A machine learning model to detect falls mimicking cardiac arrest-related collapse based on wristderived accelerometry: the DETECT-2 study

Roos Edgar, Kambiz Ebrahimkheil, Danny Meeuwsen, Maud C. de Jong,
Job J. Herrmann, Alexander M. Griffioen, Niels T.B. Scholte,
Marc A. Brouwer, Rypko J. Beukema, Eelko Ronner, Eric Boersma,
Aysun Cetinyurek-Yavuz, Peter C. Stas, Claudine J.C. Lamoth,
Niels van Royen, and Judith L. Bonnes

A machine learning model to detect falls mimicking cardiac arrest-related collapse based on wrist-derived accelerometry

In the DETECT-2 study, accelerometry data recorded with the Corsano CardioWatch wristband were used to develop a machine learning model for the detection of cardiac arrest-related collapse, with the goal of improving the performance of wearable-based automated cardiac arrest detection.

Aims
In wearable-based automated cardiac arrest detection technology, photoplethysmography (PPG) is the most commonly used sensor to detect the absence of pulsations. To minimize false-positive cardiac arrest alerts, accelerometry signals are often used for the detection of ongoing movement. We conducted the DETECT-2 study to develop an accelerometer-based machine learning model for the detection of cardiac arrest-related collapse, which is often a first manifestation of cardiac arrest.

Methods and results
Healthy volunteers simulated cardiac arrest-related collapses through sudden and soft falls without subsequent movement. Accelerometer signals were collected using the CardioWatch wristband; video recordings were made as a reference. An accelerometer-based gradient boosting model (GBM) for fall detection was trained (70%) and tested (30%). The primary endpoint was the sensitivity for the detection of falls; secondary endpoints were false-positive fall alerts. Nineteen participants performed 567 falls. In the training set (n =13; 388 falls), the sensitivity of the GBM was 99.2% (95% confidence interval [CI] 98–100%], with four false positives. In the test set (n = 6; 179 falls), sensitivity was 96.1% (95% CI 92–98%), with two false positives. For sudden falls (n = 120) and soft falls (n = 59), sensitivities were 100% (95% CI 96–100%) and 88.1% (95% CI 76–95%) in the test set (P < 0.001), respectively.

Conclusion
Using accelerometry data from the CardioWatch, sudden and soft falls that mimic cardiac arrest-related collapse can be accurately detected. The next step in the development of automated cardiac arrest detection is the integration of accelerometer signals into the existing PPG-based model, with the aim of reducing false positives and increasing sensitivity in everyday use.