How To Build A Learning Health System | Medicine School


How to build a learning health system

U of M medical school shares key ingredients

Reading time: 3.5 minutes

“Learn” may just be the defining word of last year in science and health: learning that masks work well to slow the spread of viruses and that safe and effective vaccines can be used. produced and distributed “at high speed”. A year ago, science just needed more time to learn.

To do this, many institutions have started to combine the work of improving healthcare, the implementation of evidence in practice, and data science to create a Learning Health System (LHS) – or a a system in which individual clinician-patient interactions inform the health system as a whole and generate new evidence on how to continually improve the quality of health care for all patients.

At the University of Minnesota School of Medicine, the development of LHS spurred new COVID-19 clinical trials using reused drugs and led to the first evidence-based COVID-19 clinical care guidelines for physicians in emergency on when to admit or discharge patients. The faculty even collaborated with Epic and other centers on an artificial intelligence algorithm to diagnose COVID-19 using chest x-rays and integrated it into M Health Fairview’s electronic health records.

The infrastructure behind an LHS, however, involves many moving parts – some fundamental and others more flexible. Two faculty of medicine at the U of M’s department of surgery – Genevieve Melton-Meaux, MD, PhD, professor, and Chris Tignanelli, MD, MS, assistant professor – share the key ingredients needed to build an LHS at within a university health system:

Get involved in professional or national societies related to LHS;

Build a multidisciplinary evidence synthesis team and interoperable data infrastructure;

As far as possible, find a win-win sharing with the private sector;

And, partner directly with external health systems for maximum impact.

Get involved in professional or national societies on LHS

Dr Tignanelli says the first step is to connect. In 2018, he received an invitation from the Centers for Disease Control to join their “Adapting clinical guidelines to the digital age“project. When COVID-19 hit, a C19 digital guidelines working group was developed to focus specifically on digital guidelines for COVID-19, where they began work on anticoagulation research .

“I started to participate more and more and show them what we were doing. Slowly we got more interest from those national and third-party companies who wanted to work with us, ”said Dr Tignanelli. “From there, it took off.

He suggests that members of other academic health systems engage in various working groups related to informatics and learning health systems, either within their professional societies or through national groups, such as the ‘WHO and CDC.

“And, when you’re there,” he says, “take the time to showcase and share what you’re doing and seize new partnership opportunities as they arise. “

Build a multidisciplinary evidence synthesis team and an interoperable data infrastructure

The next step is to build a multidisciplinary team of experts in the field who can synthesize the latest research evidence on a certain topic and convert that information into written guidelines and operational protocols that lead to decision support tools.

“How do you take all these published articles, put them into practice, and get everyone in 12 different hospitals to agree?” This is how we want to practice medicine, but it is probably one of the biggest challenges, ”explains Dr Tignanelli.

The multidisciplinary team of the U of M is made up of nearly 50people in the fields of medicine, intensive care, hematology and pharmacy, as well as the AHRQ-funded Evidence-Based Practice Center (run by the School of Public Health), computer scientists, scientists implementation and biostatisticians, who review the literature to determine “high or low evidence” using an agreed metric system.

“And, start making progress, if you haven’t already, in developing interoperable data standards and tools so that everyone speaks the same language and the technologies needed to wired the directive can be used. on all sites. This way the models and the results of these can be freely shared with each other, and you compare apples to apples, ”says Dr Tignanelli.

If the data infrastructure and tools are interoperable, a clinical decision support tool could be connected to other health systems and impact communities on a much broader level.

Where possible, find a win-win sharing with the private sector

LHSSometimes making an LHS possible involves collaborations with the private sector. The U of M team recognizes that third-party companies, at the end of the day, want to make an impact and support their business, so finding a shared victory is essential in the development of any LHS.

“Working with private sector companies can sometimes be seen as problematic,” says Dr Melton-Meaux. “Fortunately, we work in healthcare, so more often than not, the value of our collaborations together can be in improving patient outcomes and healthcare systems. Most companies are also open to research collaborations, the integrity of the scientific process, and the dissemination of results with tools as implemented in practice.

Collaborate directly with external health systems for maximum impact

Dr Melton-Meaux also recommends evaluating potential collaborations with other healthcare organizations by focusing on the strengths of the academic research opportunity. Whether it’s stroke or heart attack care or experimenting with some type of data analysis, align potential projects with the expertise and strengths available in patient care.

Dr Tignanelli suggests that another advantage of working with other health systems is that the data models can be strengthened with larger patient populations and with more data, which helps to externally validate the proposed methods. .

“This is the difference between a low impact or a high impact research paper, because it helps ensure that the models developed are more robust,” he says. “Finding a few hospital systems to work with early on is critical, and if you are interested in teaming up with us here in Minnesota, please contact us as we would love to have more partners. “

Dr Tignanelli and Dr Melton-Meaux both stress the value of “being open to collaboration” with everyone.

“By developing these systems, there is much less distinction between your academic and health care systems – between basic sciences and doctorates and your health sciences and physicians,” said Dr Melton-Meaux. “It’s more about how to do this together and bring people together in a different way.”


Comments are closed.