Can a Prescription for Fresh Food Treat Diabetes? At Geisinger, an Informatics-Driven Project Is Showing Promising Results | Healthcare Informatics Magazine | Health IT | Information Technology Skip to content Skip to navigation

Can a Prescription for Fresh Food Treat Diabetes? At Geisinger, an Informatics-Driven Project Is Showing Promising Results

February 8, 2018
by Heather Landi
| Reprints
Project leaders have seen significant improvements in clinical outcomes for patients enrolled in the Food Farmacy program, to date
Click To View Gallery

Hospitals and health systems across the U.S. are all feeling the impact of the growing problem of chronic disease, and diabetes is one of the most pervasive and costly chronic diseases. An estimated 30.3 million people in the U.S. have diabetes, or one in 10 adults, and at a cost to healthcare of $245 billion per year, according to the Centers for Disease Control and Prevention (CDC).

The CDC estimates that, if current trends continue, the number of U.S. adults with diabetes could rise to one in five, or even one in three, by 2050.

At the same time, food insecurity also is a widespread problem across many communities, and many healthcare leaders note that studies have shown a correlation between low food security and poor diabetes self-management. In central Pennsylvania, food insecurity is particularly serious in many of the communities that the Danville, Pa.-based Geisinger Health System serves, according to health system executives. While 12.7 percent of the U.S. population and 18 percent of children are food-insecure, in many of the counties Geisinger serves, those numbers are even worse: 14 percent of the overall population and 23 percent of children. One in eight of these food-insecure people has diabetes, according to Geisinger executive leaders in an article published in Harvard Business Review.

With the aim of addressing food insecurity, as a significant social factor impacting health, and to improve patients’ diabetes management, Geisinger launched an IT- and data analytics-driven Fresh Food Farmacy initiative to provide fresh, healthy food to diabetes patients, at no cost to the patients. The health system initially launched the program in July 2016 as a pilot project at Geisinger Shamokin Area Community Hospital in Coal Township, in Northumberland County, which has the second-highest rate of long-term diabetes complications in central Pennsylvania.

“Geisinger is very focused on approaching medical conditions from a population health perspective—we not only want to take care of each person that’s in front of us and provide them with the best state-of-the art care that we can, but we also look at our patients in their communities and see how we can improve the overall health of those that we serve,” says Andrea Feinberg, M.D., medical director of Health and Wellness at Geisinger Health, and the clinical champion of the Fresh Food Farmacy.


Experience New Records for Speed & Scale: High Performance Genomics & Imaging

Through real use cases and live demo, Frank Lee, PhD, Global Industry Leader for Healthcare & Life Sciences, will illustrate the architecture and solution for high performance data and AI...

Andrea Feinberg, M.D.

While Geisinger healthcare leaders are using an old approach, essentially “food as medicine,” to tackle medical conditions, the Fresh Food Farmacy initiative is an informatics-driven project that relies heavily on data integration, analytics and mobile technology to do everything from tracking clinical outcomes to managing the food supply chain.

Jonathan Slotkin, M.D., director of spinal surgery in the Geisinger Health System Neurosciences Institute, also serves as medical director of Geisinger in Motion, a department focusing on digital engagement and patient- and provider-facing mobile device technologies, within the division of informatics at the health system. Slotkin helps lead the informatics work that underlies the Fresh Food Farmacy project.

“For me, it’s fascinating from an informatics standpoint because it brings together traditional clinical care, which we’ve all gotten pretty good at, but it also brings in the harder issues around data and the transactional level of social determinants of health, costing, supply chain and distribution, things that most medical systems are not yet optimized for. I think as we all endeavor to manage and help our populations with social determinants of health, we are going to be faced with these challenges more and more,” he says.

An IT-Driven Effort to Provide Healthy Food

The Fresh Food Farmacy pilot began two years ago with just six patients, all diagnosed with Type 2 diabetes. To start the program, Feinberg says the project team first queried the health system’s electronic health record (EHR) to identify adult patients in selected zip codes who had a diagnosis of type 2 diabetes and hemoglobin A1C levels over 8.0, indicating that their disease was not controlled. Well-controlled diabetic patients typically have A1C levels under 7.0, Feinberg says. The program also targeted patients who received primary care through Geisinger physicians to enable the team to study and track clinical outcomes.

The project team also leveraged the MyGeisinger patient portal tool, which links to the health system’s Epic EHR, to screen patients for food insecurity. Care managers also called patients to screen them for food insecurity. “Our hypothesis was, and still is, that if you have unmet social needs and if you are faced with food insecurity and you cannot afford to pay for healthy, nutritious food, then your diabetes cannot be well controlled,” Feinberg says.

Slotkin notes, “This is an interesting informatics question because it is a large population health problem and we are approaching it that way, but at the same time, it very much affects individuals and individual families. We have a nice span of human touch and human interaction combined with the use of our EHR and our patient portal to leverage the enrollment to this program.”

Early on in the project, program leaders recognized specific data governance issues that needed to be addressed to make the program more effective, Slotkin says.In a lot of health systems, medical problems being added to the EHR problem list is something that usually only happens under physician direction. We felt that food insecurity was both pervasive enough and devastating enough that we needed to liberate it, so non-physician providers, like dieticians or others, could have the authority to add food insecurity to the problem list. Food insecurity does have a recognized diagnostic code. We took that through our senior leadership governance committee, and Andrea was successful in getting approval for non-physicians to add that to the EHR problem list.”

Jonathan Slotkin, M.D.

The program has now been expanded to 115 patients, with the goal of reaching 250 patients for the Fresh Food Farmacy in the next six months. Feinberg notes that the food provided to patients is enough to feed the patients as well as the family members in their households. “Once we get up to 250 patients, we’ll be feeding somewhere between 750 and 1,000 people per week,” she says. Geisinger has several community partners, including the Central Pennsylvania Food Bank, that provide food, mostly fresh fruits, vegetables, lean proteins and whole grains, for the program, at a reduced cost to the health system. Patients enrolled in the program are provided fresh, healthy food at no cost.

Patients who fit the screening criteria and show interest in the program are referred to an enrollment class, where they meet with their care team and receive a “prescription” for healthy, diabetes-appropriate food. A multidisciplinary team comprising a program coordinator, nurse, primary care physician, registered dietitian, pharmacist, health coach and community health assistant help to develop a nutritional counseling plan for each patient. Patients receive enough food weekly, along with recipes, to prepare healthy and nutritious meals twice a day for five days, and patients also receive more than 20 hours of diabetes education. “Our program is different than a regular food bank or food pantry in that while we believe that closing the meal gap and ending hunger is very important, we also think that taking care of diabetes is not only about the food, it’s about understanding your diseases. We expect our patients to attend our diabetes self-management class to help them to understand this very complicated condition,” Feinberg says.

Feinberg and other project leaders have seen significant improvements in clinical outcomes for patients enrolled in the Food Farmacy program, to date. With 12 months of healthy food and lifestyle changes, project leaders have seen patients’ A1C levels drop more than two points, from an average of 9.6 before the program to 7.5. “A two-point drop, or 20 percent, is very, very significant. That’s why we feel confident that we’re on the right path,” Feinberg says. “We’ve seen their A1C levels come under control, and we see very significant improvements in blood pressure, as well as total cholesterol improved.”

What’s more, utilizing payer-side claims data, project leaders drilled down into the care costs for patients in the program and found that costs dropped by two-thirds, on average, across the program.

Lessons Learned Around Behavioral Change and Analytics

There have been a number of lessons learned along the way, such as recognizing that it may take several months for patients to maintain behavioral changes. “Another lesson we’ve learned is that people who have these unmet social needs, they have a lot of unmet social needs. So, if you don’t have money to buy healthy food, it’s very possible that you also don’t have reliable housing or reliable transportation. That makes it hard for us to recruit patients and to get people engaged. Once they are in the program, they love it and we have a very low attrition rate,” Feinberg says.

Feinberg and Slotkin both agree that robust data analytics plays a critical role in the success of the Fresh Food Farmacy project. “The data analytics is huge; we have an incredible dashboard that we use and it tracks what’s going on with the patients and the program. Without that, we would not be able to support the work that we’re doing,” Feinberg says. “We all understand that if you don’t have the money to buy healthy food, then your diabetes can’t be under good control, but I need to be able to prove it, by showing the decrease in A1C levels, the drops in cholesterol, the drops in blood pressure and weight, and then follow that up by showing that it is saving money for the health system. Without that, then it’s just a nice program.”

She adds, “To other healthcare providers that are interested in this type of program, we recommend not only finding good community partners, but also make sure that you have great data analytics behind it to be successful.”

What’s more, IT leaders on the project are taking steps to improve data capture processes and are currently beta-testing a mobile app based on Apple’s CareKit platform. The app enables patient engagement, access to educational content, communication, and real-time data exchange with a provider-facing clinical dashboard on iPads. For instance, patients can wirelessly sync their Bluetooth-enabled glucometer or blood pressure cuff with the app and that data is transmitted to the provider-facing dashboards.

“What we’re seeking to do here is to connect our patients with the provider team as a method of digital engagement, but also as a method of actual clinical care and lifestyle tracking, both for the patient themselves and in communication with the care team,” Slotkin says. “What we really like about this app that it is HIPAA secure, with cloud backend syncing with multiple providers on dashboards who can drill down to the individual patient level and also look at large populations of patients at the same time, to look at things such as lab data, glucose levels and blood pressure, as well as physical activity.”

Slotkin adds, “This project has really brought out some of the absolute best in the analytics infrastructure at Geisinger. We have a range of data questions here, which include the delivery of care at the individual level and clinical outcomes, of course. Then there are the Farmacy-related questions of medication adherence or the decreased need for medication, as we’ve observed in a number of patients. And then also we have cost of care changes.”

Geisinger work closely with its health insurance company, Geisinger Health Plan, to pull in claims data and integrate it with clinical data. “A lot of the claims side data, so the reduction in per member, per month charges comes from the luxury at Geisinger of being able to get that payer-side data,” he says.

In addition, executive project leaders are looking at technology solutions to address supply chain issues related to food distribution. “Right now, we’re doing that on a homegrown system and we want to improve on that. Our future roadmap right now, we’re asking some great questions around potentially even the need for customer relationship management (CRM) solutions that can handle distribution and supply chain,” he says.

What’s more, project leaders want to incorporate more social determinants of health data from community partners. “We want to be able to communicate with a patient’s non-Geisinger social worker in the community, and a lot of that data stream is not well-meshed with current versions of electronic health records, at least in their pure form. So, whether we do this through an expanded use of conventional EHRs, or we build our own, or we work with a CRM partner, these are things that we’re actively contemplating as we speak,” he says.

“We found historically that these are often very disengaged patients; they have been disappointed, they don’t know how to take care of themselves and they don’t have resources to buy healthy food,” Feinberg says. “We’re giving them the education and the tools they need, we’re removing the obstacles, and with that, we follow the improved health and improved fiscal outcomes as well.”


2019 Southern California San Diego 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.

April 23 - 24, 2019 | Southern California


You Have to Learn to Walk Before You Can Run With Predictive Analytics

November 11, 2018
by David Raths, Contributing Editor
| Reprints
Health systems report obstacles in turning their big data into actionable insights

The title of a recent webinar says all you need to know about predictive analytics in healthcare: “Within Sight Yet Out of Reach.”

The Center for Connected Medicine, jointly operated by GE Healthcare, Nokia, and UPMC, put on the webinar and partnered with HIMSS on a survey on the state of predictive analytics in healthcare.

The survey of 100 health IT leaders found that approximately 7 out of 10 hospitals and health systems say they are taking some action to formulate or execute a strategy for predictive analytics. But despite the buzz and potential, there are obstacles for health systems that want to turn their big data into actionable insights.

Although 69 percent said they are effective at using data to describe past health events, 49 percent said they are less effective at using data to predict future outcomes. They cite a lack of interoperability and a shortage of skilled workers as barriers. “They want to put all that data to work to provide insights as we deliver care, but it is not an easy task,” said Oscar Marroquin, M.D., chief clinical analytics officer at UPMC. “They are having trouble getting access to the data in useful and standardized formats and don’t have the people in place to apply machine learning techniques.”

The top five use cases cited in the survey are:


Experience New Records for Speed & Scale: High Performance Genomics & Imaging

Through real use cases and live demo, Frank Lee, PhD, Global Industry Leader for Healthcare & Life Sciences, will illustrate the architecture and solution for high performance data and AI...

• Fostering more cost-effective care

• Reducing readmissions

• Identifying at-risk patients

• Driving proactive preventive care

• Improving chronic conditions management

UPMC’s journey into the analytics space was jump-started by an institutional commitment to building the analytics program and a recognition that it needed to be a more data-driven organization. “We were never able to consume our data to drive how we deliver care until we had a dedicated team to do analytics,” Marroquin said. “Traditionally these functions were done as a side job by team members in IT systems. We have found having a dedicated team is absolutely necessary.”

Mona Siddiqui, M.D., M.P.H., chief data officer at the U.S. Department of Health & Human Services, says she is focused on the interoperability aspect across 29 agencies. “We are looking at how we are using data across silos to create more business value for the department,” she said. “We don’t have that infrastructure in place yet,” which leads to one-off projects rather than tackling larger priorities. She is focusing on enterprise-level data governance and interoperability structures. “I think the promise of big data is real, but I don’t think a lot of organizations have thought through the tough work required to make it happen. Practitioners start to see it as buzzword rather than something creating real value. There is a lot of work that needs to happen before we see value coming from data.”

Noting the survey result about human resources, she added that “the talent pool is an incredible challenge. While we talk about sharing data and using it for business intelligence, we don’t resource our teams appropriately to fulfill that promise.”

She said the move to value-based care has made predictive analytics more important to health systems. “It is a data play from the ground up,” and now we are starting to see the real impact in terms of managing chronic conditions. “More organizations like UPMC are seeing this is about data and measurement and bringing in not just data they have, but resources and data they may not have had access to previously.”

Travis Frosch, senior director of analytics at GE Healthcare, said that hospitals generate petabytes of data per year, yet only 3 percent is tagged for analytical use later on. “So 97 percent goes down the drain,” he added, suggesting that organizations need to start small. “If you are an organization that does not have maturity in analytics, start with traditional business intelligence to build the trust and foundation to move toward higher level of analytics maturity,” Frosch said. “Pick projects that don’t require tons of data sources. If you get a good a return on investment you can open up the budget to further your analytics journey. But you have to have a unit in place to measure the impact.”


More From Healthcare Informatics


Survey: More Than Half of Healthcare CIOs Lack Strong Trust in Their Data

November 9, 2018
by Heather Landi, Associate Editor
| Reprints

For U.S. healthcare leaders, trusted data is more important than ever, as their organizations migrate from the fee-for-service model to value-based care. However, a recent survey of CIOs found that less than half of healthcare organizations show very strong levels of trust in their data.

The survey, by Burlington, Mass.-based Dimensional Insight, an analytics and data management solutions provider, is based on responses from 85 members of a professional organization of CIOs and other healthcare IT leaders about trust in data across their enterprises.

During this transition from fee-for-service to value-based care, healthcare organizations must weigh investments, risks, and trade-offs objectively with quantitative, trustworthy data. This kind of data driven decision-making will be critical in shaping the initiatives and high-stakes choices required by value-based care. The transition will require increased, high-level collaboration among different constituencies within a healthcare enterprise. It also will require decisions to be quantitatively assessed against reliable, trustworthy data, the survey report notes.

The survey sought to gauge the current state of data trust and access? How much trust do CIOs and stakeholders have in their clinical, financial, and operational data these days? How many have direct, self-service access to the information they need to make data-driven decisions? Are healthcare organizations ready to invest funds to improve trust in data and self-service capabilities?

Overall, few organizations have very strong trust in their data while levels of self-service vary across the enterprise, according to the survey. Most healthcare organizations plan to invest money toward improving both data trust and self-service, the survey found.

As part of the survey, CIOs were asked to rate the index of trust in data within their various user communities, on a 1-10 scale, with 10 being the highest. The index of trust was defined as how strongly “user populations believe that they can trust the data provided to make decisions.”

Forty-eight percent of respondents assessed financial data as an 8 or above. The percentage of “8-and-up” responses was 40 percent for clinical and 36 percent for operational.

Clinical users have the lowest levels of self-service in making data-driven decisions. More than half of CIOs report that 30 percent or less of their clinical population is self-serviced in data-driven decision making.

Approximately three-quarters of healthcare organizations plan to increase investments to improve trust in data and self-service capabilities. At least 70% responded “yes” to investments in trusted data in each of the three realms. In addition, most organizations (68 – 78 percent) plan to increase their investments towards improving users’ capacity for self-service data analytics.

The survey demonstrates that healthcare organizations have a long way to go in developing rock-solid trust in their data and self-service access to it. The survey results also indicate that executives are aware of these challenges and are ready to dedicate resources to improving both trust and access.

“Trusted data is more important than ever, as healthcare organizations migrate from the fee-for-service model to value-based care,” Fred Powers, president and CEO of Dimensional Insight, said in a statement. “During this transition, healthcare organizations must weigh investments, risks, and tradeoffs against quantitative, trustworthy data. This kind of data driven decision-making will be critical in shaping the initiatives and high-stakes choices required by value-based care.”

Dimensional Insight executives also provide a number of recommendations for improving trust in data and increasing self-service capabilities:

  • Keep subject matter experts close to the data. Healthcare organizations will need programmers and data engineers to extract data from the source systems, but it is the subject matter experts who best understand the data and how it will be used.
  • Automate business logic transformations. More automation is better when it comes to the often complex logic required to transform raw data into meaningful information.
  •  Promote transparency and visibility. The best way to make sure data is right is to let people — the frontline information consumers — at it.



Related Insights For: Analytics


Study: AI Falls Short When Analyzing Data Across Multiple Health Systems

November 7, 2018
by Heather Landi, Associate Editor
| Reprints
Click To View Gallery

Artificial intelligence (AI) tools and machine learning technologies hold the promise of transforming healthcare and there is ongoing discuss about how much of an impact AI and machine learning will have on the practice of medicine and on the business of healthcare overall.

In a recent study, researchers from New York City-based Mount Sinai Hospital and Icahn School of Medicine at Mount Sinai found that AI may fall short when analyzing data across multiple health systems. In conclusions, researchers noted that the study findings indicate healthcare organizations should carefully assess AI tools and their real-world performance. The study was published in a recent special issue of PLOS Medicine on machine learning and health care.

As interest in the use of computer system frameworks called convolutional neural networks (CNN) to analyze medical imaging and provide a computer-aided diagnosis grows, recent studies have suggested that AI image classification may not generalize to new data as well as commonly portrayed, the researchers wrote in a press release about the study.

Early results in using CNNs on X-rays to diagnose disease have been promising, but it has not yet been shown that models trained on X-rays from one hospital or one group of hospitals will work equally well at different hospitals, the researchers stated. Before these tools are used for computer-aided diagnosis in real-world clinical settings, we must verify their ability to generalize across a variety of hospital systems, according to the researchers.

The study is timely giving the interest in machine learning, particularly in the area of medical imaging. A survey from Reaction Data found that 84 percent of medical imaging professionals view the technology as being either important or extremely important in medical imaging. What’s more, about 20 percent of medical imaging professionals say they have already adopted machine learning, and about one-third say they will adopt it by 2020.

Breaking it down, 7 percent of respondents said they have just adopted some machine learning and 11 percent say they plan on adopting the technology in the next 12 months. Fourteen percent of respondents said their organizations have been using machine learning for a while. About a quarter of respondents say they plan to adopt machine learning by 2020, and another 25 percent said they are three or more years away from adopting it. Only 16 percent of medical imaging professionals say they have no plans to adopt machine learning.

That survey found that there has been very little adoption by imaging centers, and all of the current adopters are hospitals.

In this particular Mount Sinai study, researchers at the Icahn School of Medicine at Mount Sinai assessed how AI models identified pneumonia in 158,000 chest X-rays across three medical institutions: the National Institutes of Health; The Mount Sinai Hospital; and Indiana University Hospital. Researchers chose to study the diagnosis of pneumonia on chest X-rays for its common occurrence, clinical significance, and prevalence in the research community.

In three out of five comparisons, CNNs’ performance in diagnosing diseases on X-rays from hospitals outside of its own network was significantly lower than on X-rays from the original health system. However, CNNs were able to detect the hospital system where an X-ray was acquired with a high-degree of accuracy, and cheated at their predictive task based on the prevalence of pneumonia at the training institution, according to the study.

Researches concluded that AI tools trained to detect pneumonia on chest X-rays suffered significant decreases in performance when tested on data from outside health systems. What’s more, researchers noted that the difficulty of using deep learning models in medicine is that they use a massive number of parameters, making it challenging to identify specific variables driving predictions, such as the types of CT scanners used at a hospital and the resolution quality of imaging.

“The performance of CNNs in diagnosing diseases on X-rays may reflect not only their ability to identify disease-specific imaging findings on X-rays but also their ability to exploit confounding information,” the researchers wrote in the study. “Estimates of CNN performance based on test data from hospital systems used for model training may overstate their likely real-world performance.”

These findings suggest that artificial intelligence in the medical space must be carefully tested for performance across a wide range of populations; otherwise, the deep learning models may not perform as accurately as expected, the researches stated.

“Our findings should give pause to those considering rapid deployment of artificial intelligence platforms without rigorously assessing their performance in real-world clinical settings reflective of where they are being deployed,” senior author Eric Oermann, M.D., instructor in Neurosurgery at the Icahn School of Medicine at Mount Sinai, said in a statement. “Deep learning models trained to perform medical diagnosis can generalize well, but this cannot be taken for granted since patient populations and imaging techniques differ significantly across institutions.”

First author John Zech, a medical student at the Icahn School of Medicine at Mount Sinai, said, “If CNN systems are to be used for medical diagnosis, they must be tailored to carefully consider clinical questions, tested for a variety of real-world scenarios, and carefully assessed to determine how they impact accurate diagnosis.”


See more on Analytics

betebettipobetngsbahis bahis siteleringsbahis