CTG Scan Duration Prediction Using Motion Artifact Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing CTG scanning sessions, particularly with eCTG, are susceptible to noise and signal dropouts, making it difficult to determine the required duration for acquiring sufficient and quality fetal heart rate data, especially in home-based monitoring where untrained users conduct the scans.

Innovation Solution

A method and system that analyze CTG data and movement data during the scanning session to identify artifacts, leveraging machine learning algorithms to predict the remaining duration needed to obtain adequate fetal heart rate data, using sensors like accelerometers and ECG devices to improve signal quality and duration estimation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If CTG scanning session duration is extended to obtain sufficient quality data, then measurement precision is improved, but loss of time increases

Engineering Contradiction:
ImproveCTG data qualityVSAvoidscanning session duration
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of CTG signals during the scanning session to predict future signal quality and determine the remaining duration needed to acquire sufficient data. By continuously monitoring signal characteristics and using machine learning models to forecast data quality, the system can stop the scanning session once adequate data is collected, avoiding unnecessary time extension while ensuring measurement precision requirements are met.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms where acquired CTG data is continuously analyzed and used to update predictions about remaining session duration. The machine learning model processes real-time signal characteristics and provides feedback on data quality trends, allowing the system to dynamically adjust the scanning session duration based on actual signal acquisition progress rather than using fixed time parameters.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If skilled healthcare professionals manually assess CTG data to determine session duration, then measurement precision is improved, but device complexity and labor requirements increase

Engineering Contradiction:
Improvesession duration assessment accuracyVSAvoidassessment process complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system enables self-service by automatically assessing CTG data quality and predicting remaining session duration without requiring skilled healthcare professionals. The machine learning model independently analyzes signal characteristics, identifies artifacts, and determines when sufficient data has been acquired, freeing the system from human intervention while maintaining assessment accuracy.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical system of manual professional assessment with an automated computational system. Machine learning algorithms process CTG signals, detect artifacts, and predict session duration requirements, substituting human expertise with algorithmic analysis that achieves comparable or superior precision while eliminating labor intensity and professional dependency.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Ease of operation

If CTG scanning is performed in home-based settings with untrained users, then ease of operation is improved, but measurement precision deteriorates due to lack of professional assessment

Engineering Contradiction:
Improveuser accessibilityVSAvoiddata quality assessment
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system enables home-based users to conduct CTG monitoring independently with automated quality assessment. The machine learning model continuously evaluates the data quality in real-time, detecting artifacts and predicting when sufficient data has been collected, eliminating the need for professional intervention while maintaining reliable measurement precision.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system provides continuous feedback to home-based users about data quality status and estimated remaining session duration. The machine learning model monitors signal characteristics and communicates with users about acquisition progress, guiding them through the scanning process and ensuring adequate data collection without requiring professional expertise.

Inventive Principle:
Principle #23Feedback

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables accurate and automatic prediction of the scanning session duration, reducing the need for skilled professionals and improving the usability of CTG data for diagnostic purposes, especially in remote or home-based settings.

Implementation Method 1

obtaining movement data describing a movement of the subject during the CTG scanning session

Methodology Applied
Scientific EffectAccelerometer: Accelerometer

Implementation Method 2

CTG data and movement data of the subject during the scanning session are obtained

Methodology Applied
Scientific EffectElectrical signal detection: Electric Field

Data Source

PatentEP4615331B1Cardiotocographic scanning session duration
Publication Date: 2026.03.18 KONINKLIJKE PHILIPS NV
  • EP4615331B1 patent drawingFigure 1
  • EP4615331B1 patent drawingFigure 2
  • EP4615331B1 patent drawingFigure 3

AI summary

Proposed concepts aim to provide schemes, solutions, concepts, designs, methods and systems pertaining to predicting a remaining duration of a cardiotocograph (CTG) scanning session of a subject. In particular, CTG data and movement data of the subject during the scanning session are obtained. This data is then analysed to identify artifacts in the CTG data associated with movement of the subject. From the CTG data, movement data and artifacts, a remaining duration of the CTG scanning session can be predicted. In this way, despite the potential for signal drop-outs during the scanning session, acquisition of a sufficient amount of CTG data during the scanning session may be assured.