This project is an end-to-end intelligent healthcare platform that integrates IoT-based physiological data collection with machine learning-driven disease prediction. Developed using the Flask web framework and MySQL database, the system enables real-time health monitoring by collecting physiological parameters such as ECG, heart rate, blood oxygen saturation (SpO₂), body temperature, and heart/lung sounds. Data can be received automatically from wearable IoT devices through a dedicated /receive API endpoint or entered manually through a user-friendly web interface.

The collected health data is automatically preprocessed using pre-trained feature scalers before being analyzed by serialized machine learning models (Joblib). These models perform real-time inference to classify a patient’s health condition into actionable categories such as Normal, Abnormal, or Critical. The /realtime module continuously processes incoming sensor data, generates predictions instantly, and securely stores diagnostic results in the database without requiring manual intervention.

To ensure the confidentiality and integrity of patient information, the system implements secure authentication mechanisms, including password hashing, session management, and role-based access control. Each user role is provided with a dedicated dashboard tailored to its specific responsibilities.

• Administrator

  • Manage users and system settings.
  • Monitor real-time patient health data.
  • Oversee overall platform activity.

• Doctor

  • View assigned patients.
  • Access historical diagnostic reports.
  • Analyze patient health trends and monitor disease progression.

• Patient

  • Submit health measurements manually or through connected IoT devices.
  • Receive instant machine learning-based health assessments.
  • View personal health records and diagnostic history.

In addition to real-time monitoring, the platform offers several healthcare utilities designed to support preventive healthcare and early diagnosis.

• Real-Time Health Monitoring

  • Collects physiological data from IoT devices or manual user input.
  • Performs automatic preprocessing and machine learning inference.
  • Stores diagnostic results for future analysis.

• Disease Prediction

  • Predicts the likelihood of major health conditions, including:

    • Stroke
    • Cardiovascular Disease
    • Diabetes

• Health Status Classification

  • Categorizes patient conditions into:

    • Normal
    • Abnormal
    • Critical

• BMI Calculator

  • Calculates Body Mass Index (BMI) using the user’s height and weight.

• Calorie Calculator

  • Estimates daily calorie requirements based on age, gender, height, weight, and physical activity level.

• Secure User Authentication

  • User registration and login.
  • Password hashing for enhanced security.
  • Session-based authentication and authorization.

• Health History Management

  • Maintains patient health records.
  • Enables long-term trend analysis and report generation.

Designed with scalability and accessibility in mind, this platform provides a strong foundation for remote patient monitoring and intelligent healthcare management. It is particularly valuable for telemedicine applications and healthcare delivery in rural or resource-limited environments, where continuous monitoring and early disease detection can significantly improve patient outcomes.

• Frontend: HTML, CSS, JavaScript
• Backend: Python (Flask)
• Database: MySQL
• Machine Learning: Scikit-learn (Joblib serialized models)
• IoT Integration: REST API-based sensor data acquisition