We benchmarked OpenAI Privacy Filter against a John Snow Labs de-identification pipeline on 381,959 tokens of real clinical text. The John Snow Labs pipeline reached 0.95 F1 on PHI detection vs. 0.55 for OpenAI Privacy Filter, with 0.98 recall vs. 0.64. It ran 5.8× faster on CPU. The label mapping was deliberately conservative: ambiguous clinical labels were not forced into OpenAI’s taxonomy.
We benchmarked OpenAI Privacy Filter against a John Snow Labs de-identification pipeline on 381,959 tokens of real clinical text. The John Snow Labs pipeline reached 0.95 F1 on PHI detection...
Institution-scale medical reasoning: what the field is actually learning There is a version of the institution-scale clinical reasoning story that is easy to tell: AI systems that continuously reason over...
Clinical NLP extracts meaning from unstructured text. But in healthcare, extracted meaning isn't useful until it speaks the same language as the systems that need to act on it. An...
John Snow Labs, a healthcare AI company, is proud to announce that it has been named the winner of the Real World Evidence (RWE) Catalyst Challenge at PHUSE US Connect...
Why agentic AI marks a new era for healthcare data operations Healthcare organizations generate extraordinary volumes of data every day. Electronic health records, laboratory systems, imaging platforms, registries, clinical trial...
Demos
See More