Optimizing Care Transitions: Where Do Predictive Analytics Tools Fit In? | Healthcare Informatics Magazine | Health IT | Information Technology Skip to content Skip to navigation

Optimizing Care Transitions: Where Do Predictive Analytics Tools Fit In?

October 13, 2012
by Mark Hagland
| Reprints
At the five-hospital Inova Health System in northern Virginia, Daniel Rosenthal, M.D. is helping to lead a groundbreaking effort to better predict the need for interventions and optimize care transitions

Daniel Rosenthal, M.D., M.P.H., M.Sc., is director of healthcare analytics at the Falls Church, Virginia-based Inova Health System (www.inova.org) Health System. Inova encompasses five hospitals with more than 1,700 beds and 16,000 employees, as well as specialized care and research units, including the Inova Heart and Vascular Institute, Inova Translational Medicine Institute on Genomics, Inova Neuroscience Institute, and Inova Children’s Hospital.

Rosenthal, an internal medicine physician by clinical background, was most recently senior advisor in health IT at the National Quality Forum before recently coming to Inova in February 2011. He is also co-founder and president of WardManager (www.wardmanager.com), a team-based sign-out system that wirelessly enhances care management and patient safety in inpatient hospital wards and in medical specialist groups. Inova is a client of WardManager, for its sign-out solution. Rosenthal spoke recently with HCI Editor-in-Chief Mark Hagland regarding his activities at Inova and his perspectives on the challenges and opportunities involved in working to improve caregiver transitions. Below are excerpts from that interview.

Can you explain your various professional roles—executive, clinical, and entrepreneurial?

My routine is to spend four-and-a-half days a week at Inova. I see patients on Friday afternoons at George Washington University Medical Center in DC in Urgent Care. And then everything I’ve done with WardManager Signout is on nights and weekends.


Daniel Rosenthal, M.D., M.P.H., M.Sc.

How long have you been practicing as an internist?

I finished medical school in 2001, and before my residency training, I did a National Institutes of Health informatics fellowship, so I spent three years at Mass General, and got a master’s in informatics and a master’s in public health, before finishing my residency in 2007; so I’ve been practicing since 2007.

How do your various professional roles relate to each other?

Each one of my different roles might seem somewhat related, but in reality, they’re fairly divorced from each other. As director of healthcare analytics at Inova, I don’t have a particular tasking of building an EHR, or convening a particular group, for example. Our job here is to help others ask the right questions and provide the right answers. On the clinical side, “I want a dashboard of our length of stay, and stratify it by complexity of disease or co-morbidity,” for example. So it’s everything from fulfilling requests for simple extracts—“can you tell me which inpatients right now have CHF?” And most everything we do is retrospective, but could be retrospective to the past 24 hours—and ranging to an interactive dashboard to be able to zoom in and out on population health.

The hot topic right now is predictive analytics. We’ve got a million patients; can we determine the predictors of particular situations and outcomes? So it sort of runs the gamut of your traditional operational, bread-and-butter things to more lofty questions like, can you predict who will have a bad outcome? But the real challenge is, what are you going to do about it? And a lot of people in IT are attracted to the dangling, shiny object. But when it comes to building predictive tools, the question is this: is your organization positioned to build on and act on uncertainty?

How big is your team at Inova?

We have seven people on my consulting team. I’m the only physician; we have two folks with a quality background; and we have another person with a strategic planning and organizational management background, so I'm used to dealing with clinical scenarios. And on the technical side, we have a traditional database administrator, an “all-rounder” systems engineer and then a systems analyst with a traditional mix of database and IT systems background. We have an additional eight report writers and reporting coordinator.

With regard to our organization, right now, we are in the middle of our go-live process with the Epic EHR solution. Meanwhile, our whole organization is sort of shifting from a “best- of- breed” organization to a focused one, with a centralized EHR and centralized analytics. The challenge for us is how we do this well, without outstripping our organization’s ability to consume the information, and without investing in too much vaporware, so to speak.

What projects have you been working on lately, especially patient safety-related ones?

One thing we’ve been working on is a real-time sepsis monitor. It’s a very simple list: here are the patients at risk. The challenge is identifying the appropriate mechanism for integrating into the clinical workflow. The easy part is building it technically, though that’s still challenging. But the big challenge is, once you have the answer, putting in place the processes for improvement. Because there’s a lot of, “Ooh, wouldn’t it be cool to do this?” But then, afterwards, did the people asking for this realize there would be a 40-50 percent false positive rate? And the same questions go into alerts and reminders. And this sepsis alert provides clinical decision support. It says, for these patients, you should consider ordering these extra lab tests, and extra screenings. But if you deliver high false-positive information to physicians, they just ignore that information. So you have to figure out how you implement the screening process, and which people need to act on it.

So, some of the lab tests in this area will come out as false positives?

No, the lab tests themselves are quite accurate. It is the conclusions that one draws from a collection of tests and observations that predict the probability of a disease that is more art than science. Alerts built on uncertainty naturally produce false positives. So if you deliver that alert: here are the 100 patients with abnormal vital signs and abnormal lab tests, and those patients may or may not be septic, the physician may say, “Well, OK, but some of those patients may have other reasons for having abnormal tests.” In fact, in organizations that do this well, this monitoring is often not done by the physicians, but by nursing or by a centralized sepsis monitoring in the hospital. One of the challenges is that we’re building our analytic capability while we’re implementing Epic, so we’re dealing with limited organizational attention span and resources.

And a lot of the stuff we’ve done around quality so far is very, very simple stuff, such as when people say to me, ‘Danny, we don’t know who in the hospital has congestive heart failure. We could find out via chart review. But can you tell me who has CHF based on those labs and medications?’ And sure, that’s easy. We have a process here called Transitional Care Management (TCM), which is about how to engage patients while in the hospital, and how to make sure that all the discharge and follow-up processes are engaged, to prevent readmissions and adverse events.

And we had that program in place, but the case managers just didn’t have the data. So they said, “Can you tell us who in the hospital has heart failure, diabetes, and COPD [chronic obstructive pulmonary disease]?” And I said, “Sure, that’s easy.” To date, a lot of the rate-limiting steps in some of these areas have been around lack of data. But now with EHRs—and I’ve trained on at least 15 different EHRs in the course of my practice—now, we’re transitioning into the next phase of, what are we going to do with the data? And this is where I see informatics making a shift away from building and designing systems, such as building CDS or interfaces or building a button here and there, to now, with EHR vendors picking up the pace, following implementation, the question will be, how do we effectively use the data for analytics and for population health?

What do you see as the biggest patient safety issues related to transitions of care?

I think that some people believe that patients just sort of just hang out in the hospital; but in reality, these days, if you’re in the hospital, you’re very sick. So everyone in hospitals is sick 24/7, and the biggest risks to transitions of care are adequate communications processes. Sometimes, clinicians are just following too many patients. And residents are often overwhelmed, and the many institutions rely on residents for the complete management of patients. In community hospitals, nurses take a lot of that burden off the physicians. In teaching hospitals, it’s often not having adequate processes of transitions of care. Maybe you’re working off an Excel spreadsheet, and the information isn’t being captured in a structured way.

But even with great EHRs, it’s challenging, because EHRs may not have the appropriate fields available, or they’re not structured appropriately, or the workflows and printouts are awkward. So it’s not that vendors can’t do it well, but that they haven’t chosen to do it. That’s why we provide a structured, standardized process for sign-outs with Ward Manager. It’s not rocket science; it’s a web-based dashboard that allows you to manage the patients that you’re following.

So, in the inpatient setting, the challenges of transitions of care are around structured process and structured data, and making things very, very easy. If you have a system that can generate a sign-out list, it may be 50 pages long. You may have 50 patients on your list, and having 50 pages in your pocket is not workable. Another big handoff is between inpatient and outpatient, around discharge. We don’t do that yet [at WardManager] but would like to. I’ve approached all of our clients with this functionality, and they all said it sounded good in theory, but had questions as to who should pay for the service as patients are being discharged to outpatient.

Might that change with the development of accountable care organizations?

That’s the intent. But we might run into the same issues, if a patient is being discharged to a provider that’s not a part of that ACO. And the sad part is, there’s a ton of technology, and there are CCDs [continuity of care documents] and everything else; and what’s really needed is so, so minimal. You don’t need to communicate the entire record, rather just that the patient was in the hospital for this reason; they have been started on two medications and taken off another med; they had an abnormal stress test, and their last hemoglobin was 10, and you need to recheck that over the next week. And that’s a simple set of pieces of information that often gets lost in the wash of data.

So what do clinicians, care managers, and clinical informaticists need to do in this whole area in the next couple of years, to improve care quality around transitions?

I think that data capture and collection and access to information have been the bottleneck. Physicians are often overwhelmed having to collect everything. And they’re overwhelmed having to track lab results back and forth. So accessing and collecting information needs to be done for us physicians. Most quality folks spend 95 percentthe majority of their time collecting data and entering into charts and tables of some kind; but very little time analyzing data and thinking about it is actually being done. Hopefully, we will be freed from the information collection burden, and the quality folks will actually be able to work on quality, and the physicians will actually, hopefully be able to spend more time talking with patients, now that this administration task has been taken off of us.

In addition, I believe that tracking and following data will increasingly be pursued by [specialized care management professionals]. And once those tasks come off us doctors, and we’re able to spend more time on patient care, important conversations will take place among all these [stakeholder] groups.  I already see that happening here at Inova. And I wasn’t even looking for quality folks necessarily to join this team, but people are coming to the team because they’re interested in leveraging the data for quality improvement. So I’m hoping that hospital organizations will be able to change their structures to reflect not just multidisciplinary teams on rounds, but also in hospital operations.


2018 Seattle Health IT Summit

Renowned leaders in U.S. and North American healthcare gather throughout the year to present important information and share insights at the Healthcare Informatics Health IT Summits.

October 22 - 23, 2018 | Seattle


/article/optimizing-care-transitions-where-do-predictive-analytics-tools-fit

See more on

betebettipobetngsbahis