Evan Garmaise, Data Scientist
Junghoon Woo, Data Scientist
In 2016, the Department of Health and Human Services announced the certification of the Diabetes Prevention Program (DPP). The DPP aims to reach 86 million pre-diabetic Medicare participants in the United States through education, training, and lifestyle coaching. According to the physician payment rule recently announced, Medicare will be reimbursing both digital and in-person versions of the DPP; however, it remained unclear how the parameters for the digital version will be set. Due to the relatively short history of digital DPP, little is known regarding the mechanism of weight loss when the services are rendered through a mobile app. This will be critical for CMS to set payment mechanism by outcomes as it announced. To better understand the mechanism of weight loss by digital DPP solutions, and to help CMS make the most informed decision on the payment rule, we have collaborated with one of the few certified digital DPP.
Our analysis found that a majority of participants who used the mobile solution for more than 12 weeks lost more than 5% of their weight, which is comparable to a traditional, in-person based DPP. More importantly, we observed that the individual weight loss trajectory varied significantly across participants. We used a phase detection method to generalize the patterns. It was modeled as two linear phases with an intervening ‘hinge’. In general, most of the participants showed at most one hinge point based on our modeling fitting. In the early phase, most of the engaged population experienced some level of weight loss. However, at some point in time, the weight loss either became slower, plateaued, or bounced back. Interestingly, the steeper the first phase trajectory is the earlier the hinge point comes, which might reflect ‘weight loss burnout.’
Further research will be needed to better describe this phenomenon. It was critical to have a longer first phase for successful weight loss. More importantly, weight loss trajectory and logging behavior tend to show the same abrupt hinging change in the same week which might imply the timing of intervention.
Implications to DPP stakeholders would be that regular monitoring of early weight loss and hinge point patterns would result in customized interventions aimed at maximizing the success rate.
Evan Garmaise is a management consultant and data scientist in KPMG’s Lighthouse Data & Analytics group. He has a breadth of experience using data to drive institutional and corporate decision-making, particularly in the healthcare and financial spaces. For the past year he has designed and built tools to support a major healthcare payer’s value-based payment rollout, in addition to researching care optimization in diabetes prevention. His educational background includes master’s degrees in analytics and business.
Junghoon Woo is a Data Scientist within KPMG’s Data and Analytics group. He has eight years of experience working in the biotechnology and healthcare industries. He specializes in statistical modeling, high-dimensional data analysis, distributed computing, and visualization. He holds a PhD in biomedical informatics and has in-depth professional experience in the biotechnology, pharmaceutical, and healthcare industries.