting in-hospital mortality. By systematically integrating clinical features, risk stratification scores, vital signs, and invention measures, the ML models may deliver comprehensive predictions that benefit for clinical decision-making and potentially enhance clinical outcomes in the near future.

As artificial intelligence (AI) becomes widespread, there is increasing attention on investigating bias in machine learning (ML) models. Previous research concentrated on classification problems, with little emphasis on regression models. This paper presents an easy-to-apply and effective methodology for mitigating bias in bagging and boosting regression models, that is also applicable to any model trained through minimizing a differentiable loss function. Our methodology measures bias rigorously and extends the ML model's loss function with a regularization term to penalize high correlations between model errors and protected attributes. We applied our approach to three popular tree-based ensemble models: a random forest model (RF), a gradient-boosted model (GBT), and an extreme gradient boosting model (XGBoost). We implemented our methodology on a case study for predicting road-level traffic volume, where RF, GBT, and XGBoost models were shown to have high accuracy. Despite high accuracy, the ML models were shown to perform poorly on roads in minority-populated areas. Our bias mitigation approach reduced minority-related bias by over 50%.

Sustainability is an increasingly relevant issue for a wide range of organizations, and therefore sustainability management strategies and practices are of growing significance. Because many sustainability impacts are strongly influenced by operations management decisions it is critical that the operations management function embraces the requirements of sustainability management. This has implications for decisions and processes associated with all aspects of operations management including strategy, design, planning and control, and improvement. For example, appropriate environmental and social performance objectives, targets and indicators need to be integrated with quality, cost and other more conventional performance measures. The closed loop supply chain perspective must be adopted and the requirements of other stakeholders in addition to the customer must drive operations decisions. The scope of any given “operation” is thereby expanded considerably and the nature of the operations management role altered, with implications both for the professional development of managers and the research needed to support the manager in this changed role.

Background This study aimed to establish and validate a machine learning (ML) model for predicting in-hospital mortality in critically ill patients with chronic kidney disease (CKD). Methods This study collected data on CKD patients from 2008 to 2019 using the Medical Information Mart for Intensive Care IV. Six ML approaches were used to build the model. Accuracy and area under the curve (AUC) were used to choose the best model. In addition, the best model was interpreted using SHapley Additive exPlanations (SHAP) values. Results There were 8527 CKD patients eligible for participation; the median age was 75.1 (interquartile range: 65.0–83.5) years, and 61.7% (5259/8527) were male. We developed six ML models with clinical variables as input factors. Among the six models developed, the eXtreme Gradient Boosting (XGBoost) model had the highest AUC, at 0.860. According to the SHAP values, the sequential organ failure assessment score, urine output, respiratory rate, and simplified acute physiology score II were the four most influential variables in the XGBoost model. Conclusions In conclusion, we successfully developed and validated ML models for predicting mortality in critically ill patients with CKD. Among all ML models, the XGBoost model is the most effective ML model that can help clinicians accurately manage and implement early interventions, which may reduce mortality in critically ill CKD patients with a high risk of death.

The compressive strength (CS) of the hollow concrete masonry prism is known as an important parameter for designing masonry structures. In general, the CS is determined using laboratory tests, however, laboratory tests are time-consuming and high-cost. Thus, it is necessary to evaluate and estimate the CS using different methods, for example, machine learning techniques. This study employed Gradient Boosting (GB) to evaluate and predict the CS of hollow masonry prism. The database consists of 102 hollow concrete specimens taken from different previous published literature used for modeling. The output is the CS of the hollow masonry prism, while the inputs include the compressive strength of mortar (fm), the compressive strength of blocks (fb), height-to-thickness ratio (h/t), the ratio of fm/fb. To reduce the overfitting problem, this study used K-Fold cross-validation, then particle swarm optimization (PSO) was employed to obtain the optimum hyperparameter. The GB model then was modeled using the optimum hyperparameters. The results showed that the GB model performed very well in evaluating and predicting the CS of the hollow masonry prims with a high prediction accuracy, the values of R2, RMSE, MAE, and MAPE are 0.977, 0.803 MPa, 0.612 MPa, and 0.036%, respectively. The performance of the GB model in this study outperformed in comparison to six different machine learning models (decision tree, linear regression, random forest regression, ridge regression, Artificial Neural network, and Extreme Gradient Boosting) used in previous studies. The results of sensitivity analysis using SHAP and PDP-2D indicate that the CS is strongly dependent on the fb (with a mean SHAP value of 3.2), h/t (with a mean SHAP value of 1.63), while the fm/fb (with a mean SHAP value of 0.57) had a small effect on the CS. Thus, it can be stated that this research provides a good method to evaluate and predict the CS of the hollow masonry prism, which can bring good knowledge for practical application in this field.

This study addresses the challenge of predicting customer behavior in the Thai e-commerce sector using machine learning (ML) models. The research aims to evaluate the effectiveness of random forest and gradient boosting models, benchmarking them against traditional models such as logistic regression and linear regression. Utilizing a dataset from a leading Thai e-commerce platform, the study identifies key predictors of customer satisfaction and spending power, including purchase frequency, age, and customer referrals. The findings reveal that ML models outperform traditional methods in capturing complex, non-linear relationships within consumer data. These results suggest practical applications in customer segmentation, personalized marketing, and optimized resource allocation (Chen et al., 2012). The study also emphasizes the importance of ethical considerations, such as transparency and data privacy, in predictive analytics. The research contributes to the integration of technology and economics, offering insights into the potential of ML in understanding and influencing consumer behavior (Wamba et al., 2015).

647 Background: The primary treatment of most mNSTC is chemotherapy followed by surgery if the residual disease (RD) is >1 cm. However, conventional imaging lacks the specificity to characterize the tissue, often leading to overtreatment. This study hypothesizes that integrating CT-driven radiomics features with plasma miR371 and miR375 will enhance the predictive accuracy of Machine Learning (ML) models to predict teratoma, viable germ cell (vGCT) and fibrosis/necrosis (F/N) in mNSTC patients with RD. Methods: 111 lesions from52 patients, including residual teratoma (n=57), F/N (n=33), vGCT (n=10), and additional seminoma (n=11) for training purposes were included, split into training (N=78) and test cohorts (N=33). Lesions were lymph nodes (n=87), lung (n=21), and brain (n=3) with a median size of 1.6 cm (Q1-Q3 interval=1.2-2.73 cm). 3D Slicer version 5.6.1 was used to segment the RD > 1 cm (short axis) and extract radiomics features. Plasma miRNA levels before resection were measured by RT-PCR. Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting (GB), and CatBoost (CB) ML models were evaluated to define the operating characteristics of radiomics alone (R-only) and in combination with miR371 (371) and/or miR375 (375) levels in predicting teratoma, vGCT and F/N. Results: For predicting teratoma, the best models were RF (R+375 and R+371+375), CB (R+371+375), and GB (R+371 and R+371+375). While adding miR371 or miR375 to R-only slightly improved AUC across models, the best results were achieved with the R+375+371 dataset. CB achieved AUCs ranging from 0.94 to 0.97 in training and 0.81 to 0.93 in test sets, with its highest AUC of 0.93 (95% CI: 0.78-0.97) on the R+375+371 dataset to differentiate all three classes. Similarly, GB demonstrated strong performance, achieving its highest AUC of 0.93 (95% CI: 0.79-0.96) on the R+375+371 dataset (Table). Conclusions: Integration of plasma miR371, miR375 and radiomics improved accuracy of predicting histologies across all ML models. These methods could be used to characterize the histology of RD in mNSTC patients to better inform treatment decisions. Further refinement, including incorporation of histological findings of the primary tumor, will be reported. AUC values of different ML algorithms on training and test sets. TRAINING SET TEST SET Model ±SD R R+375 R+371 R+375+371 Model (95% CI) R R+375 R+371 R+375+371 RF 0.93±0.05 0.95±0.04 0.95±0.03 0.96±0.04 RF 0.8(0.59-0.89) 0.85(0.72-0.93) 0.87(0.76-0.95) 0.91(0.78-0.95) SVM 0.84±0.06 0.84±0.09 0.89±0.11 0.89±0.09 SVM 0.72(0.54-0.80) 0.74(0.56-0.82) 0.83(0.69-0.92) 0.84(0.76-0.94) GB 0.94±0.04 0.91±0.08 0.95±0.05 0.97±0.03 GB 0.84(0.61-0.96) 0.89(0.77-0.97) 0.89(0.79-0.96) 0.93(0.79-0.96) CB 0.95±0.03 0.94±0.03 0.94±0.04 0.97±0.03 CB 0.81(0.6-0.93) 0.86(0.73-0.94) 0.89(0.78-0.97) 0.93(0.78-0.97)

BackgroundAtrial fibrillation (AF) ablation is an effective treatment for reducing episodes and improving quality of life in patients with AF. However, long-term AF-free rates after AF ablation are inconsistent across the population, ranging from 50% to 75%. Patient selection relies on individual clinical assessment, highlighting a critical gap in population-level predictive analytics. While existing risk scores (eg, CHADS₂ [congestive heart failure, hypertension, age ≥75 years, diabetes mellitus, and stroke], CHA₂DS₂-VASc [congestive heart failure, hypertension, age ≥75 years, diabetes mellitus, stroke, vascular disease, age, and sex category], CAAP-AF [coronary artery disease, left atrial diameter, age, AF, antiarrhythmic drugs, and female sex category]) have been applied to predict AF ablation outcomes, their performance in administrative claims data remains unclear. Leveraging large administrative claims databases represents an opportunity to develop standardized, scalable prediction models that could inform population health management and resource allocation at a national level.ObjectiveThis study utilizes machine learning (ML) models on claims data to explore if integrating International Classification of Diseases (ICD) billing codes outperforms traditional stroke and AF risk scores in predicting 1-year AF ablation outcomes.MethodsWe analyzed claims data from the Merative MarketScan Research Medicare database (2013‐2020) to identify 14,521 patients who underwent AF ablation. To predict 1-year AF-free outcomes, we developed logistic regression and extreme gradient boosting (XGBoost) models using demographic characteristics, comorbidity indices, and ICD diagnostic codes from the 2 years preceding ablation. Model predictions were compared with claims-based implementations of established risk scores—CHADS2, CHA2DS2-VASc, and a modified CAAP-AF (without left atrial diameter and the number of failed antiarrhythmic drugs). The ML models were also assessed on subgroups of patients with paroxysmal AF, persistent AF, and both AF and atrial flutter from October 2015 onward.ResultsAmong 14,521 patients (mean age 71.5, SD 5.31 y; n=5800, 39.94% female), AF ablation success occurred in 54.01% (n=7843). XGBoost achieved areas under the receiver operating characteristic curve (AUCs) of 0.528, 0.521, and 0.529 for the whole, female, and male AF ablation groups, respectively, and better discrimination than CHADS2, CHA2DS2-VASc, and the modified CAAP-AF in all AF ablation groups (whole population, female, and male). While CHA2DS2-VASc and the modified CAAP-AF showed higher recall (>0.798), their precision (<0.540) was lower than XGBoost (0.552‐0.556). In subgroup analyses of International Classification of Disease, Tenth Revision (ICD-10) patients (n=7646), the models incorporating ICD codes demonstrated better performance than those using only demographic and comorbidity data across most AF subtypes, with the highest AUC (0.544) observed in patients with paroxysmal AF.ConclusionsWhile the ML models achieved statistically significant improvements over claim-based implementations of established clinical risk scores (AUC 0.528‐0.544 vs 0.498‐0.505), the modest predictive performance highlights challenges in predicting procedural outcomes using administrative data that lack key clinical variables (eg, left atrial size and medication details). Our findings establish that while standardized outcome prediction using nationally available administrative data is technically feasible, current performance is insufficient for clinical decision-making and better suited for health system quality monitoring and comparative effectiveness research applications.

Accurate and cost-effective mapping of soil organic carbon (SOC) is critical for understanding carbon dynamics and informing sustainable land management. Although deep learning-based methods have demonstrated strong potential in digital soil mapping, they typically require large amounts of data. However, the availability of site-level SOC observations is often limited, which poses a challenge for model performance. To address this, we propose a novel transfer learning approach based on a Convolutional Neural Network (CNN) model that does not rely on exogenous data. Specifically, when predicting SOC for a given soil layer, the model is first pre-trained on data from all layers and then fine-tuned using data from the target layer. This design enables more efficient use of limited site data. Experimental results show that the proposed transfer model consistently outperforms other machine learning models, including the Random Forest (RF), standard CNN, and Multi-Task CNN (MTCNN) models. The transfer model achieves a coefficient of determination (R2) of 0.374 and a root mean square error (RMSE) of 2.937%, indicating superior performance. These findings highlight the effectiveness of the proposed approach for digital soil mapping under data-scarce conditions and underscore its potential as a robust tool for accurate SOC estimation.

Maternal exposure to ambient PM10 during pregnancy increases the risk of congenital heart defects: Evidence from machine learning models

e14650 Background: Immune checkpoint inhibitors (ICIs), have demonstrated efficacy in treating patients with non-small cell lung cancer (NSCLC) and advanced melanoma. However, ICIs can lead to immune-related adverse events (irAE), which will cause discontinuance of the ICI treatment. The objective of this study is to identify factors that predict which patients with NSCLC or melanoma will develop irAE(s) from ICIs. Methods: We curated the patient cohort from the Immune-Oncology data repository developed at the Georgetown-Lombardi Comprehensive Cancer Center. This cohort encompassed 466 patients (245 individuals with NSCLC and 221 with advanced melanoma) who received single-agent anti-PD-(L)1 or combination of anti-PD-1 and anti-CTLA4 therapy. Parameters selected for prediction comprises baseline demographics, laboratory results, treatment information, and cancer-related mutations. The classification of irAE were identified by CTCAE V4.03 guidelines. Overall, 219 patients experienced one or more irAE, while the remaining 247 patients were irAE-free. We employed machine learning models for prediction, which were trained using 80% of the dataset with a five-fold cross-validation, and their performance was evaluated using the area under the receiver-operating curve (AUROC) and F1 score. Furthermore, we identified the key factors that significantly impacted the model by SHAP values. Results: Nine machine learning models were deployed, including logistic regression, support vector machine, gradient boosting (GB), etc. The GB model demonstrated the highest performance, achieving an AUROC score of 75% and an F1 score of 77%. According to the SHAP value obtained from the GB model, NSCLC patients exhibited a higher propensity for irAE development compared to melanoma patients. The top three features associated with a heightened likelihood of irAE development are the treatment of the combination of anti PD-1 and anti CTLA-4, a higher albumin/globulin ratio, and a pre-treatment ECOG Performance Status score of 0. The top three features associated with a lower likelihood of irAE development are an elevated red cell distribution width, the treatment with single agent anti-PD-1, and a higher globulin level. Conclusions: Our research harnesses a comprehensive set of variables to forecast the development of irAEs in NSCLC and melanoma patients undergoing ICI treatment. The results underscore the predictive capabilities of ML models. Investigating the connections between pivotal biomarkers, such as globulin and red cell distribution width, has the potential to offer insights that enable patients to mitigate irAE. These findings emphasize the promising potential of ML techniques not only in predicting the likelihood of irAE but also in the grade of irAE. To mitigate the limitation of a relatively small sample size, we are actively working to expand the data registry by collaborating with additional institutions.

Liver transplantation is severely restricted by shortages of donors, yet relying on chronological age (CA) for donor selection often results in potentially viable grafts being discarded. This study developed a machine learning-based framework to predict the biological age (BA) of liver grafts and evaluate its clinical utility. Data from 247 donors were analyzed to create BA models using conventional linear methods and four genetic algorithm-optimized machine learning models. These models were then validated in an independent temporal cohort of 82 donor-recipient pairs. While multiple linear regression (MLR) showed a higher correlation (r = 0.82), the gradient boosting (GB) model captured unique nonlinear biological signals. Importantly, BA derived from the GB model demonstrated superior clinical relevance, serving as an independent predictor of biliary complications (AUC = 0.80) and graft survival, whereas CA failed to predict these outcomes. Multivariable Cox regression analysis revealed that accelerated ageing, defined as a BA exceeding CA, was an independent risk factor for graft loss (adjusted hazard ratio = 4.188). This exploratory study suggests that BA captures the aging heterogeneity of liver grafts which cannot be identified by the CA of donors. Furthermore, the genetic algorithm-optimized model shows potential in predicting biliary complications and survival outcomes.