EUVIMEDEUVIMED entdecken
Crossref

Using natural language processing to assess proxy measures of therapeutic alliance across suicide risk tiers

Maxwell Levis, Monica Dimambro, Joshua Levy, Amit Tchizick, Michelle Nerish, Bradley Watts, Brian Shiner

Journal of Affective Disorders · 2026-10 · 410 · 121952

DOI: 10.1016/j.jad.2026.121952 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Affective Disorders, 2026-10. Verfasst von Maxwell Levis und 6 weiteren Autor:innen. Beteiligte Einrichtung: VAMC White River Junction, 163 Veterans Dr., White River Junction, VT, 05009, USA; Department of Psychiatry, Geisel School of Medicine, 1 Rope Ferry …. Hauptthemen laut MEDLINE: Therapeutic Alliance, Suicide Prevention, Natural Language Processing, Suicide. Die Arbeit nennt 65 Literaturangaben. Gefördert von: VHA ORD.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Therapeutic alliance is a core predictor of psychotherapeutic outcome, in general, and suicide prevention, specifically. Although clinical literature suggests that maintaining positive alliance with high-suicide-risk patients can be particularly challenging, few studies evaluate this phenomenon, primarily due to alliance measurement difficulties. Our study derives proxy alliance metrics using natural language processing and models differences across classified suicide risk strata and suicide decedent status. We first identified all United States Department of Veterans Affairs (VA) psychotherapists who treated patients who died by suicide within discreet suicide-risk tiers (cases) and then identified suicide-risk matched patients who did not die (controls). We then extracted all psychotherapist electronic health records and used BERTopic, a topic modeling algorithm, to derive core topics within this corpus, and evaluated difference in topic slopes when controlling for suicide-risk-tier and case/control status. Using this method, we identified three clusters of psychotherapists with significantly different topic probabilities, each endorsing alternative proxy alliance frameworks. Our identified clusters centered on reduced psychosocial care as risk increases, increased psychosocial care as risk increases, and consistent care as risk increases. Rather than being solely a matter of clinical training or professional identity, these differences suggest clinicians' discrete emotional and behavioral reactions to patients' risk. Our findings suggest the possibility of scalable proxy assessments of alliance, offering potential utility in supporting clinicians working in high-risk care. Future work should examine whether these clusters predict patient engagement, dropout, or intervention impact, and explore whether targeted training can modulate clinicians' alliance-promoting behaviors in ways that improve outcomes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Therapeutic AllianceSuicide PreventionNatural Language ProcessingSuicidePsychotherapistsHumansUnited StatesMaleFemaleMiddle AgedUnited States Department of Veterans AffairsVeteransRisk AssessmentElectronic Health Records

Stichwörter der Autor:innen

CountertransferenceMachine learningSuicideTherapeutic alliance

Autor:innen und Institutionen

  • VAMC White River Junction, 163 Veterans Dr., White River Junction, VT, 05009, USA; Department of Psychiatry, Geisel School of Medicine, 1 Rope Ferry Rd, Hanover, NH, 03755, USA. Electronic address: maxwelle.levis@va.gov.
  • VAMC White River Junction, 163 Veterans Dr., White River Junction, VT, 05009, USA.
  • Departments of Pathology and Laboratory Medicine, Cedars-Sinai, 8700 Beverly Blvd., Los Angeles, CA, 90048, USA.
  • Department of Psychology, University of Haifa, Haifa, 3103301, Israel.
  • VAMC White River Junction, 163 Veterans Dr., White River Junction, VT, 05009, USA; Department of Psychiatry, Geisel School of Medicine, 1 Rope Ferry Rd, Hanover, NH, 03755, USA.

Förderung

  • VHA ORD

Zitieren

APA

Levis, M., Dimambro, M., Levy, J., Tchizick, A., Nerish, M., Watts, B., & Shiner, B. (2026). Using natural language processing to assess proxy measures of therapeutic alliance across suicide risk tiers. Journal of Affective Disorders, 410, 121952. https://doi.org/10.1016/j.jad.2026.121952

Vancouver

Levis M, Dimambro M, Levy J, Tchizick A, Nerish M, Watts B, et al. Using natural language processing to assess proxy measures of therapeutic alliance across suicide risk tiers. Journal of Affective Disorders. 2026;410:121952. doi:10.1016/j.jad.2026.121952

BibTeX
@article{Levis2026,
  author = {Levis, Maxwell and Dimambro, Monica and Levy, Joshua and Tchizick, Amit and Nerish, Michelle and Watts, Bradley and Shiner, Brian},
  title = {Using natural language processing to assess proxy measures of therapeutic alliance across suicide risk tiers},
  journal = {Journal of Affective Disorders},
  year = {2026},
  volume = {410},
  pages = {121952},
  doi = {10.1016/j.jad.2026.121952}
}
Kostenlos starten →