Key result
A novel deep learning model incorporating activity count and HRV metrics achieved 84.5% accuracy in detecting sleep epochs, outperforming existing UCSD and Actiwatch algorithms.
Why the study?
Wrist actigraphy performance depends on interpretative algorithms, prompting the development of a novel deep learning algorithm combining activity count and heart rate variability to improve sleep quality assessment.
Does a novel deep learning model using activity count and HRV improve sleep scoring performance compared to existing algorithms in participants undergoing sleep monitoring?
Observational (n=222)
Does a novel deep learning model using activity count and HRV improve sleep scoring performance compared to existing algorithms in participants undergoing sleep monitoring?
A novel deep learning algorithm combining activity count and heart rate variability significantly improves sleep scoring performance compared to existing actigraphy algorithms.
Combining activity and HRV may improve automated sleep scoring; leaves open whether this deep learning approach translates.
Background: Performance of wrist actigraphy in assessing sleep not only depends on the sensor technology of the actigraph hardware but also on the attributes of the interpretative algorithm (IA). The objective of our research was to improve assessment of sleep quality, relative to existing IAs, through development of a novel IA using deep learning methods, utilizing as input activity count and heart rate variability (HRV) metrics of different window length (number of epochs of data). Methods: Simultaneously recorded polysomnography (PSG) and wrist actigraphy data of 222 participants were utilized. Classic deep learning models were applied to: (a) activity count alone (without HRV), (b) activity count + HRV (30-s window), (c) activity count + HRV (3-min window), and (d) activity count + HRV (5-min window) to ascertain the best set of inputs. A novel deep learning model (Haghayegh Algorithm, HA), founded on best set of inputs, was developed, and its sleep scoring performance was then compared with the most popular University of California San Diego (UCSD) and Actiwatch proprietary IAs. Results: Activity count combined with HRV metrics calculated per 5-min window produced highest agreement with PSG. HA showed 84.5% accuracy (5.3–6.2% higher than comparator IAs), 89.5% sensitivity (6.2% higher than UCSD IA and 6% lower than Actiwatch proprietary IA), 70.0% specificity (8.2–34.3% higher than comparator IAs), and 58.7% Kappa agreement (16–23% higher than comparator IAs) in detecting sleep epochs. HA did not differ significantly from PSG in deriving sleep parameters—sleep efficiency, total sleep time, sleep onset latency, and wake after sleep onset; moreover, bias and mean absolute error of the HA model in estimating them was less than the comparator IAs. HA showed, respectively, 40.9% and 54.0% Kappa agreement with PSG in detecting rapid and non-rapid eye movement (REM and NREM) epochs. Conclusions: The HA model simultaneously incorporating activity count and HRV metrics calculated per 5-min window demonstrates significantly better sleep scoring performance than existing popular IAs.
No takes yet. Share an insight, caveat, or question.
Haghayegh et al. (2020) conducted an observational in Sleep assessment (n=222). Haghayegh Algorithm (HA) using activity count and HRV vs. UCSD and Actiwatch proprietary algorithms was evaluated on Accuracy in detecting sleep epochs compared to polysomnography. A novel deep learning model incorporating activity count and HRV metrics achieved 84.5% accuracy in detecting sleep epochs, outperforming existing UCSD and Actiwatch algorithms.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: