Related Experiment Video
Updated: May 25, 2025
05:03
Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function
Published on: December 11, 2019
8.6K
Automated loss of pulse detection on a consumer smartwatch
Kamal Shah1, Anran Wang1, Yiwen Chen1
1Google Research, Mountain View, CA, USA.
Nature
|February 26, 2025
Summary
A smartwatch algorithm using photoplethysmography can detect sudden loss of pulse, a key cardiac arrest sign. This technology aims to improve survival rates by enabling faster emergency medical response while minimizing false alarms.
Area of Science:
- Biomedical Engineering
- Cardiology
- Artificial Intelligence
Background:
- Out-of-hospital cardiac arrest is a critical emergency where rapid intervention is vital for survival.
- Sudden, unwitnessed cardiac arrest has a very low survival rate, emphasizing the need for timely detection and medical assistance.
- Automated detection systems must balance sensitivity with minimizing false positives to avoid overwhelming emergency services.
Purpose of the Study:
- To develop and validate a machine learning algorithm for a smartwatch to detect sudden loss of pulse, a primary indicator of cardiac arrest.
- To assess the algorithm's performance at a scale suitable for societal deployment.
- To evaluate the potential of wearable biosensors in improving cardiac arrest survivability.
Main Methods:
- Utilized photoplethysmography (PPG) signals from a smartwatch to identify patterns similar to pulselessness during cardiac arrest (ventricular fibrillation) and induced arterial occlusion.
- Developed and validated a loss of pulse detection algorithm using data from peripheral pulselessness and real-world (free-living) conditions.
- Conducted prospective evaluations of the end-to-end algorithm in simulation and real-world settings.
Main Results:
- The developed algorithm demonstrated that wearable PPG signals during induced pulselessness resemble those during ventricular fibrillation.
- Prospective evaluation showed an unintentional emergency call rate of 1 per 21.67 user-years.
- The algorithm achieved a sensitivity of 67.23% in a prospective cardiac arrest simulation model.
Conclusions:
- A multimodal, machine learning algorithm integrated into a smartwatch shows promise for detecting sudden loss of pulse.
- The technology is potentially deployable at a societal scale, offering an opportunity to improve cardiac arrest outcomes.
- The system demonstrates a balance between detecting critical events and minimizing the societal cost of false alarms.
More Related Videos
Related Concept Videos
01:30Pulse rhythm
750
Pulse rhythm refers to the pattern of pulsations within specific intervals, offering valuable insights into the regularity or irregularity of the heart's beats as observed through the pattern of pulsation within specific intervals. A regular pulse exhibits a consistent heart rate with uniform waveforms and pulsation force, variations of which can be classified as normal, weak, or bounding.
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
750
01:13Special considerations while measuring pulse
551
Assessing a patient's pulse is a fundamental skill in healthcare, but certain situations require special attention:
551
01:16Pulse
415
When the heart pumps blood out, arterial elastic fibers play a crucial role in sustaining a high-pressure gradient. They expand to accommodate the received blood and then recoil - a process known as the pulse that can be either manually palpated or electronically quantified. Despite a reduction in its effect with increased distance from the heart, elements of the pulse's systolic and diastolic components persist, observable even at the arteriole level.
The pulse serves as a clinical...
The pulse serves as a clinical...
415
01:30Equipments Used To Measure Blood Pressure
787
Direct Method
This invasive approach involves cannulating a peripheral artery. During each cardiac contraction, pressure generates mechanical motion within the catheter, transmitted through rigid, fluid-filled tubing to a transducer. This transducer converts mechanical motion into electrical signals displayed as waveforms on a monitor. An automatic flushing system prevents blood backflow. Due to the potential risk of unexpected arterial blood loss, this method is primarily used in intensive...
This invasive approach involves cannulating a peripheral artery. During each cardiac contraction, pressure generates mechanical motion within the catheter, transmitted through rigid, fluid-filled tubing to a transducer. This transducer converts mechanical motion into electrical signals displayed as waveforms on a monitor. An automatic flushing system prevents blood backflow. Due to the potential risk of unexpected arterial blood loss, this method is primarily used in intensive...
787
01:25Assessment of apical radial pulse
710
Apical-Radial (A-R) Pulse Assessment
The A-R pulse assessment involves simultaneous evaluation of the apical and radial pulses. When the apical and radial pulse rates vary, this assessment helps identify a pulse deficit.
Pre-Procedural Preparation
The A-R pulse assessment involves simultaneous evaluation of the apical and radial pulses. When the apical and radial pulse rates vary, this assessment helps identify a pulse deficit.
Pre-Procedural Preparation
710
01:11Assessment of radial pulse
780
Assessment of Radial Pulse
The radial pulse, located at the wrist, is often the preferred site for assessing peripheral pulse because of its accessibility and dependability. The process of determining the radial pulse involves several steps:
The radial pulse, located at the wrist, is often the preferred site for assessing peripheral pulse because of its accessibility and dependability. The process of determining the radial pulse involves several steps:
780