Venkatesh Upadrista

A digital twin is a virtual model of a real-world system that updates in real-time. In healthcare, digital twins are gaining popularity for monitoring activities like diet, physical activity, and sleep. However, their application in predicting serious conditions such as heart attacks, brain strokes and cancers remains under investigation, with current research showing limited accuracy in such predictions. Moreover, concerns around data security and privacy continue to challenge the widespread adoption of these models. To address these challenges, we developed a secure, machine learning powered digital twin application with three main objectives enhancing prediction accuracy, strengthening security, and ensuring scalability. The application achieved an accuracy of 98.28% for brain stroke prediction on the selected dataset. The data security was enhanced by integrating consortium blockchain technology with machine learning. The results show that the application is tamper-proof and is capable of detecting and automatically correcting backend data anomalies to maintain robust data protection. The application can be extended to monitor other pathologies such as heart attacks, cancers, osteoporosis, and epilepsy with minimal configuration changes.

Medical negligence, errors, and delayed diagnoses lead to preventable deaths and serious health issues. These problems are mainly caused by a shortage or lack of access to qualified healthcare professionals. In the U.S. alone, medical errors cause an estimated 44,000 to 98,000 deaths annually. The rise of artificial intelligence in healthcare has introduced new opportunities for more accurate diagnoses and predictions, with numerous artificial intelligence (AI)-driven tools now available for detecting diseases such as cancer, heart conditions, lung diseases, and liver diseases. While these tools have revolutionized diagnostics, they are primarily designed for healthcare professionals, limiting their accessibility to the general public. Providing patients with a reliable platform to help them accurately assess their health condition can be transformative, reducing medical errors, enhancing patient engagement, and improving overall care. This study introduces E-Doctor, a Generative AI-powered platform designed to provide reliable second opinions for medical diagnoses. Utilizing advanced AI technologies such as BioBERT for analyzing medical texts and federated learning for maintaining data privacy, the platform addresses the shortage of professional healthcare advice. E-Doctor platform achieved high accuracy rates: 92.4% for heart attack-related advice, 90.2% for full-body checkups, and 93.9% for Deep Vein Thrombosis prediction. By combining medical image analysis with AI-driven learning models, e-Doctor offers a robust platform for enhancing patient outcomes, while ensuring data privacy and security.

Edge computing brings data processing, analytics and storage closer to the source, but the major limitation of edge devices is that they have limited processing power and storage. Some have argued that cloud can be a solution to overcome the edge computing limitations. However, performing all tasks on the cloud introduces latency issues. Therefore, we need a solution that can use edge and cloud computing intelligently and interchangeable such that the merits of both can be utilized based on the specific scenario. Such a model has not been discussed in the literature so far which poses a very important limitation. We proposed a novel architecture that intelligently switches data processing between the cloud and edge just-in-time based on specific conditions, i.e., if a healthcare scenario demands low latency data are processed at the edge, otherwise data are automatically processed on the cloud. We illustrate this by creating an Automatic edge application to monitor high risk cardiovascular disease patients who are at the risk of heart attacks after a post-operative surgery. Low latency is very important while monitoring such patients and the application is built to automatically detect all such cases and performs heart attack predictions on the edge while other patients data is processing on the cloud. The experimental results have demonstrated that our application can automatically detect high risk cardiovascular disease patients and place their workloads on the edge which is a new and unique invention in the area of automated edge computing. We have also demonstrated that the data retrieval from the edge is 55% faster than the cloud thereby ensuring low latency with edge.

Edge computing brings data processing, analytics and storage closer to the source, but the major limitation of edge devices is that they have limited processing power and storage. Some have argued that cloud can be a solution to overcome the edge computing limitations. However, performing all tasks on the cloud introduces latency issues. Therefore, we need a solution that can use edge and cloud computing intelligently and interchangeable such that the merits of both can be utilized based on the specific scenario. Such a model has not been discussed in the literature so far which poses a very important limitation. We proposed a novel architecture that intelligently switches data processing between the cloud and edge just-in-time based on specific conditions i.e., if a healthcare scenario demands low latency data is processed at the edge otherwise data is automatically processed on the cloud. We illustrate this by creating an Automatic edge application to monitor high risk cardiovascular disease patients who are at the risk of heart attacks after a post-operative surgery. Low latency is very important while monitoring such patients and the application is built to automatically detect all such cases and performs heart attack predictions on the edge while other patients data is processing on the cloud. The experimental results have demonstrated that our application can automatically detect high risk cardiovascular disease patients and place their workloads on the edge which is a new and unique invention in the area of automated edge computing. We have also demonstrated that the data retrieval from the edge is 55% faster than the cloud thereby ensuring low latency with edge.

Internet of Medical Things (IoMT) are being used across many healthcare uses cases, however these low power devices are often susceptible to cyberattacks, which can compromise medical data security, and privacy. In addition, any critical system design must address a single-point-of-failure (SPoF) as this has a direct impact on the reliability of the deployed environment. One of the ways to overcome these challenges is to secure the IoMT deployments with blockchain technologies. Although blockchain-based digital services promise trust, accountability, and transparency, there are multiple challenges associated with a combined use of IoMT and blockchain, especially for Remote Health Monitoring (RHM). Some of the recent literature describes possible solutions to these challenges however these do not address the challenges fully and are also not foolproof. In comparison to public blockchains, private blockchains are considerably safe, however, low data availability is one of the major challenges of private blockchains due to its centralized architecture and reliability is hard to achieve as only one enterprise controls the complete system. Health systems needs to be highly available and reliable to ensure real-time patient data availability, especially for monitoring patients with critical illnesses where downtime for data retrieval and unreliable data can be fatal. In this article, we provide an implementation of a reliable consortium blockchain based RHM application for monitoring critically ill patients in a home environment. The results show that a well-designed consortium blockchain can enhance reliability and avoids a single point of failure, resulting in better health and safety for the patients.

Remote Health Monitoring (RHM) is going to reinvent the future healthcare industry and bring about abundant value to hospitals, doctors, and patients by overcoming the many challenges currently being faced in monitoring patient’s well-being, promoting preventive care, and managing the quality of drugs and equipment. Despite the many benefits of RHM, it is yet to be widely deployed due to the healthcare data security and privacy challenges. Healthcare data are highly sensitive and require fail-safe measures against unauthorized data access, leakages, and manipulations, and as such, there are stringent regulations governing how healthcare data can be secured, communicated, and stored, such as General Data Protection Regulation (GDPR) and the Health Insurance Portability and Accountability Act (HIPAA). The challenges and regulatory demands in RHM applications can be addressed using blockchain technology due to its distinguishing features of decentralization, immutability, and transparency to address the challenges of data security and privacy. This article will provide a systematic review on the use of blockchain in RHM, focusing primarily on data security and privacy.