MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641063509 A) filed by Dayananda Sagar College Of Engineering, Bangalore, Karnataka, on May 20, for 'a passive bio-ai system for pre-symptomatic neurodegeneration risk prediction.'
Inventor(s) include C V Balaji; Aprameya Bharadwaj; Anjana U; Dr. Suma V; Ishwari Suyog Bhawalkar; and K Parjanya Ram.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "The current invention describes a system and method for predicting the risk of neurodegeneration in clinically normal subjects prior to symptom onset utilizing a passive, non-invasive, multi-dimensional tracking approach. This is accomplished through the integration of user generated data from wrist worn wearable devices and a food diary to monitor a subject's estimated glycemic responses, gut brain axis health proxy, heart rate variability, sleep structure and exercise habits on a continuing basis. Unlike previous approaches that have used expensive and invasive medical equipment, this system uses commercially available devices. Additionally, while other systems require the need to collect large amounts of historical data before they can be personalized, this system supports ongoing personalization at regular intervals through standardized metabolic calibrations of fasting plasma glucose and glycated hemoglobin levels. These signals then undergo a four stage artificial intelligence processing pipeline: (1) An indirect estimation of blood glucose levels using a gated recurrent unit with fasting plasma glucose and glycated hemoglobin levels serving as calibration anchors; (2) A temporal fusion transformer that constructs an individualized baseline of their physiological status over time in an initial calibration period; (3) A bidirectional long short-term memory autoencoder that identifies changes in physiological status that occur without supervision by detecting metabolic drift through a comparison of original and reconstructed data sets; and (4) An attention based fusion module that produces a quantitative, Shapley value explained risk score. In addition to providing the first opportunity to develop early interventions to prevent or delay the onset of neurodegenerative diseases such as Alzheimer's and Parkinson's disease which are currently diagnosed when irreparable neuronal loss has already occurred."
Disclaimer: Curated by HT Syndication.
