What is automatic flushing, warm air drying, and seat insulation? Researchers from Stanford University in the United States reported a set of software and hardware that can track the health and disease indicators of the user's excrement, which can be called a true smart toilet.
According to a paper published in Nature Biomedical Engineering on April 6th, this conceptual smart device can be installed on existing ordinary toilets to build and The test specifically includes three modules: urine analysis, urine flow analysis, and stool analysis. One of the novelties of
is to cooperate with the camera to train artificial intelligence vision to analyze urine flow and fecal shape, and use "anal pattern recognition" to supplement the fingerprint recognition embedded on the flush button.
Yann LeCun, one of the three giants of deep learning and the winner of the 2019 Turing Award, commented on social media: "Convolutional networks land in the toilet. This is a real benefit to mankind."
Automatic retractable test strip
Human excrement is an important health response, but it is difficult to achieve long-term and continuous monitoring in clinical practice. The Stanford team chose to start with the toilet and perform non-invasive tests on urine and feces.
From the schematic diagram, the smart toilet is equipped with 7 hardware, including 1 pressure sensor, 1 motion sensor, 1 set of urine analysis test paper, and 4 cameras.
Stanford smart toilet. (I) Pressure sensor (ii) Motion sensor (iii) Urine test strip (iv) Stool camera (v) Anal camera (vi) Urine camera
Among them, the test strip can be qualitatively targeted for 10 biomarkers And semi-quantitative analysis, including red blood cells, post-urinary porphobilinogen, bilirubin, protein, nitrite, ketones, glucose, pH, urine specific gravity and white blood cells.
Suppose an adult male aims at the center of the toilet to urinate, triggers the infrared motion sensor, and the test strip will automatically extend. About 30-60 seconds, the test strip is soaked in urine, and then automatically retracts to its original position. A camera will capture video at the same time, perform real-time motion analysis, and wirelessly transmit the data to the cloud for storage.
After urination, the test strip falls off automatically and is discarded in the toilet. Taking environmental protection into consideration, the test strip uses water-soluble polysaccharide materials instead of plastic materials.
Camera captures "tick-tick-to-answer"
For urinary flow analysis, the researchers wanted to find a new way beyond the traditional flowmeter, using the power of computer vision, and installing two wide-angle cameras, 960 × 1280 pixels, 240 frames per second.
In order to set the parameters, the researchers invited 10 men aged 19 to 40 to perform 31 urination tests, each with a flow rate ranging from 50 ml to 670 ml.
The results show that the urine flow and urination time estimated by the computer based on the video are highly correlated with the standard flow meter, and can capture the intermittent droplets at the end of urination that the flow meter cannot. Researchers believe that this can provide additional information about prostate and bladder function.
Artificial intelligence to distinguish stool
The shape and hardness of stool can be used for clinical diagnosis of cancer, but there is no existing universal standard. To this end, the researchers invited two bowel surgeons to independently label different stool images, and the results showed consistency.
Using these images, scientists gave artificial intelligence 10 classes of "feces distinguishing", teaching to distinguish between normal stool, hard stool (indicating symptoms such as constipation) and soft/liquid stool (indicating symptoms such as diarrhea). The test is in progress The AUC (an indicator for judging the authenticity of the detection method, the closer to 1, the better) is above 0.89.
In addition, the toilet is equipped with a pressure sensor to calculate the start time of defecation and trigger the camera to collect images. Subsequently, the convolutional neural network can determine the time interval from the beginning to the first bowel movement, which is closely related to the overall function of the intestine. The end time of defecation is judged by using toilet paper or standing up.
In the test, a total of 5 women and 6 men participated in 55 bowel movements.
User identification
Finally, there is another key question.
Several people may share the same toilet, so how to establish a user's personalized health file? Researchers have embedded a set of fingerprint recognition in the flush button. Whenever the system determines that the toilet is over, a green indicator light will light up on the flush button.
However, in actual situations, there is no guarantee that the person who presses the flush button must be the person who goes to the toilet. Some toilets on the market also have an automatic flushing function.
Therefore, the Stanford smart toilet is also equipped with a unique "anal pattern recognition" function, which uses the image of each person's anus to safely match the collected health data. The author of
said that the potential health benefits of this toilet system need to be evaluated through large-scale clinical studies, and the system itself needs to be optimized based on the baseline data of human excretion.
As far as the key privacy issues are concerned, the paper stated that the data will be safely stored in the cloud system and sent to healthcare workers safely. The
research team is also deeply aware that the prospect of this smart toilet is closely related to user acceptance. In a survey of 300 people in the Stanford community (of course there is a serious education level deviation), 15.33% said it was “very acceptable”, 37.33% said it was “acceptable”, and 30.00% said it was “uncomfortable”. Among them, the most popular module is "urinalysis" without camera participation, and the least popular module is "anal pattern recognition".
This article is excerpted from: The Paper
Asian Waves, Boao Vision
Based on Asia and Facing the World
Delivering the latest developments of the forum to promote in-depth cooperation in Asia
Global important dialogue Communicator Asia's common development lookout
