Ensemble Risk Scoring for Acute Coronary Triage

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current risk scoring systems for acute coronary syndromes in emergency departments lack accuracy and are insufficiently sensitive and specific, particularly in identifying high-risk patients, due to limitations in traditional clinical factors and subjective clinical judgment.

Innovation Solution

A system incorporating a 12-lead electrocardiogram (ECG) and heart rate variability (HRV) analysis, combined with an ensemble-based scoring system using weighted classifiers trained on past patient data, to determine a risk score by comparing physiological and ECG parameters.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional clinical factors and subjective clinical judgment are used for risk scoring, then the system is simple to operate, but the prediction accuracy and sensitivity for identifying high-risk patients deteriorates

Engineering Contradiction:
Improveprediction accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the risk assessment into multiple independent components: traditional clinical factors, ECG parameters, and HRV parameters. Each component is analyzed separately by dedicated modules, and their results are integrated to form a comprehensive risk score. This segmentation allows the system to incorporate complex parameters without overwhelming operational complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an automated analysis system as an intermediary between raw clinical data and risk assessment. This intermediary processes ECG and HRV data, extracts relevant parameters, and integrates them with clinical factors, thereby improving prediction accuracy while shielding operators from the complexity of the underlying analysis.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If more parameters are included in the risk scoring system, then the prediction accuracy improves, but the measurement and data processing complexity increases

Engineering Contradiction:
Improveprediction accuracyVSAvoidparameter measurement difficulty
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The system performs preliminary automated processing of ECG and HRV data before clinical interpretation. The ECG analysis module and HRV analysis module pre-extract and organize multiple parameters automatically, so that when clinicians review the data, the complex measurement and processing work has already been completed, reducing the perceived difficulty.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements self-service through automated data collection and analysis. The ECG device automatically records and analyzes cardiac electrical activity, the HRV module automatically processes heart rate variability, and the analysis module automatically integrates all parameters. This self-service capability handles the measurement complexity without requiring manual intervention for each parameter.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP2964077B1System of determining a risk score for triage
Publication Date: 2023.06.07 SINGAPORE HEALTH SERVICES PTE LTD
  • EP2964077B1 patent drawingFigure 1
  • EP2964077B1 patent drawingFigure 2
  • EP2964077B1 patent drawingFigure 3A~3C

AI summary

The present disclosure provides a system and method of determining a risk score for triage. In particular, a system is provided for providing an assessment of risk of a cardiac event for a patient, for example an incoming patient to a hospital emergency department complaining of chest pain. In the disclosure, the system includes an input device for measuring physiological data based vital signs parameter of the patient, a twelve-lead electrocardiogram (ECG) device for establishing an ECG obtained from results of the electrocardiography procedure, and determining an ECG parameter and a heart rate variability (HRV) parameter therefrom. An ensemble-based scoring system is further provided, establishing weighted classifier based on past patient data and where the vital signs parameter, the ECG parameter and the HRV parameter are compared to corresponding weighted classifiers to determine a risk score. A corresponding method to determine a risk score for triage is also provided.