Biosensing disease: smart contact lens and smart toilet

Murat Baday is Stanford Scientist and the co-founder of Smartlens – a clinical-stage medical technology company that envisages the prevention of blindness due to Glaucoma. Dr. Baday obtained his Ph.D. in Computational Biology and Biophysics from the University of Illinois at Urbana-Champaign and his M.S. in Physics from the University of Pittsburgh. Dr. Baday has been working on cancer, remote diagnostics, and AI in healthcare research at Stanford Research in Bioengineering, Radiology, and Neurology departments since 2013. Dr. Baday is co-founder/advisor of several startups. He has studied computational particle physics at Cornell University. Dr. Baday has expertise in several fields including optics, microfluidics, imaging, medical devices, machine learning, and bioinformatics.

Reducing intraocular pressure (IOP) is the only effective treatment for glaucoma, a disease that may lead to irreversible blindness due to optic nerve damage. Despite using pharmaceuticals and surgery to lower IOP, patients still progress from normal vision to blindness with current event-based management. The reasons that glaucoma-related blindness remains a major public health challenge are complex and involve health care disparities, and an unmet need to provide the clinician with a better profile of the IOP variation in an individual patient. This profile of IOP variation is a phenotype, and there is no clinical factor that predicts IOP variation. Currently, office-based IOP data does not provide sufficient IOP data throughout the day to characterize a patient’s IOP phenotype of variation. To meet this need, Smartlens, Inc. has developed a microfluidic strain sensor embedded in a comfortable and affordable soft contact lens (miLens), that provides an electronic-free, wearable, on-demand, smartphone-enabled readout, which captures variations in IOP. The miLens converts small strain changes to a large fluidic volume expansion detectable by a smartphone camera and it is a wire-free, more comfortable solution to the currently marketed telemetry devices, which are made with metallic sensors and antennae. Furthermore, our team is implementing the technology to build minimally invasive sensors to measure intracranial pressure (ICP) in the brain that could be used to monitor several brain diseases including hydrocephalus, traumatic brain injuries, and brain tumors.

Seung-min Park is an Instructor of Urology at Stanford University School of Medicine. Dr. Park had a unique educational background in Physics (bachelor’s degree, 2002) and Applied Physics (PhD, 2008), and has been exploring interdisciplinary pathways to academic independence (bioengineering, radiology, and urology). As a doctoral student at Cornell, Dr. Park pioneered the design and fabrication of micro and nanostructures for electronic, mechanical, and biological applications. His postdoctoral training at University of California, Berkeley had facilitated the cohesive development for translational applications of emerging micro/nano technologies for molecular analysis of diseases. At Stanford, Dr. Park expanded his research to include cancer diagnosis and assessment associated with liquid biopsy and developed a nanodiagnostics system for detecting genetic contents of single circulating tumor cells isolated from the blood. His recent work focuses on achieving precision health via the 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 analyzed in an encrypted cloud server. The toilet may find uses in the screening, diagnosis and longitudinal monitoring of specific patient populations.