AI-Driven Synergy Discovery Between Cannabinoid and Psilocybin Therapies Using ClinicalTrials.gov Data 

A. Landschaft (1,2), G. Hirt (2), A. Ihlenfeld (2),

1. Information Services Department, Boston Children’s Hospital, Boston, MA 02115;

2. Copeia GmbH, Bergisch Gladbach, Germany D-51469 

The rapid expansion of clinical research on both cannabinoids and psychedelics highlights a pressing need to identify areas of therapeutic overlap and potential synergy. We present a novel artificial intelligence (AI) pipeline that leverages natural language processing (NLP) and large language models (LLMs) to systematically map, classify, and compare outcome measures across cannabinoid- and psilocybin-based clinical trials. 

Data were extracted from ClinicalTrials.gov (28 August 2025) via two structured queries: one for “psilocybin” and one for “THC OR CBD OR Cannabis OR Cannabidiol OR Δ-9-THC.” Duplicates were removed and trial records concatenated. We then applied a multi-stage AI/NLP workflow: (1) automated normalization of conditions into 15 indication classes; (2) hybrid deterministic + LLM-assisted classification of intervention types (cannabinoids, psilocybin, or both); (3) semantic clustering of primary outcome measures into clinically meaningful bins (e.g., Pain and Symptom Relief, Mood and Affective Symptoms, Cognition and Neurofunction); and (4) statistical ranking of indication-outcome duos using Fisher’s exact test with false discovery rate correction. This allowed identification of therapeutic domains where cannabinoids and psilocybin demonstrate convergent or divergent evidence. 

Results demonstrate robust convergence in indications such as chronic pain, anxiety, and quality of life, while revealing divergence in cognitive and biomarker-oriented outcomes. The approach provides both a high-level map of shared therapeutic terrain and fine-grained insight into where psilocybin may complement or extend cannabinoid therapies. Importantly, the entire pipeline is automated, auditable, and adaptable to other compound classes. 

For the medical cannabis industry, this framework highlights priority domains for expansion into psychedelics; for psychedelic developers, it reveals clinically validated entry points established by cannabinoid trials. More broadly, pharmaceutical companies can adopt the same AI-driven workflow for systematic synergy discovery across any therapeutic classes, accelerating 

The ALPS Conference (Awareness Lectures on Psychedelic Science) is a scientific event organized by the ALPS Foundation. Its fifth edition took place on October 24–25, 2025, at Campus Biotech in Geneva, Switzerland, a leading center for neuroscience and biotechnology that provided the setting for two days of cutting-edge science, meaningful dialogue, and community building.

https://sites.google.com/view/alps-conference-2025