Wearable Cardioverter Defibrillator Audio Capture for Event Recording
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wearable cardioverter defibrillators (WCDs) face challenges in capturing and recording ambient sounds and patient voice commands effectively, which are crucial for understanding the patient's condition during a medical event, and existing systems struggle to accurately record and store relevant audio data for clinical review.
Innovation Solution
Incorporating a microphone on the same dongle as the cancel switch of the WCD, allowing patients to trigger audio recording through voice commands, which is then continuously recorded and stored as an exportable computer file, including both audio and ECG data, to enhance the accuracy and completeness of the patient's medical record.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If a microphone is added to the WCD system to capture ambient sounds and voice commands, then the ability to record and understand patient condition improves, but the device complexity increases
Solution Approach 1:
The microphone is integrated into the existing WCD dongle assembly, combining audio capture functionality with the cardiac monitoring system. This merging approach allows the microphone to share the same housing, power source, and data transmission infrastructure as the ECG electrodes, thereby improving audio data capture without proportionally increasing overall system complexity
Solution Approach 2:
The WCD dongle is designed to perform multiple functions: cardiac rhythm monitoring via ECG electrodes and ambient sound/voice command capture via the microphone. This multi-functionality allows a single device to gather both physiological and environmental audio data, reducing the need for separate dedicated recording devices and minimizing additional system complexity
2Loss of information
If continuous audio recording is implemented to capture all ambient sounds, then the completeness of medical record improves, but the energy consumption and data storage requirements increase
Solution Approach 1:
The system continuously monitors audio input and pre-identifies potential events of interest (such as voice commands or abnormal sounds) before full recording is triggered. This preliminary detection allows the system to maintain low-power standby mode most of the time while still being ready to capture complete audio data when clinically relevant events occur
Solution Approach 2:
Instead of continuous high-power recording, the system employs periodic sampling and event-triggered recording. The microphone continuously listens at low power, and only initiates full audio capture when specific acoustic patterns or voice commands are detected, thereby maintaining recording completeness for critical events while significantly reducing overall energy consumption
3Ease of operation
If voice command recognition is added to enable patient-triggered recording, then the ease of operation improves, but the measurement precision of voice commands may deteriorate in noisy environments
Solution Approach 1:
The system employs signal processing algorithms and noise filtering as intermediaries between the microphone input and voice command recognition. These intermediaries pre-process the audio signal to enhance speech components and suppress background noise, thereby maintaining high voice command accuracy even in noisy hospital environments while preserving ease of patient operation
Solution Approach 2:
The voice recognition system is trained on patient-specific voice patterns and adapts to individual speech characteristics. This self-adjusting capability allows the system to maintain high recognition accuracy for each patient's unique voice commands without requiring manual calibration or external assistance, thereby preserving both ease of operation and measurement precision
Data Source
AI summary
A Wearable Medical System (WMS) that implements a wearable cardioverter defibrillator (WCD), includes a microphone and related improvements. The microphone can be on the same dongle as the cancel switch of the WCD. A user trigger module may permit the patient to perform a deliberate act and, in response, the system may start recording audio from the ambient sounds, including their own voice, and/or start recording the ECG. The deliberate act may even be a voice command by the patient that is parsed by a voice recognition module. The WMS may continuously record audio and then continuously discard it, and further stop the discarding if it detects a recording trigger. The WMS may create an exportable computer file that has audio-related data, which can have playable sound data or transcribed voice data.