Upload folder using huggingface_hub

README.md

@@ -1,13 +1,25 @@
 ---
-title: Cliniguard Laboratory Ner
-emoji: 🐨
-colorFrom: green
+title: CliniGuard Laboratory NER
+emoji: 🧪
+colorFrom: red
 colorTo: gray
 sdk: gradio
 sdk_version: 6.20.0
-python_version: '3.12'
 app_file: app.py
-pinned: false
+short_description: Clinical lab result entity extraction with Bio_ClinicalBERT
+python_version: "3.12"
+startup_duration_timeout: 30m
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# CliniGuard Laboratory NER
+
+Interactive demo of [genzeonplatform/cliniguard-laboratory-ner](https://huggingface.co/genzeonplatform/cliniguard-laboratory-ner),
+a Bio_ClinicalBERT token-classification model that extracts **10 laboratory result entity categories**
+(test names, values, units, reference ranges, abnormality flags, specimen types, dates, LOINC codes,
+panels, and status) from unstructured clinical text.
+
+Paste a lab report excerpt, progress note, or discharge summary, and the model highlights each
+entity in place and lists it in a structured table alongside its confidence score.
+
+Built by Genzeon Platforms for healthcare AI pipelines — lab result extraction, critical value
+detection, lab trending, and LOINC mapping support.

app.py

@@ -0,0 +1,191 @@
+"""CliniGuard Laboratory NER — interactive demo for clinical laboratory result entity extraction.
+
+Built on Bio_ClinicalBERT fine-tuned for token classification (BIO tagging, 21 labels,
+10 laboratory result entity categories). Runs on ZeroGPU.
+"""
+
+import spaces  # MUST be first — before torch / transformers
+import torch
+from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
+
+import gradio as gr
+
+MODEL_ID = "genzeonplatform/cliniguard-laboratory-ner"
+
+# Entity type -> (legend label, description, hex color). Colors are picked to be
+# visually distinct across the 10 lab categories when rendered by HighlightedText.
+ENTITY_META = {
+    "LAB_TEST_NAME": ("Test name", "#1f77b4"),
+    "LAB_VALUE": ("Value", "#ff7f0e"),
+    "LAB_UNIT": ("Unit", "#2ca02c"),
+    "REFERENCE_RANGE": ("Reference range", "#d62728"),
+    "ABNORMALITY_FLAG": ("Abnormality flag", "#9467bd"),
+    "SPECIMEN_TYPE": ("Specimen", "#8c564b"),
+    "LAB_DATE": ("Date", "#e377c2"),
+    "LOINC_CODE": ("LOINC code", "#17becf"),
+    "TEST_PANEL": ("Panel", "#bcbd22"),
+    "LAB_STATUS": ("Status", "#7f7f7f"),
+}
+
+DESCRIPTIONS = {
+    "LAB_TEST_NAME": "Name of the laboratory test (e.g. hemoglobin, glucose, troponin I)",
+    "LAB_VALUE": "Numeric or qualitative result (e.g. 7.2, 145, positive, trace)",
+    "LAB_UNIT": "Unit of measurement (e.g. mg/dL, g/dL, mEq/L, x10^3/uL)",
+    "REFERENCE_RANGE": "Normal reference range (e.g. 12.0-17.5, < 200, 3.5-5.0)",
+    "ABNORMALITY_FLAG": "Abnormality indicator (e.g. H, L, Critical High, Normal)",
+    "SPECIMEN_TYPE": "Type of specimen (e.g. blood, serum, urine, CSF)",
+    "LAB_DATE": "Collection date/time (e.g. 03/15/2024, this morning, hospital day 3)",
+    "LOINC_CODE": "LOINC identifier code (e.g. 718-7, 2345-7, 2160-0)",
+    "TEST_PANEL": "Panel/order set name (e.g. CBC, BMP, CMP, lipid panel)",
+    "LAB_STATUS": "Result status (e.g. final, preliminary, pending)",
+}
+
+# Load model at module scope, eager .to("cuda") — ZeroGPU intercepts & packs weights.
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+model = AutoModelForTokenClassification.from_pretrained(MODEL_ID).to("cuda")
+nlp = pipeline(
+    "token-classification",
+    model=model,
+    tokenizer=tokenizer,
+    aggregation_strategy="simple",
+    device=0,  # pipeline follows model device
+)
+
+
+def _entities_to_highlight(text: str, entities):
+    """Convert HF pipeline entities into the (text, label) list HighlightedText wants,
+    filling the gaps with plain text spans."""
+    if not entities:
+        return [(text, None)]
+
+    parts = []
+    cursor = 0
+    for ent in entities:
+        start = ent["start"]
+        end = ent["end"]
+        label = ent["entity_group"]
+        if start > cursor:
+            parts.append((text[cursor:start], None))
+        parts.append((text[start:end], label))
+        cursor = end
+    if cursor < len(text):
+        parts.append((text[cursor:], None))
+    return parts
+
+
+@spaces.GPU(duration=30)
+def extract_entities(text: str):
+    """Extract laboratory result entities (test names, values, units, ranges, flags, …) from clinical text.
+
+    Args:
+        text: clinical text containing laboratory results (lab reports, progress notes, discharge summaries).
+    """
+    text = (text or "").strip()
+    if not text:
+        return [], "Please enter some clinical text to analyze."
+
+    entities = nlp(text)
+
+    # Summary table for the side panel
+    rows = []
+    for ent in entities:
+        label = ent["entity_group"]
+        legend_label = ENTITY_META.get(label, (label, None))[0]
+        rows.append([legend_label, ent["word"], f"{ent['score']:.3f}",
+                     ent["start"], ent["end"]])
+
+    highlight = _entities_to_highlight(text, entities)
+    n = len(rows)
+    summary = f"Found **{n}** entit{'y' if n == 1 else 'ies'} across {len({r[0] for r in rows}) or 0} categor{'y' if n == 1 else 'ies'}." if n else "No entities found."
+    return highlight, rows, summary
+
+
+# Build the legend options for HighlightedText from the model's labels.
+# HighlightedText accepts `combine_entities=True` to merge adjacent same-label spans.
+HIGHLIGHT_LABELS = {label: meta[1] for label, meta in ENTITY_META.items()}
+
+CSS = """
+#col-container { max-width: 1100px; margin: 0 auto; }
+.dark .gradio-container { color: var(--body-text-color); }
+.legend-chip {
+    display: inline-block; padding: 2px 8px; margin: 2px;
+    border-radius: 6px; color: #fff; font-size: 0.85em; font-weight: 600;
+}
+"""
+
+EXAMPLES = [
+    ["Lab Results: Hemoglobin: 7.2 g/dL (Reference: 12.0-17.5) [Critical Low]. Specimen: blood. Status: final. CBC panel. LOINC: 718-7."],
+    ["Sodium 145 mEq/L (ref 135-145) [H]. Potassium 3.2 mEq/L (ref 3.5-5.0) [L]. BMP panel drawn this morning, blood specimen, preliminary."],
+    ["Glucose: 210 mg/dL (ref 70-99) [Critical High]. HbA1c 9.8% (ref < 5.7). Lipid panel: LDL 160 mg/dL [H]. Status: final. LOINC: 2345-7."],
+    ["Troponin I 0.05 ng/mL (ref < 0.04) [H]. CK-MB 8.2 ng/mL (ref < 6.3) [H]. Cardiac panel, serum specimen, hospital day 3, pending."],
+]
+
+with gr.Blocks(theme=gr.themes.Citrus(), css=CSS, title="CliniGuard Laboratory NER") as demo:
+    gr.Markdown(
+        "# 🧪 CliniGuard Laboratory NER\n"
+        "Extract laboratory result entities — test names, values, units, reference ranges, "
+        "abnormality flags, specimen types, dates, LOINC codes, panels, and status — from "
+        "unstructured clinical text. Built on **Bio_ClinicalBERT** fine-tuned by Genzeon Platforms "
+        "for token classification across 10 laboratory entity categories."
+    )
+
+    legend_html = "<div>" + "".join(
+        f'<span class="legend-chip" style="background:{color}">{label}</span>'
+        for label, (_, color) in ENTITY_META.items()
+    ) + "</div>"
+    gr.HTML(legend_html)
+
+    with gr.Row():
+        text_in = gr.Textbox(
+            label="Clinical text",
+            placeholder="Paste clinical text containing laboratory results…",
+            lines=8,
+            scale=3,
+        )
+        run = gr.Button("Extract entities", variant="primary", scale=1)
+
+    highlight_out = gr.HighlightedText(
+        label="Highlighted entities",
+        combine_entities=True,
+        show_legend=True,
+        color_map={label: meta[1] for label, meta in ENTITY_META.items()},
+    )
+
+    summary_md = gr.Markdown()
+
+    table_out = gr.Dataframe(
+        headers=["Category", "Entity", "Score", "Start", "End"],
+        label="Extracted entities",
+        interactive=False,
+        wrap=True,
+    )
+
+    run.click(
+        fn=extract_entities,
+        inputs=text_in,
+        outputs=[highlight_out, table_out, summary_md],
+        api_name="extract_entities",
+    )
+    text_in.submit(
+        fn=extract_entities,
+        inputs=text_in,
+        outputs=[highlight_out, table_out, summary_md],
+        api_name="extract_entities_submit",
+    )
+
+    gr.Examples(
+        examples=EXAMPLES,
+        inputs=text_in,
+        outputs=[highlight_out, table_out, summary_md],
+        fn=extract_entities,
+        cache_examples=True,
+        cache_mode="lazy",
+    )
+
+    with gr.Accordion("Entity types", open=False):
+        gr.Markdown("\n".join(
+            f"- **{label}** — {DESCRIPTIONS[label]}" for label in ENTITY_META
+        ))
+
+if __name__ == "__main__":
+    demo.launch(mcp_server=True)

requirements.txt

@@ -0,0 +1,2 @@
+transformers
+torch