Key result
Continuous wearable monitoring detects cardiovascular events, with baseline HF present in 83% of cases.
Why the study?
Predicting sudden cardiac death using electronic health records remains difficult, but integrating continuous personal health records from wearables with electronic health records may enable early prediction.
Does an integrated personal health record (PHR) and electronic health record (EHR) alert system using wearable devices predict sudden cardiac death and cardiovascular events in high-risk patients?
Cohort (n=229)
Yes
Does an integrated personal health record (PHR) and electronic health record (EHR) alert system using wearable devices predict sudden cardiac death and cardiovascular events in high-risk patients?
Preliminary data from a prospective cohort suggests that integrating wearable-derived personal health records with electronic health records can identify high-risk baseline profiles and potentially detect pre-event physiological changes in patients susceptible to cardiovascular events.
Answers are grounded in this paper and cite their sources.
Should not yet guide risk stratification in HF or ACS; leaves open validation of integrated personal-EHR models in larger cohorts.
Background Sudden cardiac death (SCD) is a major public health challenge, responsible for millions of deaths annually. While predicting SCD using electronic health records (EHRs) remains difficult, the growing use of wearable devices enables continuous collection of personal health records (PHRs). Integrating PHRs with EHRs offers a novel database for continuous, personalised monitoring. We hypothesise that applying advanced analytical methods to this integrated dataset may enable early prediction of SCD. Purpose The ultimate objective is to develop a predictive model for SCD by integrating PHRs with EHRs. Here we report the current status and a preliminary descriptive analysis of our cohort. Methods We are prospectively enrolling high-risk patients—those with severe heart failure (HF), acute coronary syndrome (ACS), or out-of-hospital cardiac arrest—from 11 hospitals. Participants use commercial wearable devices (smartwatches and smart-rings) and home monitors to collect PHRs (body weight, blood pressures, pulse, single-lead ECGs and patient-reported outcomes). These are integrated with EHRs, including clinical outcomes (primary endpoint: SCD; secondary: cardiac arrest, HF/ACS hospitalization, lethal arrhythmias, and therapy intensification). The target is to include 1000 patients in the cohort up to March 2027. For this preliminary analysis, we compared the baseline characteristics of the patients who experienced any primary or secondary outcomes to those of the other enrolled patients. Additionally, we examined the wearable (smart-ring) ECG tracings taken from the patients with events to search for possible indicators detectable prior to the events. Results As of November 2025, 229 patients (mean age 58 ± 13 years; 76% male) were enrolled. 23 patients experienced one or more outcomes (no SCD; 3 HF, 3 ACS, 3 lethal arrhythmias; 14 therapy intensification). Compared to the Control group (N=206), the Event group (N=23) exhibited a higher prevalence of history of diabetes (61% vs. 27%; p<0.01), HF (83% vs. 51%; p<0.01), known coronary stenosis (57% vs. 24%; p<0.01), and hypertension (65% vs. 40%; p=0.03; Table 1). Notably, in a patient with ACS, a retrospective review of wearable ECG tracings identified significant ST-segment depression 2 days prior to onset, compared to baseline tracings (Figure 1). This ischemic change was resolved following percutaneous coronary intervention, suggesting its pathological significance Discussion: To the best of our knowledge, this is the first high-risk cohort study on SCD to integrate PHR and EHR data. These preliminary findings imply that patients with events had a higher baseline burden of cardiovascular risk factors. Furthermore, the detection of pre-event ECG changes demonstrates the potential of PHRs taken from wearable devices. This cohort serves as a foundation for future analyses, where we will develop models utilizing dynamic PHR trajectories to better predict SCD.
No takes yet. Share an insight, caveat, or question.
Noda et al. (2026) conducted a cohort in Severe heart failure, acute coronary syndrome, or out-of-hospital cardiac arrest (n=229). Continuous personal health record (PHR) monitoring using wearable devices was evaluated on Sudden cardiac death (SCD). Continuous personal health record monitoring using wearable devices in 229 high-risk patients detected 23 cardiovascular events, with event patients showing higher baseline heart failure.
Synapse has enriched 10 related papers. Consider them for comparative context: