AI-powered smartphone app monitors IBS using poop pictures


Researchers in the US have developed an app that uses a smartphone camera and artificial intelligence algorithms to assess images of patients’ poo for signs of disorders such as irritable bowel syndrome (IBS).

The tool is designed as an alternative to the form and frequency of stool self-reported by patients using the seven-point Bristol Stool Scale (BSS), which classifies consistency from hard to liquid but can produce widely varying results.

It is well recognized that the subjectivity of BSS can make it difficult to obtain an accurate picture of therapeutic interventions designed to improve symptoms of gastrointestinal disorders like IBS in clinical trials.

In a study of 39 subjects reported in the American Journal of Gastroentereology, researchers at Cedars-Sinai Medical Center in the United States asked patients with diarrhea-predominant IBS to take a picture of each of their stools over a period of two weeks using the app.

These images were evaluated by AI for five visual characteristics – BSS, consistency, fragmentation, edge blur and volume – with the results double-checked by two specialist gastroenterologists. Another component of the trial compared AO to patient-reported BSS scores.

Overall, there was “good agreement” between the AI ​​results and the experts on all five measures, and the app outperformed self-reporting using the BSS system, with sensitivity and 16% and 11% higher specificity, respectively, resulting in fewer false results. – positive and false negative results.

The authors note that studying gastrointestinal disorders can be difficult, especially those that are considered “functional” and rely on patients self-reporting symptoms such as abdominal pain, bloating, as well as the form and frequency of stools.

There has been an evolution in the measures used in clinical trials of new therapies for IBS, from weekly symptom assessment to daily self-reporting using the BSS.

However, the BSS “although intuitive, requires subject-based education and instruction to avoid confusion,” they write in the article.

“In this study, we show that AI is able to catalog and characterize stool shape objectively,” the authors continue.

“While the app still relies on a subject to document each bowel movement, the photos document the ‘true’ characteristics of the stool. This allows for an objective measurement of stool shape. [and] allow saddles to be evaluated with additional characteristics beyond the BSS.


About Author

Comments are closed.