A microphone sensor and machine learning algorithm can categorize excretion episodes and identify cholera or other bowel diseases.
- Cholera affects millions of people every year
- A sensor that uses a machine learning algorithm to predict cholera could be deployed in areas where cholera outbreaks are a persistent risk
Using Machine Learning to Predict Occurrence of Bowel Diseases
The method was put to the test using audio data from online sources by Gatlin and her team. Each excretion event’s audio sample was converted into a spectrogram, which essentially turns sound into a visual. The audio and spectrogram display various features depending on the occurrences. For instance, while excrement may have a single tone, urinating typically has a continuous tone. Contrarily, diarrhea is more unpredictable.A machine learning algorithm was fed spectrogram images and trained to classify every event according to its attributes. To ensure that the algorithm was picking up the correct sound features regardless of the environment surrounding the sensor, its performance was evaluated against data with and without background noises.
Sensor to Monitor Cholera Outbreak
“The hope is that this sensor, which is small in footprint and non-invasive 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 the spread of waterborne pathogens), or even in nursing/hospice care facilities to automatically monitor the bowel movements of patients. Perhaps someday, our algorithm can be used with existing in-home smart devices to monitor one’s bowel movements and health!”Source-Medindia