PsychiatryNLPKit Documentation
CEYMH Research Group at McGill University
Computational linguistics toolkit for psychosis risk assessment and thought disorder analysis. A scientific Python package that extracts validated linguistic metrics from clinical text, grounded in peer-reviewed research on language markers of psychosis, formal thought disorder, and cognitive impairment.
Developed in the CEYMH / Douglas Research Group at McGill University.
Key Features
Seven categories of linguistic metrics (Syntax, Similarity, Perplexity, Graph, Density, Lexicon, ImageSimilarity)
Support for English and French text
Automatic hardware acceleration (CUDA / MPS / XPU / CPU)
Lazy-loaded, cached computations — no redundant work across analyses
Composable API: batch mode or individual function calls
Citation
If you use PsychiatryNLPKit in research, please cite the software release:
@software{psychiatrynlpkit2026,
author = {Dou, Rukun and Wei, Tiana and Voppel, Alban Elias and Palaniyappan, Lena},
title = {PsychiatryNLPKit: Computational linguistics toolkit for psychosis risk assessment and thought disorder analysis},
year = {2026},
url = {https://github.com/rukun-dou/PsychiatryNLPKit},
version = {0.1.7},
license = {MIT}
}
Funding
This work was supported by the FRQS Partenariat Innovation-Québec-Janssen (PIQ-J) initiative (#338282), the FRQS Alliance en santé mentale grant (#348797 to Douglas Research Centre), CIHR SPOR (PJK192157), CIHR Project Grant (PJT195903), Wellcome Trust Discretionary Grant (226168/Z/22/Z), and Wellcome Trust Mental Health Award for the DIALOG consortium (314138/Z/24/Z). L. Palaniyappan is supported by the Monique H. Bourgeois Chair in Developmental Disorders and the Graham Boeckh Foundation, and holds a salary award from the Fonds de recherche du Québec – Santé (366934), with additional support through a Research Centre Grant to Douglas Research Centre (5230).
Quick Links
User Guide
API Reference