Benchmark Databricks ai_mask() for clinical de-identification: 0.71 PHI F1 vs. 0.96 for John Snow Labs Healthcare NLP, with key accuracy and compliance gaps
`ai_mask()` is a Databricks SQL function, in Public Preview and HIPAA compliant, that masks entity types named in a SQL array literal. Run against an expert-annotated clinical corpus with the...
Clinical de-identification benchmarks in 2026 put John Snow Labs Healthcare NLP at 0.96 PHI F1 on expert-annotated clinical notes, against 0.91 for Claude Opus 4.8, 0.89 for GPT-5.5, 0.86 for...
DICOM de-identification is workflow-specific because PHI can appear in metadata tags, free-text metadata fields, burned-in image pixels, and encapsulated PDF content. A production pipeline may need to inspect tags, apply...
Clinical de-identification requires removing the 18 HIPAA Safe Harbor identifier categories, the GDPR Article 9 special categories, and the contextual identifiers that make a patient re-identifiable in a longitudinal record....
Every day, healthcare organizations face an impossible balancing act. Clinical teams need AI tools to extract insights from unstructured medical records, validate de-identification results, and accelerate annotation workflows. But every...
Demos
See More