Smartwatch ECG app confirms AF at sea; CIRM diverts the ship

AI system

System: Smartwatch ECG application with atrial fibrillation classification (brand and model not stated)
Model: Not assessed
Release: Not assessed
Application developer: Not stated (the report does not name the device's maker)
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: A ship without an electrocardiograph but with a smartwatch carrying an ECG app on board. A telemedical maritime assistance service (CIRM) reachable from the ship and willing to act on a smartwatch trace. A captain able to run the app on the patient and to divert the vessel.
Human oversight: Not assessed
Relation to AI: The ECG app's automatic reading confirmed the suspected AF “within seconds”. The CIRM doctor then reviewed the trace himself and identified irregularities consistent with AF. So the classification and the human reading agreed. The diversion, drugs and hospital confirmation were human decisions. The brand is unknown, so the algorithm cannot be identified.
AI contribution: The ECG app's automatic reading confirmed the suspected AF “within seconds”. The CIRM doctor then reviewed the trace himself and identified irregularities consistent with AF. So the classification and the human reading agreed. The diversion, drugs and hospital confirmation were human decisions. The brand is unknown, so the algorithm cannot be identified.

Outcome identifiers: Not assessed
Benefit: On 29 Sep 2023 a merchant ship with no ECG used a smartwatch ECG app under CIRM guidance; it confirmed AF within seconds, the ship diverted, hospital ECG confirmed AF and the seafarer was repatriated.
Category: Improved Physical Health
Status: Not assessed
Beneficiary groups: People. Organizations.
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: Not assessed
Comparison: Assumed alternative: no electrocardiograph on board the ship
Results: Assumed comparison. Result: Within seconds, the application confirmed the diagnostic hypothesis.
Additional value from AI: Not assessed
Limitations: Not assessed
Denominators: Not assessed
Materials for replication: Not assessed

Participants: Developer: Not stated (the report does not name the device's maker). Operator: Centro Internazionale Radio Medico (CIRM), the Italian Telemedical Maritime Assistance Service, with the ship's captain.
Jurisdictions: Benefit: Indian Ocean (merchant ship), with the CIRM center in Rome, Italy. Operator: Italy.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Conditions for replication: The app's AF classification and the remote doctor's reading of the trace agree, as they did here and as the hospital ECG later confirmed. A port is within reach for diversion and the patient remains stable on the drugs available on board.
Replication attempts: Not assessed
Later findings: Not assessed
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Assessed benefits: People. Organizations.
Depth: People: 2. Organizations: 1.
Reasons: People: The seafarer received a diagnosis, rate control and aspirin at sea, diversion to port and hospital confirmation. He was repatriated without complications. Material: the authors say the service “has the potential to save lives”, but no life-threatening complication is documented. Organizations: CIRM's duty doctor could make a rhythm diagnosis and a diversion decision on an ECG trace rather than on symptoms alone. The report gives no measure beyond the single decision.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: The deployer's account

Kind: Not assessed
Related entries: Not assessed
Field: Healthcare (maritime telemedicine; cardiology). Consumer wearables.
Purpose: Smartwatch ECG apps are built to record a single-lead ECG and classify it for atrial fibrillation. This use, relayed to a telemedicine doctor, was that purpose in an unusual setting.
Dates: Date basis unassessed: 2023 (precision unassessed). Updated: 21 October 2026.
Stage: Not assessed
Version: SHA-256: 900ddc2cd62a…

Case report Deployer

Ruocco C, Amenta F, Angeloni U, Frisicale EM, Vaia F, Sagaro GG (2025). A smartwatch electrocardiogram for atrial fibrillation detection: a case report. International Maritime Health 76(2):93-96. doi:10.5603/imh.99319 (open access, CC BY-NC-ND).
Case report Deployer

Ruocco C et al. (2025), Int Marit Health 76(2):93-96, diversion.