Artificial Intelligence

Real-world evidence drawn from unstructured clinical notes was more accurate in algorithmic prediction of coronary artery disease than structured data, a new study in JAMIA shows.

In most industries, change or evolution isn’t a gradual process. You might have years and years of equilibrium, with little improvements here and there, and then all of a sudden a massive technology and/or business model change takes us to a new level. For example, the taxis of 1950 looked a lot like the taxis of 2010. Then along came ride-sharing apps. Now, as we look forward to self-driving cars, I would say that the “rent-a-ride” market is in the middle of an explosion of rapid change – how it will end, we don’t know. Looking at how technology has changed the healthcare industry, I would argue that we have already had one explosion of rapid change, and we are in the middle of a second one now.  When my career started, we wrote billing systems – systems with structured data, typed in on numeric keypads, by dedicated users of the computer. This was the first generation of success in health IT, and it digitised the administrative parts of healthcare. Then a number of technology breakthroughs happened – standardising on SQL databases, the storage and viewing of text and images, and perhaps most importantly, the graphical user interface. This allowed non-dedicated users, like physicians, nurses and patients, to use software to help them with their work and lives. This ushered in the next couple of decades where we built and deployed electronic medical records (EMRs). Now health IT is in the middle of a second explosion of rapid change. This disruption to healthcare offers the promise of even bigger benefits – with improved outcomes and reduced costs – than we have seen with digitisation to date. If you look at the disruptive technologies of today: cloud, artificial intelligence (AI), wearables, imaging/text analytics, advanced interoperability and ubiquitous user experience (UX), we have the raw ingredients for this next massive change. And if you examine that list, not one of those technologies has reached its full potential yet. They are all showing promise, but most importantly, they are incredibly promising as we explore the various use cases where they can help. The history of InterSystems has mirrored this trajectory. Our initial database technology enabled the major billing systems of the original health IT market. A couple of decades ago, we launched our Caché product line and enabled the major EMRs in the market today, including Epic, and our own EMR TrakCare. Last year, in line with this current explosion of rapid change, we launched our next platform, InterSystems IRIS for Health, to bring capabilities for this current explosion of rapid change – cloud, AI, API interoperability, analytics – to our customers. And some of our customers are already embracing these capabilities to change the way they support the healthcare industry. Earlier this year, MediWay Technology, one of the largest healthcare software companies in China, deployed its new iMedical Cloud healthcare IT ecosystem platform using IRIS for Health. This allows MediWay’s iMedical healthcare information system (HIS) to support all stakeholders in the Chinese healthcare system – including government, healthcare organisations, and consumers – in an environment where medical reform policies are driving increased collaboration, information sharing and use of big data. Two iMedical Cloud applications, hosted on Tencent Cloud, were launched – transactional cloud collaboration (Cloud HIS) and data cloud collaboration (HealthChain). These can be used within a region for real-time healthcare information exchange, centralised management control and unified allocation of resources. Built and deployed on a unified data platform, iMedical Cloud supports the vastly increased data volumes required with features like sharding. This distributes data across a number of cloud-based servers to provide flexible, inexpensive performance scaling. On the other side of the world in New York, HBI Solutions is using machine learning and predictive analytics to convert vast amounts of data into knowledge that can be applied in real time to decision support. Healthcare providers see not only their patients’ pasts, but also their likely futures. HBI’s Spotlight Data Solution identifies elements, or “features”, in health records that could indicate future problems.  What’s exciting about being in the middle of a period of rapid change is you don’t know how it will turn out. What is quite clear, based on the enabling technologies of this era, is that we are moving closer and closer to the patient, and closer and closer to being helpful to the clinicians and not just an administrative sidekick. Health IT has had a long and illustrious history digitising healthcare. But now we are about to create an even better future. I can’t wait to see what we build together. Are you looking for someone who you can talk to about your own rapid changes? Take the next step here.  About the Author As Vice President, InterSystems HealthShare, Don Woodlock oversees a family of products created to empower the transformation of health and care through comprehensive, shared health information. In his role, Woodlock is responsible for advancing the HealthShare vision to meet the challenges associated with delivering improved quality, accessibility and efficiency across the health and care industries.

Promising AI tools can enable physicians to perform more effectively across the work that they do, says Dr. Jesse Ehrenfeld, board of trustees chair for the American Medical Association.

Genomic medicine researchers at the laboratory have been using artificial intelligence, developed as part of Microsoft's Project Hanover, to help manage the vast amount of research data needed to power its precision oncology initiatives.

The leading-edge technology could provide vastly faster power and processing speeds, and enable fundamentally different algorithmic search and data homogenization strategies.

The two funds are the Artificial Intelligence and Digital Translation Fund, which boasts initial funding of $30 million over five years, and the Translational Innovation Fund, which will provide $50 million in funding over six years.

The edge computing technology's neural network algorithms can help drive workflow efficiency, detect gaps in care and deliver real-time intelligent notifications to staff, the AI developers say.

The Mayo Clinic's new 10-year partnership with Google Cloud aims to look for the next breakthroughs that diagnose and treat complex and serious illness or conditions more effectively, says CIO Cris Ross.

A new report from EY shows how health systems need to embrace AI, social, mobile, analytics, cloud and sensor technologies to unlock the potential of their data.

Researchers will also focus on adapting existing clinical decision support methods from the acute care sector, collaborating with clinicians to understand reliable signs of patient deterioration.