Apple Watch uses machine learning algorithms to detect when a wearer has had a hard fall or been in a car crash, and can automatically contact emergency services if the person is unresponsive. Fall Detection has been available since Apple Watch Series 4 in 2018. Crash Detection for severe car accidents was added with the iPhone 14 and Apple Watch Series 8 in 2022.

Fall Detection uses an accelerometer and gyroscope that measure up to 32 g-forces, combined with an on-device algorithm that analyzes wrist trajectory and impact patterns to distinguish a real fall from ordinary movements like exercise. Crash Detection uses a four-sensor combination (high-g accelerometer, gyroscope, barometer, and microphone) and a machine learning model trained on data from real crash lab simulations and recordings. Apple engineers described the system as detecting a specific pattern of sudden deceleration, pressure change, impact sound, and sustained stillness. Both features are designed to minimize false alarms: Crash Detection requires simultaneous signals from multiple sensors. If the user does not respond to the alert within approximately one minute, the device places an automatic call to emergency services.