PsychiatryNLPKit Documentation

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.

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

Quick Links

User Guide

• Getting Started
  • Installation
  • First Analysis
  • Running Specific Analyses
  • Individual Analysis Functions
  • Next Steps
• Architecture & Concepts
  • Data Flow
  • Design Principles
  • Language Support
  • Analysis Categories
  • Module Organization

API Reference

• API Reference

Indices and tables

• Index

• Module Index

• Search Page