Dell is partnering with the i2b2 tranSMART foundation to create privacy-protecting digital twins to treat the long-term symptoms of COVID-19 patients. The project hopes to treat the 5% of COVID-19 patients who develop chronic health problems. The new tools integrate anonymized data — which refers to data with all personally identifiable information removed — AI and advanced models that allow researchers to perform millions of treatment simulations based on genetic background and medical history.
This initiative is part of Dell’s long-term goal to bring digital transformation to healthcare. Jeremy Ford, Dell vice president of strategic giving and social innovation, told VentureBeat: “AI-driven research and digital twins will support hospitals and research centers worldwide and contribute to Dell’s goal of using technology and scale to improve health, education and economic development.” foster opportunities for 1 billion people by 2030.”
The i2b2 TranSMART (Informatics for Integrating Biology at the Bedside) foundation is an open-source, open-date community to enable collaboration for precision medicine. The group focuses on projects to facilitate the sharing and analysis of sensitive medical data in a way that benefits patients and protects privacy. The collaboration between Dell and i2b2 promises to create best practices for applying privacy-enhanced computation (PEC) to medical data.
I2b2 lead architect Dr. Shawn Murphy told VentureBeat that medical digital twin are essential because they allow “patients like me” comparisons between very large cohorts of similar medical twins. This will help identify things like biological markers for disease and compare treatment options for patients who share similar characteristics, such as age, gender, underlying conditions and ethnicity.
Multiple sources and types of data are used in the compilation of the medical twin, including an electronic patient record (EHR), consultation data directly from the patient, and waveform data from heart monitors, ventilators and personal fitness tracking devices.
“They could be used in the future to help researchers run millions of individualized treatment simulations to identify the best possible therapy option for each patient, based on genetic background, medical history and a greater general understanding of the long-term treatment effects,” Murphy said. .
Privacy required for adoption of medical digital twins
Privacy is a critical requirement for the widespread adoption of medical digital twins, which requires combining sensitive medical data to create the best models. “There is a significant amount of work to collect, harmonize, store and analyze the different forms of data that come from multiple locations, while preserving patient privacy and data integrity,” Murphy said.
Dell is focused on providing hardware, software and data management integration services for the project. The data enclave is designed to provide the computational, artificial intelligence, machine learning, and advanced storage capabilities needed for this work. It consists of Dell EMC PowerEdge, PowerStore and PowerScale storage systems and VMware Workspace ONE.
Researchers are still in their infancy to identify vulnerabilities in these architectures and weigh them against performance and workflow bottlenecks. With secure enclaves, sensitive data from different sources is encrypted in transit to a secure server, decrypted, and processed together. It ensures the best performance and streamlines the workflows of all PEC technologies, but also requires extensive security analysis because the data is processed clearly. Other PEC approaches, such as homomorphic computing, can process encrypted data, but are also much slower and more difficult to integrate.
Murphy said additional infrastructure would be needed to support new locations and expand the data pool to include research centers in minority institutions and hospitals outside the US. “This is particularly critical for the full representation of diversity in digital twins,” he said.
Building a common language
The digital twin research began with the establishment of the 4CE consortium, an international coalition of more than 200 hospitals and research centers, including data collaborations in the US, France, Germany, Italy, Singapore, Spain, Brazil, India and the UK. The 4CE consortium brings together all sources and types of data to create a ‘common language’ to allow comparisons between different sample populations. This makes it possible to compare medical digital twins who share similar biological markers to see which therapies work most effectively for other patients in the real world.
In theory, researchers should be able to extract data from the EHR, which is designed to manage all medical history, including treatment options, medical appointments, diagnostic tests, and the resulting treatments and prescriptions. In practice, however, Murphy said EHRs are prone to inaccuracies and missing information. For example, in the US, the code for rheumatoid arthritis is misused four times out of ten when the code for osteoarthritis should be used. “This is why we need to collect multiple sources and types of data that together will describe the patient’s condition,” Murphy explained.
The real value of the EHR comes in conjunction with real patient interviews and other forms of data to create medical digital twins and drive population-level insights. The technology used to understand long-term COVID-19 symptoms can also help create disease-specific, high-resolution medical digital twins that can be used by physicians and researchers for many other healthcare applications.
VentureBeat’s mission is to be a digital city square for tech decision makers to learn about transformative technology and transactions. Our site provides essential information on data technologies and strategies to guide you in leading your organizations. We invite you to join our community to access:
- up-to-date information on the topics that interest you
- our newsletters
- gated thought-leader content and discounted entry to our valued events, such as: Transform 2021: Learn more
- network features and more