HeartRiskDectector-AI

Inspiration

Heart disease is one of the leading causes of death worldwide, and early detection can save lives. Many people don’t have access to quick and affordable medical checkups, so we were inspired to build an AI-powered tool that can help predict heart risk from basic health parameters.

What it does

HeartRiskDetector-AI takes user health data (such as age, blood pressure, cholesterol, blood sugar, etc.), preprocesses it, and runs it through a trained machine learning model to predict whether the person is at risk of heart disease. The system provides quick, reliable, and accessible health insights.

How we built it

Collected and cleaned a publicly available heart disease dataset.
Applied data preprocessing (handling missing values, normalization, feature scaling).
Built and trained multiple machine learning models (Logistic Regression, Random Forest, etc.).
Evaluated models based on accuracy, precision, recall, and F1-score.
Integrated the best model into a Python-based system with a simple interface for user input and predictions.

Challenges we ran into

Handling missing and imbalanced data.

Choosing the best model and avoiding overfitting.

Optimizing accuracy while keeping predictions explainable.

Integrating preprocessing and prediction pipelines smoothly without runtime errors.

Accomplishments that we're proud of

Successfully built a working AI model that predicts heart disease risk with good accuracy.

Designed a structured and reusable pipeline for preprocessing and model training.

Learned how to debug and optimize real-world AI applications.

What we learned

Practical experience in data preprocessing and feature engineering.

Hands-on application of ML algorithms and evaluation techniques.

The importance of model interpretability in healthcare applications.

Collaboration and structured project development.

What's next for HeartRiskDectector-AI

Building a web or mobile app for easy accessibility.

Adding explainable AI (XAI) features to show why predictions are made.

Expanding the dataset for higher accuracy and global usability.

Integrating with wearable devices for real-time monitoring.

Built With

django
flask
joblib
matplotlib
numpy
pandas
python
scikit-learn
seaborn
streamlit
tensorflow

Created by

I contributed significantly to the design, development, and implementation of HeartRiskDetector-AI. My key roles and responsibilities included:

Project Ideation & Planning – Conceptualized the idea of an AI-powered system to detect potential heart risks early, ensuring it addresses real-world healthcare needs.

Data Preprocessing & Cleaning – Collected and processed health datasets, handled missing values, normalized inputs, and prepared the data for training.

Model Development & Training – Implemented and fine-tuned machine learning models to predict heart risk with high accuracy.

Backend Development – Designed the core AI pipeline, integrated the ML model with the application, and ensured smooth execution of predictions.

Frontend/Interface Support – Assisted in designing a simple, user-friendly interface for patients, doctors, and admins to interact with the system.

Testing & Debugging – Identified and resolved errors in preprocessing and main pipeline, ensuring the program runs smoothly without crashes.

Documentation & Reporting – Created detailed project documentation (About, Inspiration, Challenges, Learnings, etc.) to present the project in a professional format.

Collaboration & Coordination – Worked with teammates to integrate different modules, maintain version control, and align the project to its healthcare vision.

Through this project, I strengthened my skills in AI/ML, Python development, and problem-solving, while contributing to a tool that can positively impact healthcare accessibility and early diagnosis.

Livesh Jha
Bornface Kangombe