Literature DB >> 33838273

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

Parash Mani Bhandari1, Brooke Levis2, Dipika Neupane1, Scott B Patten3, Ian Shrier4, Brett D Thombs5, Andrea Benedetti6.   

Abstract

OBJECTIVE: 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. STUDY DESIGN AND
SETTING: A total of 1,000 samples of sample size 100, 200, 500 and 1,000 each were randomly drawn to simulate studies of different sample sizes from a database (n = 13,255) synthesized to assess Edinburgh Postnatal Depression Scale (EPDS) screening accuracy. Optimal cutoffs were selected by maximizing Youden's J (sensitivity+specificity-1). Optimal cutoffs and accuracy estimates in simulated samples were compared to population values.
RESULTS: Optimal cutoffs in simulated samples ranged from ≥ 5 to ≥ 17 for n = 100, ≥ 6 to ≥ 16 for n = 200, ≥ 6 to ≥ 14 for n = 500, and ≥ 8 to ≥ 13 for n = 1,000. Percentage of simulated samples identifying the population optimal cutoff (≥ 11) was 30% for n = 100, 35% for n = 200, 53% for n = 500, and 71% for n = 1,000. Mean overestimation of sensitivity and underestimation of specificity were 6.5 percentage point (pp) and -1.3 pp for n = 100, 4.2 pp and -1.1 pp for n = 200, 1.8 pp and -1.0 pp for n = 500, and 1.4 pp and -1.0 pp for n = 1,000.
CONCLUSIONS: Small accuracy studies may identify inaccurate optimal cutoff and overstate accuracy estimates with data-driven methods.
Copyright © 2021 Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Accuracy estimates; Bias; Cherry-picking; Data-driven methods; Depression; Optimal cutoff

Mesh:

Year:  2021        PMID: 33838273     DOI: 10.1016/j.jclinepi.2021.03.031

Source DB:  PubMed          Journal:  J Clin Epidemiol        ISSN: 0895-4356            Impact factor:   6.437


  1 in total

1.  Sample size and precision of estimates in studies of depression screening tool accuracy: A meta-research review of studies published in 2018-2021.

Authors:  Elsa-Lynn Nassar; Brooke Levis; Marieke A Neyer; Danielle B Rice; Linda Booij; Andrea Benedetti; Brett D Thombs
Journal:  Int J Methods Psychiatr Res       Date:  2022-04-01       Impact factor: 4.182

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.