Clinical NLP Pipeline
by Community · open-source · Last verified 2026-03-17
Processes unstructured clinical notes using medspaCy and BioClinicalBERT to extract diagnoses, medications, procedures, and lab values, then maps entities to ICD-10 and SNOMED-CT codes. Outputs FHIR-compatible JSON bundles and includes a de-identification step compliant with HIPAA Safe Harbor.
https://github.com/medspacy/medspacy ↗C+
C+—Average
Adoption: BQuality: AFreshness: ACitations: C+Engagement: F
Specifications
- License
- Apache-2.0
- Pricing
- open-source
- Capabilities
- clinical-ner, icd-10-coding, fhir-export, hipaa-deidentification
- Integrations
- medspacy, transformers, fhir-resources, spacy
- Use Cases
- ehr-structuring, clinical-coding-automation, population-health-analytics
- API Available
- No
- Language
- python
- Dependencies
- medspacy, spacy, transformers, fhir.resources, presidio-analyzer
- Environment
- Python 3.10+
- Est. Runtime
- 5-20 minutes per 10k notes
- Tags
- clinical-nlp, healthcare, icd-10, medspacy, ehr
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
55Adoption
60
Quality
86
Freshness
84
Citations
55
Engagement
0