Can a Diabetes App be as effective as a drug?

The Hong Kong Healthcare Drinks networking event ( hosted a presentation on the clinical validation and commercialization of a diabetes app, given by Nick Ray (from Queens Road Capital) and Nora Kleinman.

The Gather mobile health (mHealth) diabetes App was developed by software teams in India and China. It was launched in India in 2014, with the assistance of a few dedicated Indian Endocrinologists and Diabetes Nurses, followed by a clinical study in 2015. The mHealth intervention is built on behavioral change theories to support self-management, facilitate patient–provider communication, and enable treatment changes between visits using patient mobile phone apps and provider web portals (for patient data analysis) and mobile phone apps. Diabetes prevalence in India is 8.7% and is rising because of rapid urbanization, increasing life expectancy and a shift to a more Western diet. However, less than 20% of people living with diabetes achieve target A1C levels (a form of hemoglobin that is measured to identify average plasma glucose concentration). 90 type 2 diabetes patients were randomized 1:1 to the Gather mHealth  intervention or usual care, and observed for 6 months. At 6 months, the 80 returning participants had a mean A1C decrease of 1.5% in the intervention group and 0.8% in the usual care group, a statistically significant difference*. These results are driven mostly by better adherence to medicines, improved blood glucose testing and physicians adjusting medications remotely making it easier to manage their patients’ hypo- or hyperglycaemic events. These are encouraging results and point to how mHealth platforms could be used effectively to expand access to quality chronic disease care and improve outcomes. However, the presenters also outlined the following key learning’s from this study and the challenges encountered in driving the adoption of such mHealth tools:
  • User engagement with the App drops over time with 45% of patients still used the App after 6 months. The doctor’s recommendation for use of the App and his / her active engagement with the device drives higher patient engagement. The same is true when the Diabetes Nurse is actively communicating with the patient via the App.
  • For older patients, family members are eager stakeholders with 20% of App users being family members i.e. they logged data for the patient, messaged the physician and played educational quizzes that were on the App.
  • An automated coach feature (giving fun, bite size pieces of information about diabetes management & lifestyle changes) was the mostly frequently used function.
  • Patients preferred familiar & easy to understand data charts than fancy graphs when looking at their longer-term data trends.
  • Doctor engagement with the App was high but their busy schedule led to long delays in replying to patient messages or forgetting to update medication changes that were given via the App in the patient’s clinic records.
  • Only 13% of patient messages via the App required physician’s intervention i.e. medical-related messages. The majority of the messages could be answered by a nurse or a health coach i.e. diet, blood glucose reading & confirmation messages.
In summary this study demonstrates that:
  • A diabetes mHealth App can have similar clinical outcomes to gold standard medical interventions
  • Patients and family members want & use mHealth tools
  • Much can be automated such as using a chatbot health coach
  • Provider engagement can make a big impact but difficult to get right
  • Need healthcare business model innovation, not technology innovation
* For the full publication of the mHealth clinical study, which is published in Diabetes Care, go to: