Aegis AI // Future Health Risk Monitoring System

Developed by @developerakashp

A complete clinical-grade AI-Based Future Health Risk Monitoring System built with Python, Streamlit, and Machine Learning (scikit-learn).

The application features a sleek, modern glassmorphic dark interface styled with custom CSS. It simulates actual clinical diagnoses by training dynamic scikit-learn LogisticRegression models on-the-fly when the app boots, giving highly consistent, dynamic prediction risks (Type-2 Diabetes, Hypertension, Metabolic Obesity, and Coronary Heart Disease) based on real-time physiological inputs.

---

🌟 Core Features

• Secure Access Portal: Authenticated login interface utilizing secure st.session_state parameters to protect clinical dashboards.
• On-the-Fly ML Training: Generates a cohort dataset of 1,000 synthetic patient profiles and trains 4 discrete logistic regression models on startup to perform probability evaluations.
• Biomarker Form Registry: Sliders and inputs for Age, Blood Pressures, Fasting Glucose, Resting HR, Sleep hours, Exercise metrics, and BMI calculations.
• Aegis Predictive Dashboard: Highlights cumulative disease indexes, risk meters, and dynamic alerts.
• Interactive Visualizations:
  • Vitals Radar Chart: Mapped with Plotly to display active biomarkers against clinical optimal baselines.
  • Vitals Optimization Forecast: Predicts Fasting Glucose improvements over a 7-day course of AI protocol compliance vs. standard courses.
• AI Personalized Recommendations: Interactive dropdown accordions suggesting precise physical workouts, dietary plans, and sleep conditioning guidelines.
• Cryptographic System Logs: Allows tracking, downloading secure records backup as a JSON file, or purging database vaults.

---

🚀 Local Installation & Execution (Windows)

To run the application locally on your Windows machine, follow these steps:

1. Clone or Move to Workspace

Open your PowerShell or Command Prompt terminal and navigate to your workspace directory:

cd "d:\Akash personal"

2. Set Up a Virtual Environment (Recommended)

Create a Python virtual environment to keep dependencies isolated:

python -m venv venv

Activate the virtual environment:

venv\Scripts\activate

3. Install Dependencies

Install all required UI and scientific packages listed in requirements.txt:

pip install -r requirements.txt

4. Execute the Application

Launch the Streamlit runtime:

streamlit run app.py

The console will log and launch a browser window navigating to: http://localhost:8501

• Default Login Account ID: admin
• Default Vault Passphrase: password123

---

☁️ Deploying on Render (Free Hosting)

This project is fully structured and pre-configured for instant deployment on Render's Cloud Platform:

1. Sign Up/Log In: Go to Render and connect your GitHub repository containing this codebase.
2. Create Web Service: Click New -> Web Service.
3. Configure Environment:
   • Runtime: Python
   • Build Command: pip install -r requirements.txt
   • Start Command:

     streamlit run app.py --server.port $PORT --server.address 0.0.0.0

4. Deploy: Click Deploy Web Service. Render will automatically detect the Python configuration, download the packages in requirements.txt, bind the dynamic port $PORT, and host your application securely online!