Design matters in patient-level prediction: evaluation of a cohort vs. case-control design when developing predictive models in observational healthcare datasets

• Published in: Journal of big data Vol. 8; no. 1; pp. 1 - 18
• Main Authors: Reps, Jenna M., Ryan, Patrick B., Rijnbeek, Peter R., Schuemie, Martijn J.
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 16.08.2021; Springer Nature B.V; SpringerOpen
• Subjects: Big Data; Calibration; Case-control; Classification; Cohort; Communications Engineering; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Database Management; Dementia; Design analysis; Diabetes; Health care; Information Storage and Retrieval; Mathematical Applications in Computer Science; Networks; Patient-level prediction; Prediction; Prediction models; Predictions; Prognostic; Patient-level prediction; Cohort; Prognostic; Prediction; Classification; Case-control

Background The design used to create labelled data for training prediction models from observational healthcare databases (e.g., case-control and cohort) may impact the clinical usefulness. We aim to investigate hypothetical design issues and determine how the design impacts prediction model perform...