Health Predictor: A Flask Web Application for Depression and Cardiovascular Disease Prediction

Gouni, Vamshi Goud (2024) Health Predictor: A Flask Web Application for Depression and Cardiovascular Disease Prediction. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (873kB) | Preview

Abstract

The world’s problem of depression and cardiovascular illnesses is addressed by using the integration of Machine learning in the Flask online application Health Predictor. The focus on early intervention and tailored medication aligns with the growing demand for accessible health solutions. The main goal is to incorporate precise machine learning models to anticipate depression and cardiovascular within a user-friendly Flask application. Some specific goals include developing models using appropriate datasets, integrating apps, and evaluating performance. Some algorithms also use kaggle datasets for training. Cardiovascular disease prediction showed 72 percent accuracy for logistic regression, which proved resilient. An ensemble method, Voting Classifier (Random Forest and Gradient Boosting) with outstanding 73 percent accuracy shows the relevance of model selection. In depression prediction, Random Forest scored higher than Logistic Regression with an accuracy of 83.22 percent. While some difficulties were encountered by the ensemble method and resulted in an accuracy of 83.22 percent, these results show the limitation in optimization. The findings in both forecasts showed trade-offs in accuracy, recall, and precision. Some insights include the importance of the ensemble approach, the need for hyperparameter tuning, and achieving the right balance needed for accurate forecasting. The Flask app successfully combines multiple models for ease of application in health assessments.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Haque, Rejwanul UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence T Technology > Biomedical engineering
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Tamara Malone
Date Deposited:	03 Apr 2025 18:25
Last Modified:	03 Apr 2025 18:25
URI:	https://norma.ncirl.ie/id/eprint/7365

Actions (login required)

View Item