The Adaptive Manifold Concept with Regularized Autoencoders (AMRAE) algorithm is introduced as a novel dimensionality reduction technique that integrates manifold learning with autoencoders to capture the intrinsic geometry of high-dimensional data effectively. The study evaluates the impact of various adjustments and enhancements within the "Manifold Adjustment Box," including different regularization techniques, activation functions, and architectural choices, across diverse datasets. Key findings demonstrate that configurations such as Leaky ReLU Activation and Batch Norm Layer consistently improve accuracy, results highlight the flexibility and robustness of AMRAE. The results underscore... More >

This research presents a diagnostic method for Polycystic Ovary Syndrome (PCOS), a common hormonal disorder among women of childbearing age. The study applied machine learning classifiers—Random Forest, CatBoost, and MLP—to the Kaggle PCOS dataset, enhanced by BorutaShap and SMOTE feature selection methods. The ensemble classifier achieved an F1 score of 93.54% and an accuracy of 96.71%. These results demonstrate AI's potential to improve PCOS diagnosis for broader clinical applications. Future research should integrate genetic and epigenetic factors into AI models, validated through clinical trials. Key contributions include: using an ensemble of machine learning classifiers, advanced f... More >

This study employs K-means clustering to analyze long-term cardiovascular complications in COVID-19 patients through ECG parameters, demographics, comorbidities, and hospitalization data. Three distinct clusters emerged: Cluster 0 (moderate heart rate variability/ICU admissions), Cluster 1 (lower variability/admissions), and Cluster 2 (higher variability/admissions, indicating elevated risk). Bootstrap validation confirmed model robustness, supported by high silhouette scores and consistent cluster labels. The novel integration of multimodal data with machine learning revealed hidden cardiovascular outcome patterns, demonstrating clinical utility for risk stratification. Findings underscore... More >

This study developed a machine learning model for early risk stratification of Down syndrome by integrating maternal serum biomarkers and ultrasound measurements. A retrospective multicentre dataset was used, including maternal age, AFP, HCG, INHIBIN-A, and ultrasound parameters (NT, CRL). After imputing missing data and engineering features (e.g., Age_NT_interaction), a Gradient Boosting Machine (GBM) was trained and evaluated using AUROC, precision, recall, and F1-score. The model achieved high performance (AUROC: 0.9921; precision: 1.00; F1-score: 0.91; accuracy: 0.97). SHAP analysis identified key interactions—particularly Age_NT, Age_HCG, and Age_PAPP-A—as major contributors. High m... More >