Integrating probabilistic trees and causal networks for clinical and epidemiological data.

Towards white box modeling of compressive strength of sustainable ternary cement concrete using explainable artificial intelligence (XAI)

Ionization energy (IE) is an important property of molecules. It is highly desirable to predict IE efficiently based on, for example, machine learning (ML)-powered quantitative structure-property relationships (QSPR). In this study, we systematically compare the performance of different machine learning models in predicting the IE of molecules with distinct functional groups obtained from the NIST webbook. Mordred and PaDEL are used to generate informative and computationally inexpensive descriptors for conventional ML models. Using a descriptor to indicate if the molecule is a radical can significantly improve the performance of these ML models. Support vector regression (SVR) is the best conventional ML model for IE prediction. In graph-based models, the AttentiveFP gives an even better performance compared to SVR. The difference between these two types of models mainly comes from their predictions for radical molecules, where the local environment around an unpaired electron is better described by graph-based models. These results provide not only high-performance models for IE prediction but also useful information in choosing models to obtain reliable QSPR.

Comparative analysis of conventional and ensemble machine learning models for predicting split tensile strength in thermal stressed SCM-blended lightweight concrete

Fatigue failure poses a serious challenge for ensuring the operational safety of critical components subjected to cyclic/random loading. In this context, various machine learning (ML) models have been increasingly explored, due to their effectiveness in analyzing the relationship between fatigue life and multiple influencing factors. Nevertheless, existing ML models hinge heavily on numeric features as inputs, which encapsulate limited information on the fatigue failure process of interest. To cure the deficiency, a novel ML model based upon convolutional neural networks is developed, where numeric features are transformed into graphical ones by introducing two information enrichment operations, namely, Shapley Additive Explanations and Pearson correlation coefficient analysis. Additionally, the attention mechanism is introduced to prioritize important regions in the image-based inputs. Extensive validations using experimental results of two laser powder bed fusion-fabricated metals demonstrate that the proposed model possesses better predictive accuracy than conventional ML models.

This study presents a comprehensive review and comparative analysis of traditional machine learning (ML) and deep learning (DL) models for land cover classification in agricultural remote sensing. We evaluate the reported successes, trade-offs, and performance metrics of ML and DL models across diverse agricultural contexts. Building on this foundation, we apply both model types to the specific case of almond crop field identification in California’s Central Valley using Landsat data. DL models, including U-Net, MANet, and DeepLabv3+, achieve high accuracy rates of 97.3% to 97.5%, yet our findings demonstrate that conventional ML models—such as Decision Tree, K-Nearest Neighbor, and Random Forest—can reach comparable accuracies of 96.6% to 96.8%. Importantly, the ML models were developed using data from a single year, while DL models required extensive training data spanning 2008 to 2022. Our results highlight that traditional ML models offer robust classification performance with substantially lower computational demands, making them especially valuable in resource-constrained settings. This paper underscores the need for a balanced approach in model selection—one that weighs accuracy alongside efficiency. The findings contribute actionable insights for agricultural land cover mapping and inform ongoing model development in the geospatial sciences.

Lung cancer remains a leading cause of cancer-related deaths worldwide, with early detection critical for improving prognosis. Traditional machine learning (ML) models have shown limited generalizability in clinical settings. This study proposes a deep learning-based approach using transfer learning to accurately segment lung tumor regions from CT scans and classify images as cancerous or noncancerous, aiming to overcome the limitations of conventional ML models. We developed a two-stage model utilizing a ResNet50 backbone within a U-Net architecture for lesion segmentation, followed by a multi-layer perceptron (MLP) for binary classification. The model was trained on publicly available CT scan datasets and evaluated on an independent clinical dataset from Hazrat Rasool Hospital, Iran. Training employed binary cross-entropy and Dice loss functions. Data augmentation, dropout, and regularization were used to enhance model generalizability and prevent overfitting. The model achieved 94% accuracy on the real-world clinical test set. Evaluation metrics, including F1 score, Matthews correlation coefficient (MCC), Cohen's kappa, and Dice index, confirmed the model's robustness and diagnostic reliability. In comparison, traditional ML models performed poorly on external test data despite high training accuracy, highlighting a significant generalization gap. This research presents a reliable deep learning framework for lung cancer detection that outperforms traditional ML approaches on external validation. The results demonstrate its potential for clinical deployment. Future work will focus on prospective validation, interpretability techniques, and integration into hospital workflows to support real-time decision making and regulatory compliance.

Pretreatment values of the neutrophil-to-lymphocyte ratio (NLR) and the platelet-to-lymphocyte ratio (PLR) are well-established prognosticators in various cancers, including head and neck cancers. However, there are no studies on whether temporal changes in the NLR and PLR values after treatment are related to the development of recurrence. Therefore, in this study, we aimed to develop a deep neural network (DNN) model to discern cancer recurrence from temporal NLR and PLR values during follow-up after concurrent chemoradiotherapy (CCRT) and to evaluate the model's performance compared with conventional machine learning (ML) models. Along with conventional ML models such as logistic regression (LR), random forest (RF), and gradient boosting (GB), the DNN model to discern recurrences was trained using a dataset of 778 consecutive patients with primary head and neck cancers who received CCRT. There were 16 input features used, including 12 laboratory values related to the NLR and the PLR. Along with the original training dataset (N = 778), data were augmented to split the training dataset (N = 900). The model performance was measured using ROC-AUC and PR-AUC values. External validation was performed using a dataset of 173 patients from an unrelated external institution. The ROC-AUC and PR-AUC values of the DNN model were 0.828 ± 0.032 and 0.663 ± 0.069, respectively, in the original training dataset, which were higher than the ROC-AUC and PR-AUC values of the LR, RF, and GB models in the original training dataset. With the recursive feature elimination (RFE) algorithm, five input features were selected. The ROC-AUC and PR-AUC values of the DNN-RFE model were higher than those of the original DNN model (0.883 ± 0.027 and 0.778 ± 0.042, respectively). The ROC-AUC and PR-AUC values of the DNN-RFE model trained with a split dataset were 0.889 ± 0.032 and 0.771 ± 0.044, respectively. In the external validation, the ROC-AUC values of the DNN-RFE model trained with the original dataset and the same model trained with the split dataset were 0.710 and 0.784, respectively. The DNN model with feature selection using the RFE algorithm showed the best performance among the ML models to discern a recurrence after CCRT in patients with head and neck cancers. Data augmentation by splitting training data was helpful for model performance. The performance of the DNN-RFE model was also validated with an external dataset.

BackgroundBrain volumetric changes quantified by MRI are associated with cognitive declines in Alzheimer's disease (AD). Prior univariate approaches have established correlations for some individual brain‐behavior measures, but the whole brain (WB)‐cognition multivariate predictive relationships are yet to be systematically investigated.MethodThe integration of advanced explainable artificial intelligence (AI) techniques with WB volumetric changes has significant potential to capture complex multivariate WB‐cognition relationships in the AD continuum. Herein we utilized various machine learning (ML) models along with a deep learning (DL) model to perform cognition prediction in the AD continuum based on the WB regional features extracted from MRI data. The global cognition was assessed through the Mini‐Mental State Examination (MMSE). Moreover, the optimal predictive DL model was integrated with the Shapley Additive exPlanations (SHAP) feature importance strategy, referred to as DL‐SHAP, to identify the hierarchy of multivariate significant brain regions involved in cognitive prediction in the AD continuum. The DL‐SHAP model was initially validated on semi‐simulated data (n = 1108) and then applied to the actual experimental data (n = 668; age: 55.1‐91.5 years; 46.1% females). Finally, the severity of AD characteristics, measured by the Clinical Dementia Rating‐Sum of Boxes (CDR‐SB), was assessed within the framework of DL‐SHAP with the goal of identifying the key brain regional metrics contributing to disease severity processes.ResultThe DL model tremendously outperformed the conventional ML models for MMSE prediction using the MRI‐based WB volumetric changes data. The DL‐SHAP model portrayed robust performance on semi‐simulated data by achieving a Spearman's correlation of 0.94 between the actual and predicted MMSE scores as well as capturing dominant perturbed brain regions. It also yielded excellent performance on the experimental data by demonstrating a Spearman's correlation of 0.96 and identified several hierarchically dominant brain regions associated with MMSE estimation in the AD continuum. Additionally, DL‐SHAP captured various key brain regions involved in AD severity.ConclusionThe sophisticated explainable AI method, DL‐SHAP, showed robust performance in predicting the global cognition using a large MRI dataset, along with identifying the multivariate WB‐cognition relationships. Additionally, it portrayed compelling evidence for predicting clinical severity and identified the dominant brain regions that significantly contributed to these predictions.

Quantitative gait analysis is important for understanding the non-typical walking patterns associated with mobility impairments. Conventional linear statistical methods and machine learning (ML) models are commonly used to assess gait performance and related changes in the gait parameters. Nonetheless, explainable machine learning provides an alternative technique for distinguishing the significant and influential gait changes stemming from a given intervention. The goal of this work was to demonstrate the use of explainable ML models in gait analysis for prosthetic rehabilitation in both population- and sample-based interpretability analyses. Models were developed to classify amputee gait with two types of prosthetic knee joints. Sagittal plane gait patterns of 21 individuals with unilateral transfemoral amputations were video-recorded and 19 spatiotemporal and kinematic gait parameters were extracted and included in the models. Four ML models-logistic regression, support vector machine, random forest, and LightGBM-were assessed and tested for accuracy and precision. The Shapley Additive exPlanations (SHAP) framework was applied to examine global and local interpretability. Random Forest yielded the highest classification accuracy (98.3%). The SHAP framework quantified the level of influence of each gait parameter in the models where knee flexion-related parameters were found the most influential factors in yielding the outcomes of the models. The sample-based explainable ML provided additional insights over the population-based analyses, including an understanding of the effect of the knee type on the walking style of a specific sample, and whether or not it agreed with global interpretations. It was concluded that explainable ML models can be powerful tools for the assessment of gait-related clinical interventions, revealing important parameters that may be overlooked using conventional statistical methods.

Building highly precise prediction models for Fresh Produce (FP) market price is crucial to protect retailers from overpriced FP. In this paper we are comparing the price prediction models performance of deep learning (DL) models with statistical as well as standard machine learning (ML) models. Five types of FP are considered in performance testing. It is found that the conventional ML models outperform the statistical models such as ARIMA. On the other hand, the winning model among the conventional ML models (the Gradient Boosting model) proves to be less performant as compared with the simple or compound DL models. Moreover, the simple DL models, such as the Long Short-Term Memory (LSTM), are outperformed by the compound one, the Convolutional Long Short-Term Memory Recurrent Neural Network (CNN-LSTM), whose performance improves by adding attention. The model is capable of precisely predicting FP prices for up to three weeks ahead.

BackgroundAccurate prediction of mortality in critically ill patients with hypertension admitted to the Intensive Care Unit (ICU) is essential for guiding clinical decision-making and improving patient outcomes. Traditional prognostic tools often fall short in capturing the complex interactions between clinical variables in this high-risk population. Recent advances in machine learning (ML) and deep learning (DL) offer the potential for developing more sophisticated and accurate predictive models.ObjectiveThis study aims to evaluate the performance of various ML and DL models in predicting mortality among critically ill patients with hypertension, with a particular focus on identifying key clinical predictors and assessing the comparative effectiveness of these models.MethodsWe conducted a retrospective analysis of 30,096 critically ill patients with hypertension admitted to the ICU. Various ML models, including logistic regression, decision trees, and support vector machines, were compared with advanced DL models, including 1D convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. Model performance was evaluated using area under the receiver operating characteristic curve (AUC) and other performance metrics. SHapley Additive exPlanations (SHAP) values were used to interpret model outputs and identify key predictors of mortality.ResultsThe 1D CNN model with an initial selection of predictors achieved the highest AUC (0.7744), outperforming both traditional ML models and other DL models. Key clinical predictors of mortality identified across models included the APS-III score, age, and length of ICU stay. The SHAP analysis revealed that these predictors had a substantial influence on model predictions, underscoring their importance in assessing mortality risk in this patient population.ConclusionDeep learning models, particularly the 1D CNN, demonstrated superior predictive accuracy compared to traditional ML models in predicting mortality among critically ill patients with hypertension. The integration of these models into clinical workflows could enhance the early identification of high-risk patients, enabling more targeted interventions and improving patient outcomes. Future research should focus on the prospective validation of these models and the ethical considerations associated with their implementation in clinical practice.

This paper proposes a combination of convolutional neural network and auto-encoder (CAE) for unsupervised anomaly detection of industrial gas turbines. Autonomous monitoring systems protect the gas turbines, with the settings unchanged in their lifetime. Those systems can not detect any abnormal operation patterns which potentially risk the equipment after long-term exposure. Recently, machine learning and deep learning models are applied for industries to detect those anomalies under the nominal working range. However, for gas turbine protection, not much deep learning (DL) models are introduced. The proposed CAE detects irregular signals in unsupervised learning by combining a convolutional neural network (CNN) and auto-encoder (AE). CNN exponentially reduces the computational cost and decrease the amount of training data, by its extraction capabilities of essential features in spatial input data. A CAE identifies the anomalies by adapting characteristics of an AE, which identifies any errors larger than usual pre-trained, reconstructed errors. Using the Keras library, we developed an AE structure in one-dimensional convolution layer networks. We used actual plant operation data set for performance evaluation with conventional machine learning (ML) models. Compared to the isolation forest (iforest), k-means clustering (k-means), and one-class support vector machine (OCSVM), our model accurately predicts unusual signal patterns identified in the actual operation than conventional ML models.

Prompt lung cancer detection is essential for patient health. Deep Learning (DL) models have been intensively used for lung cancer screening, as they provide high accuracy in diagnoses. However, DL models require significant computational power, which may not be accessible in all settings. Conventional Machine Learning (ML) models may not produce high prediction accuracy, especially with large data. This study uses a Genetic Algorithm (GA) approach to select optimal features from lung cancer images and reduce their dimensionality. This allows conventional ML models to achieve a high prediction accuracy when classifying medical images while using lower computational power compared with DL models. The proposed model integrates GA along with ML for lung cancer detection. The experimental results show that using GA with a feed-forward neural network classifier achieved high performance, reaching 99.70% classification accuracy.

Deep convolutional learning for general early design stage prediction models

Background: In-vitro fertilization (IVF) outcomes, particularly their socioeconomic impact, are a major concern for Indian couples. Predicting success using pre-treatment parameters can improve clinical decision-making. This study develops and validates Bayesian-optimized voting-ensemble (BoVe), a novel machine learning (ML) algorithm, to enhance predictive accuracy for live birth outcomes. Methods: Clinical records from 2,908 IVF patients, encompassing 79 parameters-including maternal age, body mass index (BMI), Anti-Mullerian hormone (AMH) levels, number of IVF cycles, infertility type, and sperm parameters were analyzed following rigorous data preprocessing. The dataset was cleaned, transformed, and split 80:20 for training and validation. BoVe was evaluated against traditional ML models based on key performance metrics. Results: BoVe identified AMH levels >3.5 ng/mL, BMI <23, and maternal age <35 as strong predictors of live birth in female patients. Male sperm parameters significantly influenced success rates. Compared to conventional ML models, BoVe achieved superior predictive performance with an ROC-AUC score of 0.93 and accuracy of 0.87, demonstrating robust effectiveness. Additionally, an AI-powered web application was developed for cloud-based fertility guidance, providing personalized recommendations based on patient parameters. Conclusions: The BoVe model offers a highly accurate, population-specific approach to IVF prediction, surpassing previously published algorithms. Its integration into clinical workflows can enhance pre-treatment counseling, empower couples with data-driven reproductive insights, and improve success rates through personalized interventions.