Generalizability of cardiovascular disease clinical prediction models
| Autor: | Gaurav Gulati, Jenica Upshaw, Benjamin S. Wessler, Riley J. Brazil, Jason Nelson, David van Klaveren, Christine M. Lundquist, Jinny G. Park, Hannah McGinnes, Ewout W. Steyerberg, Ben Van Calster, David M. Kent |
|---|---|
| Přispěvatelé: | Public Health |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
Cardiac & Cardiovascular Systems
IMPLANTABLE CARDIOVERTER-DEFIBRILLATOR INITIATE LIFESAVING TREATMENT Risk Assessment models SDG 3 - Good Health and Well-being Humans IN-HOSPITAL MORTALITY CORONARY-HEART-DISEASE risk Heart Failure CHINESE POPULATION Science & Technology decision support techniques cardiovascular ELEVATION MYOCARDIAL-INFARCTION ORGANIZED PROGRAM cardiovascular diseases clinical decision validation study Cardiovascular System & Cardiology LIPID-LOWERING TREATMENT SYNDROME RISK SCORE PRIMARY PREVENTION Cardiology and Cardiovascular Medicine Life Sciences & Biomedicine |
| Zdroj: | Circulation. Cardiovascular quality and outcomes, 15(4). Lippincott Williams & Wilkins Circulation: Cardiovascular Quality and Outcomes, 15(4), 248-260. LIPPINCOTT WILLIAMS & WILKINS |
| ISSN: | 1941-7713 |
| DOI: | 10.1161/circoutcomes.121.008487 |
| Popis: | Background: While clinical prediction models (CPMs) are used increasingly commonly to guide patient care, the performance and clinical utility of these CPMs in new patient cohorts is poorly understood. Methods: We performed 158 external validations of 104 unique CPMs across 3 domains of cardiovascular disease (primary prevention, acute coronary syndrome, and heart failure). Validations were performed in publicly available clinical trial cohorts and model performance was assessed using measures of discrimination, calibration, and net benefit. To explore potential reasons for poor model performance, CPM-clinical trial cohort pairs were stratified based on relatedness, a domain-specific set of characteristics to qualitatively grade the similarity of derivation and validation patient populations. We also examined the model-based C-statistic to assess whether changes in discrimination were because of differences in case-mix between the derivation and validation samples. The impact of model updating on model performance was also assessed. Results: Discrimination decreased significantly between model derivation (0.76 [interquartile range 0.73–0.78]) and validation (0.64 [interquartile range 0.60–0.67], P P =0.001). When considering the full range of possible decision thresholds between half and twice the outcome incidence, 91% of models had a risk of harm (net benefit below default strategy) at some threshold; this risk could be reduced substantially via updating model intercept, calibration slope, or complete re-estimation. Conclusions: There are significant decreases in model performance when applying cardiovascular disease CPMs to new patient populations, resulting in substantial risk of harm. Model updating can mitigate these risks. Care should be taken when using CPMs to guide clinical decision-making. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|