Vital Signs

Goal of Extraction

The Core Clinical Vitals Library is a vital signs-focused clinical data extraction tool designed to identify, extract, and ontologically map vital sign measurements from unstructured clinical narratives and patient health record documentation. It extracts vital sign measurements and quantitative values documented across clinical notes, vital sign sections, and patient encounter records, standardizing representation through SNOMED CT concept mapping with associated confidence metrics.

Extraction Methodology

The extraction process operates at the sentence level, capturing each vital sign measurement with precise character-level locations (start and end positions) that enable direct traceability back to the “document”. Each extracted vital sign measurement includes the vital sign name, quantitative value, measurement unit, and temporal context. When a patient’s vital sign measurement appears multiple times within a single document—whether from repeated assessments, serial monitoring, or documentation across different note sections—those records are de-duplicated. We return the vital sign instance in the document with the highest confidence if there are more than one vital sign with the same SNOMED CT concept code and measurement value. 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 vital sign measurement is assigned a confidence score (0.0–1.0 scale) to quantify extraction certainty. This confidence score guides appropriate reliance on extracted data and supports informed clinical interpretation.

Clinical Considerations

Temporal context is critical for clinical decision-making; understanding when vital sign measurements were obtained directly impacts interpretation of results and assessment of patient status trends or response to intervention. Serial vital sign measurements provide essential context for baseline establishment, trend analysis, and detection of clinically significant changes. Measurement units should be considered in conjunction with extracted values to ensure appropriate clinical interpretation. Clinical judgment should be applied when interpreting extracted results, particularly for entries with lower confidence scores.

Target Concepts

Coding System: SNOMED CT

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

Clinical Concepts Extracted

Vital signs are clinically documented quantitative measurements that have been recorded by clinical staff. This includes measurements of blood pressure, heart rate, temperature, respiratory rate, oxygen saturation, and other vital sign parameters. Associated clinical attributes—including quantitative values, measurement units, and temporal context—are captured as they appear in source documentation.

We define vital signs with SNOMED concepts. Only concepts that fall into one of these clinical categories are included:

• Body temperature
• Heart rate
• Respiratory rate
• Blood pressure
• Peripheral oxygen saturation
• Hemoglobin saturation with oxygen
• Body height
• Body weight
• Body mass index (BMI)
• Body surface area
• Mean arterial pressure

The concept must be a specific, named vital sign. The extracted concept must meet a confidence threshold. The extraction engine assigns a confidence score to each identified concept. In addition, this extraction only includes vital signs if they have a measurement value.

Extracted Fields

Vitals Extraction Fields

Example of Extracted Output

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

Vitals Illustrative Output Example

• Example JSONL object showing a typical extraction result

1
{
2
  "filename": "patient_3.pdf",
3
  "subdoc_id": "patient_3.pdf-0004",
4
  "manifest_index": 3,
5
  "measure": "vitals",
6
  "chartdate": "2022-03-13",
7
  "subject_id": "11110010",
8
  "processing_date": "2024-03-08T00:00:00",
9
  "data": [
10
    {
11
      "sentence": "ny further fluids for hemodynamic support and her blood pressure | medications were slowly re-introduced. |  | By day 3 post admission, she had normalization of her white blood cell count and | her oxygen requirements were able to be weaned down and she was ***satting*** 93% on | her baseline oxygen requirement of 2L NP. She was subsequently started on a | steroid taper. |  | On day 4 post admission, she was seen by physiotherapy and ambulated well on her | baseline oxygen level and it was deemed safe for her to be dis",
12
      "section_name": "PROCEDURES AND TREATMENT PROVIDED",
13
      "entity_text": "satting",
14
      "entity_start": 4137,
15
      "entity_end": 4144,
16
      "concept_id": "103228002",
17
      "description": "Hemoglobin saturation with oxygen (observable entity)",
18
      "entity_confidence": 0.96,
19
      "temporality": "By day 3 post admission",
20
      "measurement_value": "93",
21
      "measurement_unit": "%"
22
    }
23
  ]
24
}