Disclosures: Gambhir and Park report being two of the coinventors on a patent application filed by Stanford University on the subject of this work (U.S. patent application number 62/695326) and Gambhir is a consultant or receives funding from several companies that work in the health care space but is not directly involved with the current work. Please see study for all other authors’ relevant financial disclosures.
April 15, 2020
3 min read
Save

‘Smart toilet’ could help detect cancer, other diseases

Disclosures: Gambhir and Park report being two of the coinventors on a patent application filed by Stanford University on the subject of this work (U.S. patent application number 62/695326) and Gambhir is a consultant or receives funding from several companies that work in the health care space but is not directly involved with the current work. Please see study for all other authors’ relevant financial disclosures.
You've successfully added to your alerts. You will receive an email when new content is published.

Click Here to Manage Email Alerts

We were unable to process your request. Please try again later. If you continue to have this issue please contact customerservice@slackinc.com.

A device that can be mounted on an everyday toilet could be used to help detect multiple diseases, including certain cancers, chronic kidney disease and irritable bowel syndrome, according to research published in Nature Biomedical Engineering.

The technology was designed to act as a continuing health monitoring device that collects health information from a user daily, similar to a wearable device.

“The thing about a smart toilet, though, is that unlike wearables, you can't take it off,” Sanjiv S. Gambhir, MD, PhD, professor of radiology in the Molecular Imaging Program at Stanford, said in a press release. “Everyone uses the bathroom — there's really no avoiding it — and that enhances its value as a disease-detecting device.”

Seung-min Park, PhD, a senior research scientist at the Stanford University of Medicine, told Healio Primary Care that the technology falls under the concept of “precision health,” which Gambhir came up with about 15 years ago and “emphasizes the prevention and early detection of diseases in a continuous manner.”

Photo of smart toilet 
A device that can be mounted on an everyday toilet could be used to help detect multiple diseases, including certain cancers, chronic kidney disease and irritable bowel syndrome, according to research published in Nature Biomedical Engineering.
Source: Seung-min Park

“In this regard, he believes that every human excretion plays a vital role in health monitoring,” Park said.

How it works

The researchers designed the device to collect physical and molecular data on urine samples through urinalysis and uroflowmetry, and physical data on stool samples.

Urinalyses are based on results of 10-parameter urinary test strips that deploy from a cartridge within the toilet system whenever a urination is detected through a motion-sensor. Uroflowmetry is measured through computer-vision analyses, which are based on videos captured by two high-speed cameras in set locations on the device. Video recordings are also used to analyze stool samples. The recordings begin when a pressure sensor is set off by a user.

Videos taken for uroflowmetry and stool analysis are assessed by a series of algorithms that determine normal urination and stool consistency from unhealthy ones.

Researchers designed the device to identify users in two ways — through a fingerprint scanner on the flush lever and an analprint scan taken by a camera in the device. Once the identity of the user is determined, data obtained during the void are stored and analyzed on a secure cloud-based web server.

‘Excellent’ validation accuracy

The technology was validated during a proof-of-concept study, during which 21 participants were followed over a period of 5 weeks. Ten participants were used to evaluate the system’s uroflowmetry monitoring, and 11 participants were used to evaluate defecation monitoring.

PAGE BREAK

Although the researchers were unable to assess the diagnostic accuracy of the technology due to an Institutional Review Board regulation, Park said the validation accuracy was “excellent.”

“Our computer vision uroflowmetry has 92 to 96 Pearson R correlations with the gold standards,” he said. “The defecation monitoring module has a comparable performance with that of trained medical personnel.”

The researchers surveyed 300 participants in the Stanford community to assess their acceptability of the device. They found that 37.33% of participants were ‘somewhat comfortable,’ 15.33% were ‘very comfortable,’ and 30% were uncomfortable with the idea of using the system.

In an “ideal scenario,” if the device were deployed in the real world, any abnormal findings collected from the smart toilet system would be sent from the secure web server to a physician who could review the data and decide whether the patient needs to present for further diagnostics, according to the press release. The current version of the device can potentially aid in diagnosing and monitoring irritable bowel syndrome, benign prostatic hyperplasia and urinary tract infections, the researchers reported.

Price tag

The research team hopes the first smart toilet attachment — which costs about $620 for the initial prototype — will be available to purchase in the next year or so, Park said.

He noted that the cost is likely to change as the parts are switched out to adapt to mass production, and the researchers “are targeting the retail price of our Smart Toilet [at] a few hundreds of dollars (US).”

A second version of the smart toilet, which would also include cancer diagnosis, is currently underway.

“We hope that this version will be available in 3 to 5 years,” Park said. – by Erin Michael

Disclosures: Gambhir and Park report being two of the coinventors on a patent application filed by Stanford University on the subject of this work (U.S. patent application number 62/695326) and Gambhir is a consultant or receives funding from several companies that work in the health care space but is not directly involved with the current work. Please see study for all other authors’ relevant financial disclosures.