Biometric Signal Analysis for Uterine Contraction Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current prenatal monitoring technologies, such as non-invasive cardiotocography and invasive fetal scalp electrodes, lack specificity and reliability, leading to adverse maternal and fetal outcomes, including unnecessary cesarean sections and inaccurate detection of fetal hypoxia.
Innovation Solution
A system comprising a wearable device with sensors to capture maternal and fetal biometric signals, including ECG, EMG, and acoustic signals, combined with a cloud-based monitoring system using machine learning models to analyze data and predict maternal and fetal outcomes, providing real-time feedback to clinicians.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If non-invasive cardiotocography is used for prenatal monitoring, then maternal and fetal safety is improved by avoiding invasive procedures, but measurement precision and reliability deteriorate leading to inaccurate detection of fetal hypoxia and unnecessary cesarean sections
Solution Approach 1:
The patent segments the monitoring task into multiple specialized sensors: acoustic sensors for fetal heart rate detection, pressure sensors for uterine contraction monitoring, and motion sensors for maternal activity tracking. This segmentation allows each sensor to optimize for its specific function while collectively providing comprehensive monitoring with improved accuracy without invasive procedures
Solution Approach 2:
The patent merges multiple sensing modalities (acoustic, pressure, motion, temperature) into a single integrated non-invasive monitoring system. By combining these different measurement approaches, the system achieves high measurement precision for detecting fetal hypoxia and uterine contractions while maintaining maternal and fetal safety through non-invasive means
2Measurement precision
If invasive fetal scalp electrodes are used for monitoring, then measurement precision of fetal cardiac activity is improved, but object-generated harmful factors increase due to risk of infection, hemorrhage, and fetal injury
Solution Approach 1:
The patent replaces the mechanical invasive electrode insertion with non-invasive acoustic sensing technology. Acoustic sensors detect fetal heart sounds through the maternal abdomen, eliminating the need for physical penetration of the fetal scalp while achieving sufficient measurement precision for clinical decision-making
Solution Approach 2:
The patent introduces acoustic waves as an intermediary medium to transmit fetal cardiac information from the fetus to the external sensors. This acoustic mediation allows precise monitoring of fetal cardiac activity without direct physical contact or invasion of the fetal body, thereby eliminating risks of infection and injury
3Reliability
If multiple biometric signals are collected and analyzed using machine learning, then measurement precision and reliability of fetal and maternal well-being assessment is improved, but device complexity and computational requirements increase
Solution Approach 1:
The patent performs preliminary processing of biometric signals at the sensor level, including noise filtering, signal normalization, and feature extraction before transmission to the cloud. This preliminary action reduces the complexity of cloud-based machine learning models by providing pre-processed, high-quality input data, thereby maintaining high reliability while managing system complexity
Solution Approach 2:
The patent implements feedback loops where machine learning model predictions are continuously refined based on new incoming biometric data and clinical outcomes. This feedback mechanism improves assessment reliability over time while the system learns to prioritize the most informative signals, effectively managing computational complexity through adaptive optimization
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
Enhances the accuracy of monitoring maternal and fetal health during labor and delivery, reducing unnecessary interventions and improving timely decision-making by clinicians, thereby minimizing adverse outcomes and healthcare costs.
Implementation Method 1
The one or more sensors are configured to capture, for example, ECG signals indicative of maternal and/or fetal cardiac activity
Implementation Method 2
EMG signals indicative of uterine contractions
Implementation Method 3
maternal and/or fetal acoustic biometric signals
Data Source
AI summary
The disclosure describes a system comprising: a memory; and one or more processors in communication with the memory. The one or more processors are configured to: receive, from a set of sensors, biometric data indicative of a muscle contraction of a patient over a period of time; and determine, based on the biometric data, a muscle contraction vector indicating a direction of the muscle contraction over the period of time. Additionally, the one or more processors are configured to determine, based on the biometric data, a likelihood that the muscle contraction comprises a true labor uterine contraction; and output, for display by a user device, the muscle contraction vector indicating the direction of the muscle contraction and the likelihood that the muscle contraction comprises a true labor uterine contraction.