iot health

IoT Evolution Health News

IoT Evolution Health Home

How AI Is Driving Behavioral Change in Mobile Health

By Special Guest
Kris Bondi, CMO, Neura
March 08, 2018

Many of today's prevalent diseases and conditions are both preventable and manageable. In most cases, the onset of heart disease, type 2 diabetes, hypertension, obesity, and other conditions can be prevented and offset by healthy lifestyle choices.

However, developing a healthy lifestyle often requires people to change specific long-term behaviors, and as we all know, changing one's behavior can be difficult.

To help with their behavioral changes, people are adopting mobile health apps and Internet-connected medical devices that encourage positive actions, while the advent of new machine learning technology is significantly augmenting the ability of these apps and devices to  encourage the desired behavioral changes.

New advances in machine learning algorithms create behavioral profiles of end-users based on their daily actions and routines in the physical world. By collecting raw sensor data from a user’s smartphone and connected devices, these algorithms convert raw sensor data from into insights about their habits, activities, and meaningful locations.
Digital health apps can draw upon these AI-driven user profiles to influence behavior change in the following three ways.

1. Reaching people at optimal moments in time to affect behavior
One way health apps try to influence people’s behavior is through notifications and alerts. For example, a wellness app may prompt a user to go for a walk each day. Alternatively, a medication adherence app may issue alerts informing a user to take their daily prescribed medication. These apps currently rely on user input to set a time to trigger an alert or the app randomly guesses the best time to issue a notification.

It is easy to imagine how ill-timed alerts could hurt the end goal of fostering healthy behaviors. If the wellness app regularly sounds off while the user is driving, it not only reduces the odds of the user addressing their wellness, it increases the odds of them, in worst cases, crashing their car. Likewise, if the medication adherence app regularly wakes the user from a deep sleep in the morning, the app could be ignored or deleted.

“User-aware” apps, however, encourage behavioral change by notifying users at optimal times. Because they know a user’s daily routines such as movements, activities, and locations, they trigger “moment-based” notifications. For example, the wellness app could prompt the user to exercise as soon as he or she arrives home from work. The app catches them at a juncture when they are most likely to engage and comply. Similarly, the medication adherence app could detect the exact moment when the user wakes up in the morning and issue a reminder. The app connects with the user at a convenient time, thus increasing the likelihood that the user will obey the instructions.

2. Empowering people with knowledge that inspires behavioral transformation.
The ability of today's mobile apps and fitness trackers to automatically log users activities is an essential step in engaging people in their health. In fact, a well-publicized Walgreens study revealed the power of automation to positively influence people’s behavior.

However, again, AI-driven behavioral profiles can multiply the benefits of lone fitness trackers and apps. Digital health tools, enhanced by machine learning, have a holistic view of a person’s physical life, not just of their daily step count.

For example, a user-aware wellness app can share detailed activity dashboards that show a user’s total wellness profile?—?exercise habits, sleeping patterns, time spent sitting in the car, and so on?—?and offer health tips based on their profile. Alternatively, an app that helps people manage a pulmonary condition can give users insight into how specific actions affect their breathing.

The more context an app provides about a person’s health, the more compelling the information is to the user. Additionally, the more compelling the information, the more likely the user will become motivated to address their harmful behaviors.

3. Providing personalized resources that resonate with users.
Apps that share generalized health resources with their users eventually become irrelevant and are ignored. However, user-aware apps can tailor their messaging to individual users based on their behavioral profiles.

For example, a dieting app, sensing that a user has poor sleeping habits, can proactively share resources on sleep disorders. In another case, a diabetes management app, knowing that a user is a workaholic, may inform them on how overworking can upset a person’s glucose balance.

This sequence has a cascading effect. If an app consistently sends the user engaging messages at the right moment, then the user is more likely to read the content of those messages. As they read more content tied to their health, these ideas become more deeply embedded in the user’s mind. These thoughts then manifest themselves in the user’s actions in the physical world.

Behavior change is a “game of inches.” Advancements in machine learning just may turn it into a game of yards.

About the author: Neura CMO Kris Bondi has more than 20 years international marketing experience. Prior to joining Neura, Kris served as Vice President of Global Marketing for, a serverless computing provider. Her background includes expertise in technology marketing with previous stints at Moka5, TIBCO and Mashery.

Edited by Ken Briodagh
Related Articles

IoT Time Podcast S.5 Ep.28 Virtium

By: Ken Briodagh    8/6/2020

In this episode of IoT Time Podcast, Ken Briodagh sits down with Scott Phillips, VP of Marketing, Virtium, to talk about storage, security, storage, d…

Read More

Kerlink and GISupply Partner on LoRa-based IoT for Health, Agriculture Markets

By: Ken Briodagh    7/28/2020

Applications Range from Heat-Stroke Avoidance for Construction Workers To Smart Farming and Aquaculture

Read More

COVID-19 Pandemic Offers Opportunity for Cybercriminals, McAfee Says

By: Ken Briodagh    7/24/2020

McAfee recently released its McAfee COVID-19 Threat Report: July 2020 examining cybercriminal activity related to COVID-19 and the evolution of cyber …

Read More

IoT Time Podcast S.5 Ep.26 KORE

By: Ken Briodagh    7/16/2020

n this episode of IoT Time Podcast, Ken Briodagh sits down with Marco Bijvelds, SVP, EMEA and APAC, KORE Wireless, to talk about KORE's global eSIM an…

Read More

Improving Care, Lowering Risk and Leveraging Data to Address COVID-19

By: Arti Loftus    7/13/2020

Televic Healthcare is implementing collaboration systems for healthcare, like nurse call, intercom, access control, patient entertainment and care reg…

Read More