Domain-aware matrix completion for phenotype imputation using electronic health record data with applications in genomic research
(2026) In Annals of Applied Statistics 20(2).- Abstract
- Large-scale biobanks and electronic health records (EHR) offer great opportunities for next-generation genetic studies. However, missing phenotype data is a pervasive feature of EHR, leading to low power of such studies. One promising solution is prediction-powered inference, where statistical or machine learning models are employed to impute phenotypes prior to performing genetic analyses. Although many such methods exist, they tend to be generic and do not incorporate domain-aware knowledge to optimize their performance for downstream genetic analyses. We propose a novel matrix completion method, covImpute, which, unlike generic matrix completion methods such as softImpute, incorporates external information in the form of a genetic... (More)
- Large-scale biobanks and electronic health records (EHR) offer great opportunities for next-generation genetic studies. However, missing phenotype data is a pervasive feature of EHR, leading to low power of such studies. One promising solution is prediction-powered inference, where statistical or machine learning models are employed to impute phenotypes prior to performing genetic analyses. Although many such methods exist, they tend to be generic and do not incorporate domain-aware knowledge to optimize their performance for downstream genetic analyses. We propose a novel matrix completion method, covImpute, which, unlike generic matrix completion methods such as softImpute, incorporates external information in the form of a genetic covariance matrix among phenotypic features and imputes missing entries with latent genetic components. We compare covImpute with existing methods, including a domain-aware liability threshold model LTPI, and generic softImpute and deep learning autoencoder models in simulations under different missingness mechanisms with respect to power in downstream genetic analyses. In applications to several diseases in UK Biobank, we show that genetically informed methods, such as covImpute and LTPI, can perform substantially better in terms of power of genetic association studies relative to generic imputation models currently in use. Moreover, compared to LTPI, covImpute’s flexible framework for incorporating external covariance information provides a more general approach with applicability beyond genetics. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/6ec64af2-ab84-4d1a-ad56-ffb42eb1ba5b
- author
- Wu, Hanqing
LU
; Lee, Cue Hyunkyu
; Abiri, Najmeh
LU
and Ionita-Laza, Iuliana
LU
- organization
- publishing date
- 2026-06-01
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Annals of Applied Statistics
- volume
- 20
- issue
- 2
- publisher
- Institute of Mathematical Statistics
- ISSN
- 1932-6157
- DOI
- 10.1214/26-AOAS2165
- language
- English
- LU publication?
- yes
- id
- 6ec64af2-ab84-4d1a-ad56-ffb42eb1ba5b
- alternative location
- https://projecteuclid.org/journals/annals-of-applied-statistics/volume-20/issue-2/Domain-aware-matrix-completion-for-phenotype-imputation-using-electronic-health/10.1214/26-AOAS2165.full
- date added to LUP
- 2026-06-28 18:54:42
- date last changed
- 2026-06-30 10:33:07
@article{6ec64af2-ab84-4d1a-ad56-ffb42eb1ba5b,
abstract = {{Large-scale biobanks and electronic health records (EHR) offer great opportunities for next-generation genetic studies. However, missing phenotype data is a pervasive feature of EHR, leading to low power of such studies. One promising solution is prediction-powered inference, where statistical or machine learning models are employed to impute phenotypes prior to performing genetic analyses. Although many such methods exist, they tend to be generic and do not incorporate domain-aware knowledge to optimize their performance for downstream genetic analyses. We propose a novel matrix completion method, covImpute, which, unlike generic matrix completion methods such as softImpute, incorporates external information in the form of a genetic covariance matrix among phenotypic features and imputes missing entries with latent genetic components. We compare covImpute with existing methods, including a domain-aware liability threshold model LTPI, and generic softImpute and deep learning autoencoder models in simulations under different missingness mechanisms with respect to power in downstream genetic analyses. In applications to several diseases in UK Biobank, we show that genetically informed methods, such as covImpute and LTPI, can perform substantially better in terms of power of genetic association studies relative to generic imputation models currently in use. Moreover, compared to LTPI, covImpute’s flexible framework for incorporating external covariance information provides a more general approach with applicability beyond genetics.}},
author = {{Wu, Hanqing and Lee, Cue Hyunkyu and Abiri, Najmeh and Ionita-Laza, Iuliana}},
issn = {{1932-6157}},
language = {{eng}},
month = {{06}},
number = {{2}},
publisher = {{Institute of Mathematical Statistics}},
series = {{Annals of Applied Statistics}},
title = {{Domain-aware matrix completion for phenotype imputation using electronic health record data with applications in genomic research}},
url = {{http://dx.doi.org/10.1214/26-AOAS2165}},
doi = {{10.1214/26-AOAS2165}},
volume = {{20}},
year = {{2026}},
}