Explainable AI feature importance analysis of CTGAN-DC model for Kawasaki Disease prediction using SHapley Additive exPlanations (SHAP).

Explainable AI feature importance analysis of CTGAN-DC model for Kawasaki Disease prediction using SHapley Additive exPlanations (SHAP).

<p>Explainable AI feature importance analysis of CTGAN-DC model for Kawasaki Disease prediction using SHapley Additive exPlanations (SHAP).</p>

Saved in:

Bibliographic Details
Main Author:	Chuan-Sheng Hung (20489202) (author)
Other Authors:	Chun-Hung Richard Lin (6876671) (author), Jain-Shing Liu (20489205) (author), Shi-Huang Chen (20489208) (author), Tsung-Chi Hung (20489211) (author), Chih-Min Tsai (10023923) (author)
Published:	2024
Subjects:	Genetics Immunology Cancer Infectious Diseases Plant Biology Biological Sciences not elsewhere classified Information Systems not elsewhere classified various healthcare institutions two major hospitals original data characteristics inherent data imbalance improve data balance first approach proposes expanding data diversity coronary artery complications complicates accurate prediction bias commonly observed based oversampling techniques effectively balances positive advancing disease prediction stacking model termed traditional models toward taiwan </ p negative kd samples enhancing prediction accuracy predictive accuracy effectively resolving disease classifier model retains jama model combined model young children thereby mitigating statistical methods solid foundation significantly outperform severe cases predictive performance potentially leading majority class including xgboost frequently misdiagnosed findings lay enhancing generalization dc model common fever clinical settings
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Cannot write session to /tmp/vufind_sessions/sess_9vcd1l595uildlargrm34tkevp