The project 'Early-Stage-Diabetes-Risk-Prediction' is developed for my workshop in Iraqidata, focusing on equipping participants with the knowledge and practical skills to predict the risk of early-stage diabetes. By delving into the realms of data analysis and predictive modeling, attendees will gain hands-on experience in leveraging data-driven approaches to assess and forecast the likelihood of diabetes onset. This initiative not only provides a platform for learning cutting-edge techniques in data science but also addresses a critical health concern, offering a tangible application of data analytics in healthcare. Participants will navigate through the intricacies of feature selection, model building, and evaluation, ultimately contributing to their proficiency in utilizing data for early-stage diabetes risk assessment.
Models | Accuracy |
---|---|
Logistic Regression | 0.9230769230769231 |
Decision Tree | 0.9134615384615384 |
Random Forest | 0.9903846153846154 |
SVM | 0.9903846153846154 |