Provide accurate dietary tracking and predictive analytics, determine personal glycemic responses, and promote behavior change for diabetics
The 29 million diabetics in the U.S. incur an average medical expenditure of $13,700 per year. Globally, the 415 million diabetics in 2015 are projected to reach 642 million by 2040: a 50% increase. Many studies unequivocally demonstrate that tight glycemic control is critical in reducing both microvascular and macrovascular diabetic complications . Dietary behavior is the main determinant of blood glucose levels, and making sound food choices that induce normal glycemic responses is imperative. However, current practices of counting carbohydrate intake and analyzing glycemic indexes to estimate glycemic responses provide mixed results. Further evidence from recent research has shown that other nutritional properties of food such as fat and protein can significantly affect postprandial glucose excursions. These findings demonstrate that insulin dose calculations need to consider full nutritional composition instead of exclusively considering carbohydrate content. With the recent FDA approval of Medtronic’s 670G hybrid artificial pancreas, developing a personal glycemic response system becomes even more important in determining insulin strategies.
Palette platform is a cognitive dietitian that uses dietary and lifestyle data to drive behavior changes. Palette comprises of a smart placemat residing on the dining table that tracks users’ meals accurately and conveniently. Palette Vault seamlessly integrates with activity-tracking devices via Apple Health, and stores all lifestyle data including exercise, sleeping patterns, stress levels, and etc.
Intelligent algorithms are then developed and used to help predict glycemic responses based on individual’s lifestyle data. By providing physicians with intelligent behavioral insight anytime and anywhere, Palette saves time and allows physicians to provide personalized care with a feedback loop that trains itself and iteratively enhances behavior engagement overtime.
What are the key outcomes and impact of your solution?
Currently, no system is available to predict postprandial blood glucose based on meal composition to determine targeted insulin strategy. Major challenges are 1) to develop an effective tool to accurately measure and track food over time and 2) to use this tool to predict glycemic responses and devise effective insulin strategy. Palette platform is the only system designed to overcome these challenges and significantly contributes to the development of closed loop artificial pancreas.
Existing tools such as carbohydrate count and glycemic index, in assessing glycemic responses, have severe limitations. Palette’s innovative cognitive dietitian technology will overcome dietary limitations of only analyzing carbohydrates, change how physicians keep postprandial glucose concentrations in range, develop sophisticated analytic systems to automatically evaluate postprandial glucose data, and provide individualized dosing recommendations. The expected outcome of Palette is better control of patients’ glycemic response through lifestyle and behavioral changes and reduce the corresponding cost of diabetes care.
What actions do you propose to realize your stated goals?
The success of our business model heavily depends on two key elements. 1) establish right partnerships to implement studies for demonstrating feasibility and enhanced efficacy in diabetes management; 2) platform partnership in patient education and implementation support.
Currently, we are collaborating on studies with Children’s Mercy Hospital in Kansas City to introduce Palette to all their pediatrics, diabetes center, and diabetes prevention program. We expect that the study with direct patients inputs from surveys and interviews will validate the feasibility of Palette platform in diabetes care and prevention.
Using B2B2C model, we plan to market directly to diabetes clinics, diabetes centers, and self-insured employers. Self-insured employers can use Palette for diabetes prevention and care in the workplace to reduce care costs. These institutional partners will be our main venue in patient education and implementation.
Who will take these actions?
Yulin Li, CEO and co-founder, serial entrepreneur and actuary, will lead the efforts with the support of his team. Previously, he worked for Transamerica Life Insurance as a senior actuary for over 10 years. Milton Li, co-founder and CTO, will lead app development, UI interface and product design. For our success, we need collaborative efforts with health plans, hospitals, individual physicians and government in implementing research studies, which involves academic institutions.
Dr. Mark Clements from Children’s Mercy Hospital is our medical advisor on pediatric diabetes. Dr. Clements is currently a pediatric endocrinologist and the director of endocrine clinical research at Children’s Mercy Hospital. He is also an associate professor of pediatrics at the University of Missouri-Kansas City School of Medicine.
Dr. Teresa Fung from the Harvard School of Public Health is our population health and nutrition advisor. Dr. Fung brings strong academic research experience in nutrition along with practice as a registered dietitian. She teaches both undergraduate and graduate courses at Simmons College while maintaining research collaboration at the Harvard School of Public Health where she is an Adjunct Professor. Dr. Fung is currently an Associate Editor for the Journal of Nutrition and a panelist for the U.S. News and World Reports Best Diet rankings. She has previously been on a Technical Expert Committee at the United States Department of Agriculture to evaluate scientific evidence on dietary patterns and health outcomes.
During the past month, we worked closely with Dr. Nancy Bohannon - an endocrinologist in San Francisco with a focus on adult diabetes - to design a physician portal and patient interface, enhance efficiency, and deliver behavior intervention using Palette platform.
We will initially focus on the US market where we have done many iterations of customer discovery and pilot studies and California in particular, since it has the largest diabetes population. Palette, once implemented, can directly serve the 2.5 million diabetes patients in California. Our patented technology and design can then be expanded to international markets.
What do you expect are the costs associated with piloting and implementing the solution, and what is your business model?
AEGLE Palette is a for-profit company that was established to help people with chronic diseases using technology and design. Our initial focus is on diabetes but we believe that many health conscious consumers and patients of other chronic disease can benefit from Palette platform. We have just completed the 3rd round of prototyping and over 100 builds of our application. Focus group study is underway with Dr. Bohannon and Dr. Clements – paving the way to launch in the institution markets. Currently we are raising $500,000 with the main goal of the funding as to reach 5000 users within 12 months through marketing efforts and hiring additional programmers.
We are conducting final engineering testing before mass production. Major efforts in the next 6 months include:
1. Feasibility study with Dr. Bohannon in San Francisco: 10 patients, 50% T1D and 50% T2D and 50% female and male.
2. We are currently in contract discussion with Children’s Mercy Hospital in Kansas City to introduce Palette to all their pediatrics, diabetes center, and diabetes prevention program (DPP).
3. Product launch in April 2017
For the next 12 months, our target is to reach 5000 Palette users and 20,000 within the next 2 years.
Diabetes is a global pandemic and we see may solutions in Solve CoLab that demonstrate promise in addressing challenges from various perspectives. However, we believe that Palette, as a cognitive dietitian, directly targets the fundamental issue of diabetes care - behavior tracking and effective engagement - and develops intelligent solutions for both patients and providers. The following are some of the related solutions:
An Unconventional Approach to fight Diabetes & other chronic diseases / NutriCount
A Digital Platform For Automated Self-Coaching For Obesity & Diabetes / Yavari
Community care practices in black people: preventing hypertension and Diabetes. / Poilera
Mobile ML for Diabetics A healthy program for scanning Nutrition Facts labeling / MEDPIKE
Eliminate Chronic Diseases: Cooking + Fitness Program for Women Of Color / Michelle Riv
1) Centers for Disease Control and Prevention. National Diabetes Statistics Report: Estimates of Diabetes and Its Burden in the United States, 2014. Atlanta, GA: U.S. Department of Health and Human Services; 2014.
2) Scientific Report of the 2015 Dietary Guidelines Advisory Committee. United States Department of Agriculture and the Department of Health and Human Services. February 2015.
3) Flegal KM, Carroll MD, Kit BK, Ogden CL. Prevalence of obesity and trends in the distribution of body mass index among US adults, 1999–2010. Journal of the American Medical Association. 2012; 307(5): 491–97.; Ogden CL, Carroll MD, Kit BK, Flegal KM. Prevalence of obesity and trends in body mass index among US children and adolescents, 1999–2010. Journal of the American Medical Association. 2012; 307(5):483–90.
4) The Cost of Diabetes in the U.S. in 2012. (2013). The American Diabetes Association, Diabetes Care. 2013 Apr;36(4):1033-46. doi: 10.2337/dc12-2625. Epub 2013 Mar 6.
5) Ma B, Lawson AB, Liese AD, Bell RA, Mayer-Davis EJ. Dairy, magnesium, and calcium intake in relation to insulin sensitivity: approaches to modeling a dose-dependent association. Am J Epidemiol. Sep 1 2006;164(5):449-458.
6) The Burden of Type 1 Diabetes. American Association of Clinical Endocrinologists,
7) Lifshitz F, ed Pediatric Endocrinology. Fifth Edition ed. New York, NY 10017: Informa Health care; 2007; No. Volume 2.
8) Gallwitz, B. (2009). Implications of postprandial glucose and weight control in people with type 2 diabetes: understanding and implementing the International Diabetes Federation guidelines. Diabetes Care 32 (Suppl 2 ), S322–S325
9) Conn, J.W., and Newburgh, L.H. (1936). The glycemic response to isoglucogenic quantities of protein and carbohydrate. J. Clin. Invest. 15, 665–671
10) Greenwood, D.C., Threapleton, D.E., Evans, C.E.L., Cleghorn, C.L., Nykjaer, C., Woodhead, C., and Burley, V.J. (2013). Glycemic index, glycemic load, carbohydrates, and type 2 diabetes: systematic review and dose-response meta-analysis of prospective studies. Diabetes Care 36, 4166–4171
11) Wolpert, H., Smith, S, etc. (2013). Dietary Fat Acutely Increases Glucose Concentrations and Insulin Requirements in PatientsWith Type 1 Diabetes.
12) Bell, K., Smart, C., Steil, G., etc. (2015). Impact of Fat, Protein, and Glycemic Index on Postprandial Glucose Control in Type 1Diabetes: Implications for Intensive Diabetes Management in the Continuous Glucose Monitoring Era.
13) Schwingshackl, L., and Hoffmann, G. (2013). Long-term effects of low glycemic index/load vs. high glycemic index/load diets on parameters of obesity and obesity-associated risks: a systematic review and meta-analysis. Nutr. Metab. Cardiovasc. Dis. 23, 699–706
How can we help people prevent, detect and manage chronic diseases, especially in resources-limited settings?