Microphone-equipped toilet will detect diseases and give you advice
There are many diseases that could potentially be detected through human waste. One such infection includes cholera. Cholera is a bacterial disease that causes diarrhea and affects millions of people each year. It results in approximately 150,000 deaths worldwide, each year.
Cholera is spread through contaminated food and water. Large epidemics that spread the bacterium are related to fecal contamination of water or food. It can sometimes be spread through undercooked shellfish and other seafood-related infections, as well.
Cholera is caused by the vibrio cholerae bacteria
Cholera is a diarrheal illness caused by an infection in the intestine with Vibrio cholerae bacteria. Although the infection is often mild, it can sometimes be life-threatening. According to the Center for Disease Control and Prevention (CDC), about one in 10 people with cholera will experience severe symptoms, including thirst, restlessness, and diarrhea.
Signs of dehydration while a patient has diarrhea could also be a warning that someone has cholera. The signs include rapid heart rate and low blood pressure. People with cholera can experience extreme dehydration, which can lead to kidney failure and death.
In order for patients to be treated for cholera, they must know that they have the disease first. However, it can be a sensitive and difficult task to monitor bowel diseases, such as cholera. Maia Gatlin, a research engineer at the Georgia Institute of Technology, created a way to use artificial intelligence to detect diarrhea. She calls her presentation The Feces Thesis: Using Machine Learning to Detect Diarrhea.
A noninvasive microphone sensor can detect disease in bowels
Gatlin will be presenting her thesis and the sensor tool today, Dec. 5, at the annual Meeting of the Acoustical Society of America, explaining her findings on how machine learning can be used to detect diseases in the bowel. She uses a noninvasive microphone sensor to identify bowel diseases, without necessarily collecting identifiable information, meaning the AI can determine the infection without having to be examined in a medical facility to collect additional data.
The method involves using the microphone and machine learning to detect diarrhea. Gatlin and her research team tested the sensor technique on audio files from online resources. Each single audio sample of an excretion, or bowel movement, was converted into a spectrogram, which captures sound in an image. A spectrogram is a visual way of representing the sound of a signal over time, representing a visual of sound.
The different types of excretion create different features in the audio and the spectrogram. The diarrheal tone produced more of a random sounding audio to the researchers. The spectrogram images were then used as input and were put into a machine learning algorithm. The algorithm’s performance was then tested against data with and without background noises to make sure it was gaining the information to interpret the sounds using the sensor, regardless of the environment.
The sensor can be used in places with persistent cholera outbreaks
Gatlin wants to use the AI sensor in locations where bowel infections such as cholera are prevalent. “The hope is that this sensor, which is small in footprint and noninvasive in approach, could be deployed to areas where cholera outbreaks are a persistent risk,” said Gatlin.
“The sensor could also be used in disaster zones (where water contamination leads to spread of waterborne pathogens), or even in nursing/hospice care facilities to automatically monitor bowel movements of patients.” Gatlin can also see the future usage of the sensory as being utilized in homes for individuals to test their own wellbeing through their bowel movements. She stated that “perhaps someday, our algorithm can be used with existing in-home smart devices to monitor one's own bowel movements and health!”
An exclusive interview uncovers a previously unrecognised connection between Earth's magnetic field and the Earth-Moon system.