Polygenic Scores Help Reduce Racial Disparities in Predictive Accuracy of Automated Type 1 Diabetes Classification Algorithms
Performance · Misclassification (incorrect T1D diagnosis) by automated algorithm, self-reported non-White vs WhiteResult — go to the resultOdds ratio 3.45 95% CI 1.54–7.69Authors' conclusion
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.
Study context
- Population
- Individuals identified with T1D by an automated algorithm in two hospital-based biobanks (Mass General Brigham [MGB] and BioMe)
- Comparison
- Automated T1D classification algorithm before vs after incorporating polygenic scores
- Outcome
- Misclassification (incorrect T1D diagnosis) by automated algorithm, self-reported non-White vs White
Methodological detailstwo hospital-based biobanks, medical record review validation
- Two hospital-based biobanks
- Medical record review validation
Performance
As reported in the abstract
Odds ratio
3.45
95% CI 1.54–7.69
P = 0.0026
Self-reported non-Whitevs Self-reported White
OR 3.45 (95% CI 1.54–7.69); P = 0.0026
Further findings
| Outcome | Algorithm | Algorithm + polygenic scores |
|---|---|---|
| PPV of T1D algorithm, self-reported White, MGB Biobank | ||
| PPV | 70 | 97% |
| PPV of T1D algorithm, self-reported non-White, MGB Biobank | ||
| PPV | 53 | 100% |
PPV in BioMe
- Similar results were found in BioMe
Original publication
Polygenic Scores Help Reduce Racial Disparities in Predictive Accuracy of Automated Type 1 Diabetes Classification Algorithms. Diabetes Care. Published 6 February 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →