AI-Powered Smart Bowl by Hoomanely Aims to Help Dog Owners Detect Illness Early

TechCrunch reports that the EverBowl measures food and water consumption, eating speed, chewing and swallowing sounds, facial thermals, oral motions and other signals. The AI platform uses that data to establish a baseline for each dog and builds a health record. Any subsequent and prolonged deviations from the baseline are shown to the owner through an app and in long-term reports, which the company says can give veterinarians more useful data if they get involved. The app also accepts user-entered information so the baseline can be updated with data outside the sensors' scope.

Sai Supriya Sharath, co-founder and CEO of Hoomanely, told TechCrunch: "Practically, the bowl is the best capture environment in a pet's life: same place, same posture, same routine, twice a day, for years." She said appetite, hydration and oral comfort are among the first things to be disrupted by pain, dental disease, digestive issues, endocrine changes and illness. "Dogs are evolved to mask lethargy and limping. They are far less able to mask how they eat and drink," she added, noting that reduced or altered intake and changed drinking are signs across a wide range of conditions.

According to TechCrunch, Hoomanely developed the platform after an 18-month beta testing phase that collected about 5 million data points from more than 80 dogs. During testing, the platform flagged changes in one dog's eating pattern that were eventually traced to a chipped tooth starting to become infected. In another case, the app showed a sustained change from a dog's usual eating and temperature baselines, prompting the owner to take the dog to the vet, where it was diagnosed with tick fever.

There are caveats. TechCrunch notes that the beta cohort was quite small and the company appears to have shipped only about 50 devices so far. The EverBowl and app reports currently require a $29-per-month subscription. Sharath said the company does not yet have independent sensitivity, specificity or false-positive rates for clinical events, because that would require a study comparing its alerts against actual diagnoses. Hoomanely acknowledges its platform is not a replacement for a veterinary diagnosis, but rather a tool to help owners and vets identify potential issues faster.

The company is using its data for formal veterinary studies to see whether the system works across a larger group of dogs. Sharath said the studies will measure sensitivity, specificity, positive predictive value and false positives for each alert category, and the company intends to report results by use case. Hoomanely also plans to build more data-gathering devices: EverSense, a wearable that measures movement and rest, and EverHub, a hub that accepts inputs from third-party devices such as smart collars, feeders or home devices for environmental data.

Sharath told TechCrunch the long-term goal is for Hoomanely to become an animal health data company, using the data gathered from its devices to support research and serve nutrition and insurance companies. Because the data-capture system isn't specifically designed for dogs, she said it may eventually expand to other animals like cats, livestock or horses. The startup has raised $1.8 million in pre-seed funding and says it's starting conversations for a seed round.