Social Determinants of Health (SDOH) Extraction

# Social Determinants of Health (SDOH) Extraction
# Based on n2c2 2022 Track 2 / SHAC Corpus
# Paper: https://pubmed.ncbi.nlm.nih.gov/36795066/
# Task: https://n2c2.dbmi.hms.harvard.edu/2022-track-2
#
# Event-based annotation schema:
# - Each SDOH event has a TRIGGER (event type) and ARGUMENTS (attributes)
# - Event types: Alcohol, Drug, Tobacco, Employment, LivingStatus
# - Arguments characterize status, extent, temporality, and type
#
# Example: "Patient quit smoking 5 years ago"
#   Trigger: Tobacco (anchored to "smoking")
#   Arguments: Status=past, StatusTime=past ("quit", "5 years ago")

annotation_task_name: "Social Determinants of Health (SDOH) Extraction"
task_dir: "."

data_files:
  - sample-data.json
item_properties:
  id_key: "id"
  text_key: "text"

output_annotation_dir: "annotation_output/"
output_annotation_format: "json"

annotation_schemes:
  # Step 1: Identify SDOH event triggers
  - annotation_type: span
    name: sdoh_trigger
    description: "Highlight the trigger word/phrase that indicates an SDOH event"
    labels:
      - Alcohol
      - Drug
      - Tobacco
      - Employment
      - LivingStatus
    label_colors:
      Alcohol: "#ef4444"
      Drug: "#f97316"
      Tobacco: "#eab308"
      Employment: "#22c55e"
      LivingStatus: "#3b82f6"
    tooltips:
      Alcohol: "Mentions of alcohol use, drinking, or alcohol-related behaviors"
      Drug: "Mentions of illicit drug use, substance abuse, or recreational drug use"
      Tobacco: "Mentions of smoking, tobacco use, vaping, or nicotine"
      Employment: "Mentions of job status, work, occupation, unemployment, or retirement"
      LivingStatus: "Mentions of housing, living situation, homelessness, or living arrangements"
    allow_overlapping: false

  # Step 2: Status of the SDOH event
  - annotation_type: radio
    name: status
    description: "What is the status of this SDOH factor?"
    labels:
      - "current"
      - "past"
      - "none"
      - "unknown"
    keyboard_shortcuts:
      "current": "c"
      "past": "p"
      "none": "n"
      "unknown": "u"
    tooltips:
      "current": "Patient currently has this status (e.g., currently smokes, currently employed)"
      "past": "Patient had this status in the past (e.g., former smoker, previously unemployed)"
      "none": "Patient does not have this status (e.g., never smoked, denies alcohol use)"
      "unknown": "Status cannot be determined from the text"

  # Step 3: Additional arguments for substance use
  - annotation_type: multiselect
    name: substance_attributes
    description: "For substance use events, select applicable attributes"
    labels:
      - "Amount mentioned"
      - "Frequency mentioned"
      - "Duration mentioned"
      - "Type/Method specified"
      - "Quit attempt mentioned"
    tooltips:
      "Amount mentioned": "Text specifies quantity (e.g., '2 drinks/day', 'pack of cigarettes')"
      "Frequency mentioned": "Text specifies how often (e.g., 'daily', 'occasionally', 'weekends')"
      "Duration mentioned": "Text specifies time period (e.g., '10 years', 'since college')"
      "Type/Method specified": "Text specifies substance type or method (e.g., 'beer', 'marijuana', 'vaping')"
      "Quit attempt mentioned": "Text mentions attempt to quit or cessation efforts"

  # Step 4: Living status type (for LivingStatus events)
  - annotation_type: radio
    name: living_type
    description: "For LivingStatus events, what is the living arrangement?"
    labels:
      - "alone"
      - "with_family"
      - "with_others"
      - "homeless"
      - "institution"
      - "not_specified"
    tooltips:
      "alone": "Patient lives alone"
      "with_family": "Patient lives with family members (spouse, children, parents)"
      "with_others": "Patient lives with non-family (roommates, friends)"
      "homeless": "Patient is homeless, in shelter, or has unstable housing"
      "institution": "Patient lives in facility (nursing home, assisted living, group home)"
      "not_specified": "Living arrangement not specified in text"

  # Step 5: Employment type (for Employment events)
  - annotation_type: radio
    name: employment_type
    description: "For Employment events, what is the employment status?"
    labels:
      - "employed"
      - "unemployed"
      - "retired"
      - "disabled"
      - "student"
      - "homemaker"
      - "not_specified"
    tooltips:
      "employed": "Patient is currently working"
      "unemployed": "Patient is not working and seeking employment"
      "retired": "Patient has retired from work"
      "disabled": "Patient is unable to work due to disability"
      "student": "Patient is a student"
      "homemaker": "Patient works in the home/is a caregiver"
      "not_specified": "Employment type not specified"

allow_all_users: true
instances_per_annotator: 100
annotation_per_instance: 2
allow_skip: true
skip_reason_required: false