Federated Privacy Intelligence for Early Detection of Diabetes-Induced Multi-Organ Risks

Read full text Summarise with VIRAT
Authors: Akshaya S, Logapriya V
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

A lifelong metabolic illness diabetes mellitus can progressively damage several organs, including the heart, kidneys, nerves, and oral tissues, if left untreated. Patients are frequently sent to higher-level institutions in many healthcare settings without first undergoing a risk- based evaluation, which puts more strain on tertiary care facilities and postpones prompt intervention for high-risk patients.A rule-based multi-organ diabetes risk assessment system that assesses patient health metrics and calculates organ-specific risk levels is presented in this project. The algorithm determines risk probabilities using a weighted scoring method based on clinically significant characteristics including blood pressure, blood sugar, HbA1c, BMI, and kidney function markers. Patients are categorized as low, moderate, or high risk based on the calculated risk. Rule-based explainable reasoning is used to emphasize the main contributing elements that account for each prediction in order to increase transparency. Furthermore, based on the level of risk, a hospital recommendation system places patients in primary, district, or tertiary healthcare institutions. Excel-based storage for analysis and visualization, an HTML-based user interface for data entry, and FastAPI for backend processing are all used in the system's implementation. The suggested method facilitates effective healthcare resource allocation, enhances decision clarity, and enables early risk detection. This work proposes a federated learning– based, rule-driven multi-organ diabetes risk prediction system, where multiple hospitals locally train models using private patient data and share only model parameters for global aggregation

Fields of Study & Subjects

Artificial Intelligence in Healthcare Privacy-Preserving Technologies in Data Machine Learning in Healthcare

Publication details

Journal / source
International Journal of Science Strategic Management and Technology
Volume
02
Issue
03
Pages
1–9
Publication date
25 March 2026
Language
EN