MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641107253 A) filed by S. Subarna; Dr. M. Sughasiny; and R. Aravind on September 07, 2026, for System And Method For Multi-Task Cardiovascular Disease Diagnosis, Readmission Risk And Survival Prediction Using Adaptive Artificial Intelligence.
Inventors include S. Subarna; Dr. M. Sughasiny; and R. Aravind.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: A computer-implemented system and method are disclosed for integrated cardiovascular disease diagnosis, readmission-risk prediction and survival estimation from longitudinal multimodal patient data. Heterogeneous clinical observations are normalized and represented with timestamps, missingness indicators and data-quality indicators. A time-aware patient-state encoder generates a shared latent representation that is supplied to a multi-task prediction engine for jointly producing a cardiovascular diagnostic output, interval-specific readmission risk and a patient-specific survival function. An uncertainty and calibration engine derives task-specific confidence, while a clinical consistency and drift engine evaluates relationships among the outputs and detects distribution shift relative to validated patient-state representations. Predictions may be recalibrated, flagged or routed to a fallback inference path in response to uncertainty or drift. An explanation module identifies influential clinical variables and temporal intervals and generates a coordinated risk-stratified decision-support output. Accompanied Drawing [FIGS. 1-2].
Disclaimer: Curated by HT Syndication.
