Journal
JOURNAL OF CLINICAL EPIDEMIOLOGY
Volume 137, Issue -, Pages 137-147Publisher
ELSEVIER SCIENCE INC
DOI: 10.1016/j.jclinepi.2021.03.031
Keywords
Optimal cutoff; Accuracy estimates; Bias; Cherry-picking; Data-driven methods; Depression
Funding
- Canadian Institutes of Health Research (CIHR) [KRS-140994]
- Research Institute of the McGill University Health Centre
- CIHR Frederick Banting and Charles Best Canada Graduate Scholarship doctoral award
- Fonds de recherche du Quebec -Sante(FRQ-S) Postdoctoral Training Award
- G.R. Caverhill Fellowship from the Faculty of Medicine, McGill University
- Vanier Canada Graduate Scholarship
- Utting Postdoctoral Fellowship from the Jewish General Hospital, Montreal, Quebec, Canada
- FRQ-S Postdoctoral Training Award
- FRQ-S Masters Training Award
- Ministry of Health of Chile
- Health Foundation [1665/608]
- Patrick and Catherine Weldon Donaghue Medical Research Foundation
- University of Connecticut Research Foundation
- Werner Otto Foundation
- Kroschke Foundation
- Feindt Foundation
- National Counsel of Technological and Scientific Development (CNPq) [403433/2004-5]
- Minas Gerais State Research Foundation (FAPEMIG) [APQ-01954-14]
- National Institute of Mental Health [K23 MH64476]
- Brazilian Ministry of Health
- Fundacao de Amparo aPesquisa do Estado de Sao Paulo
- Swiss National Science Foundation [32003B 125493]
- Child: Care Health and Development Trust
- Department of Psychiatry, University of Oxford, Oxford, UK
- Exeter College, University of Oxford
- University of Southampton National Institute for Health Research (NIHR) academic clinical fellowship in Paediatrics [POCI/SAU-ESP/56397/2004]
- European Community Fund FEDER
- Australian Government Department of Families, Housing, Community Services and Indigenous Affairs [7/98]
- Ministerio de Trabajo y Asuntos Sociales, Women's Institute, Spain
- NIHR under its Programme Grants for Applied Research Programme [RP-PG1210-12002, RP-DG-1108-10012]
- South London Clinical Research Network
- National Health and Medical and Research Council (NHMRC)
- Ratchadaphiseksomphot Endowment Fund
- Chulalongkorn University [CU-56-457-HR]
- Croatian Ministry of Science, Education, and Sports [134-0000000-2421, 13/00]
- Ministry of Work and Social Affairs, Institute of Women, Spain
- Japan Society for the Promotion of Science
- Intramural Research Grant for Neurological and Psychiatric Disorders from the National Center of Neurology and Psychiatry, Japan
- Medical Research Council UK Project Grant [G89292999N]
- Stichting Achmea Gezondheid [z-282]
- Brain and Behavior Research Foundation
- NIMH [K23MH080290]
- University of Oxford [HQ5035]
- Tuixen Foundation [9940]
- Wellcome Trust [071571, BA00457]
- American Psychological Association
- Wellcome Trust Intermediate Fellowship [211374/Z/18/Z]
- diamond Consortium, beyondblue Victorian Centre of Excellence in Depression and Related Disorders
- Swedish Research Council [VR: 521-2013-2339, VR:523-2014-2342]
- Swedish Council for Working Life and Social Research [FAS: 2011-0627]
- Marta Lundqvist Foundation
- Swedish Society of Medicine [SLS331991]
- Department of Health [DOH94F044, DOH95F022]
- China Medical University and Hospital [CMU94-105, DMR-92-92, DMR94-46]
- Thomas Wilson Sanitarium
- Myer Foundation
- Australian National Health and Medical Research Council
- Peruvian-American Endowment, Inc.
- National Institute of Child Health and Human Development grant [5 R01HD045735]
- Tier 1 Canada Research Chair
- FRQ-S Researcher Salary Awards
Ask authors/readers for more resources
Small accuracy studies using data-driven methods may identify inaccurate optimal cutoffs and overstate accuracy estimates.
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. (C) 2021 Elsevier Inc. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available