Family History

Goal of Extraction

The Core Clinical Family History Library is a family history-focused clinical data extraction tool designed to identify, extract, and ontologically map family members’ health conditions and medical histories from unstructured clinical narratives and patient health record documentation. It extracts identified family members, their health problems, and relation to the index patient that is documented in family history sections, medical histories, and social history components, standardizing representation through SNOMED CT concept mapping with associated confidence metrics.

Extraction Methodology

The extraction process operates at the sentence level, capturing each family member’s health problem with precise character-level locations (start and end positions) that enable direct traceability back to the “document”. Extracted data includes the family member’s relationship to the index patient, along with their reported health conditions. When a family member’s health problem or family relationship appears multiple times within a single document, each instance is extracted and recorded separately to preserve the full documentary record. The library performs extraction on a document-by-document basis; there is no automatic cross-document reconciliation or cross-patient data merging.

Note: A document is determined by our intelligent document splitting feature. Medical PDFs can contain a single document or multiple documents. A document’s type can provide clinical context important for the data extraction. This feature separates and categorizes an input PDF into individual documents by document type to prepare them for data extraction. An input PDF can remain one document or can be split into multiple documents through this process. A “document” in the context of this data extraction refers to the documents identified after the intelligent document splitting process.

Interpretation & Validation

Every extracted family member health problem is assigned a confidence score (0.0–1.0 scale). Family relationship information is extracted independently and assigned its own confidence score to distinguish reliable from uncertain family member identification. Polarity status indicates the presence or absence of each extracted health problem. These confidence scores and polarity designations guide appropriate reliance on extracted data and support informed clinical interpretation regarding genetic predisposition and hereditary risk.

Clinical Considerations

Genetic relevance and inheritance patterns are critical for clinical decision-making. The relationship of identified family health problems to the index patient directly impacts risk stratification and preventive care planning. Relationship specificity affects the clinical significance of the family history. The degree of certainty regarding both the family member identity and their health conditions should be considered, as family recall and documentation completeness may vary. Clinical judgment should be applied when interpreting extracted results to inform genetic counseling and surveillance recommendations.

Target Concepts

Coding System: SNOMED CT

All extracted problems are mapped to SNOMED CT (Systematized Nomenclature of Medicine Clinical Terms), with each problem assigned a valid, active SNOMED concept identifier (6–18 digit numeric codes), along with its associated full SNOMED concept description. Family members are coded using SNOMED relationship codes where applicable. This structure provides both the standardized data needed for system integration and the contextual information needed for informed clinical interpretation.

Clinical Concepts Extracted

Family health conditions are clinically meaningful conditions of family members that have been documented by a clinician. This includes diagnoses, clinical conditions, acute and chronic diseases, complications, and comorbidities reported for family members.

We define family history conditions with SNOMED concepts. Only concepts that fall into one of these clinical categories are included:

• Finding
• Morphologic abnormality
• Disorder

Family history conditions are asserted or negated. Both affirmatively stated family conditions (e.g., “mother had breast cancer”) and negated family conditions (e.g., “no family history of heart disease”) are extracted with polarity designation to indicate presence or absence of the condition in family members.

We identify family member using SNOMED concepts. The following family member concepts are included:

• Siblings
• Parents
• Grandparents & great grandparents
• Cousins (first & second)
• Uncle & great uncle
• Aunt & great aunt
• Children
• Grandchildren
• Nephew & great-nephew
• Niece & great-niece
• Immediate family member
• Family history of
• No family history of

The extracted concept must meet a confidence threshold. The extraction engine assigns a confidence score to each identified condition. Additionally, family member identification (experiencer) is assigned a separate confidence score to distinguish reliable from uncertain family member identification.

Extracted Fields

Family History Extraction Fields

Example of Extracted Output

• Note: This example demonstrates the content of the output, not the structure

Family History Illustrative Output Example

• Example JSONL object showing a typical extraction result

1
{
2
  "filename": "patient_4.pdf",
3
  "subdoc_id": "patient_4.pdf-0002",
4
  "manifest_index": 4,
5
  "measure": "family_history",
6
  "chartdate": "2022-08-29",
7
  "subject_id": "11110009",
8
  "processing_date": "2024-03-08T00:00:00",
9
  "data": [
10
    {
11
      "sentence": " No prior history of breast surgery | nor family history of breast Ca.",
12
      "section_name": "INDICATION",
13
      "entity_text": "breast Ca",
14
      "entity_start": 382,
15
      "entity_end": 391,
16
      "concept_id": "254837009",
17
      "description": "Malignant neoplasm of breast (disorder)",
18
      "entity_confidence": 0.929999113082886,
19
      "polarity": "negated",
20
      "experiencer_mention": "family history of",
21
      "experiencer_concept_id": "57177007",
22
      "experiencer_description": "Family history with explicit context (situation)",
23
      "experiencer_confidence": 0.96,
24
      "experiencer_start": 364,
25
      "experiencer_end": 381
26
    }
27
  ]
28
}