Downloads · 30 days
0
genzeonplatform/healthcare-brain-clinical-findings-ner
healthcare-brain-clinical-findings-ner is a token classification model from genzeonplatform. Use it when you need labels on individual words, such as names. It is set up for spacy. The card lists the license as apache-2.0.
Healthcare Brain Clinical Findings NER is a transformer-based clinical Named Entity Recognition model developed by Genzeon Platforms for automated extraction of clinical findings, diseases, conditions, anatomical loca…
Downloads · 30 days
0
Access
Public
Updated Jul 20, 2026
Repo size
437 MB
Likes
18
Public
Click a slice to open those files.
Other437 MB · 100%
From the Hugging Face model README
Healthcare Brain Clinical Findings NER is a transformer-based clinical Named Entity Recognition model developed by Genzeon Platforms for automated extraction of clinical findings, diseases, conditions, anatomical locations, and clinical modifiers from unstructured clinical text. Built on Bio_ClinicalBERT and fine-tuned on biomedical corpora, this model delivers production-grade entity recognition across 8 clinical finding and modifier categories.
| Property | Value |
|---|---|
| Developed by | Genzeon Platforms |
| Base model | Bio_ClinicalBERT |
| Architecture | SpaCy Transformer + TransitionBasedParser (NER) |
| Parameters | ~110M |
| Tagging scheme | BIO (17 labels) |
| Max sequence length | 512 tokens (strided spans: window=64, stride=48) |
| Framework | SpaCy 3.8 + spacy-transformers |
| License | Apache-2.0 |
Healthcare Brain Clinical Findings NER is designed for healthcare AI pipelines that need to extract structured clinical findings from unstructured clinical text. Primary use cases include:
The model recognizes 8 clinical finding and modifier entity types using BIO tagging (17 labels total):
| Category | Entity Type | Description | Examples |
|---|---|---|---|
| Diagnoses | DISEASE | Named diseases, disorders, syndromes | diabetes mellitus, hypertension, pneumonia |
| Observations | CLINICAL_FINDING | Lab results, exam findings, clinical observations | elevated WBC, fever, tachycardia |
| Pathology | CONDITION | Pathological states and processes | inflammation, fibrosis, necrosis |
| Anatomy | BODY_LOCATION | Anatomical structures and body sites | left ventricle, liver, knee joint |
| Severity | SEVERITY | Severity descriptors | mild, moderate, severe, acute |
| Laterality | LATERALITY | Side/direction qualifiers | left, right, bilateral, anterior |
| Temporal | COURSE | Disease progression and duration | chronic, progressive, recurrent |
| Status | CLINICAL_STATUS | Current clinical state | active, resolved, stable, worsening |
Note: Two additional entity types (
SYMPTOM,SIGN) are architecturally supported but require restricted clinical datasets (i2b2 2010, ShARe/CLEF) for training data. Contact Genzeon Platforms for enterprise models trained with full entity coverage.
| Metric | Precision | Recall | F1 |
|---|---|---|---|
| Micro avg | 0.6558 | 0.5895 | 0.6209 |
| Macro avg | — | — | 0.6093 |
| Entity | Precision | Recall | F1 | Support |
|---|---|---|---|---|
| DISEASE | 0.7638 | 0.7314 | 0.7472 | 4,937 |
| BODY_LOCATION | 0.7306 | 0.6314 | 0.6774 | 5,214 |
| SEVERITY | 0.6210 | 0.7440 | 0.6770 | 567 |
| COURSE | 0.6214 | 0.7110 | 0.6632 | 180 |
| CLINICAL_STATUS | 0.6110 | 0.6970 | 0.6512 | 489 |
| CONDITION | 0.5000 | 0.5450 | 0.5218 | 347 |
| LATERALITY | 0.4670 | 0.5710 | 0.5140 | 259 |
| CLINICAL_FINDING | 0.5050 | 0.3650 | 0.4237 | 3,011 |
| Entity | Precision | Recall | F1 |
|---|---|---|---|
| DISEASE | 0.9912 | 0.9458 | 0.9680 |
| BODY_LOCATION | 0.9979 | 0.8533 | 0.9200 |
| CONDITION | 0.8237 | 0.8943 | 0.8576 |
| SEVERITY | 0.7813 | 0.9323 | 0.8500 |
| CLINICAL_FINDING | 0.9974 | 0.7271 | 0.8410 |
| CLINICAL_STATUS | 0.7712 | 0.8966 | 0.8292 |
| COURSE | 0.7243 | 0.8470 | 0.7810 |
| LATERALITY | 0.6382 | 0.7865 | 0.7049 |
Relaxed matching shows significantly higher scores, indicating the model captures entity semantics well — boundary precision is the primary area for improvement.
import spacy
# Load the model
nlp = spacy.load("genzeonplatform/healthcare-brain-clinical-findings-ner")
# Process clinical text
text = """Patient presents with severe chest pain radiating to the left arm,
associated with shortness of breath and diaphoresis. History of chronic
hypertension and type 2 diabetes mellitus."""
doc = nlp(text)
# Extract entities
for ent in doc.ents:
print(f" [{ent.label_:20s}] {ent.text}")
Output:
[SEVERITY ] severe
[DISEASE ] chest pain
[LATERALITY ] left
[CLINICAL_FINDING ] shortness of breath
[DISEASE ] diaphoresis
[DISEASE ] chronic hypertension
import spacy
nlp = spacy.load("genzeonplatform/healthcare-brain-clinical-findings-ner")
clinical_notes = [
"MRI of the right knee reveals a complete ACL tear with moderate joint effusion.",
"Patient has mild fever with productive cough and bilateral crackles. Diagnosed with pneumonia.",
"Chronic heart failure with reduced ejection fraction, currently stable on medication.",
]
for doc in nlp.pipe(clinical_notes, batch_size=32):
findings = {}
for ent in doc.ents:
findings.setdefault(ent.label_, []).append(ent.text)
print(f"Text: {doc.text[:60]}...")
for entity_type, mentions in findings.items():
print(f" {entity_type}: {', '.join(mentions)}")
print()
import spacy
import json
nlp = spacy.load("genzeonplatform/healthcare-brain-clinical-findings-ner")
text = "Severe bilateral pneumonia with progressive respiratory failure."
doc = nlp(text)
# Structured extraction
entities = [
{
"text": ent.text,
"type": ent.label_,
"start": ent.start_char,
"end": ent.end_char,
}
for ent in doc.ents
]
print(json.dumps(entities, indent=2))
spacy.TransitionBasedParser.v2 with TransformerListener| Dataset | Split | Documents | Source |
|---|---|---|---|
| NCBI Disease Corpus | train/dev/test | 793 | NCBI |
| BC5CDR (Disease subset) | train/dev/test | 1,500 | BioCreative V CDR |
| MedMentions (ST21pv) | train/dev/test | 4,392 | GitHub |
| Total | train/dev/test | 3,727 / 1,478 / 1,479 |
Entity mapping: UMLS semantic types from MedMentions are mapped to target categories (e.g., T047→DISEASE, T184→SYMPTOM, T023→BODY_LOCATION). Modifier entities (SEVERITY, LATERALITY, COURSE, CLINICAL_STATUS) are extracted via context-aware keyword gazetteers.
Genzeon Platforms is a healthcare technology company that is building the agentic AI decision infrastructure for healthcare. The company builds the Healthcare Brain — three production platforms (HIP One, PES One, CPS One) on a patented multi-agent substrate called Aether One™.
Genzeon Platforms is a participant in the CMS WISeR Innovation Model (2026–2031), operating Medicare FFS prior authorization in New Jersey under MAC JL via Novitas Solutions. Live since January 1, 2026.
Q1 2026 production results:
Genzeon Platforms publishes the Aether Knowledge Pack Specification (AKPS). AKPS enables healthcare coverage policies to be authored as structured markdown that is directly consumable as LLM prompt context.
See: github.com/genzeon/aether-akps
Genzeon Platforms builds on US- and EU-origin open-weight foundation models only (Llama, Gemma, Mistral families) for healthcare and federal deployment contexts. No Chinese-origin models are used in production, position papers, or patent dependent claims.
Exton, Pennsylvania, USA
Genzeon Platforms is a Genzeon company.
| Resource | Link |
|---|---|
| Company website | https://genzeon.one |
| Healthcare Brain overview | https://genzeon.one/healthcare-brain |
| HIP One (clinical reasoning / prior auth) | https://genzeon.one/hip-one |
| PES One (patient & member engagement) | https://genzeon.one/pes-one |
| CPS One (AI governance & compliance) | https://genzeon.one/cps-one |
| Aether One™ architecture | https://genzeon.one/aether-one |
| Patents | https://genzeon.one/patents |
| WISeR production deployment | https://genzeon.one/wiser |
| AKPS open spec | https://github.com/genzeon/aether-akps |
| Security & trust | https://genzeon.one/security |
| https://www.linkedin.com/company/117124252 | |
| Contact | https://genzeon.one/contact |
If you use this model or reference Genzeon Platforms in academic, regulatory, or industry work, please cite:
Genzeon Platforms (2026). Healthcare Brain Clinical Findings NER is part of Genzeon Platform's suite of healthcare AI tools designed to accelerate clinical research and improve patient care.
For enterprise licensing, custom fine-tuning, or integration support, contact [email protected].