Evaluation of a Machine Learning Model Based on Pretreatment Symptoms and Electroencephalographic Features to Predict Outcomes of Antidepressant Treatment in Adults With Depression

Abstract

IMPORTANCE Despite the high prevalence and potential outcomes of major depressive disorder, whether and how patients will respond to antidepressant medications is not easily predicted. OBJECTIVE To identify the extent to which a machine learning approach, using gradient-boosted decision trees, can predict acute improvement for individual depressive symptoms with antidepressants based on pretreatment symptom scores and electroencephalographic (EEG) measures. DESIGN, SETTING, AND PARTICIPANTS This prognostic study analyzed data collected as part of the International Study to Predict Optimized Treatment in Depression, a randomized, prospective open-label trial to identify clinically useful predictors and moderators of response to commonly used first-line antidepressant medications. Data collection was conducted at 20 sites spanning 5 countries and including 518 adult outpatients (18-65 years of age) from primary care or specialty care practices who received a diagnosis of current major depressive disorder between December 1, 2008, and September 30, 2013. Patients were antidepressant medication naive or willing to undergo a 1-week washout period of any nonprotocol antidepressant medication. Statistical analysis was conducted from January 5 to June 30, 2019. EXPOSURES Participants with major depressive disorder were randomized in a 1:1:1 ratio to undergo 8 weeks of treatment with escitalopram oxalate (n = 162), sertraline hydrochloride (n = 176), or extended-release venlafaxine hydrochloride (n = 180). MAIN OUTCOMES AND MEASURES The primary objective was to predict improvement in individual symptoms, defined as the difference in score for each of the symptoms on the 21-item Hamilton Rating Scale for Depression from baseline to week 8, evaluated using the C index. RESULTS The resulting data set contained 518 patients (274 women; mean [SD] age, 39.0 [12.6] years; mean [SD] 21-item Hamilton Rating Scale for Depression score improvement, 13.0 [7.0]). With the use of 5-fold cross-validation for evaluation, the machine learning model achieved C index scores of 0.8 or higher on 12 of 21 clinician-rated symptoms, with the highest C index score of 0.963 (95% CI, 0.939-1.000) for loss of insight. The importance of any single EEG feature was higher than 5% for prediction of 7 symptoms, with the most important EEG features being the absolute delta band power at the occipital electrode sites (O1, 18.8%; Oz, 6.7%) for loss of insight. Over and above the use of baseline symptom scores alone, the use of both EEG and baseline symptom features was associated with a significant increase in the C index for improvement in 4 symptoms: loss of insight (continued) Key Points Question Can machine learning models predict improvement of various depressive symptoms with antidepressant treatment based on pretreatment symptom scores and electroencephalographic measures? Findings In this prognostic study, using the machine learning approach of gradient-boosted decision trees, the ElecTreeScore algorithm could reliably distinguish the patients who r...

Machine Learning Prediction of Treatment Outcome in Late-Life Depression

“…For example, in a recent study in a sample of 81,630 adults, treatment-specific predictive models from electronic health record data did not perform better than general treatment response models ( 48 ). A classifier capable of predicting treatment response to a focused range of options (e.g., SSRIs) could arguably hold higher clinical utility in practice than one that predicts response to a single agent ( 49 , 50 ).…”

Single-channel electroencephalography and its associations with anxiety and pain during oral surgery: a preliminary report

“…Possible associations between clinical perceptions and measurements were also investigated. An enormous amount of EEG data remains to be explored using informatics and advances in this field, such as machine learning and artificial intelligence [ 22 ]. With these, the brain activities of patients related to anxiety and alertness, as well as pain and other effects, after local anesthesia and the administration of anxiolytic drugs may be observed with more clarity.…”

Treatment-resistant bipolar depression: concepts and challenges for novel interventions

“…They reported that, by considering most of the evaluated symptoms and the relevance of pretreatment EEG data, machine learning had satisfactory discriminative performance for treatment response. 66 Drysdale et al used neuroimaging biomarkers defined by resting-state connectivity to identify biotypes capable of predicting treatment response for depression with repetitive TMS. For instance, 82.5% of the individuals categorized as biotype 1 presented a significant improvement to repetitive TMS, compared to 25% of those with biotype 2, even though these two biotypes were associated with similar fatigue and anergia symptomatology.…”