Development and multi-center validation of a school-home integrated machine learning model for early screening of attention-deficit/hyperactivity disorder in school-aged children.

To develop and validate a machine learning model for predicting major depressive disorder (MDD) with suicidal ideation (SI) by incorporating dietary antioxidants, and to elucidate the specific contribution of these antioxidants in the prediction. Data were obtained from NHANES 2007-2010. Dietary antioxidants, including vitamins, minerals, and polyphenols, were the primary predictors. Demographic, lifestyle, and health-related variables were also included. Collinear variables were removed, class imbalance was corrected, and data were normalized prior to modeling. Twelve machine learning algorithms were compared using a systematic benchmarking protocol within the sklearn framework: Random Forest (RF), LightGBM, AdaBoost, XGBoost, Extra Trees, CatBoost, Gradient Boosting Decision Trees, Support Vector Machine, Decision Tree, Gaussian Naïve Bayes, Stochastic Gradient Descent, and K-Nearest Neighbors. SHapley Additive exPlanation (SHAP) values were calculated to interpret feature contributions within the best-performing model. A total of 9306 participants were included, of whom 247 with MDD comorbid with SI. After preprocessing, 31 dietary antioxidants and 9 demographic and health-related variables were retained for modeling. The RF classifier achieved the highest performance with an accuracy of 83%, precision of 0.825, recall of 0.838, area under the ROC curve of 0.927, and F1 score of 0.831. SHAP analysis identified vitamin C, kaempferol, myricetin, peonidin, luteolin, eriodictyol, hesperetin, pelargonidin, and zinc as the most influential predictors. The RF model exhibited superior predictive capability for comorbid MDD and SI. SHAP analysis highlighted the critical roles of dietary antioxidants, particularly vitamin C and kaempferol, in predicting these outcomes.

In situ evaluation of an active-passive sampling (APS) technique for monitoring psychoactive compounds in effluent wastewater.

Investigating gut microbiome dysbiosis in adults with chronic kidney disease: Diabetes-induced alterations via metagenomics and qPCR.

Label-free serum SERS combined with RFE-GBDT algorithm for non-invasive screening of liver cancer.

Predicting water quality parameters using proximal spectral sensing technology and adaptive ensemble regression.

Background: Chronic Myeloid Leukemia (CML) is a myeloproliferative neoplasm characterized by uncontrolled granulocytic proliferation and is often initially suspected based on peripheral blood smear findings. Utilizing machine learning to analyze routinely available Complete Blood Count (CBC) parameters and derived inflammatory indices may facilitate early identification of CML at the time of initial diagnosis. Objectives: The objective of this study is to evaluate the diagnostic value of routinely available Complete Blood Count (CBC) parameters and derived inflammatory indices for the early identification of chronic myeloid leukemia at the time of initial diagnosis, using machine learning–based models. Materials and methods: This study was conducted on 295 newly diagnosed cases of CML and 340 normal control samples. A total of 49 factors were subjected to study, including the following: variables included in the CBC of patients, inflammatory indices, and demographic data. Logistic regression analysis was performed to identify relevant variables, resulting in the selection of 22 features. Subsequently, multiple machine learning algorithms, including Random Forest (RF), Recursive Feature Elimination (RFE), Simulated Annealing (SA), Decision Tree (DT), K-Nearest Neighbor (KNN), and Xg-Boost (XGB), were applied to evaluate the diagnostic performance pf the selected features. Results: The findings of this study indicate that the factors most pertinent in initial diagnosis in comparison with normal control include the WBC count, the relative percentage of cells including neutrophils, monocytes, and lymphocytes, and a series of indicators related to RBC such as RBC count and RDW-CV, as well as the index of inflammatory NLR, and BLR and PDW. Conclusion: This study demonstrates that machine learning models based solely on routinely available CBC parameters and derived inflammatory indices can support the early identification of CML at the time of initial diagnosis. In addition to leukocyte-related variables, RBC-related and inflammatory indices provided complementary diagnostic information, highlighting their potential value in early-stage CML detection. The application of machine learning techniques could prioritize the development of more user-friendly dashboards to facilitate the diagnosis of CML at initial diagnosis.

Impact of atmospheric correction on machine learning-based land cover classification: insights from the Sil Canyon (NW Spain)

Integrating machine learning algorithms and game theory for optimized shipyard site selection in Istanbul

Forest Aboveground Biomass Density (AGBD) estimation supports forest carbon accounting and informs carbon monitoring, reporting, and verification. Despite the demonstrated potential of airborne light detection and ranging (lidar) and satellite imagery, accurate AGBD estimation in disturbance-prone, mixed forests remains challenging. To better understand the applicability of these data in disturbance-prone forests, we sought to determine an optimal modeling framework for AGBD estimation. We utilized 70 PlanetScope (3 m), 34 airborne lidar, and 3 ancillary predictors (elevation, slope, and aspect) with field-estimated AGBD across 5 sites in the southeastern United States (US) with different kinds of wind disturbance (tornado, hurricane, straight-line wind): Bankhead, Mountain Longleaf, Oakmulgee, Weeks Bay, and Flagg Mountain. We evaluated: (1) five established variable selection methods; (a) all predictors, (b) top 5 predictors from Random Forest (RF), (c) top 10 predictors from RF, (d) Least Absolute Shrinkage and Selection Operator (lasso), and (e) Recursive Feature Elimination (RFE), and (2) compared 2 modeling algorithms; (a)RF and (b) Bayesian-based Gaussian Process Regression (GPR) for AGBD estimation. Results show that lasso and RF-based variable selection methods outperformed RFE, while GPR outperformed RF. Model accuracy (R 2 = 0.29–0.73; Root Mean Squared Error (RMSE) = 16.29–75.14 Mg/ha) was highest in the undisturbed (Bankhead) and lowest in the wind-disturbance-prone site (Oakmulgee). Findings demonstrate that AGBD estimation is more reliable in undisturbed landscapes, while such frameworks may be inadequate in disturbance-prone, dynamic landscapes. Our study offers optimal modeling frameworks for disturbance-prone mixed forests and advances the synergistic use of lidar and PlanetScope for AGBD estimation. • Built site-specific AGBD frameworks for disturbance-prone sites, fusing airborne lidar and PlanetScope (20 m). • Model accuracies are highest in undisturbed southeastern US forests, and lowest in disturbed forests. • RF-based and lasso feature selection outperformed RFE across sites.

Machine learning to predict complications after salvage surgery in head and neck cancers.

Deep feature optimization for enhanced fish freshness assessment

Machine learning prediction model for delirium after heart valve replacement with cardiopulmonary bypass: A large-scale cohort study.

Artificial intelligence and machine learning applications in ambulatory surgery - A systematic review.

This study reports the synthesis and comprehensive evaluation of a novel green-supported nanocatalyst (SiO 2 /MoO 3 -NPs) for the photodegradation of Rhodamine 6G (Rh6G) dye under visible irradiation. The nanocatalyst was developed in accordance with circular economy principles, utilizing silica (SiO 2 ) extracted from agro-industrial rice husk waste (as the catalytic support), and molybdenum trioxide nanoparticles (MoO 3 -NPs) biosynthesized using the Araucaria angustifolia extract (as the photoactive phase). The nanomaterial was fully characterized by Attenuated Total Reflection Fourier Transform Infrared (ATR-FTIR), Scanning Electron Microscopy Energy Dispersive X-ray Spectroscopy (SEM-EDS), X-Ray Diffraction (XRD), N 2 porosimetry, Zeta Potential (ZP), zero charge point (pH ZCP ), Diffuse Reflectance Spectroscopy (DRS), and acid sites present onto the surface of the nanomaterial. SiO 2 /MoO 3 -NPs confirmed the presence of α-MoO 3 and β-MoO 3 phases , as well as high surface area (260 m 2 g -1 ). The photocatalytic performance was optimized using a Central Compound Rotational Design (CCRD 2 3 ), achieving an optimal Rh6G removal of 99.9% under the ideal conditions (4.2 g L -1 of SiO 2 /MoO 3 -NPs, 1.6 mg L -1 of Rh6G, and pH 7). The kinetic degradation followed pseudo first-order model ( k = 0.027 min -1 ) and demonstrated excellent photostability, maintaining high efficiency after four reuse cycles. Furthermore, the ecotoxicity evaluation showed that the nanocatalyst and the treated wastewater were non-toxic to Artemia salina and Lactuca sativa , respectively. A Machine Learning (ML) approach (Random Forest – RF model) was successfully employed to predict of the Rh6G photodegradation mechanism, identifying key intermediate products. Therefore, these results highlight the potential of this sustainable, waste-derived nanocatalyst for efficient and environmentally friendly wastewater treatment. • Nanocatalyst (SiO 2 /MoO 3 -NPs) was bioynthesized using Araucaria angustifolia extract. • The optimized catalyst performance achieved a 99.9% removal of the Rhodamine 6G dye. • Random Forest model was successfully employed to predict the degradation mechanism. • SiO 2 /MoO 3 -NPs and treated wastewater were non-toxic ( A. salina and L. sativa ).

Predictive proteomics: Binary classification of Streptococcus pneumoniae vaccine types via MALDI-TOF MS and supervised learning algorithms.

AI-Driven Circular Manufacturing Framework for Predictive Material Flow Optimisation

Explainable ensemble learning for predicting mechanical properties of ABX₃ perovskites using elemental composition descriptors

Machine learning detecting aggression among mood disorder patients visited in psychiatric emergency departments.

• Data Augmentation-Driven High-Precision Breakage Strength Prediction • Quantitative Dominance of Particle Size in Breakage Mechanisms • Mechanical Decoupling of Multiscale Shape Descriptors Particle breakage governs the strength and deformation behavior of rockfill materials, critically influencing the long-term mechanical performance and stability of large-scale geotechnical and civil infrastructures such as rockfill dams. To unravel the coupled effects of particle shape and size on breakage strength, this study proposes a machine learning framework enhanced by Gaussian noise-based data augmentation. The training dataset was expanded by injecting Gaussian noise with 1.6 times augmentation of the original feature values, simulating natural variability in particle morphology. Key input features—particle size and shape descriptors (e.g., Domokos shape factor for convexity and Yang roundness for edge curvature)—were selected through correlation analysis. Random Forest (RF) and XGBoost models were employed to predict single-particle compressive breakage strength. Results demonstrate that particle size dominates breakage strength, significantly outperforming shape factors (Domokos factor, Yang roundness). Data augmentation markedly improved model accuracy, achieving R² scores of 0.89 (RF) and 0.84 (XGBoost). This framework can be integrated into multi-scale simulation platforms for rockfill dams, enabling optimized zoning design through breakage strength distribution mapping and providing a novel tool for settlement risk early-warning.