Academic Journal
Predicting Dropout in Psychotherapy for Major Depressive Disorder: A Machine Learning Approach to Identifying At-Risk Patients.
| Τίτλος: | Predicting Dropout in Psychotherapy for Major Depressive Disorder: A Machine Learning Approach to Identifying At-Risk Patients. |
|---|---|
| Συγγραφείς: | Bremer-Hoeve S; Dimence Mental Health Group, Deventer, the Netherlands., van Bronswijk SC; Department of Psychiatry and Neuropsychology, School for Mental health and Neuroscience, Faculty of Health Medicine and Life Sciences, Maastricht University, Maastricht, the Netherlands.; Department of Psychiatry and Psychology, Maastricht University Medical Center, Maastricht, the Netherlands., Beekman ATF; Department of Psychiatry, Amsterdam University Medical Center, Vrije Universiteit Medical Center, Amsterdam, the Netherlands., Miggiels M; Dimence Mental Health Group, Deventer, the Netherlands., Bruijniks SJE; Department of Clinical Psychology, Utrecht University, Utrecht, the Netherlands., van Dijk MK; Dimence Mental Health Group, Deventer, the Netherlands. |
| Πηγή: | Clinical psychology & psychotherapy [Clin Psychol Psychother] 2026 Jul-Aug; Vol. 33 (4), pp. e70320. |
| Τύπος έκδοσης: | Journal Article; Randomized Controlled Trial |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: John Wiley & Sons Country of Publication: England NLM ID: 9416196 Publication Model: Print Cited Medium: Internet ISSN: 1099-0879 (Electronic) Linking ISSN: 10633995 NLM ISO Abbreviation: Clin Psychol Psychother Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Chichester, West Sussex, England : John Wiley & Sons, c1993- |
| Ιατρικοί όροι (MeSH): | Major Depressive Disorder*/therapy , Major Depressive Disorder*/psychology , Patient Dropouts*/statistics & numerical data , Patient Dropouts*/psychology , Cognitive Behavioral Therapy*/methods , Machine Learning* , Psychotherapy, Psychodynamic*, Humans ; Female ; Predictive Learning Models ; Adult ; Male ; Random Forest ; Prediction Algorithms ; Middle Aged ; Classification Algorithms ; Risk Factors |
| Περίληψη: | Introduction: Dropout from psychotherapy for major depressive disorder (MDD) undermines treatment effectiveness for both patients and clinicians. Early identification of individuals at risk of discontinuation is therefore essential. Machine learning methods, particularly those incorporating resampling techniques to address imbalanced clinical data, may offer improved predictive capacity. This study evaluates several machine-learning approaches to determine their potential in identifying patients at elevated risk of dropout. Methods: Data were drawn from a randomised controlled trial of outpatients with MDD (n = 290) receiving short-term psychodynamic supportive psychotherapy (SPSP) or cognitive behavioural therapy (CBT). Candidate predictors were restricted to variables available in both the development and external validation datasets, resulting in a limited number of overlapping predictors. Multiple machine learning models and resampling strategies were applied to predict dropout, and the best-performing models were subsequently externally validated using an independent clinical dataset (n = 96). Results: Models demonstrated low predictive performance overall. Resampling strategies influenced outcomes, with SMOTE consistently improving F1-scores compared with no resampling. The combination of random forest with SMOTE achieved the highest F1-score (0.303). Five key predictors of dropout emerged: younger age, unemployment, a higher number of comorbid Axis I disorders, absence of a partner, and moderate depression severity. All models showed reduced performance during external validation. Discussion: The models showed very limited predictive performance, which may in part reflect the restricted predictor set resulting from the requirement that variables be assessed in both trials. While clinical application is premature at this stage, the findings provide a valuable proof of concept and highlight key methodological challenges inherent in cross-trial dropout prediction. Despite this, the identified predictors are routinely available in clinical practice, suggesting that future models, if developed with richer predictor sets and validated in larger samples, could ultimately support therapists in the early identification of patients at risk of dropout and in proactively addressing disengagement. (© 2026 John Wiley & Sons Ltd.) |
| References: | J Clin Psychiatry. 1998;59 Suppl 20:22-33;quiz 34-57. (PMID: 9881538) BMC Psychiatry. 2015 Jun 30;15:137. (PMID: 26122891) Psychiatr Serv. 2010 Jul;61(7):684-9. (PMID: 20592003) Br J Clin Psychol. 2003 Jun;42(Pt 2):133-43. (PMID: 12828803) JAMA Psychiatry. 2020 Mar 1;77(3):294-302. (PMID: 31799994) Nord J Psychiatry. 2011 Jun;65(3):183-91. (PMID: 20854221) BMC Psychiatry. 2021 May 4;21(1):233. (PMID: 33947374) Psychother Res. 2021 Jan;31(1):78-91. (PMID: 32964809) Br J Psychiatry. 2022 Apr;220(4):192-201. (PMID: 35177132) PLoS One. 2018 Mar 27;13(3):e0194889. (PMID: 29584784) Sci Rep. 2018 May 18;8(1):7819. (PMID: 29777110) Psychother Res. 2011 Jul;21(4):400-15. (PMID: 21557135) Psychother Res. 2023 Jul;33(6):683-695. (PMID: 36669124) Psychotherapy (Chic). 2017 Mar;54(1):47-57. (PMID: 28263651) Eur Arch Psychiatry Clin Neurosci. 2023 Aug;273(5):1151-1161. (PMID: 36253582) Schizophr Bull. 2021 Mar 16;47(2):284-297. (PMID: 32914178) BMC Psychiatry. 2023 May 24;23(1):358. (PMID: 37226210) J Consult Clin Psychol. 2012 Aug;80(4):547-59. (PMID: 22506792) Psychotherapy (Chic). 2008 Jun 1;45(2):247-267. (PMID: 19838318) Front Psychiatry. 2023 Nov 22;14:1174285. (PMID: 38076685) Clin Psychol Psychother. 2017 Mar;24(2):312-321. (PMID: 27160543) J Clin Psychol. 2011 Feb;67(2):155-65. (PMID: 21120917) Psychol Med. 2021 Sep;51(12):2104-2116. (PMID: 32343221) J Affect Disord. 2007 Jan;97(1-3):197-202. (PMID: 16857266) World Psychiatry. 2021 Jun;20(2):283-293. (PMID: 34002502) Psychother Res. 2025 Jun;35(5):838-851. (PMID: 38862129) Br J Psychiatry. 2020 Apr;216(4):222-230. (PMID: 32029012) J Affect Disord. 2025 Feb 15;371:344-351. (PMID: 39486646) Healthcare (Basel). 2022 Jul 13;10(7):. (PMID: 35885819) Clin Psychol Rev. 2015 Aug;40:57-65. (PMID: 26067572) J Clin Epidemiol. 2003 Sep;56(9):826-32. (PMID: 14505766) |
| Grant Information: | Dimence Mental Health Care; VCVGZ association |
| Contributed Indexing: | Keywords: cognitive behavioural therapy; depression; dropout prediction; machine learning; short‐term psychodynamic supportive psychotherapy |
| Entry Date(s): | Date Created: 20260813 Date Completed: 20260813 Latest Revision: 20260815 |
| Update Code: | 20260815 |
| PubMed Central ID: | PMC13469726 |
| DOI: | 10.1002/cpp.70320 |
| PMID: | 42590821 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1099-0879 |
|---|---|
| DOI: | 10.1002/cpp.70320 |