PredictLab: An AI-Powered Multi-Disease Clinical Risk Prediction Platform Using Machine Learning and Large Language Model Explanations
Year: 2026
Type: article
Abstract: PredictLab is an AI-powered multi-disease clinical risk prediction platform designed to improve healthcare accessibility in rural and underserved communities. The system integrates machine learning models for Diabetes, Stroke, and Heart Disease prediction within a unified FastAPI-based web application. Each prediction is enhanced using Meta's Llama 3.1-8B Instant large language model through the Groq API to generate contextual, plain-language explanations for non-expert users. The platform utilizes Support Vector Machine (SVM), Random Forest, and Logistic Regression models trained on benchmark healthcare datasets with Scikit-learn preprocessing pipelines and cross-validation methodologies. PredictLab is containerized using Docker and publicly deployed on Hugging Face Spaces, enabling free browser-based access without specialized clinical infrastructure. This work demonstrates an open-source, production-ready framework for explainable healthcare AI deployment using machine learning, FastAPI, Docker, and large language models.
Author: K V, Vinayak
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W7161492435
FWCI:
Cites:
Cited by:
Related to: