Predicting non-response to ketamine for depression: An exploratory symptom-level analysis of real-world data among military veterans.

Ketamine helps some patients with treatment-resistant depression, but predicting who will respond is difficult. Analyzing symptom trajectories from 120 patients treated with ketamine or esketamine in a real-world clinic, all symptoms improved on average, with depressed mood improving faster than low energy. A principal component analysis identified overall treatment response and a second component reflecting differences between affective and somatic symptoms. Logistic regression classifiers predicted overall response better than chance using baseline symptoms alone. By adjusting decision thresholds, models identified 22% of patients who would not respond with over 96% negative predictive value, potentially guiding treatment recommendations to avoid ineffective treatments.

Study at a glance

Abstract

Ketamine helps some patients with treatment resistant depression (TRD), but reliable methods for predicting which patients will, or will not, respond to treatment are lacking. Herein, we aim to inform prediction models of non-response to ketamine/esketamine in adults with TRD. This is a retrospective analysis of PHQ-9 item response data from 120 patients with TRD who received repeated doses of intravenous racemic ketamine or intranasal eskatamine in a real-world clinic. Regression models were fit to patients' symptom trajectories, showing that all symptoms improved on average, but depressed mood improved relatively faster than low energy. Principal component analysis revealed a first principal component (PC) representing overall treatment response, and a second PC that reflects variance across affective versus somatic symptom subdomains. We then trained logistic regression classifiers to predict overall response (improvement on PC1) better than chance using patients' baseline symptoms alone. Finally, by parametrically adjusting the classifier decision thresholds, we identified optimal models for predicting non-response with a negative predictive value of over 96 %, while retaining a specificity of 22 %. Thus, we could identify 22 % of patients who would not respond based purely on their baseline symptoms. This approach could inform rational treatment recommendations to avoid additional treatment failures.