i2b2 Clinical Named Entity Recognition

# i2b2 Clinical Named Entity Recognition
# Based on Stubbs et al., JAMIA 2015
# Paper: https://academic.oup.com/jamia/article/22/6/1220/2357822
# Dataset: https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/
#
# Annotate de-identified clinical notes for medical entities and assertion status.
# This follows the i2b2/VA 2010 shared task framework for concept extraction
# and assertion classification in clinical text.
#
# Entity Types:
# - Problem: Medical conditions, diagnoses, symptoms (e.g., pneumonia, chest pain)
# - Treatment: Procedures, therapies, interventions (e.g., appendectomy, chemotherapy)
# - Test: Diagnostic tests and examinations (e.g., CBC, chest X-ray, MRI)
# - Medication: Drug names (e.g., metformin, lisinopril)
# - Dosage: Drug dosage amounts (e.g., 500 mg, 10 mg/day)
# - Duration: Time spans for treatments (e.g., 7 days, 3 weeks)
# - Frequency: How often something occurs (e.g., twice daily, q6h)
#
# Assertion Status:
# - Present: The entity is currently present or active
# - Absent: The entity is explicitly negated or denied
# - Possible: The entity is uncertain or suspected
# - Conditional: The entity depends on a condition
# - Associated with Patient: The entity pertains to the patient directly
# - Associated with Other: The entity pertains to a family member or other person
#
# Guidelines:
# 1. Mark all clinical entity spans precisely
# 2. Classify the assertion status of the primary clinical finding
# 3. Use clinical context to determine assertion (e.g., "no fever" = Absent)

annotation_task_name: "i2b2 Clinical Named Entity Recognition"
task_dir: "."

data_files:
  - sample-data.json

item_properties:
  id_key: "id"
  text_key: "text"

output_annotation_dir: "annotation_output/"
output_annotation_format: "json"

port: 8000
server_name: localhost

annotation_schemes:
  - annotation_type: span
    name: clinical_entities
    description: "Highlight and label clinical entities in the text"
    labels:
      - "Problem"
      - "Treatment"
      - "Test"
      - "Medication"
      - "Dosage"
      - "Duration"
      - "Frequency"
    tooltips:
      "Problem": "Medical condition, diagnosis, or symptom (e.g., pneumonia, chest pain, diabetes)"
      "Treatment": "Procedure, therapy, or intervention (e.g., appendectomy, physical therapy)"
      "Test": "Diagnostic test or examination (e.g., CBC, chest X-ray, blood glucose)"
      "Medication": "Drug or medication name (e.g., metformin, lisinopril, aspirin)"
      "Dosage": "Drug dosage amount (e.g., 500 mg, 10 mg/day, 2 tablets)"
      "Duration": "Time span for a treatment or condition (e.g., 7 days, 3 weeks, since 2020)"
      "Frequency": "How often something is administered or occurs (e.g., twice daily, q6h, PRN)"

  - annotation_type: radio
    name: assertion_status
    description: "What is the assertion status of the primary clinical finding in this note?"
    labels:
      - "Present"
      - "Absent"
      - "Possible"
      - "Conditional"
      - "Associated with Patient"
      - "Associated with Other"
    keyboard_shortcuts:
      "Present": "1"
      "Absent": "2"
      "Possible": "3"
      "Conditional": "4"
      "Associated with Patient": "5"
      "Associated with Other": "6"
    tooltips:
      "Present": "The clinical finding is currently present and active"
      "Absent": "The finding is explicitly negated or denied (e.g., 'no fever', 'denies pain')"
      "Possible": "The finding is uncertain or suspected (e.g., 'possible pneumonia', 'rule out MI')"
      "Conditional": "The finding depends on a condition (e.g., 'chest pain if exerting')"
      "Associated with Patient": "The finding directly pertains to the patient"
      "Associated with Other": "The finding pertains to a family member or other individual"

annotation_instructions: |
  Annotate de-identified clinical notes for medical entities and assertion status.

  For each clinical note:
  1. Read the entire note to understand the clinical context.
  2. Use the span tool to highlight and label all clinical entities.
  3. Classify the assertion status of the primary clinical finding.

  Important notes:
  - Mark spans precisely (e.g., "chest pain" not "complains of chest pain")
  - Pay attention to negation cues (no, denies, without, negative for)
  - Distinguish between patient conditions and family history mentions

html_layout: |
  <div style="padding: 15px; max-width: 800px; margin: auto;">
    <div style="background: #f0fdf4; border: 1px solid #bbf7d0; border-radius: 8px; padding: 16px;">
      <strong style="color: #166534;">Clinical Note:</strong>
      <p style="font-size: 16px; line-height: 1.8; margin: 8px 0 0 0; white-space: pre-wrap;">{{text}}</p>
    </div>
  </div>

allow_all_users: true
instances_per_annotator: 50
annotation_per_instance: 2
allow_skip: true
skip_reason_required: false