Predicting changes in depressive symptomatology following oral esketamine treatment in treatment-resistant depression: A machine-learning approach.
Journal of psychiatric research June 12, 2026 Juliana Lima Constantino, Tobias Stephan Freimann, Jens H van Dalfsen et al.
Oral esketamine can be an effective and well-tolerated treatment for treatment-resistant depression (TRD), but about half of those treated do not respond. This study tested whether sociodemographic and clinical features, including depressive symptoms and treatment resistance, could predict how much depressive symptoms would improve in 131 TRD patients receiving individually adjusted oral esketamine doses (0.5 mg/kg to 3 mg/kg) twice weekly for six weeks. Machine learning models—linear regression, elastic net, and random forest—failed to predict symptom change above chance. The findings suggest that oral esketamine may work similarly across the TRD population, regardless of treatment-resistance levels.