Predictors for improvement in personality functioning during outpatient psychotherapy: A machine learning approach within a psychodynamic psychotherapy sample
Abstract Background Since its introduction in the diagnostic manuals DSM-5 and ICD-11, the construct of personality functioning has gained increasing attention. However, it remains unclear which factors might predict improvement in personality functioning. Methods We examined a sample of 648 comple...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Cambridge University Press
2024-01-01
|
| Series: | European Psychiatry |
| Subjects: | |
| Online Access: | https://www.cambridge.org/core/product/identifier/S0924933824017802/type/journal_article |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846166910159290368 |
|---|---|
| author | I. Dönnhoff D. Kindermann S. Stahl-Toyota J. Nowak M. Orth H.-C. Friederich C. Nikendei |
| author_facet | I. Dönnhoff D. Kindermann S. Stahl-Toyota J. Nowak M. Orth H.-C. Friederich C. Nikendei |
| author_sort | I. Dönnhoff |
| collection | DOAJ |
| description | Abstract
Background
Since its introduction in the diagnostic manuals DSM-5 and ICD-11, the construct of personality functioning has gained increasing attention. However, it remains unclear which factors might predict improvement in personality functioning.
Methods
We examined a sample of 648 completed psychodynamic psychotherapies conducted by 172 therapists at the Heidelberg Institute for Psychotherapy. A machine learning approach was used to filter for variables that are relevant for the prediction of the improvement of personality functioning from a broad data set of variables collected at the beginning of each psychodynamic psychotherapy.
Results
On average, we found an improvement of 0.24 (SD = 0.48) in the OPD-SQ. This corresponds to a medium effect in the improvement of personality functioning. Patients with initially high impairment experienced particularly large improvements. Overall, we found a large number of variables that proved to be predictive for the improvement of personality functioning. Limitations in social activity due to physical and emotional problems proved to be one of the most important predictors of improvement. Most of the effect sizes were small.
Conclusions
Overall, the improvement in personality functioning during psychotherapy is determined more by the sum of a large number of small effects than by individual variables. In particular, variables that capture social areas of life proved to be robust predictors.
|
| format | Article |
| id | doaj-art-87a82c9122e4461c8972fde994ed2f4a |
| institution | Kabale University |
| issn | 0924-9338 1778-3585 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Cambridge University Press |
| record_format | Article |
| series | European Psychiatry |
| spelling | doaj-art-87a82c9122e4461c8972fde994ed2f4a2024-11-15T06:52:39ZengCambridge University PressEuropean Psychiatry0924-93381778-35852024-01-016710.1192/j.eurpsy.2024.1780Predictors for improvement in personality functioning during outpatient psychotherapy: A machine learning approach within a psychodynamic psychotherapy sampleI. Dönnhoff0https://orcid.org/0000-0003-1538-9971D. Kindermann1S. Stahl-Toyota2https://orcid.org/0000-0003-0168-3811J. Nowak3https://orcid.org/0009-0009-9058-4663M. Orth4https://orcid.org/0000-0002-1704-2229H.-C. Friederich5https://orcid.org/0000-0003-4344-8959C. Nikendei6Centre for Psychosocial Medicine, Department of General Internal Medicine and Psychosomatics, University Hospital Heidelberg, Heidelberg, GermanyCentre for Psychosocial Medicine, Department of General Internal Medicine and Psychosomatics, University Hospital Heidelberg, Heidelberg, GermanyCentre for Psychosocial Medicine, Department of General Internal Medicine and Psychosomatics, University Hospital Heidelberg, Heidelberg, GermanyCentre for Psychosocial Medicine, Department of General Internal Medicine and Psychosomatics, University Hospital Heidelberg, Heidelberg, GermanyCentre for Psychosocial Medicine, Department of General Internal Medicine and Psychosomatics, University Hospital Heidelberg, Heidelberg, GermanyCentre for Psychosocial Medicine, Department of General Internal Medicine and Psychosomatics, University Hospital Heidelberg, Heidelberg, GermanyCentre for Psychosocial Medicine, Department of General Internal Medicine and Psychosomatics, University Hospital Heidelberg, Heidelberg, GermanyAbstract Background Since its introduction in the diagnostic manuals DSM-5 and ICD-11, the construct of personality functioning has gained increasing attention. However, it remains unclear which factors might predict improvement in personality functioning. Methods We examined a sample of 648 completed psychodynamic psychotherapies conducted by 172 therapists at the Heidelberg Institute for Psychotherapy. A machine learning approach was used to filter for variables that are relevant for the prediction of the improvement of personality functioning from a broad data set of variables collected at the beginning of each psychodynamic psychotherapy. Results On average, we found an improvement of 0.24 (SD = 0.48) in the OPD-SQ. This corresponds to a medium effect in the improvement of personality functioning. Patients with initially high impairment experienced particularly large improvements. Overall, we found a large number of variables that proved to be predictive for the improvement of personality functioning. Limitations in social activity due to physical and emotional problems proved to be one of the most important predictors of improvement. Most of the effect sizes were small. Conclusions Overall, the improvement in personality functioning during psychotherapy is determined more by the sum of a large number of small effects than by individual variables. In particular, variables that capture social areas of life proved to be robust predictors. https://www.cambridge.org/core/product/identifier/S0924933824017802/type/journal_articlepersonality functioningmachine learningmissing data analysis in machine learningpsychotherapy success |
| spellingShingle | I. Dönnhoff D. Kindermann S. Stahl-Toyota J. Nowak M. Orth H.-C. Friederich C. Nikendei Predictors for improvement in personality functioning during outpatient psychotherapy: A machine learning approach within a psychodynamic psychotherapy sample European Psychiatry personality functioning machine learning missing data analysis in machine learning psychotherapy success |
| title | Predictors for improvement in personality functioning during outpatient psychotherapy: A machine learning approach within a psychodynamic psychotherapy sample |
| title_full | Predictors for improvement in personality functioning during outpatient psychotherapy: A machine learning approach within a psychodynamic psychotherapy sample |
| title_fullStr | Predictors for improvement in personality functioning during outpatient psychotherapy: A machine learning approach within a psychodynamic psychotherapy sample |
| title_full_unstemmed | Predictors for improvement in personality functioning during outpatient psychotherapy: A machine learning approach within a psychodynamic psychotherapy sample |
| title_short | Predictors for improvement in personality functioning during outpatient psychotherapy: A machine learning approach within a psychodynamic psychotherapy sample |
| title_sort | predictors for improvement in personality functioning during outpatient psychotherapy a machine learning approach within a psychodynamic psychotherapy sample |
| topic | personality functioning machine learning missing data analysis in machine learning psychotherapy success |
| url | https://www.cambridge.org/core/product/identifier/S0924933824017802/type/journal_article |
| work_keys_str_mv | AT idonnhoff predictorsforimprovementinpersonalityfunctioningduringoutpatientpsychotherapyamachinelearningapproachwithinapsychodynamicpsychotherapysample AT dkindermann predictorsforimprovementinpersonalityfunctioningduringoutpatientpsychotherapyamachinelearningapproachwithinapsychodynamicpsychotherapysample AT sstahltoyota predictorsforimprovementinpersonalityfunctioningduringoutpatientpsychotherapyamachinelearningapproachwithinapsychodynamicpsychotherapysample AT jnowak predictorsforimprovementinpersonalityfunctioningduringoutpatientpsychotherapyamachinelearningapproachwithinapsychodynamicpsychotherapysample AT morth predictorsforimprovementinpersonalityfunctioningduringoutpatientpsychotherapyamachinelearningapproachwithinapsychodynamicpsychotherapysample AT hcfriederich predictorsforimprovementinpersonalityfunctioningduringoutpatientpsychotherapyamachinelearningapproachwithinapsychodynamicpsychotherapysample AT cnikendei predictorsforimprovementinpersonalityfunctioningduringoutpatientpsychotherapyamachinelearningapproachwithinapsychodynamicpsychotherapysample |