Machine learning meta-analysis identifies individual characteristics moderating cognitive intervention efficacy for anxiety and depression symptoms
Abstract Cognitive training is a promising intervention for psychological distress; however, its effectiveness has yielded inconsistent outcomes across studies. This research is a pre-registered individual-level meta-analysis to identify factors contributing to cognitive training efficacy for anxiet...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-025-01449-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571298972172288 |
|---|---|
| author | Thalia Richter Reut Shani Shachaf Tal Nazanin Derakshan Noga Cohen Philip M. Enock Richard J. McNally Nilly Mor Shimrit Daches Alishia D. Williams Jenny Yiend Per Carlbring Jennie M. Kuckertz Wenhui Yang Andrea Reinecke Christopher G. Beevers Brian E. Bunnell Ernst H. W. Koster Sigal Zilcha-Mano Hadas Okon-Singer |
| author_facet | Thalia Richter Reut Shani Shachaf Tal Nazanin Derakshan Noga Cohen Philip M. Enock Richard J. McNally Nilly Mor Shimrit Daches Alishia D. Williams Jenny Yiend Per Carlbring Jennie M. Kuckertz Wenhui Yang Andrea Reinecke Christopher G. Beevers Brian E. Bunnell Ernst H. W. Koster Sigal Zilcha-Mano Hadas Okon-Singer |
| author_sort | Thalia Richter |
| collection | DOAJ |
| description | Abstract Cognitive training is a promising intervention for psychological distress; however, its effectiveness has yielded inconsistent outcomes across studies. This research is a pre-registered individual-level meta-analysis to identify factors contributing to cognitive training efficacy for anxiety and depression symptoms. Machine learning methods, alongside traditional statistical approaches, were employed to analyze 22 datasets with 1544 participants who underwent working memory training, attention bias modification, interpretation bias modification, or inhibitory control training. Baseline depression and anxiety symptoms were found to be the most influential factor, with individuals with more severe symptoms showing the greatest improvement. The number of training sessions was also important, with more sessions yielding greater benefits. Cognitive trainings were associated with higher predicted improvement than control conditions, with attention and interpretation bias modification showing the most promise. Despite the limitations of heterogeneous datasets, this investigation highlights the value of large-scale comprehensive analyses in guiding the development of personalized training interventions. |
| format | Article |
| id | doaj-art-48a41c60fce5471092ba0ec0521baee2 |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-48a41c60fce5471092ba0ec0521baee22025-02-02T12:43:35ZengNature Portfolionpj Digital Medicine2398-63522025-01-018111510.1038/s41746-025-01449-wMachine learning meta-analysis identifies individual characteristics moderating cognitive intervention efficacy for anxiety and depression symptomsThalia Richter0Reut Shani1Shachaf Tal2Nazanin Derakshan3Noga Cohen4Philip M. Enock5Richard J. McNally6Nilly Mor7Shimrit Daches8Alishia D. Williams9Jenny Yiend10Per Carlbring11Jennie M. Kuckertz12Wenhui Yang13Andrea Reinecke14Christopher G. Beevers15Brian E. Bunnell16Ernst H. W. Koster17Sigal Zilcha-Mano18Hadas Okon-Singer19School of Psychological Sciences, University of HaifaSchool of Psychological Sciences, University of HaifaSchool of Psychological Sciences, University of HaifaCentre for Resilience and Posttraumatic Growth, National Centre for Integrative Oncology (NCIO)Department of Special Education, University of HaifaDepartment of Psychology, Harvard UniversityDepartment of Psychology, Harvard UniversityDepartment of Psychology, The Hebrew University of JerusalemPsychology Department, Bar Ilan UniversitySchool of Psychiatry, UNSW Medicine, University of New South WalesKing’s College LondonDepartment of Psychology, Stockholm UniversityDepartment of Psychiatry, McLean HospitalDepartment of Psychology, Hunan Normal UniversityDepartment of Psychiatry, University of OxfordInstitute for Mental Health Research and Department of Psychology, University of Texas at AustinDepartment of Psychiatry and Behavioral Neurosciences, Morsani College of Medicine, University of South FloridaDepartment of Experimental Clinical and Health Psychology, Ghent UniversitySchool of Psychological Sciences, University of HaifaSchool of Psychological Sciences, University of HaifaAbstract Cognitive training is a promising intervention for psychological distress; however, its effectiveness has yielded inconsistent outcomes across studies. This research is a pre-registered individual-level meta-analysis to identify factors contributing to cognitive training efficacy for anxiety and depression symptoms. Machine learning methods, alongside traditional statistical approaches, were employed to analyze 22 datasets with 1544 participants who underwent working memory training, attention bias modification, interpretation bias modification, or inhibitory control training. Baseline depression and anxiety symptoms were found to be the most influential factor, with individuals with more severe symptoms showing the greatest improvement. The number of training sessions was also important, with more sessions yielding greater benefits. Cognitive trainings were associated with higher predicted improvement than control conditions, with attention and interpretation bias modification showing the most promise. Despite the limitations of heterogeneous datasets, this investigation highlights the value of large-scale comprehensive analyses in guiding the development of personalized training interventions.https://doi.org/10.1038/s41746-025-01449-w |
| spellingShingle | Thalia Richter Reut Shani Shachaf Tal Nazanin Derakshan Noga Cohen Philip M. Enock Richard J. McNally Nilly Mor Shimrit Daches Alishia D. Williams Jenny Yiend Per Carlbring Jennie M. Kuckertz Wenhui Yang Andrea Reinecke Christopher G. Beevers Brian E. Bunnell Ernst H. W. Koster Sigal Zilcha-Mano Hadas Okon-Singer Machine learning meta-analysis identifies individual characteristics moderating cognitive intervention efficacy for anxiety and depression symptoms npj Digital Medicine |
| title | Machine learning meta-analysis identifies individual characteristics moderating cognitive intervention efficacy for anxiety and depression symptoms |
| title_full | Machine learning meta-analysis identifies individual characteristics moderating cognitive intervention efficacy for anxiety and depression symptoms |
| title_fullStr | Machine learning meta-analysis identifies individual characteristics moderating cognitive intervention efficacy for anxiety and depression symptoms |
| title_full_unstemmed | Machine learning meta-analysis identifies individual characteristics moderating cognitive intervention efficacy for anxiety and depression symptoms |
| title_short | Machine learning meta-analysis identifies individual characteristics moderating cognitive intervention efficacy for anxiety and depression symptoms |
| title_sort | machine learning meta analysis identifies individual characteristics moderating cognitive intervention efficacy for anxiety and depression symptoms |
| url | https://doi.org/10.1038/s41746-025-01449-w |
| work_keys_str_mv | AT thaliarichter machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT reutshani machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT shachaftal machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT nazaninderakshan machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT nogacohen machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT philipmenock machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT richardjmcnally machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT nillymor machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT shimritdaches machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT alishiadwilliams machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT jennyyiend machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT percarlbring machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT jenniemkuckertz machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT wenhuiyang machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT andreareinecke machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT christophergbeevers machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT brianebunnell machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT ernsthwkoster machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT sigalzilchamano machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms AT hadasokonsinger machinelearningmetaanalysisidentifiesindividualcharacteristicsmoderatingcognitiveinterventionefficacyforanxietyanddepressionsymptoms |