A Comparative Analysis of Signal Quality and Morphological Fidelity in ECG Smartwatches
- 1Delve Health
Abstract
This study provides a direct objective comparison of the ECG signal quality and morphological features preservation of four leading commercial smartwatches: the Apple Watch Series 9, Samsung Galaxy Watch 6, Fitbit Sense 2, and Withings ScanWatch, using a controlled dataset. The Philips TC30 is used as the reference standard. ECG signal quality is assessed through Signal-to-Noise Ratio (SNR), Standard Deviation of Baseline Wander and Power Spectral Density (PSD), while the preservation of the morphological features is assessed through comparing the performance differences of our J-point and ST deviation automatic detection algorithms when run on each watchs recordings separately. J-point detection is assessed by comparing each devices performance against the reference device, while ST deviation is assessed using simulator defined ground truth values. The Apple Watch and Withings ScanWatch had the best SNR, while the Samsung Galaxy Watch had much lower values. The Withings ScanWatch had the most stable baseline, while the Fitbit Sense 2 had the most variable baseline. All devices showed a consistent negative bias in J-point detection, which suggests that internal signal processing tends to smooth out small changes in waveforms. For ST-segment classification, the Apple Watch achieved the most balanced performance across sensitivity and specificity. These results give researchers and clinicians data-driven advice on how to choose the best device for their specific needs.
Related
- Quality, readability, and information fidelity of large language model–generated versus physician-authored informed-consent content for targeted therapies: a blinded, paired comparative study
- Visual fidelity–driven quality assessment of medical image translation
- Performance of GPT-4o in CT-based crista galli morphological classification: image-only versus morphometric dataset-driven approaches: a controlled comparative study
- Application of smartwatches in the wireless monitoring of patients in radiation-controlled areas: a pilot study
- Gynecological malignancy signal triage: A two-dimensional framework integrating US-derived FAERS data with comparative US–China GBD trajectories
BibTeX
@misc{muhammed2026comparative,
title = {{A Comparative Analysis of Signal Quality and Morphological Fidelity in ECG Smartwatches}},
author = {S. M. Muhammed and N. A. Omran and S. Sowelam},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.09.26362599},
url = {https://www.medrxiv.org/content/10.64898/2026.09.09.26362599v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - A Comparative Analysis of Signal Quality and Morphological Fidelity in ECG Smartwatches
AU - S. M. Muhammed
AU - N. A. Omran
AU - S. Sowelam
PY - 2026
DA - 2026/09/09
PB - medRxiv
DO - 10.64898/2026.09.09.26362599
UR - https://www.medrxiv.org/content/10.64898/2026.09.09.26362599v1
AB - This study provides a direct objective comparison of the ECG signal quality and morphological features preservation of four leading commercial smartwatches: the Apple Watch Series 9, Samsung Galaxy Watch 6, Fitbit Sense 2, and Withings ScanWatch, using a controlled dataset. The Philips TC30 is used as the reference standard. ECG signal quality is assessed through Signal-to-Noise Ratio (SNR), Standard Deviation of Baseline Wander and Power Spectral Density (PSD), while the preservation of the morphological features is assessed through comparing the performance differences of our J-point and ST deviation automatic detection algorithms when run on each watchs recordings separately. J-point detection is assessed by comparing each devices performance against the reference device, while ST deviation is assessed using simulator defined ground truth values. The Apple Watch and Withings ScanWatch had the best SNR, while the Samsung Galaxy Watch had much lower values. The Withings ScanWatch had the most stable baseline, while the Fitbit Sense 2 had the most variable baseline. All devices showed a consistent negative bias in J-point detection, which suggests that internal signal processing tends to smooth out small changes in waveforms. For ST-segment classification, the Apple Watch achieved the most balanced performance across sensitivity and specificity. These results give researchers and clinicians data-driven advice on how to choose the best device for their specific needs.
ER -