MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641051434 A) filed by Dr. M. Praveena; Dr. Sridhar D; Mrs K Pandi Meena; Dr E Saranya Devi; Dr. V. Baby Shalini; Mrs. Tamil Selvi S; Dayananda Sagar Academy Of Technology And Management; Dr. Aruna M; Dr. Priyanka Jayaraj; and Dr Geetha Raj Prakash, Coimbatore, Tamil Nadu, on April 22, for 'generative ai in healthcare: revolutionizing diagnosis, treatment, and patient care.'
Inventor(s) include Dr. M. Praveena; Dr. Sridhar D; Mrs K Pandi Meena; Dr E Saranya Devi; Dr. V. Baby Shalini; Mrs. Selvi S; Dr. Aruna M; Dr. Priyanka Jayaraj; and Dr Geetha Raj Prakash.
The application for the patent was published on May 1, under issue no. 18/2026.
According to the abstract released by the Intellectual Property India: "In addition, the emergence of new technologies such as digital health records, medical images, and monitoring data creates opportunities for improving clinical decisions through data analysis. Nevertheless, problems such as data availability and imbalance, and risk detection delays are still affecting the efficiency of conventional data analysis tools. This study proposes a framework that employs artificial intelligence technology and a generative framework to improve disease diagnosis and treatment support and patient monitoring services. In addition, it employs Generative Adversarial Networks (GANs) technology to improve the availability of medical data and enhance diagnosis accuracy through data augmentation. Moreover, it employs Transformer technology to improve disease diagnosis and risk detection by analyzing electronic health records and identifying temporal patterns and trends. In addition, physiological signals from wearable technology are analyzed using predictive models and algorithms to improve disease diagnosis and risk detection and support timely medical intervention and detection of anomalies. The study's findings indicate that the framework can improve reliable and personalized healthcare services and enhance the efficiency of clinical decisions and disease diagnosis and treatment support. Significant changes are happening in the world-wide health care system as a result of the rapid digitalization of health care processes and the increased usage of data-intensive technologies. Contemporary health care systems produce a large amount of heterogeneous data from different sources, such as electronic health records, medical imaging techniques, laboratory information systems, genome sequencing techniques, and wearable sensing devices. The data streams offer rich clinical information about the health care process, disease detection, and treatment. However, the high volumes, varieties, and complexities of health care data cause major problems in the application of traditional analysis techniques that are not equipped to mine high-level health care patterns in a timely manner . Artificial Intelligence (AI), specifically deep learning, has been identified as a promising technology to help overcome these issues. Deep neural networks have been reported to have high performance in medical image interpretation, automated diagnosis, and outcome prediction. Convolutional Neural Networks (CNNs) have achieved expert-level performance in radiology and pathology image analysis, and Natural Language Processing (NLP) has been used to derive relevant information from unstructured clinical texts and doctor notes . However, the performance of conventional deep learning models is often limited by several limitations in their practical application. Medical image and clinical data are often limited in size and difficult to share due to privacy and ethical issues. Generative Artificial Intelligence has recently emerged as a potential tool to overcome the data-related challenges associated with the field of healthcare. Generative models, especially Generative Adversarial Networks (GANs), have the potential to learn from the underlying distributions of the medical data and generate synthetic data that resembles the original data. This synthetic data can be used to overcome the limitations of the available data and make the diagnostic models more reliable and efficient [5], [6]. Besides the potential of Generative AI to generate synthetic medical images, this technology also has the potential to facilitate the sharing of medical data while ensuring the privacy of the data, especially the patient data used in medical research. On the other hand, the transformer architecture has also shown significant potential to handle complex medical data more efficiently than other machine learning models. The transformer architecture was originally developed to handle the complex relationship between the words used in the English language; however, this architecture has also been used to handle medical data efficiently, especially to model the long-range relationships present in the medical data used to make clinical decisions, which helps to identify critical conditions in the initial stages [7], [8]. The next emerging aspect of digital healthcare services would be the continuous monitoring of patients using wearable devices and remote sensing technologies. These devices would be capable of providing continuous physiological data such as heart rate, oxygen levels, activity patterns, and sleep patterns, among others."
Disclaimer: Curated by HT Syndication.
