Apple Watch Crash Detection calls 911 for Andi Burns in a river

AI system

System: Apple Watch Crash Detection
Model: Not assessed
Release: Not assessed
Application developer: Apple
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: A supported Apple Watch (Series 8 or later, SE 2nd generation, Ultra) with Crash Detection on and a cellular or Wi-Fi path to emergency services. A severe crash (rollover into water) with the wearer unable to reach a phone. A dispatcher able to act on the automated call and location.
Human oversight: Not assessed
Relation to AI: ABC News, citing Clermont County officials, and WLWT say the Apple Watch's Crash Detection placed the 911 call. Apple's support page says the feature detects severe crashes from on-device sensor data. It calls automatically after a countdown if the wearer does not respond. Burns also told WKRC that a Life360 crash-detection service on her mother's phone called police and family. The watch may not have been the only alert. Only news reports are among the sources, and no dispatch log or agency statement is on record.
AI contribution: ABC News, citing Clermont County officials, and WLWT say the Apple Watch's Crash Detection placed the 911 call. Apple's support page says the feature detects severe crashes from on-device sensor data. It calls automatically after a countdown if the wearer does not respond. Burns also told WKRC that a Life360 crash-detection service on her mother's phone called police and family. The watch may not have been the only alert. Only news reports are among the sources, and no dispatch log or agency statement is on record.

Benefits

Outcome identifiers: Not assessed
Benefit: On 22 February 2026 near Batavia, Ohio, a 19-year-old's truck flipped into the Little Miami River; Clermont County officials say her Apple Watch called 911 by Crash Detection and crews freed her.
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

Measurement

Studies: Not assessed
Study design: Not assessed
Measurement: Not assessed
Setting and sample: Not assessed
Measures: Not assessed
Comparison: Not assessed
Results: Not assessed
Additional value from AI: Not assessed
Limitations: Not assessed
Denominators: Not assessed
Materials for replication: Not assessed

Money

Kind of value: Not assessed
Amount: Not assessed
Currency and prices: Not assessed
Period and unit: Not assessed
Realization: Not assessed
Recipients and payers: Not assessed
Gross or net: Not assessed
Included costs: Not assessed
Comparison: Not assessed
Method: Not assessed
Return and payback: Not assessed

People and places

Participants: Developer: Apple.
Jurisdictions: Benefit: Batavia Township, Clermont County, Ohio, United States. Developer: United States.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Follow-up

Conditions for replication: The on-device crash classifier recognizes the impact as a severe car crash. The wearer does not dismiss the alert within the countdown. Responders can reach the transmitted location in time.
Replication attempts: 1 follow-up entries. Benefit recurred: 1.
Later findings: 11 March 2026. WKRC reported on 11 March 2026 that Burns was alive and well and had thanked the Clermont County responders; ABC News (4 March) said the accident report recorded only bruises.
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Evidence

Source numbers: AIBD-0302-source-0001–0004
Citations: Numbered references below.
Language: Not assessed
Source relationships: Independent, Developer
Original evidence: Not assessed
Access and versions: Not assessed
Supported findings: Not assessed
Evidence links: Not assessed
Evidence strength: Not assessed
Missing evidence: Not assessed

Grades

Assessed benefits: People. Organizations.
Depth: People: 3. Organizations: 1.
Reasons: People: Rescuers and Burns describe a submerged cab with four to six inches of air. Firefighter Jetter called her survival “very, very, very lucky”. The call brought crews at night to a river crash. Whether anyone else would have called is not documented, and the sources are news reports. Organizations: Clermont County dispatch received the automated call with a location and stayed on the line. The sheriff's office released the body-camera video. No agency statement on timing or resources is among the sources.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: Independently reported

Entry details

Kind: Not assessed
Related entries: Not assessed
Field: Emergency response / road traffic injury. Consumer wearables.
Purpose: Crash Detection is built to recognize a severe car crash from sensor data. It then calls emergency services with the device's location if the wearer does not respond. This call was that purpose.
Dates: Date basis unassessed: 2026 (precision unassessed). Updated: 21 October 2026.
Stage: Not assessed
Version: SHA-256: ddecf428306c…

References

Other identifiers: Not assessed
Category mappings: Not assessed
Brief: Not assessed
Revisions: 6 revisions. Latest: 21 October 2026.

Sources

News report Independent author

ABC News / Good Morning America (2026). 19-year-old rescued from car sinking in freezing water speaks out. 4 March 2026.
News report Independent author

WLWT News 5 (2026). 19-year-old pulled from near-drowning truck crash in Little Miami River. Updated 26 February 2026.
News report Independent author

Clements A (2026). Woman thanks rescuers who saved her from crash into Clermont County river. WKRC Local 12, 11 March 2026.
Press release Developer

Apple Support. Use Crash Detection on iPhone or Apple Watch to call for help in an accident (article 104959).