Data-driven methods distort optimal cutoffs and accuracy estimates of depression screening tools: a simulation study using individual participant data

• Author(s): Bhandari, Parash Mani ; Levis, Brooke ; Neupane, Dipika ; Patten, Scott B ; Shrier, Ian ; Thombs, Brett D ; Benedetti, Andrea ; Figueiredo, Bárbara ; Tendais, Iva Alexandra Barbosa ; DEPRESsion Screening Data (DEPRESSD) EPDS Collaboration
• Date: 2021
• Persistent ID: https://hdl.handle.net/1822/91224
• Origin: RepositóriUM - Universidade do Minho
• Project/scholarship: info:eu-repo/grantAgreement/FCT/POCI/POCI%2FSAU-ESP%2F56397%2F2004/PT
• Subject(s): Computer simulation; Depression; Female; Humans; Psychiatric status rating scales; Reproducibility of results; Data science; Optimal cutoff; Accuracy estimates; Bias; Cherry-picking; Data-driven methods
• Document Type: Journal article
• Language: English
• Contributor(s): Universidade do Minho

Description

To evaluate, across multiple sample sizes, the degree that data-driven methods result in (1) optimal cutoffs different from population optimal cutoff and (2) bias in accuracy estimates.

NIMH -National Institute of Mental Health(13/00)