Project Purpose: Beyond a single industry, this project was designed to showcase a core set of transferable, high-impact skills:

• The Next Piece: After I have completed this project, my next platform will be built on the same principles, but applied to a different domain, more specifically I am looking to create a tool that is able to analyze the stock market, do sentiment analysis, and make grounded suggestions for investment decisions. Demonstrating that the core concepts and systems architecture can be transferred and applied to any strategic business domain in any industry. More to come on that soon!

The Unified Business Problem: Healthcare professionals are drowning in two distinct but related floods of data: a flood of predictive data (medical images, patient metrics) and a flood of unstructured knowledge (clinical guidelines, research papers, drug databases). A system that only solves one half of the problem is incomplete. This platform provides a single, unified "co-pilot" that delivers both AI-driven diagnostics from patient data and trustworthy, evidence-based answers from the world's medical knowledge.

Module 1: The Data Engineering & Cloud Foundation

This module establishes the enterprise-grade foundation of the platform, focusing on the essential task of creating a secure, multi-modal data architecture. It involves provisioning a HIPAA-compliant Azure environment using Terraform (Infrastructure as Code), and building two parallel Python data pipelines: one for ingesting and processing medical images (Predictive Pipeline), and another for chunking and embedding unstructured medical documents into a vector database using LangChain (Generative Pipeline).

Module 2: The AI & ML Core (The Hybrid Brain)

This is where the two AI paradigms meet. The platform features two interconnected "brains." The Predictive Brain uses a fine-tuned Vision Transformer (PyTorch) to classify medical images and an LGBM model to predict operational risks. The Generative Brain is a production-grade RAG system that uses Azure OpenAI's GPT-4 to provide citable, evidence-based answers from the medical knowledge base. The output of the predictive brain serves as context for the generative brain, creating a seamless and intelligent workflow.

Module 3: The Application Layer (The Clinician's Co-Pilot)

The unified interface is a full-stack application. It features a robust FastAPI backend to serve the AI models and an interactive Streamlit web application for the front-end. The interface allows a clinician to upload a medical image, see the diagnostic results, and immediately ask follow-up questions to the RAG chatbot about treatment protocols. The entire application is containerized using Docker.