eess.SPOct 16, 2026
SaveECG-SDI: Single-lead Electrocardiogram Enables Continuous Sleep Depth Index Profiling and Scalable Digital Biomarkers for Sleep Health
Organizations: Institute of Medical Technology, Peking University Health Science Center, Beijing, China · National Institute of Health Data Science, Peking University, Beijing, China · Department of Computer Science, Tianjin University of Technology, Tianjin, China · Department of Statistics and Data Science, Tsinghua University, Beijing, China ·
Abstract
Conventional sleep staging provides a coarse-grained representation that obscures within-stage depth variation. We developed ECG-SDI, a single-lead electrocardiography (ECG) framework for continuous sleep-depth profiling and digital biomarker extraction. Using 12,392 overnight polysomnographic recordings, we trained and validated a two-stage deep learning model supervised by conventional sleep-stage labels. Correlations with ordered stages excluding rapid eye movement (REM) sleep were 0.828 in the pooled internal test set and 0.848 in the external Cleveland Family Study; corresponding REM classification AUROCs were 0.954 and 0.977. Overnight trajectories captured within-stage variation. Biomarker-based phenotyping identified a disturbed subtype associated with poorer subjective sleep quality and higher all-cause mortality in the Sleep Heart Health Study (adjusted hazard ratio, 1.20; 95% CI, 1.05-1.38). Among 507 participants with paired recordings before and after continuous positive airway pressure (CPAP), normalized sleep-depth area increased by 6.1% and shallow-sleep burden below 0.3 decreased by 16.0%. Exploratory analyses linked reductions in approximate entropy and depth variability to reduced oxygen desaturation and increased sleep efficiency, respectively (Spearman rho = 0.24 and 0.12); both associations remained positive after covariate adjustment. Mean ECG-SDI within N2 increased by 0.017 (95% CI, 0.004-0.030). A wearable proof-of-concept illustrated the acquisition-to-report workflow. These findings support ECG-based sleep phenotyping and further evaluation of CPAP response monitoring at home.
Figures & tables
Figure 1: Overall study framework and analytical pipeline. a, Single-lead ECG was extracted from multi-cohort PSG recordings to construct internal datasets for model development (SHHS, MESA, and MrOS) and fully independent external validation datasets (CFS and BZ-CPAP). b, A two-stage neural network was used to learn a continuous sleep depth index (ECG-SDI) from raw ECG under supervision from conventional discrete sleep-stage labels, thereby transforming coarse-grained sleep staging into a continuous representation of sleep depth. c, Digital biomarkers were then derived from whole-night ECG-SDI trajectories and used for sleep-phenotype clustering, clinical risk stratification, and tracking CPAP treatment effects, enabling systematic evaluation of the physiological relevance, clinical utility, and treatment responsiveness of ECG-SDI.
| Cohort | Corr. SS (excl. REM) | REM class. AUROC |
| Pooled internal test | 0.828 (0.827–0.828) | 0.954 (0.953–0.954) |
| Internal SHHS | 0.730 (0.729–0.732) | 0.908 (0.907–0.909) |
| Internal MESA | 0.797 (0.796–0.798) | 0.934 (0.933–0.935) |
| Internal MrOS | 0.882 (0.882–0.883) | 0.987 (0.987–0.988) |
| External CFS | 0.848 (0.847–0.849) | 0.977 (0.976–0.977) |
| External BZ-CPAP (pre-CPAP) | 0.456 (0.453–0.459) | 0.803 (0.802–0.805) |
Table 1: Performance of ECG-SDI for sleep-depth ordering and REM classification in internal and external cohorts. Corr. SS (excl. REM), correlation between ECG-SDI and ordered sleep stages excluding REM; REM class. AUROC, area under the receiver operating characteristic curve for REM classification. Values are reported as point estimates with corresponding uncertainty intervals.
Figure 2: Whole-night ECG-SDI trajectories and within-stage ECG examples in the external CFS cohort. A,B, Conventional hypnograms (upper panels) and corresponding ECG-SDI trajectories (lower panels) for a lower-AHI recording ( A ; cfs-visit5-802076) and an OSA recording ( B ; cfs-visit5-801193). REM epochs are highlighted in red, and wake/NREM epochs are shown in blue. Insets report total sleep time (TST), sleep efficiency (SE), apnea–hypopnea index (AHI), normalized area under the depth curve (AP), and area under the depth curve (AUC). C–E, Representative 30-s ECG segments from REM ( C ; cfs-visit5-800129), N1 ( D ; cfs-visit5-802137), and N2 ( E ; cfs-visit5-801622). Within each row, three epochs from the same participant and conventional sleep stage are arranged in ascending order of ECG-SDI. Each segment is annotated with its epoch identifier, stage, SDI value, and heart rate (HR; beats min -1 ). The labels shallow, medium, and deep indicate relative positions on the ECG-SDI scale within the illustrated stage and do not represent additional conventional sleep stages.
Figure 3: Clinical profiles and all-cause mortality associated with ECG-SDI-derived sleep phenotypes. A, Comparisons between the normal sleep and disturbed sleep subtypes in SHHS, CFS, and MrOS. Upper panels show Cohen’s for demographic characteristics, conventional sleep measures, and ECG-SDI-derived biomarkers; positive values indicate higher values in the disturbed subtype. Lower panels show odds ratios for binary characteristics and clinical outcomes. Points and horizontal bars denote estimates and 95% confidence intervals, respectively. Clinical outcome models were adjusted for age, body mass index, sex, sleep efficiency, and sleep latency, where applicable. Biomarker comparisons describe variables used for clustering. B, Kaplan–Meier curves for all-cause mortality in SHHS, with shaded 95% confidence intervals and numbers at risk below. Blue and red indicate the normal sleep and disturbed sleep subtypes, respectively. The inset reports the log-rank test and Cox proportional hazards estimates. Model 1 adjusts for age, sex, and race; Model 2 additionally adjusts for body mass index, smoking status, hypertension, and diabetes mellitus; Model 3 additionally adjusts for apnea–hypopnea index and total sleep time.
Figure 4: Paired distributions of key ECG-SDI-derived biomarkers before and after CPAP treatment in the BZ-CPAP cohort. Violin plots with embedded boxplots compare the distributions of AP, RB, RB 0.3 , CV, SK, APPe, DETRf, MDR, and PR between pre-CPAP and post-CPAP recordings. Red horizontal lines indicate medians, boxes denote interquartile ranges, and violin contours represent the full distribution of each biomarker. Across multiple metrics, post-CPAP values shifted toward higher accumulated sleep depth and reduced shallow-sleep burden, consistent with improved sleep continuity after treatment.
Figure 5: Exploratory associations of CPAP-associated ECG-SDI changes with PSG outcomes and within-stage sleep depth. A, Association between reductions in APPe and PSG-derived ODI 3 , both calculated as pre-CPAP minus post-CPAP values. B, Association between the reduction in CV (pre-CPAP minus post-CPAP) and the increase in PSG-derived sleep efficiency (post-CPAP minus pre-CPAP, in percentage points). Points represent paired participant-level changes; solid lines illustrate fitted trends. Spearman correlations, 95% confidence intervals (CIs), and values are reported in each panel. C, Adjusted standardized regression coefficients and 95% CIs for the associations shown in A and B, with 395 paired participants included in each model. M0 adjusts for age, sex, BMI, baseline AHI, and the corresponding baseline PSG outcome; M1 additionally adjusts for the baseline value of the corresponding ECG-SDI biomarker. Open circles denote M0 and filled diamonds denote M1. D, Paired mean ECG-SDI values within PSG-defined N2 before and after CPAP, restricted to participants with at least 10 min of N2 at each visit. Lines connect paired observations. The mean paired change, its 95% CI, and the paired -test value are shown. APPe, approximate entropy; CV, coefficient of variation; ODI 3 , oxygen desaturation index.
Figure 6: Proof-of-concept wearable workflow for home ECG-SDI reporting. A, Illustration of overnight single-lead ECG acquisition using a chest-worn device in a modified Lead II configuration. B, Smartphone connection interface and automated analysis workflow comprising ECG-SDI inference and biomarker extraction. C, Illustrative report displaying an overnight ECG-SDI trajectory and summary values for AP, PR, RB, and CV. Interface elements, trajectories, and numerical values illustrate the workflow and do not constitute a home-validation dataset or validated normal/abnormal classifications.
Appendix figures & tables7 assets
Supplementary material from the paper’s appendix.
Appendix
| Cohort | Number | Age (years) | Female (%) | BMI (kg/m 2 ) | AHI | Timeframe |
| CFS | 726 | 41.4 19.4 | 55% | 32.4 9.5 | 10.2 18.5 | 2001–2006 |
| MrOS | 2,806 | 76.4 5.5 | 0% | 27.2 3.8 | 13.7 14.4 | 2003–2012 |
| MESA | 2,055 | 69.4 9.1 | 54% | 28.7 5.5 | 14.8 16.7 | 2010–2013 |
| SHHS | 5,791 | 63.1 11.2 | 52% | 28.2 5.1 | 10.2 13.6 | 1995–2010 |
| BZ-CPAP | 507 | 47.0 11.8 | 9% | 30.7 4.8 | pre: 52.38 25.04 post: 5.68 7.28 | 2019–2025 |
Table 2: Baseline characteristics of the study cohorts included in this work. Continuous variables are reported as mean standard deviation unless otherwise specified. In the BZ-CPAP cohort, pre and post in the AHI column denote measurements obtained before and after CPAP treatment, respectively.
Figure 7: Stage-wise distribution of ECG-SDI across conventional sleep stages in the SHHS, CFS, MESA, and MrOS cohorts. Boxplots show the distributions of ECG-SDI for wake (W), N1, N2, N3, and REM sleep. The center line denotes the median, the box denotes the interquartile range, and the whiskers indicate the distribution spread.
| Metric | pre-CPAP | post-CPAP | Change | value | Sig |
| AP | 0.5909 | 0.6269 | +6.10% | ||
| RB | 0.0926 | 0.0820 | -11.45% | 0.0368 | |
| RB 0.3 | 0.1580 | 0.1327 | -16.01% | ||
| CV | 0.5277 | 0.5021 | -4.85% | ||
| SK | -0.2192 | -0.4483 | -104.5% | ||
| APPe | 1.1257 | 0.9243 | -17.89% |
Table 4: Detailed paired comparison of ECG-SDI-derived biomarkers before and after CPAP treatment in the BZ-CPAP cohort. pre-CPAP, before treatment; post-CPAP, after treatment; Change, post-CPAP minus pre-CPAP. values were obtained from two-sided paired tests. Sig indicates significance level: * , ** , *** , ns not significant.
Figure 8: Detailed architecture of the proposed ECG-SDI framework. The proposed ECG-SDI framework is built upon a pretrained and frozen two-stage single-lead ECG sleep-staging backbone. In Stage 1, each 30-s ECG epoch is preprocessed and passed through a CNN-based time-domain encoder together with a handcrafted-feature branch, where 39 frequency- and time–frequency-domain features are projected through two fully connected layers and fused with the CNN representation to form an epoch-level sleep embedding. In Stage 2, the frozen Stage-1 encoder generates sequential multi-epoch representations, which are further processed by a Transformer-based temporal module to capture inter-epoch contextual dependencies and refine sleep representations. During ECG-SDI adaptation, the original refined sleep-staging head is replaced with two lightweight task-specific heads: one for REM-related binary classification and the other for continuous sleep-depth estimation, producing REM-related outputs and the continuous ECG-SDI score, respectively. This design repurposes a pretrained sleep-staging backbone for continuous sleep-depth biomarker learning while preserving multi-epoch temporal modeling.
| Metric | Category | Brief description |
| AP | Depth burden | Normalized area under the whole-night ECG-SDI curve. Higher values indicate greater cumulative sleep-depth burden across the night. |
| RB | Shallow-sleep burden | Proportion of epochs with ECG-SDI values below 0.2, reflecting the overall dominance of shallow sleep. |
| RB 0.3 | Shallow-sleep burden | Proportion of epochs with ECG-SDI values below 0.3. This is a less stringent shallow-sleep index used mainly for treatment-response analysis. |
| CV | Variability | Coefficient of variation of the overnight ECG-SDI trajectory, describing the relative extent of night-long fluctuation. |
| SK | Distribution shape | Skewness of the ECG-SDI distribution, reflecting whether the depth profile is shifted toward shallower or deeper values. |
| APPe | Complexity | Approximate entropy, used to characterize the regularity and predictability of the ECG-SDI time series. Lower values indicate a more regular trajectory. |
Table 5: Brief description of ECG-SDI-derived digital biomarkers used in clustering and treatment-response analyses. Descriptions are intended to provide intuitive physiological interpretation rather than formal mathematical definitions. RB 0.3 was additionally used in the CPAP treatment-response analysis.
| Setting | CNN staging | Transformer staging | ECG-SDI heads |
| Optimizer | Adam | Adam | Adam |
| Initial learning rate | |||
| Weight decay | 0 | 0 | |
| Maximum training epochs | 50 | 100 | 100 |
| Early-stopping patience | 5 | 5 | 5 |
| Batch size | 256 ECG epochs | 64 recordings a | 1 recording |
Table 6: Training settings in the released research scripts.
| Cohort | Poor sleep quality | Insomnia symptoms |
| SHHS | ltdp10 and rest10 | diffa10 |
| CFS | slpqua and desslp | easlp and difbak |
| MrOS | poxqual1 and poxqual3 | poxfall min |
Table 7: Operational definitions of questionnaire-derived binary outcomes.
More in this topic
Sleep Stage Classification
Sleep stage classification assigns sleep epochs to physiological stages from signals such as EEG, helping quantify sleep architecture and support clinical monitoring.
See all 40 papers