Individual Risk of Not Responding to Psychotherapy in Latin America: Bringing Data-Informed Precision Care to Underresourced Clinical Settings.

Objective: Machine learning has a great potential for prospectively forecasting individual patient response to mental health care (MHC), thereby enabling treatment personalization. However, previous efforts have been limited to populations living in predominantly higher income, developed countries....

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Consulting & Clinical Psychology Vol. 92; no. 12; pp. 836 - 843
Autores principales: Gómez Penedo, Juan Martín, Errázuriz, Paula, Coyne, Alice E., Flückiger, Christoph
Formato: Artículo
Publicado: American Psychological Association Dec2024
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=181806006&site=ehost-live
header:
  @attributes:
    shortDbName: ssf
    uiTerm: 181806006
    longDbName: Social Sciences Full Text (H.W. Wilson)
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        0022006X
        JCC
      jtl: Journal of Consulting & Clinical Psychology
      issn: 0022006X
      maglogo: N
    pubinfo:
      dt: Dec2024
      vid: 92
      iid: 12
      pid: 34
      pub: American Psychological Association
    artinfo:
      ui:
        181806006
        10.1037/ccp0000931
      ppf: 836
      ppct: 7
      formats:
      tig:
        atl: Individual Risk of Not Responding to Psychotherapy in Latin America: Bringing Data-Informed Precision Care to Underresourced Clinical Settings.
      aug:
        au:
          Gómez Penedo, Juan Martín
          Errázuriz, Paula
          Coyne, Alice E.
          Flückiger, Christoph
        affil:
          Department of Psychology, Universität Kassel
          Department of Psychology, University of Buenos Aires
          School of Psychology, Pontificia Universidad Católica de Chile
          Millennium Institute for Research on Depression and Personality
          Department of Psychology, College of Arts and Sciences, American University
      su:
        Mental health services
        Psychotherapy
        Random forest algorithms
        Machine learning
        Clinical medicine
        Developing countries
      sug:
        subj:
          Mental health services
          Psychotherapy
          Psychiatric and Substance Abuse Hospitals
          Residential Mental Health and Substance Abuse Facilities
          Offices of Mental Health Practitioners (except Physicians)
          Random forest algorithms
          Machine learning
          Clinical medicine
          Developing countries
      keyword:
        developing countries
        machine learning algorithm
        prospective prediction
        psychotherapy outcome
        treatment personalization
        developing countries
        machine learning algorithm
        prospective prediction
        psychotherapy outcome
        treatment personalization
      ab: Objective: Machine learning has a great potential for prospectively forecasting individual patient response to mental health care (MHC), thereby enabling treatment personalization. However, previous efforts have been limited to populations living in predominantly higher income, developed countries. This study aimed to extend the reach of precision MHC systems by developing and testing a feasible and readily implementable algorithm for identifying patients at risk of nonresponse to routinely delivered psychotherapy in Chile, a developing country in Latin America. Method: Data were derived from a community-based, randomized trial that tested the effects of progress feedback on naturalistically delivered psychotherapy outcome. Patients were 547 adults who were consecutively admitted to an outpatient clinic in Santiago, Chile. Treatment response was defined using norms for reliable improvement on the Outcome Questionnaire–30. Based on 10 sociodemographic and seven clinical predictors, we trained elastic net and random forest algorithms on a randomly selected training set (70%; n = 384). The best performing algorithm was tested on a hold-out sample (30%; n = 163). Results: Reliable improvement was achieved in 42% of the cases. A random forest algorithm demonstrated moderate performance in the hold-out sample (area under the curve =.74, Brier score =.21), correctly identifying 73% of the patients who did not respond. Conclusion: This study developed a predictive algorithm that demonstrated moderate accuracy in identifying patients at risk of nonresponse to naturalistic psychotherapy in Chile, using routinely assessed and easy-to-collect sociodemographic and clinical information. Using such tools may represent one step toward reducing the multilayered outcome disparities faced by individuals receiving MHC in socioeconomically disadvantaged contexts. What is the public health significance of this article?: This study provides a freely available algorithm that uses routinely assessed and easy-to-collect sociodemographic and clinical information and demonstrates moderate accuracy in predicting psychotherapy outcome in the context of a developing country in Latin America. This tool represents one step toward reducing the multilayered outcome disparities that are often faced by individuals receiving mental health care in economically disadvantaged contexts.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: N
    holdings:
      @attributes:
        islocal: N