Precision Medicine - Translational Sensors for Real-Time Health Monitoring

Hadar Ben-Yoav

Department of Biomedical Engineering, Ben-Gurion University of the Negev

Complex biological systems – whether physiological or environmental – may be viewed through a prism of biomarkers. Biomarkers are thus used in investigations of molecular mechanisms underlying diseases and as indicators of the presence and status of certain diseases. However, the exploitation of biomarkers for routine early detection and surveillance of diseases is hampered by the lack of sensitive, but easy to use, diagnostic kits for real-time analysis at the point of test. This need could be met by the development of an electrochemical sensor for detecting in a biofluid (such as blood, urine, or sweat) disease-associated molecules, including the redox molecules that could serve as biomarkers for cancers, inflammation, and neurodegenerative diseases. In this talk, I will review the state-of-the-art of electrochemical micro-sensors, challenges, and potential applications. I will present our recent studies of electrochemical micro-sensors to rapidly probe redox biomarkers in biofluids in three modes of detection: (1) direct detection of a specific biomarker, (2) indirect detection by influencing the masking signals that interfere with the biomarker’s electrochemical signature, and (3) detection of a profile of biomarkers using array of micro-sensors and intelligent chemometric models. We will also demonstrate the proof of concept detection in real-world scenarios by (1) amplifying antipsychotic clozapine electrochemical signature in untreated whole blood by using microelectrodes modified with electrocatalytic films (such as reduced graphene oxide) that will provide better schizophrenia treatment outcome, (2) shifting the interfering signature generated by other redox molecules in the biofluid (such as uric acid) by using electrodes modified with the biopolymer chitosan encapsulating electrocatalytic carbon nanotubes, and (3) utilizing an array of electrodes modified with various films and selectivities to differentiate electrochemical fingerprints from urine that are related to depression.

נציגי חברת אלביט יפגשו אתכם/ן ליום זרקור ברוח חג החנוכה.

יהיו סופגניות, מתנות והגרלה!

תבואו מוכנים עם קו"ח
 

(The talk will be given in English)

Speaker:     Dr. Yair Carmon
                     Stanford University

Monday, December 23^rd, 2019
15:00 - 16:00

Room 011, Kitot Bldg., Faculty of Engineering

Fundamental limits of modern machine learning and how to get around them

Abstract

The computational barriers concern nonconvex optimization: we prove unconditional lower bounds on the oracle complexity of finding stationary points using (stochastic) gradient methods. To bypass these lower bounds, we develop a “convex until proven guilty” principle that leverages additional smoothness available for many problems. Combining it with classical momentum techniques, we obtain an accelerated method for nonconvex optimization.

The statistical barriers concern the sample complexity of adversarially robust learning. We prove that unlabeled data allows us to circumvent an information theoretic gap between robust and standard classification in a Gaussian model. Our analysis directly leads to a general robust self-training procedure; we use it to improve state-of-the-art performance on the challenging and extensively studied CIFAR-10 adversarial robustness benchmark by up to 7 points.

Short Bio
Yair Carmon is a PhD student at Stanford University working with Prof. John Duchi and Prof. Aaron Sidford. His research focuses on the foundations of machine learning and draws on optimization, algorithm analysis, statistics and information theory. Yair received an M.Sc. from the Technion in 2015, under the supervision of Prof. Shlomo Shamai and Prof. Tsachy Weissman. Between 2009 and 2015 he held several positions as an algorithm engineer and research team leader, working on communications, signal processing and computer vision. His awards include the Stanford Graduate Fellowship, the Numerical Technologies Fellowship, and membership in the Technion Excellence Program.   ‏