Addressing overfitting bias due to sample overlap in polygenic risk scoring
Alzheimer's & Dementia · 2025-04 · 21 (4)
DOI: 10.1002/alz.70109 ↗Kurz gefasst
Fachartikel in der Zeitschrift Alzheimer's & Dementia, online erschienen am 06.04.2025. Verfasst von Seokho Jeong und 13 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Alzheimer Disease, Multifactorial Inheritance, Genetic Predisposition to Disease. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHLBI NIH HHS, the Ministry of Science and ICT, NIH HHS.
Abstract (Originalsprache)
INTRODUCTION Numerous studies on Alzheimer's disease polygenic risk scores (PRSs) overlook sample overlap between International Genomics of Alzheimer's Project (IGAP) and target datasets like Alzheimer's Disease Neuroimaging Initiative (ADNI). METHODS To address this, we developed overlap‐adjusted PRS (OA PRS) and tested it on simulated data to assess biases from different scenarios by varying training, testing, and overlap proportions. OA PRS was used to adjust for sample bias in simulations; then, we applied OA PRS to IGAP and ADNI datasets and validated through visual diagnosis. RESULTS OA PRS effectively adjusted for sample overlap in all simulation scenarios, as well as for IGAP and ADNI. The original IGAP PRS showed an inflated area under the receiver operating characteristic (AUROC: 0.915) on overlapping samples. OA PRS reduced the AUROC to 0.726, closely aligning with the AUROC of non‐overlapping samples (0.712). Further, visual diagnostics confirmed the effectiveness of our adjustments. DISCUSSION With OA PRS, we were able to adjust the IGAP summary‐based PRS for the overlapped ADNI samples, allowing the dataset to be fully used without the risk of overfitting. Highlights Sample overlap between large Alzheimer's disease (AD) cohorts poses overfitting bias when using AD polygenic risk scores (PRSs). This study highlighted the effectiveness of overlap‐adjusted PRS (OA ‐PRS) in mitigating overfitting and improving the accuracy of PRS estimations. New PRSs based on adjusted effect sizes showed increased power in association with clinical features.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea.
- Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
- Department of Medical Informatics, Kangwon National University, College of Medicine, Chuncheon, Republic of Korea.
- Samsung Advanced Institute for Health Sciences and Technology (SAIHST), Samsung Medical Center, Sungkyunkwan University, Seoul, Republic of Korea.
- Indiana Alzheimer's Disease Research Center, Indiana University School of Medicine, Indianapolis, Indiana, USA.
- Center for Computational Biology and Bioinformatics, Indiana University School of Medicine, Indianapolis, Indiana, USA.
ORCID-Profile: Dokyoon Kim
Förderung
- NHLBI NIH HHS
- the Ministry of Science and ICT
- NIH HHS
- NIA NIH HHS
- NIGMS NIH HHS
- National Institutes of Health
Zitieren
APA
Jeong, S., Shivakumar, M., Jung, S. H., Won, H. H., Nho, K., Huang, H., Davatzikos, C., Saykin, A. J., Thompson, P. M., Shen, L., Kim, Y. J., Kim, B. J., Lee, S., & Kim, D. (2025). Addressing overfitting bias due to sample overlap in polygenic risk scoring. Alzheimer's & Dementia, 21(4). https://doi.org/10.1002/alz.70109
Vancouver
Jeong S, Shivakumar M, Jung SH, Won HH, Nho K, Huang H, et al. Addressing overfitting bias due to sample overlap in polygenic risk scoring. Alzheimer's & Dementia. 2025;21(4). doi:10.1002/alz.70109
BibTeX
@article{Jeong2025,
author = {Jeong, Seokho and Shivakumar, Manu and Jung, Sang-Hyuk and Won, Hong-Hee and Nho, Kwangsik and Huang, Heng and Davatzikos, Christos and Saykin, Andrew J and Thompson, Paul M and Shen, Li and Kim, Young Jin and Kim, Bong-Jo and Lee, Seunggeun and Kim, Dokyoon},
title = {Addressing overfitting bias due to sample overlap in polygenic risk scoring},
journal = {Alzheimer's & Dementia},
year = {2025},
volume = {21},
number = {4},
doi = {10.1002/alz.70109}
}
EUVIMED