Support teaching, research, and patient care.
Consumer health monitoring devices are increasingly found in our phones, on our wrists, and in our bedrooms, but not in our bathrooms due to the taboo surrounding human excreta. I want to challenge this taboo by highlighting the valuable information found in urine and stool - ranging from the microbiome to cancer biomarkers. The “Precision Health Toilet” (PH Toilet) I developed aims to improve human health by passively monitoring human excreta for signs of disease. Passive health monitoring is the key to ‘precision health’, a proactive and personalized approach to healthcare that focuses on the prevention and early detection of disease, and the PH Toilet will integrate this into the background of daily routines. My prototype is a non-invasive, low-cost method that uses artificial intelligence (computer vision and deep learning) to analyze human excreta for personalized monitoring and shows immense promise to become an integral tool in the new era of precision health.I am the inventor of the PH Toilet for proactive healthcare. The seminal work of this prototype development was published in Nature Biomedical Engineering last year and has garnered tremendous media attention. Despite the inundation of COVID-19 related research articles, this paper was ranked #7 by the Altmetric media attention score among all published articles in 2020. It demonstrates a functional, field-tested prototype of the PH Toilet, which includes urinalysis, uroflowmetry, defecation analysis and user identification with computer vision and deep learning. I am developing an upgraded version of the PH toilet that can screen various diseases (e.g., infectious disease [COVID-19], cancer) through biochemical analysis of human excreta.
Technologies for the longitudinal monitoring of a person’s health are poorly integrated with clinical workflows, and have rarely produced actionable biometric data for healthcare providers. Here, we describe easily deployable hardware and software for the long-term analysis of a user’s excreta through data collection and models of human health. The ‘smart’ toilet, which is self-contained and operates autonomously by leveraging pressure and motion sensors, analyses the user’s urine using a standard-of-care colorimetric assay that traces red–green–blue values from images of urinalysis strips, calculates the flow rate and volume of urine using computer vision as a uroflowmeter, and classifies stool according to the Bristol stool form scale using deep learning, with performance that is comparable to the performance of trained medical personnel. Each user of the toilet is identified through their fingerprint and the distinctive features of their anoderm, and the data are securely stored and analysed in an encrypted cloud server. The toilet may find uses in the screening, diagnosis and longitudinal monitoring of specific patient populations.
My educational background and training have focused on creating micro- and nano-scale devices using newly-developed techniques and applying these processes to advance research in molecular/cellular biology. So far, my area of expertise has focused on developing methods to pattern, sort, and analyze biological materials, especially circulating tumor cells. Through my work I have created multiple Microelectromechanical System (MEMS) and Nanoelectromechanical System (NEMS) devices that can not only identify miniscule mass changes in microfluidics, but integrate mass spectrometry for molecular detection, and manipulate oligonucleotide species for sort and analysis. I am confident that my background provides the expertise in the design and fabrication of micro-/nano-scale functional modules necessary for developing next-generation devices in solving critical problems in biomedical engineering.