Decoding Diabetes: A Journey Through Random Forest and SHAP Interpretability

Q: How many days will it take for my paper to be published?

The review time for papers is not fixed. However, if the paper is accepted and the author completes the processing charges formalities, the paper will be published within a few working days.

Q: I would like to receive a hard copy of the journal materials. Are there any additional charges?

You can log in to the author portal and pay 500 INR to receive the hard copy materials.

Mithun Kamashetty; Chetan C; Vishnu Anand T; P Sushmita Singh

Decoding Diabetes: A Journey Through Random Forest and SHAP Interpretability

Authors: Mithun Kamashetty, Chetan C, Vishnu Anand T, P Sushmita Singh

Unique Paper ID: 179066
Volume: 11
Issue: 12
PageNo: 7974-7982

Keywords: Diabetes Prediction Machine Learning Ran- dom Forest Artificial Neural Networks Pima Indians Dataset SHAP Early Diagnosis Clinical Decision Support

Abstract:
Millions of people worldwide suffer from diabetes every day, a chronic illness that affects how your body processes sugar, posing a significant burden on healthcare systems due to its long-term complications. Early diagnosis and timely intervention are essential to manage and prevent the progression of the disease. This study presents the development of a machine learning-based system designed to predict the likelihood of diabetes in individuals using commonly avail- able health parameters. Leveraging the Pima Indians Diabetes Dataset, the system incorporates features such as age, BMI, glucose level, blood pressure, insulin levels, and family history to train and evaluate multiple classification algorithms including Logistic Regression, Decision Trees, Random Forests, and Artificial Neural Networks (ANN). Among these, the Random Forest model achieved the highest performance with an accuracy of over 85%, precision of 0.90, recall of 0.86, and an F1-score of 0.87. The system also integrates SHAP-based interpretability to provide transparency in predictions, making it suitable for clinical decision support. This approach offers a scalable, cost- effective, and user-friendly solution for early diabetes detection, particularly valuable in resource-constrained healthcare settings.

Download article

email to a friend

Cite This Article

ISSN: 2349-6002
Volume: 11
Issue: 12
PageNo: 7974-7982

Decoding Diabetes: A Journey Through Random Forest and SHAP Interpretability

Available:https://ijirt.org/article?manuscript=179066

Impact Factor
8.01 (Year 2024)

UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now