Predictive modeling of treatment resistant depression using data from STARD and an independent clinical study

• Published in: PloS one Vol. 13; no. 6; p. e0197268
• Main Authors: Nie, Zhi, Vairavan, Srinivasan, Narayan, Vaibhav A, Ye, Jieping, Li, Qingqin S
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 07-06-2018; Public Library of Science (PLoS)
• Subjects: Adult; Antidepressants; Antidepressive Agents - administration & dosage; Anxiety disorders; Artificial intelligence; Bioinformatics; Biomarkers; Care and treatment; Clinical trials; Cluster analysis; Clustering; Computer and Information Sciences; Computer engineering; Computer science; Databases, Factual; Datasets; Depressive Disorder, Major - drug therapy; Depressive Disorder, Major - physiopathology; Dosage and administration; Drug Resistance; Electrical engineering; Female; Gene expression; Generalized linear models; Humans; Information technology; Learning algorithms; Machine Learning; Major depressive disorder; Male; Mathematical models; Medicine and Health Sciences; Mental depression; Model testing; Modelling; Models, Biological; Neurosciences; Physical Sciences; Prediction models; Predictive Value of Tests; R&D; Remission; Research & development; Research and Analysis Methods; Resistance factors; Risk analysis; Risk Factors; Training; Upper bounds; Vector quantization; Ann Arbor Michigan; United States > US
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0197268

Identification of risk factors of treatment resistance may be useful to guide treatment selection, avoid inefficient trial-and-error, and improve major depressive disorder (MDD) care. We extended the work in predictive modeling of treatment resistant depression (TRD) via partition of the data from the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) cohort into a training and a testing dataset. We also included data from a small yet completely independent cohort RIS-INT-93 as an external test dataset. We used features from enrollment and level 1 treatment (up to week 2 response only) of STAR*D to explore the feature space comprehensively and applied machine learning methods to model TRD outcome at level 2. For TRD defined using QIDS-C16 remission criteria, multiple machine learning models were internally cross-validated in the STAR*D training dataset and externally validated in both the STAR*D testing dataset and RIS-INT-93 independent dataset with an area under the receiver operating characteristic curve (AUC) of 0.70-0.78 and 0.72-0.77, respectively. The upper bound for the AUC achievable with the full set of features could be as high as 0.78 in the STAR*D testing dataset. Model developed using top 30 features identified using feature selection technique (k-means clustering followed by χ2 test) achieved an AUC of 0.77 in the STAR*D testing dataset. In addition, the model developed using overlapping features between STAR*D and RIS-INT-93, achieved an AUC of > 0.70 in both the STAR*D testing and RIS-INT-93 datasets. Among all the features explored in STAR*D and RIS-INT-93 datasets, the most important feature was early or initial treatment response or symptom severity at week 2. These results indicate that prediction of TRD prior to undergoing a second round of antidepressant treatment could be feasible even in the absence of biomarker data.