Development and Validation of a Prediction Model for Incident Hypothyroidism in a National Chronic Kidney Disease Cohort
Authors' conclusion
In a national cohort of CKD patients, we developed a clinical prediction tool identifying those at risk for incident hypothyroidism to inform prioritized screening, monitoring, and treatment in this population.
Study context
- Population
- Patients with stages 4 to 5 chronic kidney disease (CKD) without evidence of pre-existing thyroid disease, Optum Labs Data Warehouse
- Participants
- 15,642 patients
- Comparison
- Development set vs Validation set
- Outcome
- Incident hypothyroidism (TSH > 5.0 mIU/L)
- Follow-up
- Median 3.4 years
Methodological detailsCox models, two-thirds development set and one-third validation set, national cohort
- Cox models
- Two-thirds development set and one-third validation set
- National cohort
Performance
As reported in the abstract
Model discrimination (C-statistic) for incident hypothyroidism
- C-statistic in the development dataset
- 0.77 (95% CI 0.75-0.78)
- C-statistic in the validation dataset
- 0.76 (95% CI 0.74-0.78)
- Goodness-of-fit, overall cohort (adequate fit)
- P = .47
- Goodness-of-fit, stage 5 CKD subcohort (adequate fit)
- P = .33
Further findings
Model goodness-of-fit
- Adequate fit, overall cohort
- P = 0.47
- Adequate fit, stage 5 CKD subcohort
- P = 0.33
Original publication
Development and Validation of a Prediction Model for Incident Hypothyroidism in a National Chronic Kidney Disease Cohort. J Clin Endocrinol Metab. Published 15 May 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →