Polygenic Scores Help Reduce Racial Disparities in Predictive Accuracy of Automated Type 1 Diabetes Classification Algorithms

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Polygenic Scores Help Reduce Racial Disparities in Predictive Accuracy of Automated Type 1 Diabetes Classification Algorithms. / Deutsch, Aaron J.; Stalbow, Lauren; Majarian, Timothy D.; Mercader, Josep M.; Manning, Alisa K.; Florez, Jose C.; Loos, Ruth J.F.; Udler, Miriam S.

In: Diabetes Care, Vol. 46, No. 4, 2023, p. 794-800.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Deutsch, AJ, Stalbow, L, Majarian, TD, Mercader, JM, Manning, AK, Florez, JC, Loos, RJF & Udler, MS 2023, 'Polygenic Scores Help Reduce Racial Disparities in Predictive Accuracy of Automated Type 1 Diabetes Classification Algorithms', Diabetes Care, vol. 46, no. 4, pp. 794-800. https://doi.org/10.2337/dc22-1833

APA

Deutsch, A. J., Stalbow, L., Majarian, T. D., Mercader, J. M., Manning, A. K., Florez, J. C., Loos, R. J. F., & Udler, M. S. (2023). Polygenic Scores Help Reduce Racial Disparities in Predictive Accuracy of Automated Type 1 Diabetes Classification Algorithms. Diabetes Care, 46(4), 794-800. https://doi.org/10.2337/dc22-1833

Vancouver

Deutsch AJ, Stalbow L, Majarian TD, Mercader JM, Manning AK, Florez JC et al. Polygenic Scores Help Reduce Racial Disparities in Predictive Accuracy of Automated Type 1 Diabetes Classification Algorithms. Diabetes Care. 2023;46(4):794-800. https://doi.org/10.2337/dc22-1833

Author

Deutsch, Aaron J. ; Stalbow, Lauren ; Majarian, Timothy D. ; Mercader, Josep M. ; Manning, Alisa K. ; Florez, Jose C. ; Loos, Ruth J.F. ; Udler, Miriam S. / Polygenic Scores Help Reduce Racial Disparities in Predictive Accuracy of Automated Type 1 Diabetes Classification Algorithms. In: Diabetes Care. 2023 ; Vol. 46, No. 4. pp. 794-800.

Bibtex

@article{3b55f911cf6b4029af760d40587a5fd5,
title = "Polygenic Scores Help Reduce Racial Disparities in Predictive Accuracy of Automated Type 1 Diabetes Classification Algorithms",
abstract = "OBJECTIVE: Automated algorithms to identify individuals with type 1 diabetes using electronic health records are increasingly used in biomedical research. It is not known whether the accuracy of these algorithms differs by self-reported race. We investigated whether polygenic scores improve identification of individuals with type 1 diabetes. RESEARCH DESIGN AND METHODS: We investigated two large hospital-based biobanks (Mass General Brigham [MGB] and BioMe) and identified individuals with type 1 diabetes using an established automated algorithm. We performed medical record reviews to validate the diagnosis of type 1 diabetes. We implemented two published polygenic scores for type 1 diabetes (developed in individuals of European or African ancestry). We assessed the classification algorithm before and after incorporating polygenic scores. RESULTS: The automated algorithm was more likely to incorrectly assign a diagnosis of type 1 diabetes in self-reported non-White individuals than in self-reported White individuals (odds ratio 3.45; 95% CI 1.54-7.69; P = 0.0026). After incorporating polygenic scores into the MGB Biobank, the positive predictive value of the type 1 diabetes algorithm increased from 70 to 97% for self-reported White individuals (meaning that 97% of those predicted to have type 1 diabetes indeed had type 1 diabetes) and from 53 to 100% for self-reported non-White individuals. Similar results were found in BioMe. CONCLUSIONS: Automated phenotyping algorithms may exacerbate health disparities because of an increased risk of misclassification of individuals from underrepresented populations. Polygenic scores may be used to improve the performance of phenotyping algorithms and potentially reduce this disparity.",
author = "Deutsch, {Aaron J.} and Lauren Stalbow and Majarian, {Timothy D.} and Mercader, {Josep M.} and Manning, {Alisa K.} and Florez, {Jose C.} and Loos, {Ruth J.F.} and Udler, {Miriam S.}",
note = "Publisher Copyright: {\textcopyright} 2023 by the American Diabetes Association.",
year = "2023",
doi = "10.2337/dc22-1833",
language = "English",
volume = "46",
pages = "794--800",
journal = "Diabetes Care",
issn = "1935-5548",
publisher = "American Diabetes Association",
number = "4",

}

RIS

TY - JOUR

T1 - Polygenic Scores Help Reduce Racial Disparities in Predictive Accuracy of Automated Type 1 Diabetes Classification Algorithms

AU - Deutsch, Aaron J.

AU - Stalbow, Lauren

AU - Majarian, Timothy D.

AU - Mercader, Josep M.

AU - Manning, Alisa K.

AU - Florez, Jose C.

AU - Loos, Ruth J.F.

AU - Udler, Miriam S.

N1 - Publisher Copyright: © 2023 by the American Diabetes Association.

PY - 2023

Y1 - 2023

N2 - OBJECTIVE: Automated algorithms to identify individuals with type 1 diabetes using electronic health records are increasingly used in biomedical research. It is not known whether the accuracy of these algorithms differs by self-reported race. We investigated whether polygenic scores improve identification of individuals with type 1 diabetes. RESEARCH DESIGN AND METHODS: We investigated two large hospital-based biobanks (Mass General Brigham [MGB] and BioMe) and identified individuals with type 1 diabetes using an established automated algorithm. We performed medical record reviews to validate the diagnosis of type 1 diabetes. We implemented two published polygenic scores for type 1 diabetes (developed in individuals of European or African ancestry). We assessed the classification algorithm before and after incorporating polygenic scores. RESULTS: The automated algorithm was more likely to incorrectly assign a diagnosis of type 1 diabetes in self-reported non-White individuals than in self-reported White individuals (odds ratio 3.45; 95% CI 1.54-7.69; P = 0.0026). After incorporating polygenic scores into the MGB Biobank, the positive predictive value of the type 1 diabetes algorithm increased from 70 to 97% for self-reported White individuals (meaning that 97% of those predicted to have type 1 diabetes indeed had type 1 diabetes) and from 53 to 100% for self-reported non-White individuals. Similar results were found in BioMe. CONCLUSIONS: Automated phenotyping algorithms may exacerbate health disparities because of an increased risk of misclassification of individuals from underrepresented populations. Polygenic scores may be used to improve the performance of phenotyping algorithms and potentially reduce this disparity.

AB - OBJECTIVE: Automated algorithms to identify individuals with type 1 diabetes using electronic health records are increasingly used in biomedical research. It is not known whether the accuracy of these algorithms differs by self-reported race. We investigated whether polygenic scores improve identification of individuals with type 1 diabetes. RESEARCH DESIGN AND METHODS: We investigated two large hospital-based biobanks (Mass General Brigham [MGB] and BioMe) and identified individuals with type 1 diabetes using an established automated algorithm. We performed medical record reviews to validate the diagnosis of type 1 diabetes. We implemented two published polygenic scores for type 1 diabetes (developed in individuals of European or African ancestry). We assessed the classification algorithm before and after incorporating polygenic scores. RESULTS: The automated algorithm was more likely to incorrectly assign a diagnosis of type 1 diabetes in self-reported non-White individuals than in self-reported White individuals (odds ratio 3.45; 95% CI 1.54-7.69; P = 0.0026). After incorporating polygenic scores into the MGB Biobank, the positive predictive value of the type 1 diabetes algorithm increased from 70 to 97% for self-reported White individuals (meaning that 97% of those predicted to have type 1 diabetes indeed had type 1 diabetes) and from 53 to 100% for self-reported non-White individuals. Similar results were found in BioMe. CONCLUSIONS: Automated phenotyping algorithms may exacerbate health disparities because of an increased risk of misclassification of individuals from underrepresented populations. Polygenic scores may be used to improve the performance of phenotyping algorithms and potentially reduce this disparity.

U2 - 10.2337/dc22-1833

DO - 10.2337/dc22-1833

M3 - Journal article

C2 - 36745605

AN - SCOPUS:85151043437

VL - 46

SP - 794

EP - 800

JO - Diabetes Care

JF - Diabetes Care

SN - 1935-5548

IS - 4

ER -

ID: 342529354