AI in pet health: A Computer Weekly Downtime Upload podcast

Mars, which owns popular dog and cat food brands like Pedigree, Iams, Sheba and Whiskas, is using digital technologies to help pet owners understand their pets’ health.

Kate Balingit currently runs Mars Pet Nutrition’s digital health initiative, which has deployed artificial intelligence (AI) in a novel way to assess the gut and teeth health of pets. 

She says: “It all starts with the pet parent. We're putting the pet parent experience at the centre of everything we do.” Her work combines science, data science and software engineering to develop software-enabled products that help pet parents understand the health of their pets. Two products are now available: Greenies Canine Dental Check and Iams Poopscan, which helps pet owners understand their pet’s digestive health.

Having previously worked for nine years at Google and Waze, Balingit joined Mars Petcare in 2022, to head up its Whistle, “FitBit for dogs” business. While at Google she worked with carmakers like Audi, Ford and Toyota, helping them use Google’s advertising products in innovative new ways. She says: “It was digital transformation, before I really knew what that term meant. We worked with these global enterprises who had to transform a lot of their internal processes to accommodate for the realities of the new digital economy.”

Balingit heads up Mars Pet Nutrition’s head of digital innovation. Reporting the CIO of Mars Petcare, she describes her role as “a bit unique”. It involves orchestrating the digital health initiative across three core functions of the business: science, data science and software engineering.

She says: “The digital health initiative all starts with science. We're building scientific instruments.” These algorithms are capable of detecting the emerging presence of health conditions in dogs. “I start by partnering with the global R&D science function - which includes specialists in oral health, skin health, gut health, healthy ageing - and we spec out  the capability that we want to build.”

The team works out the symptoms of a health condition the software needs to detect, then develops a computer vision model to identify these health issues using smartphone photographs submitted by pet owners. Consider the challenge of analysing a photo taken by a dog owner: it is not just about identifying that the photo is indeed that of a dog, but is the picture showing a dog's mouth, are the teeth visible and then how healthy are the teeth?

Balingit works with the data science team to build the computer vision algorithm. In the case of Greenies Canine Dental Check, she says: “We're detecting plaque and tartar and gum irritation.” The team acquires training data, which is labelled. Microsoft Azure developer tools are then used to build the computer vision model.

Once the computer vision model is ready, she says it is made available via an application programming interface (API). Software engineering teams are then able to develop what Balingit describes as “the actual product experience.”

Among the challenges the company aims to address is how to build a product and digital experience that meet the unique needs of individual brands, individual business units and offers a unique differentiator as Balingit explains: “We're working with emerging technologies like computer vision and trying to build products with a platform approach to enable us to repurpose these assets in different types of applications.”

Understanding what our pets are saying

Balingit believes that the world of sensors and AI offers a way to help pet parents understand their pets better. She says: “Our pets do talk to us with their movements, their facial expressions.” Balingit believes there is an opportunity to use sensor data to help quantify animal behaviour and then apply AI to translate the sensor data into something humans can understand. What this means is that perhaps one day, tech innovation may actually offer a way for pet parents to have a closer relationship with their furry friends.