1 Definition 2 Functional Requirements 3 Syntax 4 Semantics

1 Definition

Physiological Signal Qualifier is a set of Data providing additional information on Physiological Signal Data for potential use by a machine.

The combination of Physiological Signal Data and Physiological Signal Qualifier is called Physiological Signal Object, specified by AIH-HSP V1.1.

2 Functional Requirements

Physiological Signal Qualifier must allow the expression of the following Elements:

  1. Sub-Type
  2. Format
  3. Attributes

Users needing additional entries in the Physiological Signal Qualifier or support of new Qualifiers should make a documented request to the MPAI Secretariat. Requests will be considered by the appropriate MPAI committee.

An instance of the Qualifier states ONE Sub-Type of the data (SubType), from the Sub-Types listed in Semantics, and may state the group it belongs to (SubTypeGroup); and ONE Format (Format), from the Formats listed, and may state its group (FormatGroup). The mapping between Sub-Type groups and Format groups (GroupMap) is part of the specification of the Qualifier and is optional in an instance.

The Qualifier may include Findings: what the data show. Each Finding has an identifier (FindingID), a Code, the Coding System of the Code, chosen among those of this domain, the name of the label set when the Code is from a data set’s own labels (LabelSet), and where in the data the Finding is (Where). Who set a Finding and how sure that source is are not part of the Qualifier: they are in the AIH Data that carries the data (FindingTrust).

3 Syntax

https://schemas.mpai.community/TFA/V1.5/data/PhysiologicalSignalQualifier.json

4 Semantics

  1. Sub‑Types
    1. ECG (Electrocardiogram)
      1. Resting 12‑lead ECG
      2. Exercise / Stress ECG
      3. Signal‑Averaged ECG (SAE)
      4. Heart Rate Variability (HRV)
      5. Ambulatory ECG (Holter)
      6. Wearable ECG
    2. PPG (Photoplethysmography)
      1. Reflective PPG
      2. Transmissive PPG
      3. Multi‑wavelength PPG
      4. Wearable PPG
    3. EMG (Electromyography)
      1. Surface EMG (sEMG)
      2. Intramuscular EMG
      3. High‑density EMG
    4. EOG (Electrooculography)
      1. Horizontal/vertical EOG
      2. Blink detection EOG
      3. Saccade tracking EOG
    5. Ventilation
      1. Airflow
      2. Respiratory effort (thoracic/abdominal belts)
      3. Capnography (CO₂ waveform)
    6. GSR (Galvanic Skin Response)/ EDA (Electrodermal Activity)
      1. Skin conductance
      2. Skin resistance
      3. Tonic/phasic EDA
    7. Blood Pressure Waveform
      1. Arterial pressure waveform
      2. Pulse transit time waveform
      3. Continuous non‑invasive BP waveform
    8. Formats
    9. ECG Formats
    1. HL7 aECG (Annotated ECG)
    2. SCP‑ECG (Standard Communications Protocol for Computer‑Assisted Electrocardiography)
    3. DICOM‑ECG (DICOM Waveform for ECG)
    4. ecgML (XML‑based ECG format)
    5. mECGML (Mobile ECG Markup Language)
    6. ML‑ECG (Machine Learning ECG format)
    7. MFER (Medical Waveform Format Encoding Rules)
    8. Philips XML (Philips ECG XML format)
    9. ecgAware (ECG markup for ambulatory monitoring)
    10. EDF / EDF+ (General biosignal format)
    11. BDF (BioSemi Data Format)
    12. WFDB (PhysioNet waveform format)
  1. PPG Formats
    1. OpenSignals (Biosignal format used by BITalino and wearables)
    2. EDF / EDF+
    3. BDF
    4. WFDB
    5. HDF5 (Large biosignal datasets)
    6. PPG‑BDF (BioSemi PPG variant)
    7. PPG‑CSV/TSV (Common export formats)
  1. EMG Formats
    1. SENIAM‑compatible CSV/TSV (Standard EMG electrode placement & data conventions)
    2. EDF / EDF+
    3. BDF
    4. WFDB
    5. OpenSignals
    6. HDF5
    7. EMG‑MAT (MATLAB‑based EMG format)
  1. EOG Formats
    1. EDF / EDF+
    2. BDF
    3. WFDB
    4. OpenSignals
    5. HDF5
    6. EOG‑MAT
  1. Ventilation Formats
    1. EDF / EDF+
    2. WFDB
    3. DICOM‑Waveform (for capnography)
    4. HDF5
    5. Resp‑CSV/TSV
  1. GSR / EDA Formats
    1. OpenSignals
    2. EDF / EDF+
    3. WFDB
    4. HDF5
    5. EDA‑CSV/TSV
  1. Blood Pressure Waveform Formats
    1. DICOM‑Waveform
    2. WFDB
    3. EDF / EDF+
    4. HDF5
    5. BP‑CSV/TSV

Findings

Label Description
Findings What the data show, each Finding coded in a vocabulary of this domain: the labels a Neural Network Model learns from and is checked against.
FindingID Identifier of the Finding; the FindingTrust of AIH Data refers to it.
Code The Finding, as the Coding System writes it.
CodingSystem One of: SNOMEDCT, LOINC, ICD10, ICD11, DatasetLabelSet.
LabelSet The name of the label set when the CodingSystem is DatasetLabelSet (a data set’s own labels, e.g. NIH ChestX-ray14).
Where Where in the data the Finding is: Start, End (seconds from the start of the recording); Channels.

5 References