Research on categorical prediction of diabetes based on XGBoost

Mengyuan Li

doi:10.1117/12.2691805

23 August 2023 Research on categorical prediction of diabetes based on XGBoost

Mengyuan Li

Proceedings Volume 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023); 127840K (2023) https://doi.org/10.1117/12.2691805
Event: 2023 2nd International Conference on Applied Statistics, Computational Mathematics and Software Engineering (ASCMSE 2023), 2023, Kaifeng, China

Abstract

Diabetes has become the third chronic non communicable disease that seriously threatens the national health after cancer, cardiovascular and cerebrovascular diseases, and is showing a trend of youth.[1] To explore the impact of life factors on diabetes, this paper constructs XGBoost categorical prediction model. With the Kaggle website as the data source, after data processing and exploratory analysis, the processed data is used as the model input, and the grid search algorithm is used to optimize the model parameters to obtain the optimal XGBoost prediction model and obtain the high impact factors on diabetes. The results show that the optimized XGBoost model performs well in evaluation indicators, with an accuracy rate of 98.95%, F1-score of 0.9787, AUC of 0.9792. The top four factors are BMI, duration of deep sleep, family history of diabetes and pregnancy times.

Citation Download Citation

Mengyuan Li "Research on categorical prediction of diabetes based on XGBoost", Proc. SPIE 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023), 127840K (23 August 2023); https://doi.org/10.1117/12.2691805

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available