Ahmed Elmalla
Ahmed Elmalla
Expert Python, Java, and VB.NET Programming Guidance IB Computer Science Tutor AP Computer Science A Tutor Python Programming Tutor Java Programming Tutor Experienced VB.NET Coding Tutor
Ahmed Elmalla

Portfolio

AI-Powered Cardiovascular Disease Prediction: Smart Health App Prototype

Machine Learning

AI-Powered Cardiovascular Disease Prediction: Smart Health App Prototype

AI-Driven Cardiovascular Disease Prediction: Smart Health App Prototype

Cardiovascular diseases (CVDs) are the leading cause of death worldwide, responsible for an estimated 17.9 million deaths annually. CVDs encompass a range of disorders affecting the heart and blood vessels, including coronary heart disease, cerebrovascular disease, rheumatic heart disease, and more. Alarmingly, nearly 86% of diabetes patients are at risk of developing cardiovascular complications.

To address this, I’ve developed a working prototype within the Smart Health app that can predict a patient's risk of developing cardiovascular disease. The prediction is based on key health indicators such as blood pressure, age, gender, fasting glucose level, smoking status, and alcohol intake (see the app images below).

AI-Powered Healthcare Solutions

With my expertise in building AI-driven healthcare prediction models, I’ve also started working on models for predicting diabetes risk based on BMI and fasting glucose measurements. The current cardiovascular disease prediction model was trained on a dataset of 70,000 patients using the Gradient Boosting algorithm, achieving an AUC (Area Under the Curve) score of 80%, indicating strong predictive performance.

The predictions are processed in the cloud using the Flask framework and Python, hosted on Heroku servers. Please ensure that your device is connected to the internet before attempting a prediction in the app.

 The image on the right shows an example prediction result.

AI Prediction in the Smart Health App

This prototype is a step forward in integrating AI and healthcare, making advanced prediction tools accessible to users. The goal is to empower patients and healthcare providers with early detection tools, potentially saving lives by addressing health risks before they become critical.

The image on the most right shows the result of a prediction. 

 

AI prediction in Smarthealth App

 

How to Use the Smart Health App for Prediction

To get a prediction, simply input the following details:

  1. Age (in years)
  2. Height (in cm)
  3. Weight (in kg)
  4. Systolic blood pressure (120 mm Hg to 200 mm Hg)
  5. Diastolic blood pressure (60 mm Hg to 100 mm Hg)
  6. Cholesterol level:
    • Normal: Less than 200 mg/dL
    • Above Normal: 200 to 239 mg/dL
    • High: 240 mg/dL or higher
  7. Fasting glucose level:
    • Normal: 99 mg/dL or lower
    • Above Normal: 100 to 125 mg/dL
    • High: 126 mg/dL or higher

After entering the required information, press “Predict” to receive your cardiovascular risk score.

Add Comment