RAPID: Collaborative Research: Data Analytics for Mechano-acoustic and Physiological Monitoring of COVID19 Symptoms

点击翻译按钮获取中文摘要

The novelty of the Covid-19 pathogen, diversity of its transmission modes, lack of universal testing capability, absence of a vaccine, lack of medical supplies and personnel in hospitals needed for effective treatment represent key challenges in confronting the pandemic. This RAPID project addresses a key issue with pandemics in general and Covid-19 in particular – the limited capacity of any health-care system – whereby hospitals and health-care providers struggle to provide targeted care to patients needing treatment. This project proposes to address this challenge by developing low-cost sensing and in-situ data analytics platform technologies to enable individualized, distributed and continuous health monitoring of individuals and thereby provide early disease detection capabilities in-residence, minimize the number of unnecessary hospital visits, and act as an early warning system to enable preventive measures to be taken early on especially for high-risk individuals such as seniors and elderly individuals who are most vulnerable to Covid-19. This project will enable: (1) monitoring of early signs of disease spread across health care workers in clinical settings, (2) tracking of the progression of the disease in infected individuals, both in the home and the hospital to allow for efficient provisioning of resources and also to capture basic aspects of the effects, and (3) accurately and precisely measuring the effectiveness and the timescale of operation of the large number of various therapeutics that are currently under evaluation. The low-cost and distributed nature of these sensory processing platforms will ensure that populations at high-risk of contracting and succumbing to Covid-19 will be able to access the health care needed. Overall, this research will enable rapid and accurate diagnosis and tracking of the Covid-19 infection in a pervasive manner – building on unique wireless device platforms that are currently deployed in the Chicago medical complex -- and thereby contribute significantly to limiting the impact the current and future pandemics on society. The proposed technology will acquire mechano-acoustic signatures of the underlying physiological processes (such as those measured by a stethoscope) and precision kinematics of core-body motions using a skin-mounted soft electronics compute platform (“The Patch”) from individuals tested for Covid-19, develop low-complexity data analytic algorithms using a hybrid of digital signal processing (DSP) and machine learning (ML) to detect the presence of infection with high accuracy, and deploy these algorithms on such resource-constrained compute platforms for rapid diagnosis. Proposed work will augment the Patch, which is currently deployed at the local hospitals, with pulse oximeter (SpO2) sensors. The proposed work includes: 1) development of low-complexity fixed-point ML algorithms for Covid-19 specific analytics using patient data acquired by the current deployment of the Patch; 2) development of methods for energy-efficient embedding of such algorithms on to the SpO2-enabled Patch and associated hardware; 3) and deployment of the ML-based Covid-19 specific data analytics in the field with patients. This research brings together innovations in flexible wireless electronics, mechano-acoustic sensing devices, energy-efficient inference architectures, and low-complexity data analytics for the purposes of rapid, early and continuous diagnosis and monitoring of various diseases and infections including Covid-19. The vertically-integrated (materials-to-systems) nature of this research overcomes traditional disciplinary boundaries. In this process, new knowledge will be generated both at a fundamental level and in terms of new applications.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.