Rehearsal-based continual learning in Medical IoT (MIoT) autoencoders requires replaying latent codes of past clinical tasks to prevent catastrophic forgetting. When these latent codes are derived from patient data, each replay constitutes a fresh privacy query, and existing differential privacy (DP) composition theorems-designed for finite, pre-specified query sequences-fail to bound cumulative privacy leakage over an unbounded task horizon. This paper presents PRISM-DP, a Privacy-Resilient Infinite-Sequence Memory framework that introduces a martingale-based DP composition theorem for unbounded replay sequences. PRISM-DP proves that a geometrically decaying per-task privacy schedule combin... More >

Contemporary medicine is shifting from reactive, symptom-based treatment toward proactive, preventive intervention, yet endocrine and metabolic disorders frequently progress through subtle, subclinical phases that are overlooked during routine primary-care encounters, delaying diagnosis and increasing the longitudinal cost of care. This paper presents EndocrineAI, a full-stack, high-integrity clinical decision support system (CDSS) for early-stage endocrine and metabolic risk screening. The platform adopts a hybrid architecture that synthesizes deterministic, rule-based clinical logic with probabilistic Machine Learning (ML) inference and Generative AI summarization. An eight-stage processin... More >

Polycystic Ovary Syndrome (PCOS) is a prevalent endocrine disorder affecting reproductive-age women, leading to infertility, hormonal imbalance, insulin resistance, and cardiovascular complications. Early diagnosis remains challenging due to heterogeneous manifestations, overlapping symptoms, and lack of automated screening tools. To address these issues, this study presents a comprehensive comparative framework for PCOS prediction using machine learning and deep learning on a public dataset of 541 patient records. The framework incorporates missing value imputation, feature standardization, SMOTE class balancing, and correlation-based feature selection. Five machine learning algorithms (Dec... More >