Study: Apple’s newest AI model flags health conditions with up to 92% accuracy

A new study supported by Apple suggests behavioral data from wearables can be a stronger health indicator than traditional biometric measurements. Researchers developed a foundation model called WBM trained on 2.5 billion hours of wearable data, outperforming existing models in many health prediction tasks. The model combines with sensor data for improved accuracy in detecting conditions like pregnancy and sleep quality, potentially enabling earlier identification of health changes.