Digital health has quickly moved to a point where we can now collect data on everything from step counts and hours of sleep to blood pressure and glucose – all day, every day and everywhere.
In addition to these advances in data science, more recently, digital health has begun using behavioral science to better understand what people are doing about their health and why they are doing it in order to motivate them to make healthy choices.
The next frontier in digital health is happening at the interface between these two sciences a place called Behavioral data science.
Overall, AI-based digital health tools are valuable because they remove barriers to access to health care and reach more people than an inpatient doctor’s office can. More importantly, unlike telemedicine solutions, AI can reduce the daily cognitive burden of coping with a chronic illness.
For example, a person with type 1 diabetes, on average, suffers from 180 health-related decisions every day. AI-powered digital tools provide real-time data and recommendations based on that person’s daily experience – whenever they need it, to simplify decision-making and avoid guesswork.
This type of continuous feedback, which provides up-to-the-minute instructions for getting the best results, is particularly beneficial for people with chronic illnesses. You will also benefit from tools based on behavioral data science, as properly managing a chronic condition requires monitoring health metrics and getting feedback on how behavior is affecting them.
Let’s take a closer look at how integrating behavioral science and data science into digital tools helps people cope with their chronic conditions better than tools based on just one of these sciences.
Integration is important
It is important to recognize that no single scientific discipline can or should describe digital health solutions. A company may develop the best data logging and data analysis tool that it has developed, but when exposure to the tool is low – That said, few people use it – then it is of little use. The best digital solutions are those that embrace the interdisciplinary approach of behavioral data science.
Of course, AI-based digital health tools need to be firmly anchored in the data. Data science-based tools collect and analyze all kinds of health metrics and data, and then use that analysis to provide individual health information such as blood pressure and dietary patterns over time and recommend appropriate action.
However, tools based solely on data science have two main disadvantages. First, the value of the recommendations depends heavily on how often the person interacts with the tool to provide the necessary data – for example, food intake to measure antihypertensive sodium intake. Second, the data can show how much weight loss would be beneficial for better blood pressure regulation, but cannot explain the behavioral barriers the person may have to overcome in order to lose that amount of weight.
The point is that digital tools have to be able to do more than just provide people with data. You also need to motivate them to improve their health. This is where behavioral research comes in. She can support a level of engagement and retention with the tool that will help keep the individual motivated to stay healthy.
In the context of digital health tools, this science relies on a feedback loop between a person’s health data and their behavior that continuously evaluates their health status and modifies behavioral recommendations accordingly:
- Data science provides quantitative information about the current state of health and its short-term effects.
- Behavioral science determines how and when this quantitative information is “translated” into messages that the person can understand and are most likely to follow.
- Individual health metrics provide data on the effects of these recommendations on the person’s health.
- These metrics, as well as the engagement of the person with the tool, provide insights into the interaction of behavior and data and enable continuous refinement of the recommendations.
This feedback loop between behavior and data enables the digital tool to evolve with the individual as their health needs change over time. Digital tools based on behavioral data science can also reduce treatment effort by giving people recommendations for chronic diseases that are already tailored to their behavior – as the tool has learned – and are therefore easy to adopt.
Digital solutions based on behavioral data science are essential for people with chronic illnesses to achieve their best health outcomes. These integrated solutions are also critical for digital health companies as the individual acceptance and continued commitment to tools that deliver critical metric-based health information in a way that adjusts to the ups and downs of people as they strive to to improve their health will be higher.
Digital tools based solely on understanding the brain or body will drive many people with chronic illnesses to look elsewhere for the support they need.
Dan Goldner is Executive Vice President of Advanced Technologies, Research and Discovery at One Drop, a global provider of precision health solutions for people with chronic diseases. He oversees One Drop’s data science team, which transforms more than 31 billion health data points into predictive analytics solutions – especially CE-marked glucose prognoses and CE-marked blood pressure data.
Prior to joining One Drop, Goldner served as a data science, modeling, and simulation consultant, assisting the Federal Aviation Administration, NASA, and Fortune 50 companies in the pharmaceutical, aerospace, technology, and consumer products sectors. He holds a PhD from MIT and a BA from Harvard University, both in physical oceanography, and an MEd in secondary mathematics from the Boston Teacher Residency.
Harpreet Nagra is a behavioral scientist, clinical researcher and licensed psychologist with over 15 years experience in nonprofits, academic institutions, clinics and private practices. At One Drop, Nagra leads the application of behavioral frameworks and methodologies to key components of its AI-based platform. Most recently Nagra worked as a licensed psychologist and was Deputy Director of Vista Counseling & Consultation. Nagra was also a visiting lecturer at Purdue University Global. Prior to these positions, Nagra was an Assistant Professor at Oregon Health & Science University, specializing in mental health and interdisciplinary care for pediatric and adult patients with diabetes mellitus, including program development for the Young Adult Diabetes Clinic. Nagra holds a PhD in Counseling Psychology from the University of Oregon and a Masters in Counseling from Arizona State University.