Clinical Nlp Python Packages

medspacy

Library for clinical NLP with spaCy.

opentargets-mira

Multi-source Indication & Report Analytics

umlsmatch

Python-native clinical NLP pipeline for clinical concept extraction

meddeid

Local-first multilingual clinical text de-identification framework with Dutch and English models, pluggable language profiles, and Python, CLI, batch, and HTTP interfaces.

belgian-deduce

Python package for rule-based de-identification of Belgian clinical text

meddeid-data

Data import, splitting, and synthetic generation for MedDeID.

meddeid-training

Model training, selection, refit, and bundle export for MedDeID.

fa-redact

Privacy-first Persian PII detection and de-identification for healthcare, clinical NLP, and sensitive data workflows. Open source, local-first, and built for Python.

clingrounder

Offset-safe clinical text grounding to terminology-linked knowledge graphs.

meddeid-eval

Metrics and stability analysis for MedDeID.

meddeid-language-nl

Dutch nl-BE and nl-NL language profiles and resources for MedDeID.

meddeid-core

Canonical MedDeID schema, taxonomy, normalization, and validation.

multiversity

Open-source multimodal dataset: 98K+ clinical cases & 139K+ medical images from PubMed Central

bh-sentinel-ml

Open-source clinical safety signal detection for behavioral health systems. Text in. Flags out. Clinician decides.

bh-sentinel-core

Open-source clinical safety signal detection for behavioral health systems. Text in. Flags out. Clinician decides.

pat2vec

A comprehensive Python package for healthcare data engineering, designed to extract, transform, and feature engineer patient data from CogStack-based EHR datalakes. Enables patient-level aggregation, longitudinal time series construction (up to 25 years retrospective), flexiblefeature engineering (biochemistry, demographics, medications, diagnoses

ehrextract

Structured feature extraction from clinical notes with LLMs — local HuggingFace (LoRA adapters), OpenAI-compatible, and Anthropic providers

forte-health

The project is in the incubation stage and still under development. ForteHealth is a flexible and powerful ML workflow builder for biomedical and clinical scenarios. This is part of the CASL project: http://casl-project.ai/