Advanced Architectures in Preventive Health Informatics: A Hybrid Clinical Decision Support System for Early Endocrine and Metabolic Risk Screening

Vollständiger Abstract

Worum geht es in dieser Arbeit?

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 processing pipeline validates patient profiles, extracts eight clinical markers from unstructured laboratory text via regular-expression parsing, computes rule-based risk levels against established reference ranges, optionally refines borderline cases through a scikit-learn fallback chain, and generates natural-language assessments. The system stratifies risk across five physiological categories---thyroid dysfunction, insulin resistance / type 2 diabetes risk, PCOS risk, adrenal stress, and metabolic syndrome---and emits a standardized JSON risk schema for Electronic Health Record (EHR) interoperability, while a ``safe fallback'' design guarantees a baseline rule-based assessment whenever ML or generative components fail, preventing black-box failure modes. The paper further describes the clinical-governance framework that separates decision support from formal diagnosis, and the deployment parameters---managed PostgreSQL persistence, role-based access control, and secret management---required for longitudinal tracking in cloud environments. EndocrineAI demonstrates that a decoupled deterministic/probabilistic pipeline can convert unstructured clinical data into structured, actionable intelligence, offering a scalable blueprint for preventive CDSS that mitigate clinician burnout while empowering proactive metabolic care.