Please use this identifier to cite or link to this item: https://scholarhub.balamand.edu.lb/handle/uob/7170
Title: Proof-of-concept of a data-driven approach to estimate the associations of comorbid mental and physical disorders with global health-related disability
Authors: de Vries, Ymkje Anna
Alonso, Jordi
Chatterji, Somnath
de Jonge, Peter
Lokkerbol, Joran
McGrath, John J.
Petukhova, Maria V.
Sampson, Nancy A.
Sverdrup, Erik
Vigo, Daniel V.
Wager, Stefan
Al-Hamzawi, Ali
Borges, Guilherme
Bruffaerts, Ronny
Bunting, Brendan
Chardoul, Stephanie
Karam, Elie G.
Kiejna, Andrzej
Kovess-Masfety, Viviane
Navarro-Mateu, Fernando
Ojagbemi, Akin
Piazza, Marina
Posada-Villa, José
Sasu, Carmen
Scott, Kate M.
Tachimori, Hisateru
Have, Margreet Ten
Torres, Yolanda
Viana, Maria Carmen
Zamparini, Manuel
Zarkov, Zahari
Kessler, Ronald C.
Affiliations: Faculty of Medicine 
Keywords: Causal forest
Comorbidity
Disability
Global burden of disease
Mental disorders
Issue Date: 2024-03-01
Publisher: Wiley Online Library
Part of: International Journal of Methods in Psychiatric Research
Volume: 33
Issue: 1
Abstract: 
Objective: The standard method of generating disorder-specific disability scores has lay raters make rankings between pairs of disorders based on brief disorder vignettes. This method introduces bias due to differential rater knowledge of disorders and inability to disentangle the disability due to disorders from the disability due to comorbidities. Methods: We propose an alternative, data-driven, method of generating disorder-specific disability scores that assesses disorders in a sample of individuals either from population medical registry data or population survey self-reports and uses Generalized Random Forests (GRF) to predict global (rather than disorder-specific) disability assessed by clinician ratings or by survey respondent self-reports. This method also provides a principled basis for studying patterns and predictors of heterogeneity in disorder-specific disability. We illustrate this method by analyzing data for 16 disorders assessed in the World Mental Health Surveys (n = 53,645). Results: Adjustments for comorbidity decreased estimates of disorder-specific disability substantially. Estimates were generally somewhat higher with GRF than conventional multivariable regression models. Heterogeneity was nonsignificant. Conclusions: The results show clearly that the proposed approach is practical, and that adjustment is needed for comorbidities to obtain accurate estimates of disorder-specific disability. Expansion to a wider range of disorders would likely find more evidence for heterogeneity.
URI: https://scholarhub.balamand.edu.lb/handle/uob/7170
ISSN: 10498931
DOI: 10.1002/mpr.2003
Ezproxy URL: Link to full text
Type: Journal Article
Appears in Collections:Faculty of Medicine

Show full item record

Record view(s)

13
checked on May 19, 2024

Google ScholarTM

Check

Dimensions Altmetric

Dimensions Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.