Diagnosis is equally tricky, and, currently, there are no reliable tests. Doctors can only rule out other conditions.
For instance, blood analysis may be used to identify celiac disease or another condition that might explain the symptoms, and stool samples can rule out inflammatory bowel disorder or infections.
Another option is a colonoscopy, which allows doctors to visually inspect the bowel, but it is an invasive procedure that can be painful.
Because of these difficulties, IBS often goes undiagnosed, and people do not receive treatment that could potentially relieve their symptoms.
Listening in on digestion
Researchers at the Marshall Centre at the University of Western Australia in Perth are approaching this diagnostic conundrum from an unusual direction.
Their results were recently presented at Digestive Disease Week — a gathering of experts in the fields of gastroenterology, hepatology, endoscopy, and gastrointestinal surgery — held in Washington, D.C.
Study leader Barry Marshall, a Nobel Laureate and the director of the Marshall Centre, explains the researchers' aims:
"IBS is an extremely common disorder that is notoriously difficult to diagnose. We wanted to find a way to listen to the rumblings and grumblings of the gut to identify patterns that characterize chronic gut conditions, like IBS."
The equipment that they used to listen in on the gut's activity came into existence for very different reasons.
As Marshall explains, "We used acoustic sensing technology that was originally created to track the munching sounds of termites to see if we could detect problems in the human gut."
Machine learning and acoustic data
This acoustic technology was fitted to a wearable belt. And, using machine learning techniques, the belt was trained to distinguish the complicated patterns of sounds that are made by the human gut as it works.
Initially, the belt was fitted on 31 people with IBS diagnoses and 37 people without IBS. Any sounds were tracked for 2 hours after fasting and then for 40 minutes after a meal.
From this acoustic data, their system was able to build up an "IBS acoustic index model." They used a statistical method referred to as "leave one out cross-validation" to build up the system's accuracy.
Next, they used the belt on 15 patients with IBS and 15 people without. It correctly diagnosed IBS in 87 percent of cases.
"This study allowed us to achieve proof of concept. Once we further develop the belt and test it on more patients, this tool will be intended for use in primary care settings for the diagnosis of IBS."
Josephine Muir, Ph.D., associate director of the Marshall Centre
The team plans to continue testing the technology and fine-tuning the data capture and analysis.
Muir concludes, "The hope is that this new technology can offer a less invasive way to diagnose this painful, and sometimes debilitating, condition."