EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Leveraging Shapley Additive Explanations for Feature Selection in Ensemble Models for Diabetes Prediction

Prasant Kumar Mohanty iD, Sharmila Anand John Francis iD, Rabindra Kumar Barik iD, Diptendu Sinha Roy iD, Manob Jyoti Saikia iD

Bioengineering · 30.11.2024 · 11 (12) · 1215

DOI: 10.3390/bioengineering11121215 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 30.11.2024. Verfasst von Prasant Kumar Mohanty und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, National Institute of Technology, Meghalaya 793003, India. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Biomedical Sensors & Systems Lab, University of Memphis, Memphis, TN 38152, USA.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetes, a significant global health crisis, is primarily driven in India by unhealthy diets and sedentary lifestyles, with rapid urbanization amplifying these effects through convenience-oriented living and limited physical activity opportunities, underscoring the need for advanced preventative strategies and technology for effective management. This study integrates Shapley Additive explanations (SHAPs) into ensemble machine learning models to improve the accuracy and efficiency of diabetes predictions. By identifying the most influential features using SHAP, this study examined their role in maintaining high predictive performance while minimizing computational demands. The impact of feature selection on model accuracy was assessed across ten models using three feature sets: all features, the top three influential features, and all except these top three. Models focusing on the top three features achieved superior performance, with the ensemble model attaining a better performance in most of the metrics, outperforming comparable approaches. Notably, excluding these features led to a significant decline in performance, reinforcing their critical influence. These findings validate the effectiveness of targeted feature selection for efficient and robust clinical applications.

Schlagwörter

Stichwörter der Autor:innen

Shapley additive explanationsdiabetes predictionensemble modelsinfluential feature values

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, National Institute of Technology, Meghalaya 793003, India.
  • Department of Computer Science, King Khalid University, Abha Campus, Rijal Alma, Abha 61421, Saudi Arabia.
  • School of Computer Applications, KIIT Deemed to be University, Bhubaneswar 751024, India.
  • Biomedical Sensors & Systems Lab, University of Memphis, Memphis, TN 38152, USA.
  • Electrical and Computer Engineering Department, University of Memphis, Memphis, TN 38152, USA.

ORCID-Profile: Prasant Kumar Mohanty, Sharmila Anand John Francis, Rabindra Kumar Barik, Diptendu Sinha Roy, Manob Jyoti Saikia

Förderung

  • Biomedical Sensors & Systems Lab, University of Memphis, Memphis, TN 38152, USA

Zitieren

APA

Mohanty, P. K., Francis, S. A. J., Barik, R. K., Roy, D. S., & Saikia, M. J. (2024). Leveraging Shapley Additive Explanations for Feature Selection in Ensemble Models for Diabetes Prediction. Bioengineering, 11(12), 1215. https://doi.org/10.3390/bioengineering11121215

Vancouver

Mohanty PK, Francis SAJ, Barik RK, Roy DS, Saikia MJ. Leveraging Shapley Additive Explanations for Feature Selection in Ensemble Models for Diabetes Prediction. Bioengineering. 2024;11(12):1215. doi:10.3390/bioengineering11121215

BibTeX
@article{Mohanty2024,
  author = {Mohanty, Prasant Kumar and Francis, Sharmila Anand John and Barik, Rabindra Kumar and Roy, Diptendu Sinha and Saikia, Manob Jyoti},
  title = {Leveraging Shapley Additive Explanations for Feature Selection in Ensemble Models for Diabetes Prediction},
  journal = {Bioengineering},
  year = {2024},
  volume = {11},
  number = {12},
  pages = {1215},
  doi = {10.3390/bioengineering11121215}
}
Kostenlos starten →