Machine learning models predicted which patients with treatment-resistant depression would respond to esketamine nasal spray. In a retrospective study of 149 patients, three random forest classifiers achieved 68.53% accuracy for response at one month and 66.26% at three months, and 68.60% accuracy for remission at three months. Features such as severe anhedonia, anxious distress, mixed symptoms, and bipolarity positively predicted response and remission, while benzodiazepine use and depression severity were linked to delayed responses. The findings suggest machine learning may aid personalized treatment decisions for treatment-resistant depression.
Intranasal esketamine rapidly reduces suicidal ideation and depressive symptoms in patients with treatment-resistant depression. Suicidal ideation scores dropped from 1.56 at baseline to 0.78 after one week and to 0.12 after six months. Depressive symptoms improved from a mean Montgomery-Åsberg Depression Rating Scale score of 30.9 at baseline to 17.5 after one week and 9.8 after six months. Male gender was a negative predictor of response; no other baseline variable predicted outcomes. The findings suggest intranasal esketamine is effective for rapid reduction and resolution of suicidal ideation in this population, and gender differences should be considered in treatment planning.