Dectects if someone has a Heart Disease with python using the Public Health Dataset of heart diseases.
Research and Poster Presentation: I recently presented a poster on this machine learning model project at the MICRO NANO TECHNOLOGY EDUCATION SPECIAL INTEREST GROUP program. The presentation was well-received, and if you're interested in learning more about my findings, I encourage you to check out the detailed poster. https://www.mntesig.net/mntesig-2023-virtual.html
My Machine Learning Model that predicts if a user would be diagnosed with heart disease based on the Public Health Dataset via https://www.kaggle.com/. This trained machine learning model utilized both the random forest and the naive Bayes classifier to test its accuracy in predicting if an individual would have heart disease.
Primary goal: The primary goal is to develop a predictive model to determine the likelihood of a user being diagnosed with heart disease based on relevant health-related features.
Dataset Source: The model is trained on a public health dataset sourced from heart.csv. This dataset comprises hundreds of instances related to individuals' health. This data set dates from 1988 and consists of four databases: Cleveland, Hungary, Switzerland, and Long Beach V.
The dataset includes features such as age sex chest pain type (4 values) resting blood pressure serum cholestoral in mg/dl fasting blood sugar > 120 mg/dl resting electrocardiographic results (values 0,1,2) maximum heart rate achieved exercise induced angina oldpeak = ST depression induced by exercise relative to rest the slope of the peak exercise ST segment number of major vessels (0-3) colored by flourosopy thal: 0 = normal; 1 = fixed defect; 2 = reversable defect The names and social security numbers of the patients were recently removed from the database, replaced with dummy values.
The target variable is the diagnosis of heart disease, represented as 0 or 1, where 0 indicates no heart disease and 1 indicates the presence of heart disease.
Model Selection and Training: The Random Forest Classifier algorithm was selected for its suitability in binary classification tasks. In the updated version of this model, I used the Naive Bayes classifier to test each classifier's accuracy.
The dataset was split into training and testing sets (80/20 split), and the model was trained on the training set.
This model can be deployed in a web application using scikit_learn
Here are some screenshots of how the model is deployed in the web app:
If you have any questions, comments, or concerns please reach out!