Machine Learning Prediction of Treatment Outcome in Late-Life Depression

Adrienne Grzenda; William Speier; Prabha Siddarth; Anurag Pant; Beatrix Krause-Sorio; Katherine Narr; Helen Lavretsky

doi:10.3389/fpsyt.2021.738494

Machine Learning Prediction of Treatment Outcome in Late-Life Depression

Front Psychiatry. 2021 Oct 20:12:738494. doi: 10.3389/fpsyt.2021.738494. eCollection 2021.

Authors

Adrienne Grzenda¹, William Speier², Prabha Siddarth^{1

3}, Anurag Pant³, Beatrix Krause-Sorio^{1

3}, Katherine Narr^{3

4}, Helen Lavretsky^{1

3}

Affiliations

¹ Department of Psychiatry and Biobehavioral Science, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, United States.
² Medical Imaging and Informatics Group, Department of Radiological Sciences, University of California, Los Angeles, Los Angeles, CA, United States.
³ Jane and Terry Semel Institute for Neuroscience and Human Behavior, University of California, Los Angeles, Los Angeles, CA, United States.
⁴ Department of Neurology, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, United States.

Abstract

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.

Keywords: computational modeling; late-life depression (LLD); machine learning; pharmacology; prediction model.