Arrhythmias & electrophysiology
Role of Artificial Intelligence in Reducing Data Deluge From Cardiac Implantable Electronic Devices
Authors' conclusion
AI interpretation of transmissions was found to have an accuracy similar to that of DT with superior sensitivity but lesser specificity.
Study context
- Population
- Remote monitoring data of cardiac implantable electronic devices (CIEDs) from 78 US device clinicstransmissions from 74,217 devices
- Participants
- 690,673 participants
- Exposure
- Artificial intelligence (AI) vs DT
- DTn = 495,054reference
- Outcome
- Transmissions processed and forwarded to device clinics
- Follow-up
- 8 months
Methodological detailsmulticentre, blinded adjudication of ≈15% random sample
- Multicentre
- Blinded adjudication of ≈15% random sample
Main finding
As reported in the abstract
| Group | Processed | Forwarded |
|---|---|---|
| AI | 28.3% | 22.8% (n = 44,550) |
| DT | 71.7% (n = 495,054) | 38.5% (n = 190,492) |
Processed
AI28.3%
DT71.7% (n = 495,054)
Forwarded
AI22.8% (n = 44,550)
DT38.5% (n = 190,492)
- Total transmissions forwarded to device clinics
- 34% (n = 235,042)
Observational data: associations, not effects.
Further findings
- AI performance vs electrophysiologist adjudication (gold standard)
- 93.8% · Accuracy · Sensitivity 99.1% · Specificity 93% · F1 score 81%
Original publication
Role of Artificial Intelligence in Reducing Data Deluge From Cardiac Implantable Electronic Devices. JACC Adv. Published 28 August 2025. doi:10.
Summarised from the published abstract; every number is checked against it