harshGenzeonPlatforms commited on
Commit
e1e4b40
·
verified ·
1 Parent(s): d5e9747

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -18,13 +18,13 @@ We build for a domain where being right, auditable, and defensible matters as mu
18
 
19
  🔬 What we've open-sourced
20
 
21
- CliniGuard — clinical NER family
22
 
23
- CliniGuard is our family of production-grade clinical Named Entity Recognition models. They're built on trusted biomedical bases (Bio_ClinicalBERT, PubMedBERT), fine-tuned on clinical corpora, and released under Apache-2.0 so you can actually use them in real systems. Each ships with a live demo Space you can try in the browser.
24
 
25
- ModelExtractsBaseLabelsLicenseDemoCliniGuard Clinical NERGeneral clinical entitiesBio_ClinicalBERT—Apache-2.0—CliniGuard Medication NERDrug names, dosages, routes, frequencies, administration details (12 categories)Bio_ClinicalBERTBIO · 25Apache-2.0Try it →CliniGuard Laboratory NERLab tests, values, units + rule-based numeric extractionBio_ClinicalBERTBIO · 21Apache-2.0Try it →CliniGuard Diagnosis / ICD NERDiagnoses & conditions, with ICD-10 / SNOMED linking via SapBERT (9 categories)PubMedBERTBIO · 19Apache-2.0Try it →
26
 
27
- All CliniGuard models are ~110M parameters, use a 512-token window, and run on standard HuggingFace Transformers — small enough to deploy on-prem or at the edge, which matters a lot for PHI. The Diagnosis / ICD model runs a two-stage pipeline: NER extraction, then entity linking for automated code mapping.
28
 
29
 
30
  A note on models we build on: for healthcare and government contexts we deliberately restrict our open-weight bases to US/EU-origin models. It's a sovereignty and trust choice, and it's baked into how we pick every base you see here.
@@ -46,7 +46,7 @@ PES One — the engagement lobe. Conversational AI for member and patient engage
46
  CPS One — the governance lobe. Privacy program operations, breach response, and AI governance.
47
 
48
 
49
- All three run on Aether One™, our patent-protected substrate (USPTO filings in progress). The CliniGuard models you see here are the kind of grounded, auditable NLP that feeds that system.
50
 
51
 
52
  ✅ Where we are
@@ -75,7 +75,7 @@ Building in healthcare AI and want to compare notes? Reach out through genzeon.o
75
 
76
  🌐 Website — genzeon.one
77
  📰 Newsletter — Building the Healthcare Brain on LinkedIn
78
- 🤗 Hugging Face — @genzeon-platforms
79
 
80
 
81
 
 
18
 
19
  🔬 What we've open-sourced
20
 
21
+ Healthcare Brain — clinical NER family
22
 
23
+ The Healthcare Brain NER family is our set of production-grade clinical Named Entity Recognition models. They're built on trusted biomedical bases (Bio_ClinicalBERT, PubMedBERT), fine-tuned on clinical corpora, and released under Apache-2.0 so you can actually use them in real systems. Each ships with a live demo Space you can try in the browser.
24
 
25
+ ModelExtractsBaseLabelsLicenseDemoHealthcare Brain Medication NERDrug names, dosages, routes, frequencies, administration details (12 categories)Bio_ClinicalBERTBIO · 25Apache-2.0Try it →Healthcare Brain Laboratory NERLab tests, values, units + rule-based numeric extractionBio_ClinicalBERTBIO · 21Apache-2.0Try it →Healthcare Brain Diagnosis / ICD NERDiagnoses & conditions, with ICD-10 / SNOMED linking via SapBERT (9 categories)PubMedBERTBIO · 19Apache-2.0Try it →Healthcare Brain Clinical Findings NERSymptoms, findings and clinical mentions from free-text notesBio_ClinicalBERT · spaCy—Apache-2.0Try it →Healthcare Brain Vitals NERBlood pressure, heart rate, temperature, SpO₂ and other vital signsBio_ClinicalBERT—Apache-2.0Try it →Healthcare Brain NER (base)PHI / PII entities for de-identification before downstream useBio_ClinicalBERT—Apache-2.0Try it →
26
 
27
+ All models are ~110M parameters, use a 512-token window, and run on standard HuggingFace Transformers — small enough to deploy on-prem or at the edge, which matters a lot for PHI. The Diagnosis / ICD model runs a two-stage pipeline: NER extraction, then entity linking for automated code mapping.
28
 
29
 
30
  A note on models we build on: for healthcare and government contexts we deliberately restrict our open-weight bases to US/EU-origin models. It's a sovereignty and trust choice, and it's baked into how we pick every base you see here.
 
46
  CPS One — the governance lobe. Privacy program operations, breach response, and AI governance.
47
 
48
 
49
+ All three run on Aether One™, our patent-protected substrate (USPTO filings in progress). The NER models above are the kind of grounded, auditable NLP that feeds that system.
50
 
51
 
52
  ✅ Where we are
 
75
 
76
  🌐 Website — genzeon.one
77
  📰 Newsletter — Building the Healthcare Brain on LinkedIn
78
+ 🤗 Hugging Face — @genzeonplatform
79
 
80
 
81