Machine Learning Prediction of Treatment Outcome in Late-Life Depression

Dados Bibliográficos

ID15525366
AutoresAdrienne Grzenda (0000-0001-5952-6953, University of California, Los Angeles, autor correspondente), William Speier (0000-0002-0890-8684, University of California, Los Angeles), Prabha Siddarth (0000-0001-8746-6353, University of California, Los Angeles), Anurag Pant (University of California, Los Angeles), Beatrix Krause (0000-0001-5495-6348, University of California, Los Angeles), Beatrix Krause-Sorio, Katherine L Narr (0000-0002-9396-7936, University of California, Los Angeles), Katherine Narr, Helen Lavretsky (0000-0001-9990-5085, University of California, Los Angeles)
Ano2021
Volume12
Páginas738494-738494
Data de publicação2021-10-20
Peer ReviewedSim
Open AccessSim
TipoARTICLE
PeriódicoFrontiers in Psychiatry (JOURNAL)
Identificadores do periódicoISSN: 1664-0640 • E-ISSN: 1664-0640
EditoraFrontiers Media (PUBLISHER • CH)
DOI10.3389/fpsyt.2021.738494
PMID34744829
OpenAlexW3211089406
IdiomaEN
Citações recebidas2
Referências citadas48

Background: Recent evidence suggests that integration of multi-modal data improves performance in machine learning prediction of depression treatment outcomes. Here, we compared the predictive performance of three machine learning classifiers using differing combinations of sociodemographic characteristics, baseline clinical self-reports, cognitive tests, and structural magnetic resonance imaging (MRI) features to predict treatment outcomes in late-life depression (LLD). Methods: Data were combined from two clinical trials conducted with depressed adults aged 60 and older, including response to escitalopram ( N = 32, NCT01902004) and Tai Chi ( N = 35, NCT02460666). Remission was defined as a score of 6 or less on the 24-item Hamilton Rating Scale for Depression (HAMD) at the end of 24 weeks of treatment. Features subsets were constructed from baseline sociodemographic and clinical features, gray matter volumes (GMVs), or both. Three classification algorithms were compared: (1) Support Vector Machine-Radial Bias Function (SVMRBF), (2) Random Forest (RF), and (3) Logistic Regression (LR). A repeated 5-fold cross-validation approach with a wrapper-based feature selection method was used for model fitting. Model performance metrics included Area under the ROC Curve (AUC) and Matthews correlation coefficient (MCC). Cross-validated performance significance was tested by permutation analysis. Classifiers were compared by Cochran's Q and post-hoc pairwise comparisons using McNemar's Chi-Square test with Bonferroni correction. Results: For the RF and SVMRBF algorithms, the combined feature set outperformed the clinical and GMV feature sets with a final cross-validated AUC of 0.83 ± 0.11 and 0.80 ± 0.11, respectively. Both classifiers passed permutation analysis. The LR algorithm performed best using GMV features alone (AUC 0.79 ± 0.14) but failed to pass permutation analysis using any feature set. Performance of the three classifiers differed significantly for all three features sets. Important predictive features of treatment response included anterior and posterior cingulate volumes, depression characteristics, and self-reported health-related quality scores. Conclusion: This preliminary exploration into the use of ML and multi-modal data to identify predictors of general treatment response in LLD indicates that integration of clinical and structural MRI features significantly increases predictive capability. Identified features are among those previously implicated in geriatric depression, encouraging future work in this arena

Bonferroni correction · Feature selection · Logistic regression · Machine learning · McNemar's test · Random forest · Receiver operating characteristic · Statistics · Support vector machine · Computer Science · Dementia and Cognitive Impairment Research · Functional Brain Connectivity Studies · Mathematics · Medicine · Mental Health Research Topics · Psychology · Artificial Intelligence