Proof‐of‐concept of a data‐driven approach to estimate the associations of comorbid mental and physical disorders with global health‐related disability
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...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-03-01
|
| Series: | International Journal of Methods in Psychiatric Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/mpr.2003 |
| _version_ | 1827304705139671040 |
|---|---|
| author | Ymkje Anna deVries Jordi Alonso Somnath Chatterji Peter deJonge Joran Lokkerbol John J. McGrath Maria V. Petukhova Nancy A. Sampson Erik Sverdrup Daniel V. Vigo Stefan Wager Ali Al‐Hamzawi Guilherme Borges Ronny Bruffaerts Brendan Bunting Stephanie Chardoul Elie G. Karam Andrzej Kiejna Viviane Kovess‐Masfety Fernando Navarro‐Mateu Akin Ojagbemi Marina Piazza José Posada‐Villa Carmen Sasu Kate M. Scott Hisateru Tachimori Margreet Ten Have Yolanda Torres Maria Carmen Viana Manuel Zamparini Zahari Zarkov Ronald C. Kessler World Mental Health Survey Collaborators |
| author_facet | Ymkje Anna deVries Jordi Alonso Somnath Chatterji Peter deJonge Joran Lokkerbol John J. McGrath Maria V. Petukhova Nancy A. Sampson Erik Sverdrup Daniel V. Vigo Stefan Wager Ali Al‐Hamzawi Guilherme Borges Ronny Bruffaerts Brendan Bunting Stephanie Chardoul Elie G. Karam Andrzej Kiejna Viviane Kovess‐Masfety Fernando Navarro‐Mateu Akin Ojagbemi Marina Piazza José Posada‐Villa Carmen Sasu Kate M. Scott Hisateru Tachimori Margreet Ten Have Yolanda Torres Maria Carmen Viana Manuel Zamparini Zahari Zarkov Ronald C. Kessler World Mental Health Survey Collaborators |
| author_sort | Ymkje Anna deVries |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-24T17:43:35Z |
| format | Article |
| id | doaj.art-141212e3f5624a249f0eab1f5192b31e |
| institution | Directory Open Access Journal |
| issn | 1049-8931 1557-0657 |
| language | English |
| last_indexed | 2024-04-24T17:43:35Z |
| publishDate | 2024-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Methods in Psychiatric Research |
| spelling | doaj.art-141212e3f5624a249f0eab1f5192b31e2024-03-27T15:10:42ZengWileyInternational Journal of Methods in Psychiatric Research1049-89311557-06572024-03-01331n/an/a10.1002/mpr.2003Proof‐of‐concept of a data‐driven approach to estimate the associations of comorbid mental and physical disorders with global health‐related disabilityYmkje Anna deVries0Jordi Alonso1Somnath Chatterji2Peter deJonge3Joran Lokkerbol4John J. McGrath5Maria V. Petukhova6Nancy A. Sampson7Erik Sverdrup8Daniel V. Vigo9Stefan Wager10Ali Al‐Hamzawi11Guilherme Borges12Ronny Bruffaerts13Brendan Bunting14Stephanie Chardoul15Elie G. Karam16Andrzej Kiejna17Viviane Kovess‐Masfety18Fernando Navarro‐Mateu19Akin Ojagbemi20Marina Piazza21José Posada‐Villa22Carmen Sasu23Kate M. Scott24Hisateru Tachimori25Margreet Ten Have26Yolanda Torres27Maria Carmen Viana28Manuel Zamparini29Zahari Zarkov30Ronald C. Kessler31World Mental Health Survey CollaboratorsDepartment of Child and Adolescent Psychiatry University of Groningen University Medical Center Groningen Groningen The NetherlandsHealth Services Research Group Institut Hospital del Mar d’Investigacions Mediques Barcelona SpainDepartment of Information, Evidence, and Research World Health Organization Geneva SwitzerlandDepartment of Developmental Psychology University of Groningen Groningen NetherlandsCentre of Economic Evaluation Trimbos Institute (Netherlands Institute of Mental Health) Utrecht NetherlandsQueensland Centre for Mental Health Research The Park Centre for Mental Health Wacol Queensland AustraliaDepartment of Health Care Policy Harvard Medical School Boston Massachusetts USADepartment of Health Care Policy Harvard Medical School Boston Massachusetts USAStanford Graduate School of Business Stanford University Stanford California USADepartment of Psychiatry University of British Columbia Vancouver British Columbia CanadaStanford Graduate School of Business Stanford University Stanford California USACollege of Medicine University of Al‐Qadisiya Diwaniya Governorate Al Diwaniyah IraqNational Institute of Psychiatry Ramón de la Fuente Muñiz Mexico City MexicoUniversitair Psychiatrisch Centrum ‐ Katholieke Universiteit Leuven (UPC‐KUL) Campus Gasthuisberg Leuven BelgiumSchool of Psychology Ulster University Londonderry UKSurvey Research Center Institute for Social Research University of Michigan Ann Arbor Michigan USAInstitute for Development, Research, Advocacy and Applied Care (IDRAAC) Beirut LebanonFaculty of Applied Studies University of Lower Silesia Wroclaw PolandInstitut de Psychologie EA 4057 Université Paris Cité Paris FranceUnidad de Docencia Investigación y Formación en Salud Mental (UDIF‐SM) Gerencia Salud Mental Servicio Murciano de Salud Murcia SpainDepartment of Psychiatry University of Ibadan Ibadan NigeriaSchool of Public Health and Administration Universidad Cayetano Heredia Lima PeruFaculty of Social Sciences Colegio Mayor de Cundinamarca University Bogota ColombiaNational Institute of Health Services Management Bucharest RomaniaDepartment of Psychological Medicine University of Otago Dunedin Otago New ZealandKeio University School of Medicine Tokyo JapanDepartment of Epidemiology Netherlands Institute of Mental Health and Addiction Trimbos Institute Utrecht NetherlandsCenter for Excellence on Research in Mental Health CES University Medellin ColombiaDepartment of Social Medicine Federal University of Espírito Santo Vitoria BrazilIRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli Brescia ItalyNational Center of Public Health and Analyses Sofia BulgariaDepartment of Health Care Policy Harvard Medical School Boston Massachusetts USAAbstract 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.https://doi.org/10.1002/mpr.2003causal forestcomorbiditydisabilityglobal burden of diseasemental disorders |
| spellingShingle | Ymkje Anna deVries Jordi Alonso Somnath Chatterji Peter deJonge Joran Lokkerbol John J. McGrath Maria V. Petukhova Nancy A. Sampson Erik Sverdrup Daniel V. Vigo Stefan Wager Ali Al‐Hamzawi Guilherme Borges Ronny Bruffaerts Brendan Bunting Stephanie Chardoul Elie G. Karam Andrzej Kiejna Viviane Kovess‐Masfety Fernando Navarro‐Mateu Akin Ojagbemi Marina Piazza José Posada‐Villa Carmen Sasu Kate M. Scott Hisateru Tachimori Margreet Ten Have Yolanda Torres Maria Carmen Viana Manuel Zamparini Zahari Zarkov Ronald C. Kessler World Mental Health Survey Collaborators Proof‐of‐concept of a data‐driven approach to estimate the associations of comorbid mental and physical disorders with global health‐related disability International Journal of Methods in Psychiatric Research causal forest comorbidity disability global burden of disease mental disorders |
| title | Proof‐of‐concept of a data‐driven approach to estimate the associations of comorbid mental and physical disorders with global health‐related disability |
| title_full | Proof‐of‐concept of a data‐driven approach to estimate the associations of comorbid mental and physical disorders with global health‐related disability |
| title_fullStr | Proof‐of‐concept of a data‐driven approach to estimate the associations of comorbid mental and physical disorders with global health‐related disability |
| title_full_unstemmed | Proof‐of‐concept of a data‐driven approach to estimate the associations of comorbid mental and physical disorders with global health‐related disability |
| title_short | Proof‐of‐concept of a data‐driven approach to estimate the associations of comorbid mental and physical disorders with global health‐related disability |
| title_sort | proof of concept of a data driven approach to estimate the associations of comorbid mental and physical disorders with global health related disability |
| topic | causal forest comorbidity disability global burden of disease mental disorders |
| url | https://doi.org/10.1002/mpr.2003 |
| work_keys_str_mv | AT ymkjeannadevries proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT jordialonso proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT somnathchatterji proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT peterdejonge proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT joranlokkerbol proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT johnjmcgrath proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT mariavpetukhova proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT nancyasampson proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT eriksverdrup proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT danielvvigo proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT stefanwager proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT alialhamzawi proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT guilhermeborges proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT ronnybruffaerts proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT brendanbunting proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT stephaniechardoul proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT eliegkaram proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT andrzejkiejna proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT vivianekovessmasfety proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT fernandonavarromateu proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT akinojagbemi proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT marinapiazza proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT joseposadavilla proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT carmensasu proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT katemscott proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT hisaterutachimori proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT margreettenhave proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT yolandatorres proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT mariacarmenviana proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT manuelzamparini proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT zaharizarkov proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT ronaldckessler proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability AT worldmentalhealthsurveycollaborators proofofconceptofadatadrivenapproachtoestimatetheassociationsofcomorbidmentalandphysicaldisorderswithglobalhealthrelateddisability |