Accelerated discovery of eutectic compositionally complex alloys by generative machine learning

Machine learning framework for predicting failure mode and shear capacity of ultra high performance concrete beams

Background and purposeThis study aims to develop a robust and user-friendly prediction model for radiation-induced hypothyroidism (RIHT) in nasopharyngeal carcinoma (NPC) patients.Materials and methodsNPC patients treated with IMRT between Jan. 2019 and Dec. 2021 were randomly assigned to a training cohort (n = 328) and a validation cohort (n = 141) at a ratio of 7:3. A total of 33 clinical and dose-volume variables were collected. Significant variables (p < 0.05) were identified through univariate Cox analysis and further refined using a 101-combination machine learning (ML) framework to develop a robust predictive model. The model was subsequently simplified through multivariate Cox analysis and a nomogram. Finally, the performance of the model was evaluated using the C-index, calibration plots, and decision curve analysis.ResultsUsing a 101-combination ML framework, we developed a predictive model for RIHT in NPC. The Coxboost + RSF method with 11 predictors achieved the best performance (C-index: 0.91 [training], 0.71 [validation]). A simplified five-variable model (pre-treatment TSH, TSH-to-thyroid-volume ratio, age, V45, V20) was created via multi-cox regression, with a C-index of 0.80 [training] and 0.71 [validation]. High-risk patients had significantly higher three-year RIHT incidences (72.3% vs. 18.6%, p < 0.0001) in the training cohort, and 67.9% versus 24.4% (p < 0.0001) in the validation cohort. The model showed strong calibration and confirmed clinical utility through decision curve analysis, supporting its use in personalized treatment planning.ConclusionWe developed a ML framework to identify key predictive factors for RIHT, which was simplified into a five-variable model for clinical use, offering a robust tool for predicting RIHT risk in decision-making.Supplementary InformationThe online version contains supplementary material available at 10.1186/s13014-025-02725-5.

Hospital-acquired complications (HACs) have an adverse impact on patient recovery by impeding their path to full recovery and increasing healthcare costs. The aim of this study was to create a HAC risk prediction machine learning (ML) framework using hospital administrative data collections within North Metropolitan Health Service (NMHS), Western Australia. A retrospective cohort study was performed among 64,315 patients between July 2020 to June 2022 to develop an automated ML framework by inputting HAC and the healthcare site to obtain site-specific predictive algorithms for patients admitted to the hospital in NMHS. Univariate analysis was used for initial feature screening for 270 variables. Of these, 77 variables had significant relationship with any HAC. After excluding non-contemporaneous data, 37 variables were included in developing the ML framework based on logistic regression (LR), decision tree (DT) and random forest (RF) models to predict occurrence of four specific HACs: delirium, aspiration pneumonia, pneumonia and urinary tract infection. All models exhibited similar performance with area under the curve scores around 0.90 for both training and testing datasets. For sensitivity, DT and RF exceeded LR performance while on average, false positives were lowest for LR-based models. Patient's length of stay, Charlson Index, operation length and intensive care unit stay were common predictors. Integrating ML-based risk detection systems into clinical workflows can potentially enhance patient safety and optimise resource allocation. LR-based models exhibited best performance. We have successfully developed a "real-time" risk prediction model, where patient risk scores are calculated and reviewed daily.

Introduction: Heart failure (HF) in critical care settings exhibits complex interactions with glycemic dysregulation. Traditional metrics fail to capture dynamic glucose fluctuations linked to poor outcomes. This study defines ICU-specific glycemic targets and establishes a machine learning (ML) framework integrating novel glucose indicators to predict 28-day mortality. Methods: Cohort: 18,211 ICU HF patients (MIMIC-IV, 2008-2019). Analysis: 1. Glycemic Metrics: Calculated time-weighted average glucose (TWABG), time-in-range (TIR), time-below-range (TBR), time-above-range (TAR) 2. Association Studies: Restricted cubic splines (RCS) to identify optimal glycemic ranges. Multivariable Cox regression with adjustment and subgroup analysis with interaction testing. 3. ML Modeling: Dual-stage feature selection: Lasso regression and Boruta algorithm. Model development: Developed models using 14 algorithms; SHAP interpretation applied to best-performing model (highest ROC-AUC). Validation: SHAP analysis of an exemplar case demonstrated individualized mortality risk interpretation without formal model validation. Results: 1. Optimal Glycemic Ranges: Patients within the optimal TWABG range (85–133 mg/dL) demonstrated the lowest mortality (15.09%,P< 0.001), with improved survival associated with both higher time-in-range (TIR) proportion and absence of glycemic excursions (time-below-range [TBR] or time-above-range [TAR] exposure) 2. ML Prediction: Feature selection via Lasso regression identified 30 predictors. Boruta algorithm confirmed 29 significant features. The optimized XGBoost model predicted 28-day mortality with AUC 0.779 (0.762-0.796) Conclusions: Maintaining blood glucose within TWABG 85–133 mg/dL and maximizing TIR significantly reduces 28-day mortality in ICU HF patients, while avoiding excursions independently improves survival. Our ML framework, integrating dynamic glucose metrics with clinically selected features, accurately predicted mortality risk (AUC 0.779). Findings advocate ICU-specific glucose management and demonstrate ML’s potential for risk stratification and personalized interventions.

Failure in brittle materials led by the evolution of micro- to macro-cracks under repetitive or increasing loads is often catastrophic with no significant plasticity to advert the onset of fracture. Early failure detection with respective location are utterly important features in any practical application, both of which can be effectively addressed using artificial intelligence. In this paper, we develop a supervised machine learning (ML) framework to predict failure in an isothermal, linear elastic and isotropic phase-field model for damage and fatigue of brittle materials. Time-series data of the phase-field model is extracted from virtual sensing nodes at different locations of the geometry. A pattern recognition scheme is introduced to represent time-series data/sensor nodes responses as a pattern with a corresponding label, integrated with ML algorithms, used for damage classification with identified patterns. We perform an uncertainty analysis by superposing random noise to the time-series data to assess the robustness of the framework with noise-polluted data. Results indicate that the proposed framework is capable of predicting failure with acceptable accuracy even in the presence of high noise levels. The findings demonstrate satisfactory performance of the supervised ML framework, and the applicability of artificial intelligence and ML to a practical engineering problem, i.,e, data-driven failure prediction in brittle materials.

In this paper, the risk pattern of e-bike riders in China was examined, based on tree-structured machine learning techniques. Three-year crash/violation data were acquired from the Kunshan traffic police department, China. Firstly, high-risk (HR) electric bicycle (e-bike) riders were defined as those with at-fault crash involvement, while others (i.e., non-at-fault or without crash involvement) were considered as non-high-risk (NHR) riders, based on quasi-induced exposure theory. Then, for e-bike riders, their demographics and previous violation-related features were developed based on the crash/violation records. After that, a systematic machine learning (ML) framework was proposed so as to capture the complex risk patterns of those e-bike riders. An ensemble sampling method was selected to deal with the imbalanced datasets. Four tree-structured machine learning methods were compared, and a gradient boost decision tree (GBDT) appeared to be the best. The feature importance and partial dependence were further examined. Interesting findings include the following: (1) tree-structured ML models are able to capture complex risk patterns and interpret them properly; (2) spatial-temporal violation features were found as important indicators of high-risk e-bike riders; and (3) violation behavior features appeared to be more effective than violation punishment-related features, in terms of identifying high-risk e-bike riders. In general, the proposed ML framework is able to identify the complex crash risk pattern of e-bike riders. This paper provides useful insights for policy-makers and traffic practitioners regarding e-bike safety improvement in China.

Accurate prediction of significant wave height (SWH) is central to coastal ocean dynamics, wave–climate assessment, and operational marine forecasting, yet many high-performing machine-learning (ML) models remain opaque and weakly connected to underlying wave physics. We propose an explainable, feature engineering-guided ML framework for coastal SWH prediction that combines extremal wave statistics, temporal descriptors, and SHAP-based interpretation. Using 30 min buoy observations from a high-energy, wave-dominated coastal site off Australia’s Gold Coast, we benchmarked seven regression models (Linear Regression, Decision Tree, Random Forest, Gradient Boosting, Support Vector Regression, K-Nearest Neighbors, and Neural Networks) across four feature sets: (i) Base (Hmax, Tz, Tp, SST, peak direction), (ii) Base + Temporal (lags, rolling statistics, cyclical hour/month encodings), (iii) Base + a physics-informed Wave Height Ratio, WHR = Hmax/Hs, and (iv) Full (Base + Temporal + WHR). Model skill is evaluated for full-year, 1-month, and 10-day prediction windows. Performance was assessed using R2, RMSE, MAE, and bias metrics, with the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) employed for multi-criteria ranking. Inclusion of WHR systematically improves performance, raising test R2 from a baseline range of ~0.85–0.95 to values exceeding 0.97 and reducing RMSE by up to 86%, with a Random Forest|Base + WHR configuration achieving the top TOPSIS score (1.000). SHAP analysis identifies WHR and lagged SWH as dominant predictors, linking model behavior to extremal sea states and short-term memory in the wave field. The proposed framework demonstrates how embedding simple, physically motivated features and explainable AI tools can transform black-box coastal wave predictors into transparent models suitable for geophysical fluid dynamics, coastal hazard assessment, and wave-energy applications.

Hematology research has greatly benefited from the integration of diverse biological data resources and advanced machine learning (ML) frameworks. This integration has not only deepened our understanding of blood diseases such as leukemia and lymphoma, but also enhanced diagnostic accuracy and personalized treatment strategies. By applying ML algorithms to analyze large-scale biological data, researchers can more effectively identify disease patterns, predict treatment responses, and provide new perspectives for the diagnosis and treatment of hematologic disorders. Here, we provide an overview of the current landscape of biological data resources and the application of ML frameworks pertinent to hematology research.

This study presents a machine learning (ML) framework for predicting heat transfer in magnetohydrodynamic (MHD) mixed convection within a complex V-shaped cavity filled with a nano-enhanced phase change material (NEPCM) suspension. Accurate computational fluid dynamics (CFD) simulations are essential for understanding heat transfer mechanisms in such systems, but generating comprehensive data through high-fidelity models remains computationally expensive. To address this challenge, we develop an integrated ML approach that combines synthetic data generation, physics-informed feature engineering, and optimized ensemble boosting. The methodology first augments a limited 34-sample CFD dataset to 2034 samples using Latin Hypercube Sampling with Radial Basis Function interpolation. Next, 14 physics-based features are engineered to encode the underlying physical phenomena. Finally, hyperparameters of three gradient boosting models—eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost)–are optimized via cross-validation. The framework predicts the average Nusselt number ( N u avg ) and average kinetic energy ( K E avg ) from seven geometric and operational inputs. CatBoost achieved optimal performance for N u avg ( R 2 = 0 . 9745 , mean absolute percentage error = 1.27%), while XGBoost excelled for K E avg ( R 2 = 0 . 9920 , mean absolute percentage error = 1.04%). The novelty of this work lies in its ability to generalize across different output variables and significantly reduce computational cost, enabling rapid design optimization and in-depth parametric analysis. This generalizable approach reduces computation time from hours to milliseconds, facilitating efficient design optimization and in-depth parametric studies. • ML framework predicts heat transfer in MHD mixed convection of NEPCM suspension. • Combines physics-informed feature engineering with optimized ensemble boosting. • CatBoost best for Nusselt number (R 2 = 0.9745), XGBoost for kinetic energy (R 2 = 0.9920). • Synthetic data generation expands limited CFD dataset from 34 to 2034 samples. • Reduces simulation time from hours to milliseconds for efficient design exploration.

Parkinson's disease (PD) presents a growing global health challenge, with early detection being crucial for effective management and treatment. This study seeks to develop an innovative machine learning (ML) framework for the early detection of PD by integrating advanced techniques for data preprocessing, dimensionality reduction, feature selection, and ensemble classification, aiming to significantly improve detection accuracy and timeliness. The research employs a robust ML pipeline, beginning with data preprocessing using mean imputation, standardization, min-max scaling, and SMOTE (Synthetic Minority Over-sampling Technique) to handle imbalanced data. Dimensionality reduction is achieved through Principal Component Analysis (PCA), while feature selection is performed using SelectKBest coupled with the ANOVA F-test to identify the most relevant features. Four ensemble methods—Random Forest, Gradient Boosting, XGBoost, and Support Vector Machine (SVM)—are evaluated for classification. Among the classifiers tested, the Gradient Boosting model stands out with an impressive accuracy of 0.9487, demonstrating its superior performance in PD detection. Integrating multiple preprocessing, dimensionality reduction, and feature selection techniques proves essential in optimizing model performance, highlighting the importance of a multifaceted approach in handling complex datasets. This research introduces a comprehensive ML framework that combines multiple advanced techniques in a streamlined process, significantly improving the early detection of Parkinson's disease. Ensemble methods, combined with strategic feature selection and data balancing techniques, offer a novel approach that could be applied to other neurodegenerative disorders, expanding its potential impact beyond PD detection.

This paper presents the development of a novel virtual reality (VR) machine learning (ML) framework that incorporates haptic feedback to improve sports training scenarios. The framework uses You Look Only Once (YoLo) for object detection, and combines it with ensemble learning to analyze the performance of athletes in a simulated environment and provide real-time feedbacks. The system includes haptic feedback devices that are controlled via Grey Wolf Optimization (GWO) to simulate the physical sensation of a real-world sports scenario, allowing athletes to experience the sensation of force, impact, and movements. The proposed system was tested using a group of professional athletes who participated in various sports, including football, basketball, and tennis. The athletes were asked to perform various training scenarios in the virtual environment, and their performance was compared with their real-world performance levels. The results showed that the proposed system improved the athletes' performance significantly, as they were able to receive immediate and accurate feedback on their movements, and the haptic feedback provided a realistic sensory experience that enhanced their trainings. The proposed research has the potential to revolutionize sports training by providing athletes with an efficient and effective way to improve their performance in a set of safe and controlled environments. The system can be customized to suit various sports and training scenarios, and the ML algorithms can be trained on large datasets to improve their accuracy and effectiveness. The incorporation of haptic feedback provides a unique and realistic experience, making the training more engaging and effective under real-time scenarios. The proposed system showcased an accuracy 93.5%, with 3.5% higher precision, and 4.9% higher recall than existing models, which has the potential to enhance athletic performance and revolutionize the way athletes train for different sports.

A tensile properties-related fatigue strength predicted machine learning framework for alloys used in aerospace

Occupant behavior prediction has become a significant part of smart building technologies. This research emphasizes on HVAC (Heating Ventilation and Air Conditioning) system as its operation is crucial in terms of both energy usage and user comfort. In previous researches, comfort prediction is developed using the filled questionnaires from occupants. The prediction output is employed to control the mechanical components of the system. On/Off control is mostly developed using rule-based distance triggering that turns on/off the system when occupants enter/exit a specific perimeter. This article proposes a plug-and-play HVAC control system with an adaptive cloud machine learning (ML) framework that utilizes room current ambient conditions together with the historical adjustment log to automatically adjust room temperature according to the user comfort using Support Vector Classification (SVC). This system can also turn on air conditioner automatically using predictive control which implements GPS location and the occupant's data on the Artificial Neural Network (ANN). Furthermore, cloud deployment can solve problems in processing power and storage of an end device, also provide scalability for future development. Findings show that an adaptive algorithm in the ML framework can perform well, even when the occupant's behavior changes slowly.

Rationale: Pneumonia induces heterogeneous immune and pathophysiological processes in the lung. We aimed to better define these responses using pulmonary histopathology, and to determine whether varying pulmonary pathologies yielded distinct subphenotypes of pneumonia. Mouse models are often used to study human pneumonias, yet we lack a direct comparison between the two. We aimed to characterize the similarities and disconnects between mouse and human pneumonia. Methods: H&amp;E slides from elderly subjects with pneumonia diagnosis at autopsy n=276) and with no known lung disease (n=16) were scored across 18 histopathological features (e.g., necrosis, hyaline membranes, peribronchiolar metaplasia, etc.) by 2 pathologists. Multiplex fluorescence immunohistochemistry (mfIHC) was used to quantify 5 immune cell types including CD4+ T helper cells, CD8+ cytotoxic T cells, MPO+ neutrophils, CD68+ macrophages, and CD19+ B cells on a subset of samples (n=159). 100 mouse samples were scored for the same histopathological features across multiple models including bacterial (pneumococcus serotypes 3 or 19F, E.coli, or Klebsiella pneumoniae) and viral (Influenza A virus PR8, and 2 mouse-adapted strains of SARS-CoV2) infections of young adult and (for select pathogens) elderly mice. We used a machine learning (ML) framework to characterize subphenotypes in humans and mice. Results: Each histopathology feature demonstrated variation across pneumonic human subjects, and no single feature or set of features consistently defined pneumonia. Our ML framework segregated samples into 7 clusters of human pneumonias with distinct histopathological patterns (e.g., 3.6% had coincidently high type 2 cell hyperplasia, hyaline membranes, lymphoplasmacytosis, and fibrosis, while a different 19% were distinguished by high neutrophils, edema, alveolar fibrin, and necrosis without hemorrhage). mfIHC indicated that immune cells associated with specific features and clusters (e.g., CD68+ cells positively associated with the alveolar hemorrhage feature and with the cluster of 11% of samples for which that feature had the highest variable importance score). The mouse samples also segregated into distinct pulmonary pathology clusters. Combined clustering of human &amp; mice samples, averaged per cluster indicated that each mouse cluster could be linked to corresponding human clusters. However, some histopathology features observed in humans (e.g., abscess &amp; granuloma) were never observed in these mouse models. Conclusions: Our analyses indicate seven distinct pulmonary pathology sub-phenotypes of pneumonia. Refinements to mouse models are needed to fully capture the diverse histopathological landscape of human pneumonias, but the mouse models examined will have promising utility for assessing the biology of pneumonia pulmonary pathology sub-phenotypes including underlying mechanisms and pathophysiological significance.

Metabolic disorders, such as type 2 diabetes mellitus (T2DM), pose substantial global health challenges, particularly affecting genetically predisposed populations like the Pima Indians. This study proposes a novel machine learning (ML) framework that integrates predictive modeling with gene-agnostic pathway mapping to identify high-risk individuals and discover therapeutic targets. Employing the PIMA Indian dataset, logistic regression and t-tests identified key predictors of T2DM, achieving a model accuracy of 78.43%. A pathway mapping strategy links these predictors to insulin signaling, AMPK, and PPAR pathways, facilitating mechanistic insights without molecular data. Therapeutic strategies encompass dual GLP-1/GIP receptor agonists, AMPK activators, SIRT1 modulators, and phytochemicals, validated through pathway enrichment. This framework advances precision medicine by providing interpretable, scalable solutions for early detection and targeted intervention in metabolic disorders and contributions:(1) An ML framework combining logistic regression and principal component analysis (PCA) for T2DM risk prediction; (2) A gene-agnostic pathway mapping method for mechanistic insights;(3) Novel therapeutic targets for high-risk populations.