Samsung Develops AI-Powered Health Foundation Models for Wearable Devices
Samsung Research America (SRA) has recently introduced two foundation models, xMAE (Physiology-Aware Masked Cross-Modal Reconstruction for Biosignal Representation Learning) and HiMAE (Hierarchical Masked Autoencoder), designed to analyze biosignals from wearable devices and provide personalized health insights. This development is part of Samsung’s efforts to enhance its digital health offerings, as evident from the company’s Connected Care vision unveiled at the Galaxy Unpacked event in July 2026.
What are Health Foundation Models?
Health foundation models are a form of artificial intelligence (AI) designed to produce a wide variety of outputs, including text, image, or audio generation, and are being adopted across various sectors. According to the Ada Lovelace Institute, foundation models are capable of automating complex tasks and can be used in applications such as text generation, image recognition, and audio analysis. In the context of healthcare, foundation models can help analyze biosignals from wearable devices, such as smartwatches, to provide personalized health insights and recommendations.
How do xMAE and HiMAE Models Work?
The xMAE and HiMAE models developed by Samsung Research America are specifically designed to analyze biosignals from wearable devices. xMAE learns the temporal relationship between different biosignals, while HiMAE understands health patterns across different time scales in wearable time-series data. Both models demonstrate advancements in health AI that can better understand the physiological relationships and temporal structure of biosignals. As highlighted in the Samsung News article, these models have the potential to provide more accurate and personalized health insights for users.
What Came Before: Samsung’s History in Healthcare
Samsung has a long history in healthcare, dating back to 1994 when it opened the Samsung Medical Center, the largest cancer center in Asia. Since then, the company has launched several health and wellness-focused apps, partnered with healthcare companies to develop remote patient monitoring solutions, and conducted research on using virtual reality for pain management. As mentioned in the HLTH article, Samsung has also partnered with b.well Connected Health to advance digital check-ins and consumer-mediated health data sharing.
Why it Matters: Impact on the Healthcare Industry
The development of AI-powered health foundation models by Samsung has significant implications for the healthcare industry. As noted by Scale AI, reliable AI systems can help reduce physician cognitive load by turning complex patient records into clinical intelligence. The use of foundation models in healthcare can also enhance public services by automating the review of complex contracts and case files, as highlighted in the Ada Lovelace Institute report. Furthermore, the integration of foundation models in wearable devices can provide users with more accurate and personalized health insights, enabling them to take a more proactive approach to their health and wellbeing. As the Google Blog article mentions, the Pixel Watch 5 introduces advanced health tracking features, including industry-first breathing emergency detection and monthly wellness trend summaries.
