Catheter Position Classification Using Diaphragm Bioelectrical Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for accurately positioning nasogastric catheters, particularly in sedated patients, are hindered by the dominance of electrocardiographic signals over electromyographic signals, leading to difficulty in detecting correct placement and reliance on continuous clinician attention, with inexperienced clinicians facing challenges in fine-tuning catheter position.
Innovation Solution
A machine learning algorithm trained using bioelectrical signals from a catheter, divided into subsets based on relative position to the diaphragm, with data balancing and filtering techniques to enhance accuracy and reduce reliance on electromyographic signals, allowing for continuous and automatic catheter position monitoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If electrocardiographic signals are used for catheter positioning assessment, then continuous monitoring is possible, but the signals are 1000 times stronger than electromyographic signals making it difficult to detect correct placement
Solution Approach 1:
The patent segments the monitoring task into two distinct signal analysis components: electromyographic signal detection for diaphragm positioning and electrocardiographic signal analysis for confirmation. By separating the detection of these overlapping signals, the system can identify the specific EMG pattern that indicates correct catheter placement at the diaphragm while using ECG as supplementary verification, thereby resolving the signal detection difficulty.
Solution Approach 2:
The patent introduces an intermediary algorithm that processes and distinguishes between EMG and ECG signals. This intermediary system analyzes signal characteristics, identifies EMG patterns specific to diaphragm contraction, and filters out the dominant ECG interference, enabling accurate catheter positioning assessment even when ECG signals are 1000 times stronger than the target EMG signals.
2Measurement precision
If clinician monitoring is used for catheter positioning, then positioning assessment can be performed, but continuous attention is required and inexperienced clinicians struggle with fine-tuning
Solution Approach 1:
The patent implements a self-service monitoring system where the catheter itself performs the positioning assessment through integrated sensors that automatically detect EMG and ECG signals. The system processes the signals through algorithms that identify correct placement without requiring clinician interpretation, thereby eliminating the need for continuous clinician attention and removing the skill-dependent variability in positioning accuracy.
Solution Approach 2:
The patent replaces the mechanical system of manual clinician monitoring with an automated electronic monitoring system. Sensors embedded in the catheter continuously record bioelectrical signals, and processing algorithms automatically analyze these signals to determine catheter position, substituting the clinician's visual and manual assessment with an objective, continuous electronic measurement system that does not require human attention or expertise.
3Reliability
If electromyographic signals are used for positioning assessment, then correct catheter placement can be identified, but sedated patients who are not breathing spontaneously do not generate these signals
Solution Approach 1:
The patent creates a universal monitoring system that can operate in multiple patient conditions by implementing dual signal detection: electromyographic signals for patients with spontaneous breathing and electrocardiographic signals for patients without spontaneous breathing. The system automatically adapts its detection methodology based on the patient's respiratory status, ensuring reliable catheter placement assessment across all patient populations including those on mechanical ventilation.
Solution Approach 2:
The patent implements a dynamic monitoring system that adapts its signal detection strategy based on real-time patient condition. When EMG signals are detected (spontaneous breathing), the system uses them for positioning assessment; when EMG signals are absent (mechanical ventilation), the system dynamically switches to using ECG signal patterns for catheter placement determination, thereby maintaining reliability across varying patient states.
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
The solution provides accurate, continuous, and automatic catheter positioning, reducing the risk of complications and enabling reliable bioelectrical signal sourcing for ventilation systems, while minimizing the need for costly or time-consuming verification methods.
Implementation Method 1
The sensors can measure electrocardiographic signals and electromyographic signals emanating from nearby muscles within the body
Implementation Method 2
The sensors can measure electrocardiographic signals and electromyographic signals emanating from nearby muscles within the body
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure relates to position monitoring of medical devices, and more specifically to technologies for enabling the automatic monitoring of a position of a catheter in relation to a diaphragm. Aspects of the disclosure comprises determining training data to be used for training a machine learning algorithm to classify a position of a catheter in relation to a diaphragm of a patient. Further aspects of the disclosure comprising using a trained machine learning algorithm for classifying a position of a catheter in relation to a diaphragm of a patient.