Free EMR Newsletter Want to receive the latest news on EMR, Meaningful Use, ARRA and Healthcare IT sent straight to your email? Join thousands of healthcare pros who subscribe to EMR and EHR for FREE!

Partners AI System Gives Clinicians Better Information

Posted on January 25, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

While HIT professionals typically understand AI technology, clinicians may not. After all, using AI usually isn’t part of their job, so they can be forgiven for ignoring all of the noise and hype around it.

Aware of this problem, Partners Connected Health and partner Hitachi have come together to create an AI-driven process which isolates data physicians can use. The new approach, dubbed ‘explainable AI,’ is designed to list the key factors the system has relied upon in making projections, making it easier for physicians to make relevant care decisions.

Explainable AI, a newer term used by the two organizations, refers not only to the work being done to develop the Partners system, but also a broader universe in which machines can explain their decisions and actions to human users. Ultimately, explainable AI should help users trust and use AI tools effectively, according to a Hitachi statement.

Initially, Partners will use the AI system to predict the risk of 30-day readmissions for patients with heart failure. Preventing such readmissions can potentially save $7,000 per patient per year.

The problem is, how can organizations like Partners make AI results useful to physicians? Most AI-driven results are something of a black box for clinicians, as they don’t know what data contributed to the score. After all, the algorithm analyses about 3,000 variables that might be a factor in readmissions, drawing from both structured and unstructured data. Without help, there’s little chance physicians can isolate ways to improve their own performance.

But in this case, the AI system offers much better information. Having calculated the predictive score, it isolates factors that physicians can address directly as part of the course of care. It also identifies which patients would be the best candidates for a post-discharge program focused on preventing readmissions.

All of this is well and good, but will it actually deliver the results that Partners hoped for? As it turns out, the initial results of a pilot program are promising.

To conduct the pilot, the Partners Connected Health Innovation team drew on real-life data from heart failure patients under its care. The patients were part of the Partners Connected Cardiac Care Program, a remote monitoring education program focused on managing their care effectively in reducing the risk of hospitalization.

The test compared the results calculated by the AI system with real-life results drawn from about 12,000 heart failure patients hospitalized and discharged from the Partners HealthCare network in 2014 in 2015. As it turned out, there was a high correlation between actual patient readmissions and the level predicted by the system. Next, Partners will share a list of variables that played the biggest role in the AI’s projects. It’s definitely a move in the right direction.

We’re Just Getting Started with an Internet of Healthy Things (Part 3 of 3)

Posted on November 27, 2015 I Written By

Andy Oram is an editor at O'Reilly Media, a highly respected book publisher and technology information provider. An employee of the company since 1992, Andy currently specializes in open source, software engineering, and health IT, but his editorial output has ranged from a legal guide covering intellectual property to a graphic novel about teenage hackers. His articles have appeared often on EMR & EHR and other blogs in the health IT space. Andy also writes often for O'Reilly's Radar site (http://oreilly.com/) and other publications on policy issues related to the Internet and on trends affecting technical innovation and its effects on society. Print publications where his work has appeared include The Economist, Communications of the ACM, Copyright World, the Journal of Information Technology & Politics, Vanguardia Dossier, and Internet Law and Business. Conferences where he has presented talks include O'Reilly's Open Source Convention, FISL (Brazil), FOSDEM, and DebConf.

The previous sections of this article described the state of health care today and some of the impressive advances described in Joseph Kvedar’s new book, The Internet of Healthy Things. Now we’ll look at the possibilities for advancing further, and what stands in the way.

Futures postponed

Later in the book, Kvedar explores the promise of analytics. On a small scale, analytics can tie the results of traditional clinical research to recommendations for individuals. For instance, if the A1C hemoglobin of a person with diabetes hits a certain level that clinical research has established as dangerous, she can be notified. We also know what heart rates are best for exercising and other useful statistics. Walgreens and CVS also use data at this level to market their products to consumers who sign up for their fitness tracking programs.
Read more..

We’re Just Getting Started with an Internet of Healthy Things (Part 2 of 3)

Posted on November 25, 2015 I Written By

Andy Oram is an editor at O'Reilly Media, a highly respected book publisher and technology information provider. An employee of the company since 1992, Andy currently specializes in open source, software engineering, and health IT, but his editorial output has ranged from a legal guide covering intellectual property to a graphic novel about teenage hackers. His articles have appeared often on EMR & EHR and other blogs in the health IT space. Andy also writes often for O'Reilly's Radar site (http://oreilly.com/) and other publications on policy issues related to the Internet and on trends affecting technical innovation and its effects on society. Print publications where his work has appeared include The Economist, Communications of the ACM, Copyright World, the Journal of Information Technology & Politics, Vanguardia Dossier, and Internet Law and Business. Conferences where he has presented talks include O'Reilly's Open Source Convention, FISL (Brazil), FOSDEM, and DebConf.

The previous section of this article described the dire condition of health care today. So where does Kvedar’s book, The Internet of Healthy Things,fit into all this? It encapsulates all those years of learning at his Center for Connected Health, set up by the Boston-area giant Partners HealthCare and now renamed Partners Connected Health. From these insights, the book pinpoints the areas where innovators can make headway. He shows the gap between how we approach chronic health conditions now–even among the companies experimenting with mobile health and patient engagement–and the ideal for which the Partners Connected Health is striving. In reviewing his suggestions, I’ll try also to shine lights into passageways he did not explore.

Lessons from the field

Kvedar divides the evolution of connected health into three broad phases. Most companies are now in the first phase of simply reporting statistics back to patients and doctors. You can find out from a mobile app what your blood sugar is, and from your fitness bracelet how far you’ve walked during the day. This phase can have some benefits on athletes and the small set of Quantified Selfers who love data, but has absolutely no appeal for the vast mass of people who most need support.

Partners Connected Health has entered the second phase and has its own data to show the great strides it has made. In this phase, you engage the patients by connecting him to his providers, family, and friends, making him feel watched (the Sentinel Effect) and therefore extracting healthier behavior. This starts to achieve the changes we want, but is still limited in the people we reach.

The third stage is to fit the intervention directly to the lifestyle and needs of the individual, a process Kvedar calls “hyperpersonalization.” If walking your dog is an important part of your life, the system should feed you messages encouraging you to do things that improve your endurance and walking ability. If you want to fit into smaller clothing for an upcoming wedding, focus on everything that can get your waistline down.

Kvedar’s vision does not seem to be the automated-intelligence utopia laid out by Vinod Khosla and others, where patients get automated diagnoses and treatment recommendations from the “cloud” and avoid physicians for most ailments. Rather, technology for Kvedar supports a strong relationship between patient and clinician. At the same time, the technology extends the clinician’s reach–and allows her to treat many more people with greater effectiveness–by bringing the treatment plan into the patient’s everyday life, throughout the day.

The first chapter of the book lays out a fantasy scenario for an automated coach that follows the individual around and sends messages right before he reaches for a cookie or is about to stay up too late at night. Kvedar unveiled the same scenario, which was quite amusing, in his introduction to the Connected Health conference. I covered the major aspects of this hyperpersonalization–automated, contextual, motivational, empowering, and incentivizing–in another article. It has to be done very careful in order not to appear intrusive and annoying, but it offers a greater promise to change behavior than anything else we know.

I already see one difficulty with organizations aiming at this vision of health care. Kvedar talks a great deal about apps–the little agents you download from the Apple Store or Google Play. But hyperpersonalization is not an app. It’s a whole environment for dealing with personal lifestyle–aided by apps, to be sure, but requiring a deep investigation into the patients’ needs and interests. What Kvedar is really calling for is not a prize-winning app, but a reconfiguration of our health system.

In the face of such a challenge, several organizations are stepping up. Among their ranks are scattered a few traditional health care organizations (providers such as Kaiser Permanente and Kvedar’s own Partners HealthCare, insurers such as Aetna) but most come from the outside. Kvedar concentrates on the clinics and wellness programs set up by Walgreens pharmacy. Their integration of convenience and support for ongoing behavior change is much more thorough than most people realize.

Another example of an integrated strategy is provided by a single teenager whose caretakers are monitoring his diabetes remotely. The process brings the teen’s doctor and mother into the picture with technologies that include an unusual skin sensor, Apple HealthKit, and an Epic health record. The solution is not an open one.

It’s great for Walgreen’s to fix sore throats and minor cuts, and even to start offering primary care. But people with serious health needs will eventually need to interact with a traditional clinic or hospital. If these institutions still can’t accept data from the urgent health clinic (some already can), the same old inefficiencies and errors will re-emerge. And this failure to evolve with the times is a danger even though, as Dr. Kvedar repeatedly warns, it threatens the continued existence of the traditional hospitals.

The final section of this article will look at the gap between where we are now and where The Internet of Healthy Things would like us to be.