Predictive Modeling and Explainability of Student Employability in the Philippines Using Random Forest and Shapley Additive Explanations

BackgroundTotal joint arthroplasty (TJA) complications necessitate the development of accurate risk prediction models; however, interpretability in machine learning remains a challenge. While Shapley Additive Explanations (SHAP) offers insights at the individual level, partial dependence plots (PDPs) may provide a better understanding at the population level for developing clinical guidelines. This study compared PDPs and SHAP in explaining machine learning-based 30-day complication risk prediction following TJA.MethodsWe conducted a retrospective cohort study using the American College of Surgeons National Surgical Quality Improvement Program (NSQIP) database (2019–2023), including 517,826 primary TJA cases. Binary classification models (Random Forest, Gradient Boosting) predicted composite 30-day complications based on 20 clinical predictors. A comprehensive interpretability analysis employed directional concordance validation between PDP and SHAP, permutation importance thresholding (5% relative influence), followed by one- and two-dimensional partial dependence analyses with explicit interaction modeling.ResultsThe cohort comprised 517,826 primary TJA procedures with a complication rate of 6.67%. The baseline Random Forest model achieved test AUC = 0.678. Directional concordance analysis demonstrated 97.8% weighted agreement between PDP trends and SHAP attributions, validating methodological comparison. Threshold analysis identified seven significant features, with interaction effects accounting for 49.9% of total model influence (71.9% among top features). PDPs showed actionable dose–response relationships, including critical thresholds for preoperative hematocrit (< 38%), operative time (> 120 min), and complementary interactions, such as age × ASA classification (19.1% importance), operative time × ASA classification (10.1%), and hematocrit × diabetes (6.4%). Comparative patient analysis demonstrated that while SHAP quantified individual contributions, only PDPs provided population thresholds directly translatable to institutional protocols.ConclusionPDPs appear more methodologically appropriate than SHAP for population-level clinical guideline development, offering actionable dose–response relationships and population risk thresholds that SHAP’s individualized attribution framework cannot provide. The dominance of interaction effects among the most influential predictors validates that PDPs accurately capture complementary relationships while presenting them in a format directly applicable to evidence-based perioperative protocols and institutional quality improvement initiatives.Video Supplementary InformationThe online version contains supplementary material available at 10.1186/s42836-025-00360-9.

BackgroundTwin neonates face disproportionately higher risks of severe composite adverse outcomes, such as intraventricular hemorrhage (IVH), periventricular leukomalacia (PVL), and bronchopulmonary dysplasia (BPD), compared to singletons. However, specific predictive tools for this vulnerable population are lacking, as existing scoring systems often fail to account for twin-specific physiological dynamics. This study aimed to develop and validate an interpretable machine learning (ML) model for early risk stratification of adverse outcomes in twin neonates.MethodsThis single-center retrospective cohort study included twin neonates admitted to the neonatal intensive care unit (NICU) at Shanxi Children’s Hospital. A derivation cohort (n=912; July 2022–June 2023) was used for model development, and a temporally separated cohort (n=592; July–December 2023) for temporal validation. Missing data were addressed using multiple imputation. We developed and compared ML prediction models, evaluating discrimination, calibration, and decision-curve analysis. Shapley additive explanations (SHAP) were used to provide clinician-facing global and patient-level explanations of risk estimates.ResultsAfter comparing four feature selection strategies, the 10-feature subset identified by least absolute shrinkage and selection operator (LASSO) was utilized for model development. In temporal validation, random forest (RF) and gradient boosting (GB) models showed comparable discrimination [area under the curve (AUC): 0.851 vs. 0.844]. GB demonstrated a more balanced classification performance across clinically relevant thresholds, with acceptable calibration and positive net benefit on decision-curve analysis, and was selected as the final model. A web-based risk calculator was implemented using the GB model.ConclusionsWe developed and temporally validated an interpretable GB-based ML model using routinely available NICU variables to support early risk stratification for severe adverse outcomes in twin neonates. Combined with a web-based risk calculator and SHAP-based interpretability, this model may assist NICU clinicians in identifying higher-risk twin neonates and prioritizing closer monitoring or early intervention. Multicenter external validation is warranted before broader clinical implementation.

BackgroundEarly prediction of heart failure (HF) after acute myocardial infarction (AMI) is essential for personalized treatment. We aimed to use interpretable machine learning (ML) methods to develop a risk prediction model for HF in AMI patients.MethodsWe retrospectively included patients initially with AMI who received percutaneous coronary intervention (PCI) in our hospital from November 2016 to February 2020. The primary endpoint was the occurrence of HF within 3 years after operation. For developing a predictive model for HF risk in AMI patients, the least absolute shrinkage and selection operator (LASSO) Regression was used to feature selection, and four ML algorithms including Random Forest (RF), Extreme Gradient Boost (XGBoost), Support Vector Machine (SVM), and Logistic Regression (LR) were employed to develop the model on the training set. The performance evaluation of the prediction model was carried out on the training set and the testing set, utilizing metrics including AUC (Area under the receiver operating characteristic curve), calibration plot, and decision curve analysis (DCA). In addition, we used the Shapley Additive Explanations (SHAP) value to determine the importance of the selected features and interpret the optimal model.ResultsA total of 1220 AMI patients were included and 244 (20%) patients developed HF during follow-up. Among the four evaluated ML models, the XGBoost model exhibited exceptional accuracy, with an AUC value of 0.922. The SHAP method showed that left ventricular ejection fraction (LVEF), left ventricular end-systolic diameter (LVDs) and lactate dehydrogenase (LDH) were identified as the three most important characteristics to predict HF risk in AMI patients. Individual risk assessment was performed using SHAP plots and waterfall plot analysis.ConclusionsOur research demonstrates the potential of ML methods in the early prediction of HF risk in AMI patients. Furthermore, it enhances the interpretability of the XGBoost model through SHAP analysis to guide clinical decision-making.

Delirium is the most common neuropsychological complication among older adults admitted to the intensive care unit (ICU) and is often associated with a poor prognosis. This study aimed to construct and validate an interpretable machine learning (ML) for early delirium prediction in older ICU patients. This was a retrospective observational cohort study and patient data were extracted from the Medical Information Mart for Intensive Care-IV database. Feature variables associated with delirium, including predisposing factors, disease-related factors, and iatrogenic and environmental factors, were selected using least absolute shrinkage and selection operator regression, and prediction models were built using logistic regression, decision trees, support vector machines, extreme gradient boosting (XGBoost), k-nearest neighbors and naive Bayes methods. Multiple metrics were used for evaluation of performance of the models, including the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, recall, F1 score, calibration plot, and decision curve analysis. SHapley Additive exPlanations (SHAP) were used to improve the interpretability of the final model. Nine thousand seven hundred forty-eight adults aged 65 years or older were included for analysis. Twenty-six features were selected to construct ML prediction models. Among the models compared, the XGBoost model demonstrated the best performance including the highest AUC (0.836), accuracy (0.765), sensitivity (0.713), recall (0.713), and F1 score (0.725) in the training set. It also exhibited excellent discrimination with AUC of 0.810, good calibration, and had the highest net benefit in the validation cohort. The SHAP summary analysis showed that Glasgow Coma Scale, mechanical ventilation, and sedation were the top three risk features for outcome prediction. The SHAP dependency plot and SHAP force analysis interpreted the model at both the factor level and individual level, respectively. ML is a reliable tool for predicting the risk of critical delirium in elderly patients. By combining XGBoost and SHAP, it can provide clear explanations for personalized risk prediction and more intuitive understanding of the effect of key features in the model. The establishment of such a model would facilitate the early risk assessment and prompt intervention for delirium.

The dual imperative of mitigating carbon emissions and maximizing hydrocarbon recovery has amplified global interest in carbon capture, utilization, and storage (CCUS) technologies. These integrated processes hold significant promise for achieving net-zero targets while extending the productive life of mature oil reservoirs. However, their effectiveness hinges on a nuanced understanding of the complex interactions between geological formations, reservoir characteristics, and injection strategies. In this study, a comprehensive machine learning-based framework is presented for estimating CO2 storage capacity and enhanced oil recovery (EOR) performance simultaneously in subsurface reservoirs. The methodology combines simulation-driven uncertainty quantification with supervised machine learning to develop predictive surrogate models. Simulation results were used to generate a diverse dataset of reservoir and operational parameters, which served as inputs for training and testing three machine learning models: Random Forest, Extreme Gradient Boosting (XGBoost), and Artificial Neural Networks (ANN). The models were trained to predict three key performance indicators (KPIs): cumulative oil production (bbl), oil recovery factor (%), and CO2 sequestration volume (SCF). All three models exhibited exceptional predictive accuracy, achieving coefficients of determination (R2) greater than 0.999 across both training and testing datasets for all KPIs. Specifically, the Random Forest and XGBoost models consistently outperformed the ANN model in terms of generalization, particularly for CO2 sequestration volume predictions. These results underscore the robustness and reliability of machine learning models for evaluating and forecasting the performance of CO2-EOR and sequestration strategies. To enhance model interpretability and support decision-making, SHapley Additive exPlanations (SHAP) analysis was applied. SHAP, grounded in cooperative game theory, offers a model-agnostic approach to feature attribution by assigning an importance value to each input parameter for a given prediction. The SHAP results provided transparent and quantifiable insights into how geological and operational features such as porosity, injection rate, water production rate, pressure, etc., affect key output metrics. Overall, this study demonstrates that integrating machine learning with domain-specific simulation data offers a scalable approach for optimizing CCUS operations. The insights derived from the predictive models and SHAP analysis can inform strategic planning, reduce operational uncertainty, and support more sustainable oilfield development practices.

BACKGROUND: Unmeasured contextual factors contribute to Black-White disparities in preterm birth (PTB), but their effects are difficult to isolate due to complex relationships with individual factors connected in non-linear ways. To address this, we applied explainable machine learning to model interactions between individual and contextual factors to predict PTB and identify its key predictors among non-Hispanic Black (NHB) and non-Hispanic White (NHW) primiparous women in the U.S. METHODS: Elastic Net, Random Forest, and XGBoost models were developed using Pregnancy Risk Assessment Monitoring System and the Social Vulnerability Index data from nine U.S. states. SHAP (SHapley Additive exPlanations) values were computed to assess feature importance. Model performance was evaluated using the area under the ROC curve (AUC). RESULTS: Our models predicted PTB with high accuracy (AUC: 0.87–0.93) for NHB and NHW primiparous women, identifying both shared and distinct multidimensional predictors. Shared individual predictors included ≥ 9 prenatal care visits (protective; mean |SHAP| 0.42–1.58), adequate + prenatal care (risk-increasing; mean |SHAP| 0.69 for NHB and 1.18 for NHW), and gestational hypertension (risk-increasing; mean |SHAP| 0.17 and 0.20, respectively). Contextual socioeconomic status and household composition also contributed significantly to PTB prediction, with a stronger impact among NHB women. CONCLUSIONS: Explainble machine learning with SHAP values can accurately quantify the contribution of individual and contextual factors to PTB risk specific to NHB and NHW primiparous women. By integrating feature importance with the prevalence of risk factors, this approach offers actionable insights to identify priority areas for intervention and inform tailored preventive strategies aimed at reducing Black-White disparities in PTB.

BackgroundMild cognitive impairment (MCI), especially the amnestic form, is considered a transitional state between normal aging and Alzheimer's disease (AD). However, not all amnestic MCI (aMCI) patients progress to AD. Thus, developing a predictive model for AD progression in aMCI patients has been considered important. Prametric methods such as logistic regression have been developed, but it is difficult to reflect complex patterns such as nonlinear relationships and interactions between variables. This study aims to improve the predictive power of aMCI patients' conversion to dementia by using an interpretable machine learning (IML) model and to identify factors that increase the risk of individual dementia conversion in each patient.MethodWe obtained 760 aMCI patients, who had been followed at least three years after baseline neuropsychological tests from Samsung Medical Center from 2007 to 2019. We used neuropsychological tests and apolipoprotein E (APOE) genotype data for developing predictive models. Model building and model validation data sets were composed of 565 and 140 patients, respectively. For global interpretation, four models of logistic regression, random forest, support vector machine, and extreme gradient boost were compared. For local interpretation, individual conditional expectations (ICE) and SHapley Additive exPlanations (SHAP) were used to analyze individual patients.ResultAmong 4 models, the extreme gradient boost model showed the best performance with an AUC of 0.83, an accuracy of 0.76, and an f1‐score of 0.65. The variables such as RCFT‐DR, CDR‐SOB, age, K‐MMSE, COWAT‐animal, education, SVLT‐DR, RCFT‐copy time, and APOE genotype were important features for creating the model. Through ICE and SHAP analysis, it was also possible to interpret which variables acted as strong factors for each patient.ConclusionThe present study developed a model for predicting dementia conversion in aMCI patients using IML technique. This predictive IML model is expected to be useful in clinical practice and research field as it can suggest conversion with high accuracy and identify the degree of influence of risk factors for each patient.

Increasing water scarcity and climate variability have intensified the need for precise agricultural irrigation management. Accurate estimation of crop coefficients (Kc) is critical for determining crop water requirements, especially in arid and semi-arid regions. However, conventional methods for estimating Kc often rely on generalized plant characteristics, which may not account for local climatic variations. In this study, we address this challenge by predicting the daily crop coefficient for soybean using four machine learning models: Extreme Gradient Boosting (XGBoost), Extra Tree (ET), Random Forest (RF), and CatBoost. These models were trained on meteorological data from Suhaj Governorate, Egypt, spanning 1979–2014. Additionally, SHapley Additive exPlanations (SHAP), Sobol sensitivity analysis, and Local Interpretable Model-agnostic Explanations (LIME) were applied to evaluate model interpretability and consistency with physical processes. Among the models evaluated, the ET model achieved the highest accuracy, with r = 0.96, NSE = 0.93, RMSE = 0.05, and MAE = 0.02. XGBoost and RF also performed well, each obtaining r = 0.96, NSE = 0.92, RMSE = 0.06, and MAE = 0.02. In comparison, CatBoost demonstrated slightly lower accuracy, with r = 0.95, NSE = 0.91, RMSE = 0.06, and MAE = 0.02. SHAP and Sobol analyses consistently identified the antecedent crop coefficient [:Kc(d-1)] and solar radiation (Sin) as the most influential variables. LIME results revealed localized variations in predictions, reflecting dynamic crop-climate interactions. This study underscores the importance of integrating interpretable machine learning models to enhance both predictive accuracy and reliability while maintaining alignment with critical physical processes. The proposed framework offers a robust tool for improving daily Kc estimation, thereby supporting more sustainable irrigation practices and climate-resilient agriculture.

This study sought to establish machine learning models for forecasting in-hospital mortality in non-ST-segment elevation myocardial infarction (NSTEMI) patients, and focused on model interpretability using Shapley additive explanations (SHAP). Data were gathered from the Medical Information Mart for Intensive Care—IV database. The synthetic minority over-sampling technique and Edited Nearest Neighbors were used to address class imbalance. Four machine learning algorithms were employed, including Adaptive Boosting (AdaBoost), Random Forest (RF), Gradient Boosting Decision Trees (GBDT), and eXtreme Gradient Boosting (XGBoost). SHAP was utilized to improve transparency and credibility. The all-features RF model demonstrated optimal performance, with an accuracy of 0.8513, precision of 0.9016, and AUC of 0.8903. The SHAP summary plot for the RF model revealed that Acute Physiology Score III, lactate dehydrogenase, and lactate were the three most crucial characteristics, with higher values indicating a greater risk. The study demonstrates the applicability of machine learning, particularly RF, in predicting in-hospital mortality for NSTEMI patients, with the use of SHAP enhancing model interpretability and providing clinicians with clearer insights into feature contributions.

6076 Background: Definitive chemoradiation is the current standard treatment in LAHNSCC. Prognostic biomarkers that enable to reliably predict LAHNSCC disease progression are needed to stratify the risk of progression to tailor treatment intensity in future clinical trials. Imaging biomarkers have emerged as promising alternatives to non-invasively predict patient outcomes. Aim: to identify an imaging signature to predict progression-free survival (PFS) in LAHNSCC. Methods: A single-center, retrospective, observational study was designed. Clinical data and pre-treatment CT images from LAHNSCC patients treated with definitive chemoradiation from 2014 to 2022 were collected. Manual tumor segmentation was performed slice by slice by a qualified image technician and supervised by a radiologist with 20+ years in HNSCC using the DICOM viewer of Quibim platform. A total of 108 radiomic features (shape and textures) were extracted from each region of interest. Feature reduction techniques were applied to select the characteristics used in the classification model. The primary endpoint of this study was 5-year PFS. Random Forest, Support Vector Classifier (SVC), Logistic Regression, Gradient Boosting (GB) and Extreme Gradient Boosting classification models were used. A 5-fold cross validation strategy was followed to evaluate the performance of the models in terms of AUROC, sensitivity, specificity, and accuracy. The importance of each feature in the model was measured by applying the Shapley Additive exPlanations (SHAP) method. Results: Baseline CT exams from 102 LAHNSCC patients were included; 50% and 23% were stage IVA and IVB, respectively. The remaining 27% (stage II [3%] and stage III [24%]) were treated in an organ-preservation intention. 67% of patients presented locoregional or distant progression at 5 years. All radiomic features (108) and 6 clinical variables were used in the predictive model, for which a cross-validation was performed. GB as the feature selection technique and SVC as the classification model provided the best results. The final model was able to predict 5-year PFS with an average AUC of 0.82 (95% CI: [0.73, 0.91]), a sensitivity of 0.69 (95% CI: [0.57, 0.81]), a specificity of 0.82 (95% CI: [0.7, 0.94]) and an accuracy of 0.73 (95% CI: [0.62, 0.84]). From most to least important, features contributing to the predictive model were: TNM stage (SHAP: 0.038), glszm Small Area Emphasis (SHAP: 0.026), glcm Idmn (SHAP: 0.023), glszm Large Area High Gray Level Emphasis (SHAP: 0.018) and glrlm Run Entropy (SHAP: 0.015). Conclusions: Radiomic biomarkers from pre-treatment CT images in combination with TNM stage were predictive of 5-year PFS to chemoradiation in LAHNSCC patients and might be helpful for patient risk stratification. Further validation of these imaging biomarkers is ongoing.

Tree-based machine learning (ML) algorithms, such as Extra Trees (ET), Random Forest (RF), Gradient Boosting Machine (GBM), and XGBoost (XGB) are among the most widely used in early drug discovery, given their versatility and performance. However, models based on these algorithms often suffer from misclassification and reduced interpretability issues, which limit their applicability in practice. To address these challenges, several approaches have been proposed, including the use of SHapley Additive Explanations (SHAP). While SHAP values are commonly used to elucidate the importance of features driving models' predictions, they can also be employed in strategies to improve their prediction performance. Building on these premises, we propose a novel approach that integrates SHAP and features value analyses to reduce misclassification in model predictions. Specifically, we benchmarked classifiers based on ET, RF, GBM, and XGB algorithms using data sets of compounds with known antiproliferative activity against three prostate cancer (PC) cell lines (i.e., PC3, LNCaP, and DU-145). The best-performing models, based on RDKit and ECFP4 descriptors with GBM and XGB algorithms, achieved MCC values above 0.58 and F1-score above 0.8 across all data sets, demonstrating satisfactory accuracy and precision. Analyses of SHAP values revealed that many misclassified compounds possess feature values that fall within the range typically associated with the opposite class. Based on these findings, we developed a misclassification-detection framework using four filtering rules, which we termed "RAW", SHAP, "RAW OR SHAP", and "RAW AND SHAP". These filtering rules successfully identified several potentially misclassified predictions, with the "RAW OR SHAP" rule retrieving up to 21%, 23%, and 63% of misclassified compounds in the PC3, DU-145, and LNCaP test sets, respectively. The developed flagging rules enable the systematic exclusion of likely misclassified compounds, even across progressively higher prediction confidence levels, thus providing a valuable approach to improve classifier performance in virtual screening applications.

Children with Kawasaki disease (KD) who are resistant to intravenous immunoglobulin (IVIG) therapy face a substantially increased risk of developing coronary artery lesions (CALs). Developing a robust predictive model to identify pediatric patients at high risk of IVIG resistance is crucial for optimizing clinical decision-making and improving prognosis. This study aimed identify risk predictors for IVIG resistance in children with KD and to establish and validate an interpretable machine learning (ML)-based predictive model for clinical application. Retrospective analysis was carried out on clinical data sourced from 1,584 KD patients who received initial IVIG treatment during their first hospitalization at Xuzhou Children's Hospital between January 2019 and December 2024. This cohort was randomly allocated into the training (70%) and test (30%) sets. Six distinct ML algorithms-Light Gradient Boosting Machine (LightGBM), Random Forest, eXtreme Gradient Boosting (XGBoost), Neural Network (NeuralNet), Support Vector Machine (SVM), and ElasticNet Logistic Regression-were employed to develop predictive models. Comparative performance was evaluated employing the area under the receiver operating characteristic curve (AUC). Then, SHapley Additive exPlanations (SHAP) were applied to quantify each variable's contribution to the optimal model. The LightGBM model demonstrated superior discriminative performance, attaining an AUC of 0.832 [95% confidence interval (CI): 0.766-0.898] on the independent test set, with a sensitivity of 0.860 and a specificity of 0.639. SHAP summary plots revealed that the five most influential features predicting IVIG resistance were, in descending order: fever duration before initial IVIG, the neutrophil-to-lymphocyte ratio (NLR), interleukin-1β (IL-1β) level, albumin (ALB) level, and aspartate aminotransferase (AST) level. Our analysis identified five pivotal predictors (fever duration before initial IVIG, NLR, IL-1β, ALB, and AST) for IVIG resistance and validated an interpretable LightGBM model with satisfactory performance. This model shows potential for estimating the risk of IVIG resistance, thereby aiding in the personalized therapeutic strategies for children with KD.

This study introduces CARE-Cirrhosis (Cirrhosis Ascites Risk Prediction and Explainability with Recommendation Engine), a unified methodological framework that systematically integrates predictive modeling, multi-level explainability, and a personalized recommendation engine into a single, deployable clinical decision-support architecture. Rather than applying interpretability tools in isolation, the framework embeds Explainable AI (XAI) methods like SHapley Additive exPlanations (SHAP), Local Interpretable Model agnostic Explanations (LIME), and counterfactual reasoning within an operational pipeline that transforms predictive outputs into transparent, actionable, patient-specific clinical guidance. Thus, it is advancing the methodological foundations of interpretable machine learning(ML) for biomedical applications. Data from the Mayo Clinic Primary Biliary Cirrhosis (PBC) cohort ( n = 418) were analyzed using Logistic Regression (LR), Random Forest (RF), and Extreme Gradient Boosting (XGB), evaluated under stratified 5-fold cross-validation(CV). Multi-level interpretability was achieved through XAI methods like global attribution (SHAP), local surrogate reasoning (LIME), and counterfactual analysis (DiCE). These layers were synthesized within a unified interpretability framework, linked to a rule-based recommendation engine for generating patient-specific, physiologically plausible “what-if” scenarios. The pipeline was implemented as a mobile application to demonstrate translational applicability and real-time deployment feasibility. All models demonstrated strong discriminative performance (AUROC 0.90–0.92). SHAP identified albumin, platelets, prothrombin, and edema as consistent global predictors, while counterfactual reasoning delineated clinically meaningful feature thresholds (probability 0.3–0.4). The interpretability synthesis enabled cross-validation of feature attributions across explanation paradigms, improving transparency and robustness. The integrated recommendation module generated individualized monitoring strategies and actionable insights. CARE-Cirrhosis establishes a generalizable methodological approach for unifying predictive modeling, explainability, and clinical recommendation within a single, deployable framework. By demonstrating a reproducible process for multi-level interpretability integration, it advances the methodological scope of biomedical informatics beyond model development toward transparent, interpretable, and actionable decision-support systems applicable across clinical domains. • Introduced CARE-Cirrhosis, a unified explainable AI (XAI) framework that integrates predictive modeling, multi-level interpretability XAI methods (SHAP, LIME, DiCE), and personalized recommendation into a single operational architecture. • Embedded interpretability within the model development workflow rather than as a post hoc step, achieving consistent global, local, and counterfactual transparency to enhance clinical trust. • Developed a hybrid recommendation engine that combines rule-based hepatology knowledge with model-driven feature gradients to generate physiologically plausible, patient-specific “what-if” guidance. • Achieved strong predictive performance (AUROC ≈ 0.90–0.92) across LR, RF, and XGB, with robustness confirmed through stratified cross-validation and synthetic external validation on perturbed datasets. • Deployed CARE-Cirrhosis as a mobile application integrating real-time risk scoring, interpretability visualization, and actionable recommendations into a clinician- and patient-friendly interface. • Designed the framework to be disease-agnostic and data schema–independent, enabling adaptation to other biomedical domains such as cardiology, oncology, and chronic disease management.

BackgroundAdmission to the neonatal intensive care unit (NICU) is a critical event for preterm infants, with significant implications for resource allocation and parental counseling. However, existing prediction tools are often limited by low accuracy or lack of interpretability. This study aimed to develop an interpretable machine learning (ML) model for predicting NICU admission in preterm infants using readily available prenatal and intrapartum features, with a focus on both the overall cohort and the clinically challenging subgroup of late preterm infants (34–37 weeks).MethodsA retrospective cohort of 2,610 preterm infants was analyzed. Features were selected using Boruta and least absolute shrinkage and selection operator (LASSO). Multiple models were trained and optimized via 5-fold cross-validation. The optimal model was evaluated using area under the curve (AUC), calibration, and decision curve analysis. Subgroup analysis was performed in late preterm infants (34–37 weeks) to assess model performance in this population. Interpretability was assessed with Shapley Additive exPlanations (SHAP).ResultsThe random forest (RF) model demonstrated superior and robust performance, achieving an AUC of 0.861 [95% confidence interval (CI): 0.830–0.891] in the validation set and 0.869 (0.841–0.897) in the testing set. SHAP analysis identified birth weight (mean |SHAP| value =0.17), prenatal checkup status (0.13), and gestational age (0.09) as the three most influential predictors. Low birth weight, lack of prenatal care, and gestational age below 32 weeks were associated with a significantly elevated risk of NICU admission. In the late preterm subgroup (34–37 weeks), the RF model maintained robust performance with an AUC of 0.842 (validation) and 0.838 (test), demonstrating good calibration and positive net benefit on decision curve analysis.ConclusionsThe interpretable ML model developed in this study accurately identifies preterm infants at high risk of NICU admission, with consistent performance in the late preterm subgroup. By providing individualized risk quantification and visual explanation via SHAP, it facilitates timely clinical decision-making and enhances clinician-parent communication. This tool holds significant potential for optimizing resource allocation and improving perinatal care pathways.

The alignment between higher education curricula and industry requirements is a critical factor in enhancing employability and workforce readiness in the contemporary global economy. Despite rapid technological advancements and evolving job market dynamics, many higher education institutions continue to follow traditional curriculum structures that often fail to equip students with industry-relevant skills. This study evaluates the effectiveness of higher education curricula in addressing industry demands, with a specific focus on skill development and employability. Employing a descriptive and analytical approach, this research examines the integration of technical, digital, and soft skills within academic programs. By leveraging qualitative and quantitative data from industry reports, employer surveys, and higher education frameworks, the study identifies key gaps between educational outcomes and labor market expectations. Additionally, it explores policy initiatives such as India’s National Education Policy (NEP) 2020 and global best practices aimed at enhancing curriculum effectiveness. The findings emphasize the necessity for curriculum restructuring, focusing on industry-academia collaboration, experiential learning, and competency-based education. The study concludes with strategic recommendations for higher education institutions, policymakers, and industry stakeholders to develop a skill-based education ecosystem that bridges the gap between academic learning and professional competence. Aligning curricula with industry needs is essential for enhancing employability and preparing graduates for an innovation-driven economy. Keywords: Higher Education, Skill Development, Curriculum Effectiveness, Industry Requirements, Employability, Workforce Readiness, Education Policy.