Apple Watch Series 3 drop from 99 to 65 bpm marks AF reversion

AI system

System: Apple Watch Series 3 heart-rate readings (optical photoplethysmography)
Model: Not assessed
Release: Exact release not established.
Application developer: Apple
Role: Not assessed
Configuration: The participant used an Apple Watch Series 3.
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: A patient with known paroxysmal AF wearing a heart-rate-displaying smartwatch while a Holter monitor was also fitted. The patient noticing and reporting a sudden, persistent heart-rate drop with its time. Clinicians willing to export the watch readings (Apple Health app to Excel) and align them with the Holter.
Human oversight: Not assessed
Relation to AI: No alert, notification or rhythm classifier was involved. The watch displayed a photoplethysmographic heart-rate estimate, the patient noticed the drop, and the authors compared the readings with the Holter afterwards. The paper does not describe the heart-rate estimation as machine learning. So the AI character of the contribution is not established.
AI contribution: No alert, notification or rhythm classifier was involved. The watch displayed a photoplethysmographic heart-rate estimate, the patient noticed the drop, and the authors compared the readings with the Holter afterwards. The paper does not describe the heart-rate estimation as machine learning. So the AI character of the contribution is not established.

Outcome identifiers: Not assessed
Benefit: sudden 99-to-65 bpm drop at 19:29 that coincided with reversion from AF to sinus rhythm
Category: Improved Physical Health
Status: Not assessed
Beneficiary groups: People.
Beneficiaries: Not assessed
Reach: Not assessed
Distribution and access: Not assessed
Duration: Not assessed
Expected?: Yes
Costs and harms: Not assessed

Studies: Not assessed
Study design: Not assessed
Measurement: Not assessed
Setting and sample: Not assessed
Measures: sudden 99-to-65 bpm drop at 19:29 that coincided with reversion from AF to sinus rhythm
Comparison: a concurrent 24-hour Holter monitor
Results: sudden 99-to-65 bpm drop at 19:29 that coincided with reversion from AF to sinus rhythm
Additional value from AI: Not assessed
Limitations: Not assessed
Denominators: Not assessed
Materials for replication: Not assessed

Conditions for replication: The rhythm change produces a heart-rate change large enough to be visible on the watch's optical estimate. A reference recording (Holter) exists to confirm what the watch suggested.
Replication attempts: Not assessed
Later findings: The report says only that outcomes of smartwatch-detected arrhythmias are the subject of ongoing research; nothing later was found.
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Assessed benefits: People.
Depth: People: 1.
Reasons: People: The patient learned from her watch, and had confirmed by Holter, that her rhythm had reverted at 19:29. The report records no change in management, so the benefit is informational only.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: Independently studied

Kind: Not assessed
Related entries: Not assessed
Field: Healthcare (cardiology). Consumer wearables.
Purpose: The watch's optical heart-rate estimate is built to show the wearer their pulse. Its use here to time a rhythm change was that function, read by the patient rather than flagged by the device.
Dates: Date basis unassessed: 2020 (precision unassessed). Updated: 21 October 2026.
Stage: Not assessed
Version: SHA-256: 21ad16cb86c2…

Case report Independent author

Toner L, Al-Kaisey AM, Koshy A, Lim HS (2020). Spontaneous reversion of paroxysmal atrial fibrillation detected by smart watch. BMJ Case Reports 13(2):e233431. doi:10.1136/bcr-2019-233431 (PMC7035811).
Case report Independent author

Toner L et al. (2020), BMJ Case Reports 13(2):e233431, Holter confirmation.