Free ‘poop app’ detects liver disease in babies

The PoopMD app could provide reassurance to most parents that their newborn's stool color is normal, and the baby is not at risk for bilary atresia. (Credit: iStockphoto)

A diaper-decoding smartphone app accurately analyzes a newborn’s poop color to screen for a rare but life-threatening liver disorder.

In a small study, the free app—available to Apple and Android smartphone users—correctly identified all high-risk poop samples without a single false positive.

Called PoopMD, the app could provide reassurance to most parents that their newborn’s stool color is normal, and the baby is not at risk for bilary atresia.

But for the one in 14,000 newborns with BA—about 400 babies each year in the United States—parents can rely on the app to spot the symptomatic pale yellow to chalky grey stools that indicate medical assessment is urgently needed.

Pediatric liver disease

“Days matter in diagnosing BA,” says Douglas Mogul, a pediatric gastroenterologist at Johns Hopkins Children’s Center and lead author of the study published online in the journal PLOS ONE.

Bilary atresia causes nearly half of pediatric end-stage liver disease in the United States. Babies treated within the first two months of life have the best outcomes and are far less likely to need a liver transplant later. The first line of treatment involves surgery to repair bile ducts and restore bile flow to prevent irreversible liver damage.

The 60-day window is often missed, researchers say. The average time to diagnosis in the US is 70 days.

“PoopMD does what it says it will do,” says Mogul, who worked with HCB Health to create the app, released in 2014. Among more than 100,000 medical health apps currently available, he says, only a few have been rigorously tested to see if they deliver the benefits they promise.

Poop color card

The app was built on experience with an earlier “color card” distributed to new parents. To analyze the app’s effectiveness, researchers first had seven expert pediatricians classify 34 photographs of pale-colored stool. Twenty-seven were determined to be of normal stool, but seven photos were deemed to signal high risk for BA.

Next, one expert and three laypeople were asked to use the app on Apple and Android devices to look at and analyze the same pictures under a variety of lighting conditions and using a variety of smartphone models.

“These individuals were essentially asked to take a picture of the stool photograph and determine if the app identifies the photo as normal or pale,” Mogul says. In normal use, however, a parent just takes pictures of the contents of a diaper.

Even using the picture of the picture, the researchers say, the app correctly identified all of the high-risk stool samples and correctly identified 24 of the 27 normal stools. It labeled the other three “indeterminate.”


“That means the app never identified a normal stool as pale, a type of false positive that could cause unnecessary anxiety for a parent or other app user,” Mogul says.

The app can store results for future and comparative reference, and parents can email a photo to a pediatrician directly from the app. The app also reminds parents to check their newborn’s stool color every two weeks.

“Four out of five adults in the US ages 18 to 35—the age of young parents—have a smartphone, and that’s independent of income level,” Mogul says, “so the app gives us a great opportunity to distribute interactive content that helps young parents pay attention to educational advice.”

Beyond the health and lifesaving benefits of early diagnosis and treatment of BA, the potential cost savings are enormous. Avoiding a liver transplant saves about $150,000, plus $25,000 a year for immunosuppression to keep the child’s body from rejecting the new organ.

Other authors on the paper were from Johns Hopkins and from HCB Health of Austin, Texas, which developed PoopMD.

Source: Johns Hopkins University