MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641105950 A) filed by Sri Eshwar College Of Engineering on September 02, 2026, for A Hybrid Lstm–gan Based System For Predicting Rare Hospital Readmission Events Using Imbalanced Healthcare Data.
Inventor includes Dr. C. Arunkumar.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: The figure illustrates a hybrid predictive framework for rare hospital readmission event prediction using imbalanced healthcare data. Anonymized patient electronic health record (EHR) data is first subjected to preprocessing and feature structuring to form sequential time-series inputs. A Generative Adversarial Network (GAN) module generates synthetic samples corresponding to rare readmission events to address class imbalance in the dataset. The augmented dataset is then provided as input to a Long Short-Term Memory (LSTM) network, which models temporal dependencies in patient histories and predicts the probability of hospital readmission events. The output of the system is a readmission risk prediction score, which can be used for healthcare analytics and decision-support purposes. The framework operates without direct patient interaction and is intended for research and predictive analysis applications
Disclaimer: Curated by HT Syndication.
