Brian Klepper and John Rodis
Posted Mar 7, 2021 on The Doctor Weighs In
Now and then, a solution emerges for a large, seemingly intractable problem. In some cases the fix is straightforward, grounded in a fresh evaluation of well-understood circumstances. But more often it’s born from a sustained, in-depth effort that permits incremental successes and takes time to achieve a fully capable answer. MedsEngine, described below, is a good example.
There is little question that better management of major chronic conditions – like hypertension, diabetes, heart failure and asthma – represents our most important health care outpatient improvement opportunity. In 2016, chronic conditions and the downstream health and productivity events they generate – heart attacks, strokes, amputations, emergency visits, hospital admissions, absenteeism – consumed a breathtakingly large portion of our national economic output, about one-fifth of US Gross Domestic Product.
Worse, our efforts to manage chronic conditions have yielded despairingly weak results. Performance can be measured by the percentage of cases that are “controlled,” meaning patients’ metrics are within acceptable limits. Currently only 44% of Americans with hypertension are controlled. Fewer than 10% of diabetics are controlled. Better control would translate to safer patients, with better health outcomes and lower costs.
The standard response to poor results has been to assign blame. Patients are lax about taking their meds. Doctors don’t give patients the attention they need. Chronic conditions are simply too resistant to control. With these assumptions as a backdrop, most interventions aim to change patient behavior, typically with little success.
But these reactions ignore the complex structure of chronic diseases and what it takes to manage that complexity. As it turns out, two elements are necessary for successful chronic condition management. First, physicians must prescribe the right medications for each patient, and, second, patients must be engaged, participating in therapy and self-care. Let’s put aside the second, on the assumption that the better health outcomes associated with the right drugs are a reward that should easily win patients’ buy-in.
Prescribing the most appropriate drugs is an obvious goal, but more complicated than it seems due to the number of variables involved in choosing them. So consider, for example, that there are five distinct causes for hypertension, each with its own physiologic configuration. At least 28 medical conditions require consideration in hypertension therapy. Twelve different drug classes – with multiple drugs within each class – apply to hypertension management, though most physicians are familiar with and adhere to, at most, four or five. And then there are dozens of different demographic risk groups, each with slightly different physiologic sensibilities. There are other variables as well, including the effect of these medications on co-morbidities, as well as the drug-drug interactions.
These dynamics present an overwhelming management challenge, easily exceeding a clinician’s capacity to competently match an individual patient’s details to a treatment pathway. Choosing the correct medications for a patient’s chronic condition can be a process that literally requires sifting through millions of permutations. Complexity inevitably hits a ceiling, with the upshot that physicians often prescribe drugs and/or dosages that are not the best fit for the patient.
But machines may allow us to juggle many more variables competently and reliably. That has been the vision of MediSync, a firm that, in other parts of its business, develops management solutions for large primary care and multi-specialty physician practices. It has taken two decades to sort out next steps and do the work that brought MedsEngine to fruition.
What makes it worth considering the sheer complexity involved in an ambitious project like this? First is science. Driven by artificial intelligence, the MedsEngine coding had to reflect our current understanding of each chronic disease’s physiology and pharmacology, and the relevant interactions occurring among and between them. It had to pull patient information from the electronic health record to determine the specific physiology involved and the medications best suited to that. But it also required being transparent about the sources of each part of the science, so that physicians and other clinicians can trust and buy into its credibility.
The proof is in the data. The first table below shows the percentage of patients with a specific condition who are adequately controlled. The second table shows cost and savings data across different populations.
| Chronic Outcomes | Control | |
| Chronic Disease | US Avg | MedsEngine |
| Hypertension | 44% | 93% |
| Diabetes (3 Way) | <10% | 57% |
| Lipids (Statins) | 62% | 75% |
| Benchmark/Population | MedsEngine (Reduction) | PMPY Reduction | |
| Regional Total Cost PMPY (Risk Adjusted) | $5,037 | $3,732 (26%) | |
| Medicaid (2017) | 11,515 Patients | $4.4 Million | $382.11 |
| Medicare Advantage (2017) | 942 Patients | $1.3 Million | $1,380.04 |
This performance has been validated and recognized by credible third party groups. PriMed Physicians, a primary care group in Dayton, OH, was one of two practices that piloted the MedsEngine. The medical group practice association, AMGA, ranked PriMed best in the US at achieving blood pressure outcomes ≤139/89, with 95% of their hypertension population under control. Similarly, the Centers for Disease Control and Prevention certified PriMed as first in their Million Hearts awards program and as the only large group nationally to exceed 90% of hypertension patients under control.
The same technology drove PriMed’s control of Type 2 diabetes, which was also recognized by AMGA as first among US physician groups, achieving simultaneous control of all three major Type 2 diabetes markers: blood pressure, LDL and HbA1c.
Relatively few primary care physicians currently track their success at controlling chronic conditions, small wonder when the results have been so lackluster. But the ability to predictably control these major chronic diseases is a significant advance, with important clinical and financial impacts for the larger health system. A system that allows providers to reliably achieve performance targets not only enhances patient care and value, but allows those providers to guarantee health outcomes and savings, making them far more desirable in a value-focused marketplace. As a result, MedsEngine can serve as the foundation for care that is more evidence-based, predictable and accountable.
MedsEngine’s AI-driven platform capabilities have already been established for three major chronic conditions, but can reasonably extend to ten or so other conditions. Mark DeRubeis, CEO of Premier Physicians in Pittsburgh, the other MedsEngine pilot site, summed up the promise represented by this approach: “The MedsEngine offers the opportunity for exponential improvement in chronic care management. It enables you to get the diagnosis right the first time, to prescribe the right medicine the first time. If you look at the alternative to that, it may take two or three or four times the effort, and this enables you to cut all of that out and gain an efficiency that didn’t exist prior.”
MedsEngine is the first of what will almost certainly be a flood of new digital tools that facilitate far more effective care. But make no mistake, building these tools well is as complicated as the problems they seek to address. Fortunately, the rewards, in terms of better health and lower costs, are likely to be equally powerful.
Brian Klepper, PhD is a health care analyst focused on proven high performing health care innovators. John F. Rodis, MD was formerly President of Saint Francis Hospital in Hartford, CT.
Care And Cost 