SCREENING BIOCHEMICAL CHANGES INDUCED BY AYAHUASCA IN HEALTHY SUBJECTS AND PATIENTS WITH DEPRESSION: A MACHINE LEARNING APPROACH TO RCT DATA
ayahuasca, machine-learning, depression, biomarkers
Ayahuasca is an ancient psychedelic beverage from Amazonia with potential antidepressant effects. In a first double-blind, randomized placebo-controlled trial, we observed rapid antidepressant effects of Ayahuasca in patients with treatment-resistant depression (TRD). The present work is a secondary analysis that assessed ayahuasca impact on biochemical markers in healthy subjects (control group - CG, n = 42) and patients with TRD (n = 28). To analyze data, we used machine learning techniques, specifically random forest algorithms with recursive feature elimination and 5-fold cross-validation. We found that the model identified c-reactive protein (CRP), awakening salivary cortisol, and total cholesterol as key features differentiating CG and TRD. The model showed low performance in distinguishing Ayahuasca from placebo in the CG, suggesting minimal impact on these biomarkers in healthy subjects. On the other hand, to distinguish Ayahuasca's effects from placebo in TRD, the model suggests a modulation of glucose, CRP, lymphocytes, LDL cholesterol, red blood cells, brain derived neurotrophic factor (BDNF), and aspartate aminotransferase (AST). Recursive feature elimination and correlation analysis highlighted BDNF and plasmatic cortisol as predictors of Ayahuasca's therapeutic outcomes in TRD. Overall, our findings reinforce Ayahuasca's safety in healthy individuals and associate biomarker shifts with its effect in TRD patients.