Translating polygenic risk scores for clinical use by estimating the confidence bounds of risk prediction
(2021) In Nature Communications 12. p.5276-5276- Abstract
A promise of genomics in precision medicine is to provide individualized genetic risk predictions. Polygenic risk scores (PRS), computed by aggregating effects from many genomic variants, have been developed as a useful tool in complex disease research. However, the application of PRS as a tool for predicting an individual's disease susceptibility in a clinical setting is challenging because PRS typically provide a relative measure of risk evaluated at the level of a group of people but not at individual level. Here, we introduce a machine-learning technique, Mondrian Cross-Conformal Prediction (MCCP), to estimate the confidence bounds of PRS-to-disease-risk prediction. MCCP can report disease status conditional probability value for... (More)
A promise of genomics in precision medicine is to provide individualized genetic risk predictions. Polygenic risk scores (PRS), computed by aggregating effects from many genomic variants, have been developed as a useful tool in complex disease research. However, the application of PRS as a tool for predicting an individual's disease susceptibility in a clinical setting is challenging because PRS typically provide a relative measure of risk evaluated at the level of a group of people but not at individual level. Here, we introduce a machine-learning technique, Mondrian Cross-Conformal Prediction (MCCP), to estimate the confidence bounds of PRS-to-disease-risk prediction. MCCP can report disease status conditional probability value for each individual and give a prediction at a desired error level. Moreover, with a user-defined prediction error rate, MCCP can estimate the proportion of sample (coverage) with a correct prediction.
(Less)
- author
- author collaboration
- organization
-
- Cardiovascular Research - Translational Studies (research group)
- EXODIAB: Excellence of Diabetes Research in Sweden
- Diabetes - Molecular Metabolism (research group)
- Nutrition Epidemiology (research group)
- EpiHealth: Epidemiology for Health
- Diabetes - Cardiovascular Disease (research group)
- Cardiovascular Research - Hypertension (research group)
- Cardiovascular Research - Epidemiology (research group)
- publishing date
- 2021-09-06
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Genetic Predisposition to Disease, Machine Learning
- in
- Nature Communications
- volume
- 12
- pages
- 5276 - 5276
- publisher
- Nature Publishing Group
- external identifiers
-
- scopus:85114717685
- pmid:34489429
- ISSN
- 2041-1723
- DOI
- 10.1038/s41467-021-25014-7
- language
- English
- LU publication?
- yes
- id
- 57a7683a-e8e0-4228-8e35-bed47c93cdb9
- date added to LUP
- 2021-09-14 10:22:56
- date last changed
- 2024-04-20 11:18:58
@article{57a7683a-e8e0-4228-8e35-bed47c93cdb9, abstract = {{<p>A promise of genomics in precision medicine is to provide individualized genetic risk predictions. Polygenic risk scores (PRS), computed by aggregating effects from many genomic variants, have been developed as a useful tool in complex disease research. However, the application of PRS as a tool for predicting an individual's disease susceptibility in a clinical setting is challenging because PRS typically provide a relative measure of risk evaluated at the level of a group of people but not at individual level. Here, we introduce a machine-learning technique, Mondrian Cross-Conformal Prediction (MCCP), to estimate the confidence bounds of PRS-to-disease-risk prediction. MCCP can report disease status conditional probability value for each individual and give a prediction at a desired error level. Moreover, with a user-defined prediction error rate, MCCP can estimate the proportion of sample (coverage) with a correct prediction.</p>}}, author = {{Sun, Jiangming and Wang, Yunpeng and Folkersen, Lasse and Borné, Yan and Amlien, Inge and Buil, Alfonso and Orho-Melander, Marju and Børglum, Anders D and Hougaard, David M and Melander, Olle and Engström, Gunnar and Werge, Thomas and Lage, Kasper}}, issn = {{2041-1723}}, keywords = {{Genetic Predisposition to Disease; Machine Learning}}, language = {{eng}}, month = {{09}}, pages = {{5276--5276}}, publisher = {{Nature Publishing Group}}, series = {{Nature Communications}}, title = {{Translating polygenic risk scores for clinical use by estimating the confidence bounds of risk prediction}}, url = {{http://dx.doi.org/10.1038/s41467-021-25014-7}}, doi = {{10.1038/s41467-021-25014-7}}, volume = {{12}}, year = {{2021}}, }