Meta funds university research into infant monitoring and dementia care

Meta is providing $2 million in grants across five US universities to support research using its models in medicine and science. The partnerships involve Caltech, The Ohio State University College of Medicine, Louisiana State University, Indiana University and UTHealth Houston. Support includes access to its latest models and direct researcher collaboration, with projects spanning healthcare, physics, chemistry, biology, computer science and mathematics.

At Louisiana State University, Dr. Michael Dunham’s Eyes-On project is developing computer vision to detect displaced tracheostomy tubes and signs of distress in infants who cannot reliably vocalize. The team is exploring Meta’s open-weight SAM models for tracking, with a system designed for bedside cameras and edge computing. A proof-of-concept has been published.

Indiana University’s Dr. David Crandall is developing multimodal AI methods to analyze conversations involving older adults with dementia. The goal is to help conversational agents, including social robots, adapt to individual communication patterns.

At Ohio State, Dr. Yuan Xue, Dr. Yuchi Han and Dr. Xia Ning are investigating whether open-weight models can predict future risk of heart failure with preserved ejection fraction. Their approach uses routine abdominal CT scans, longitudinal medical records and ECG data when available, while accounting for missing inputs common in clinical practice.