Predicting outcome with Intranasal Esketamine treatment: A machine-learning, three-month study in Treatment-Resistant Depression (ESK-LEARNING)
Mauro Pettorruso, Roberto Guidotti, Giacomo D’andrea, Luisa de Risio, Antea D’Andrea, Stefania Chiappini, Rosalba Carullo, Sergio Barlati, Raffaella Zanardi, Gianluca Rosso, Sergio De Filippis, Marco di Nicola, Ileana Andriola, Matteo Marcatili, Giuseppe Nicolò, Vassilis Martiadis, Roberta Bassetti, Domenica Nucifora, Pasquale de Fazio, Joshua D. Rosenblat, Massimo Clerici, Bernardo Maria Dell’osso, Antonio Vita, Laura Marzetti, Stefano L. Sensi, Giorgio Di Lorenzo, Roger S. McIntyre, Giovanni Martinotti
Psychiatry Research July 29, 2023 DOI: 10.1016/j.psychres.2023.115378 via OpenAlex
Summary
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.
Study at a glance
| Characteristics | Retrospective, multicentric, real-world study Peer reviewed |
|---|---|
| Sample size | 149 |
| Population | Treatment-resistant depression patients |
| Intervention | Esketamine Nasal Spray |
| Duration | Three months post-treatment initiation |
| Topics | Anxiety Depression |
| Keywords | Rating scale Depression economics Anhedonia Clinical psychology |
| Citations | 56 |
| Key finding | Machine learning classifiers predicted response to esketamine nasal spray in treatment-resistant depression with accuracies of 68.53% at one month and 66.26% at three months, and remission at three months with 68.60% accuracy. |
Abstract
Treatment-resistant depression (TRD) represents a severe clinical condition with high social and economic costs. Esketamine Nasal Spray (ESK-NS) has recently been approved for TRD by EMA and FDA, but data about predictors of response are still lacking. Thus, a tool that can predict the individual patients' probability of response to ESK-NS is needed. This study investigates sociodemographic and clinical features predicting responses to ESK-NS in TRD patients using machine learning techniques. In a retrospective, multicentric, real-world study involving 149 TRD subjects, psychometric data (Montgomery-Asberg-Depression-Rating-Scale/MADRS, Brief-Psychiatric-Rating-Scale/BPRS, Hamilton-Anxiety-Rating-Scale/HAM-A, Hamilton-Depression-Rating-Scale/HAMD-17) were collected at baseline and at one month/T1 and three months/T2 post-treatment initiation. We trained three different random forest classifiers, able to predict responses to ESK-NS with accuracies of 68.53% at T1 and 66.26% at T2 and remission at T2 with 68.60% of accuracy. Features like severe anhedonia, anxious distress, mixed symptoms as well as bipolarity were found to positively predict response and remission. At the same time, benzodiazepine usage and depression severity were linked to delayed responses. Despite some limitations (i.e., retrospective study, lack of biomarkers, lack of a correct interrater-reliability across the different centers), these findings suggest the potential of machine learning in personalized intervention for TRD.