Does Using a Stacking Ensemble Method to Combine Multiple Base Learners Within a Database Improve Model Transportability?

Cynthia Yang; Egill A Fridgeirsson; Jan A Kors; Jenna M Reps; Peter R Rijnbeek; Jenna Wong; Ross D Williams

doi:10.3233/SHTI230080

Does Using a Stacking Ensemble Method to Combine Multiple Base Learners Within a Database Improve Model Transportability?

Stud Health Technol Inform. 2023 May 18:302:129-130. doi: 10.3233/SHTI230080.

Authors

Cynthia Yang¹, Egill A Fridgeirsson¹, Jan A Kors¹, Jenna M Reps^{1

2}, Peter R Rijnbeek¹, Jenna Wong³, Ross D Williams¹

Affiliations

¹ Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands.
² Observational Health Data Analytics, Janssen Research and Development, Titusville, NJ, USA.
³ Department of Population Medicine, Harvard Pilgrim Health Care Institute and Harvard Medical School, Boston, MA, USA.

PMID: 37203625
DOI: 10.3233/SHTI230080

Abstract

We investigated a stacking ensemble method that combines multiple base learners within a database. The results on external validation across four large databases suggest a stacking ensemble could improve model transportability.

Keywords: Clinical prediction model; external validation; stacking ensemble.

MeSH terms

Databases, Factual*