Methods for Training Foundation Models for Processing Optical Physiological Signals

Nokia Solutions and Networks Oy, through inventors Dimitrios Spathis, Mohammad Malekzadeh, and Arvind Thanga Chellappa Pillai, has filed USPTO Patent Application US20260093979A1 for training AI foundation models using Photoplethysmography (PPG) physiological signals. The application discloses methods for providing training data to an AI model comprising multiple machine learning models, where the training data includes PPG signals obtained from multiple individuals, and training the model to determine outputs based on the physiological data.

This patent application represents a prior art disclosure and intellectual property filing rather than a regulatory action. Technology companies developing AI systems for physiological signal processing, health monitoring devices, or wearable technology may wish to review the claims to assess potential freedom-to-operate implications. Legal and R&D teams should evaluate whether their existing or planned AI training methodologies for PPG data could conflict with or benefit from this patent.