MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202641043551 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on April 6, for 'osteoporosis risk stratification and bone degeneration prediction using causal-aware graph neural networks.'
Inventor(s) include Parvathi R; and A. Iffana.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "Osteoporosis Risk Stratification and Progressive Bone Degeneration Prediction System. A computer-implemented system for osteoporosis risk stratification and progressive bone degeneration prediction is disclosed. The system processes patient clinical data comprising bone metabolic indicators, hormone-related inflammation indicators, lifestyle inflammation indicators, and demographic attributes including age and gender. The received data is subjected to preprocessing and normalization to generate stabilized biomarker feature representations for each patient. A composite degeneration score is computed by integrating metabolic and inflammatory indicators, and a demographic-conditioned baseline is estimated using patient cohorts grouped by demographic attributes. An individualized degeneration delta is determined by comparing the composite degeneration score with the demographic baseline to quantify deviation from expected physiological conditions. Patients are categorized into bone health stages including healthy bone condition, osteopenia, and osteoporosis based on the distribution of degeneration delta values. A relational patient similarity graph is constructed to represent similarity relationships between patients, and directional connections are assigned using degeneration potential values. Directed graph attention mechanisms perform relational inference across the graph to generate embedding representations used for stage prediction. The system produces outputs including predicted osteoporosis stage, probability confidence scores, and degeneration delta indicators suitable for clinical decision support."
Disclaimer: Curated by HT Syndication.
