Key result
Deep learning model accurately estimates ultra-short term HRV from 10-s PPG segments versus ECG references.
Why the study?
Continuous ICU HRV tracking via extended ECG monitoring has limited applicability, creating a need for rapid HRV measurement from a single unobtrusive sensor.
Does an end-to-end deep learning model using 10-s PPG signals accurately estimate ultra-short term heart rate variability compared to ECG-based references in ICU patients?
Does an end-to-end deep learning model using 10-s PPG signals accurately estimate ultra-short term heart rate variability compared to ECG-based references in ICU patients?
An end-to-end deep learning model can accurately estimate ultra-short term heart rate variability from 10-second PPG signals, offering a promising unobtrusive monitoring method for ICU patients.
Answers are grounded in this paper and cite their sources.
Supports PPG-based ultra-short HRV monitoring in ICU; hypothesis-generating pending prospective validation.
Heart rate variability (HRV) is a marker that could be indicative of critical health events. Continuous monitoring of HRV in intensive care unit (ICU) holds great promise for improving patient's prognosis. However, current methods requiring measuring HRV using electrocardiogram (ECG) sensors over an extended duration offer limited applicability for continuous and disturbance-free HRV tracking in ICU cases. This underscores the need for new methods that can rapidly measure HRV from a single unobtrusive sensor. Here, we explore the feasibility of using an end-to-end deep learning model to enable real-time ultra-short term HRV (usHRV) estimation from 10-s segments of photoplethysmogram (PPG) signal, acquired from an optical sensor commonly present in ICU settings. Validated on testing data from hold-out ICU subjects, the results from our deep learning model are in excellent agreement with the ECG-based references for estimating usHRV metrics, achieving R-squared scores of 1.00, 0.89 and 0.93 in estimating MeanNN, SDNN and RMSSD, respectively. Furthermore, our model outperforms PPG-based manually-extracted pulse rate variability (PRV), an HRV surrogate, in both accuracy and robustness. Overall, our study offers a promising perspective for the use of small-scale deep learning models in achieving reliable usHRV tracking in intensive care scenarios.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2024) studied Intensive care unit (ICU) patients requiring heart rate variability monitoring. End-to-end deep learning model using 10-s segments of photoplethysmogram (PPG) signal vs. ECG-based references and PPG-based manually-extracted pulse rate variability (PRV) was evaluated on Estimation of ultra-short term HRV (usHRV) metrics (MeanNN, SDNN, RMSSD) (R-squared scores of 1.00, 0.89 and 0.93 for MeanNN, SDNN and RMSSD). An end-to-end deep learning model using 10-s PPG segments accurately estimated ultra-short term HRV metrics compared to ECG references, achieving R-squared scores of 1.00, 0.89, and 0.93.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: