Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 12, 2026European Journal of Preventive CardiologyOpen Access

Using wearable and lifestyle data to predict adverse cardiac events in patients with established coronary artery disease

View Full Paper
Ask AI
Bookmark
Share

Key result

Wearable and chatbot models predict adverse cardiac events with an AUC of 0.75, outperforming SMART2.

  • p < 0.01

Why the study?

The SMART2 risk score relies on static clinical parameters, whereas real-world recovery factors like sleep, activity, and autonomic function also affect recurrent CV risk and can be continuously monitored with digital health tools.

Do digital biomarkers from wearable and chatbot monitoring improve the prediction of adverse cardiac events compared to SMART2 risk score and lifestyle questionnaires in patients with established coronary artery disease after revascularization?

Comparison

SMART2 parameters vs lifestyle questionnaires vs wearable/chatbot data vs all combined

Design

Cohort study

Follow-up

two years

Authors

FBF J C Van BlerckVEV A A Van EsWGW F Goevaerts

Discussion

Loading...

Member takes

Overview

Should not yet change post-revascularization care; leaves open whether wearable and chatbot data enhance adverse event prediction.

Key Points

  • This research aims to assess the predictive capabilities of lifestyle, wearable, and clinical data for adverse cardiac events in coronary artery disease patients.
  • Monitored 66 patients post-coronary revascularization for 21 days using a smartwatch and a chatbot platform.
  • Compared predictive performance of SMART2 parameters, lifestyle questionnaires, and wearable/chatbot data.
  • Developed a scoring system based on identified predictors for classifying risk of adverse cardiac events.
  • 39% of participants experienced adverse cardiac events during follow-up.
  • Wearable and chatbot model achieved highest AUC of 0.75, significantly outperforming other models (p < 0.01).
  • The new scoring system classified patients into moderate (17-24%) and high-risk (25-85%) tiers based on predictive factors.

Structured PICO

Do digital biomarkers from wearable and chatbot monitoring improve the prediction of adverse cardiac events compared to SMART2 risk score and lifestyle questionnaires in patients with established coronary artery disease after revascularization?

P
Population
66 patients with coronary artery disease (median age 60 years; 88% male) recovering from coronary revascularisation
I
Intervention
Digital biomarkers from wearable (smartwatch) and chatbot monitoring (activity, sleep, heart-rate metrics and self-reported lifestyle) for 21 days after coronary revascularisation
C
Comparator
SMART2 risk score clinical parameters and validated lifestyle questionnaires
O
Outcome
Adverse cardiac events (composite of CV death, re-event, new CV disease, or unplanned admission) during two years of follow upcomposite

Early post-discharge digital monitoring of sleep, activity, and circadian HR dynamics predicts adverse cardiac events more accurately than standard clinical risk scores in patients recovering from coronary revascularization.

Cite This Study

Blerck et al. (2026) studied this question. A wearable and chatbot model predicted adverse cardiac events with higher discrimination (AUC 0.75) than the SMART2 risk score (AUC 0.63) or lifestyle questionnaires (AUC 0.54) (p < 0.01).

synapsesocial.com/papers/6a2bd1386550ea4541ffe9dchttps://doi.org/10.1093/eurjpc/zwag249.177
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Is the SMART risk prediction model ready for real-world implementation? A validation study in a routine care setting of approximately 380 000 individuals2021 · 17 citations
  2. 2A blood-based biomarker score for monitoring secondary prevention in coronary artery disease2025
  3. 3Improving 10-year cardiovascular risk prediction in patients with established cardiovascular disease: flexible addition of risk predictors on top of the SMART2 risk score2026
  4. 4A lifestyle monitoring system for cardiovascular care: protocol of a prospective observational trial2023 · 1 citations
  5. 5Prediction of physical activity decline post-cardiac intervention: a machine learning approach2026