A set of hardware and software that can be mounted on standard toilets to track biomarkers of health and disease in the users’ urine and stool is reported in a paper published in Nature Biomedical Engineering. This ‘smart toilet’, which operates autonomously, would enable individuals to monitor data on their health and allow for screening, diagnostic and patient-monitoring studies.
Technology that could repeatedly measure an individual’s health status non-invasively and inexpensively would facilitate the prevention and prediction of disease, as well as more precise diagnoses and treatment decisions. However, most technologies that are used to monitor a person’s health often do not produce actionable data and are poorly integrated within clinical workflows.
Sam Gambhir and colleagues designed a modular toilet system that incorporates pressure and motion sensors; test strips and video cameras for analysing the flow of urine and its basic biochemical composition; computer-vision and machine-learning algorithms for classifying stools according to a clinical scale of their morphology and liquidity; and biometric identification via a fingerprint scanner embedded in the flush lever.
The potential health benefits of the toilet system will need to be assessed in large clinical studies. The system will also need to be optimized with baseline data of the excreta of human populations. Although some of the modules in the proof-of-concept ‘smart toilet’ were built and tested only for sitting toilets and standing male participants, the authors note that future implementations of the toilet system will broaden its use and may include additional clinically relevant biophysical and biochemical assays of human excreta.
Machine learning: Model identifies three biomarkers associated with COVID-19 mortalityNature Machine Intelligence
Virology: SARS-CoV-2 capable of infecting intestinal cellsNature Medicine
Immunology: A method to detect antibodies to SARS-CoV-2Nature Medicine