2020 ARCHES Projects
2020 COVID RESPONSE: JUMP SIMULATION PROJECTS
REMOTE STATE ANXIETY DETECTION AND MONITORING USING MULTIMODAL WEARABLE SENSORS
Investigators: Manuel E. Hernandez, PhD, UIUC; Elizabeth Hsiao-Wecksler, PhD, UIUC; Richard Sowers, PhD, UIUC; Brent Roberts, PhD, UIUC; Susan Caldecott-Johnson, MD, UICOMP, OSF HealthCare Children’s Hospital of Illinois; Jean Clore, PhD, UICOMP
In frontline health care workers, recent evidence suggests increased depression, anxiety, insomnia and distress due to the COVID-19 pandemic. Even without COVID-19, physician trainees face mental health challenges as they provide care and learn clinical best practices. This project will integrate data from a suite of wearable sensors to quantify symptoms of stress and anxiety in physician trainees. The idea is to use information gleaned from sensors to monitor and potentially improve wellbeing before mental health disorders develop.
SPATIO-TEMPORAL ANALYSIS WITH TENSOR FACTORIZATION AND VISUALIZATION FOR PEDIATRIC MOBILE VACCINATION
Investigators: Jimeng Sun, PhD, UIUC; Mary Stapel, MD, OSF HealthCare; Scott Barrows, OSF HealthCare; Adam Cross, MD, OSF HealthCare; Elise Albers, OSF HealthCare; Ginger Barton, OSF HealthCare; Michelle Sheppard, OSF HealthCare; George Heintz, MSPH, MSE, UIUC; Yaroslav Daniel Bodnar, MD, OSF HealthCare, UICOMP
This project proposes to use AI technology to understand and improve the pediatric population health challenge of timely vaccination. With the help of AI, the project will visualize spatio-temporal patterns, identify critical geographic areas with the most concerning rates of under-vaccination, predict the supply need and deploy mobile immunization units to increase vaccination rates for those areas. This will improve vaccination rates in high-risk zip codes, revealing barriers around access to care and other social determinant obstacles.
TOWARD AUTOMATED DIAGNOSIS OF SEIZURES AND 3D REPRESENTATION OF SEEG CLINICAL DATA
Investigators: Matthew Bramlet, MD, UICOMP, OSF HealthCare; Brad Sutton, PhD, UIUC; Yogatheesan Varatharajah, PhD, UIUC; Andres Maldonado, MD, UICOMP, OSF HealthCare; Michael Xu, MD, PhD, UICOMP, OSF HealthCare
Some patients with seizures face debilitating effects that pharmacologic therapy cannot treat. These patients are left with surgery as their best option that requires an invasive procedure (stereotactic-electroencephalography or SEEG) to pinpoint the origin of these seizures. This project will present surgeons with a stereoscopic 3D model to give surgeons a better mental representation of where seizures are occurring. The group also wants to develop an automated interpretation algorithm of SEEG tracings, and create predictive algorithms to reduce invasive testing.
VIDEO ENHANCED NEUROLOGY (VEN)
Investigators: Chris Zallek, MD, OSF HealthCare; George Heintz, MSPH, MSE, University of Illinois at Urbana-Champaign (UIUC); and Steven Kastelein, OSF HealthCare
The number of individuals in need of neurology evaluations continues to outpace the number of available neurologists. This can create delays in diagnoses and treatment for some patients. This project will develop an infrastructure allowing clinicians to use video recorded neurological exams to reliably communicate findings to neurologists as well as improve monitoring for those already diagnosed with neurodegenerative conditions.
MEDLANG PHASE II: AN INTELLIGENT MEDICAL RECORD
Investigators: William Cope, PhD, UIUC; Cheng Xiang Zhai, PhD, UIUC; Mary Kalantzis, PhD, UIUC; Richard Tapping, PhD, University of Illinois College of Medicine Peoria (UICOMP); Yerko Berrocal, MD, UICOMP; Duncan Ferguson, PhD, UIUC; Jessica Hanks, MD, OSF HealthCare, UICOMP; Meenakshy Aiyer MD, UICOMP, OSF HealthCare
The goal of this project is to design an intelligent medical record that would work hand-in-hand with the electronic medical record for more precise documentation of cases, and aid in medical decision-making as well as rapid, accurate diagnoses. It would also include machine learning capabilities as more cases are fed into the system.
VISUALIZATIONS OF SOCIAL COMMUNICATION BEHAVIOR OF CHILDREN WITH AUTISM
Investigators: Karrie Karahalios, PhD, UIUC; Siraj Siddiqi, MD, OSF HealthCare; David Forsyth, PhD, UIUC; Mark Hasegawa-Johnson, PhD, UIUC; Hedda Meadan, PhD, BCBA-D, UIUC
Given that many children with autism spectrum disorder have deficits and delays in communication skills, researchers have been exploring ways to diagnose children early and begin with interventions at a very young age. Much of this begins with improving communication between parents and clinicians. This project’s objective is to develop a series of digital, interactive and visual tools to do just that. The idea is that these visualizations could mitigate challenges in discussions between parents and providers.
EARLY DETECTION OF DEVELOPMENTAL DISORDERS VIA A REMOTE SENSING PLATFORM
Investigators: Nancy McElwain, PhD, UIUC; Susan Caldecott-Johnson, MD, UICOMP, OSF HealthCare Children’s Hospital of Illinois; Mark Hasegawa-Johnson, PhD, UIUC; Siraj Siddiqi, MD, OSF HealthCare; Romit Roy Choudhury, PhD, UIUC
Child mental, behavioral and developmental disorders often go undiagnosed and untreated, thus increasing risk of spiraling disturbance well beyond childhood. This project will provide “proof of concept” for continuous, unobtrusive, large-scale and automated monitoring of young children’s functioning within the home environment, using wearable sensors. In doing so, a long-term objective is to detect potential developmental disorders or delays before such problems become clinically significant.
COMMUNITY-BASED TELE-REHABILITATION HEALTH NETWORK FOR ROBOTIC STROKE THERAPY
Investigators: T. Kesavadas, UIUC; Dusan Stipanovic, PhD, UIUC; Anne Horowitz, OTR/L, CSRS, MSCS, OSF HealthCare
Existing robot-based rehabilitation systems lack effective methods to monitor and enforce a patients’ participation in therapy. We propose to develop a community-based, networked robotic therapy system. This system uses a home-based haptic interface for rehabilitation of fine motor skills, with assistance from a remote external agent, such as a therapist, caregiver or artificial intelligence, who monitors progress and accordingly modifies the therapy regimen.
MEDLANG PHASE IL: A CONCEPT MAPPING TOOL FOR CASE ANALYSIS BY MEDICAL STUDENTS AND RESEARCHERS
Investigators: William Cope, PhD, UIUC; Cheng Xiang Zhai, PhD, UIUC; Mary Kalantzis, PhD, UIUC; Richard Tapping, PhD, UICOMP; Yerko Berrocal, MD, UICOMP; Jessica Hanks, MD, OSF HealthCare, UICOMP; Meenakshy Aiyer MD, UICOMP, OSF HealthCare
This project extends the recently completed Jump ARCHES project in which the group prototyped MedLang, an ontology-based medical concept mapping tool. The goal is to apply the tool to the analysis of single medical cases by medical students and researchers, and the addition of an artificial intelligence (AI) component to its suggestion system. The benefits of this tool for medical students will be to provide a rigorous learning space for the development of critical clinical thinking and offer a web-based infrastructure which will allow speedy peer review of cases and their accompanying concept maps.
SOFT AND DEXTEROUS SERVICE ROBOT CONFIGURATIONS TO SUPPORT HEALTHCARE AT HOME FOR OLDER ADULTS
Investigators: Girish Krishnan, PhD, UIUC; Wendy Rogers, PhD, UIUC; Ryan Riech, MD, MPH, OSF HealthCare
An increasing number of older adults live independently but have health care conditions that must be managed – both chronic and acute. The goal of this project is to investigate the effectiveness of soft robotic configurations in offering effective telehealth solutions, and understanding the social and behavioral aspects of how a robot builds trust with its user.
OPTIMAL DEPLOYMENT OF CANCER PREVENTION THROUGH DIGITAL HEALTH WORKERS
Investigators: Sarah de Ramirez, MD, OSF HealthCare, UICOMP; Hyojung Kang, PhD, UIUC; Lavanya Marla, PhD, UIUC; Roopa Foulger, OSF HealthCare; Mackenzie McGee, MD, OSF HealthCare; Abby Lotz, OSF HealthCare; Melinda Cooling, APRN, OSF HealthCare
This project proposes to develop a Digital Health Worker (DHW) program to use multiple varying digital modalities to decrease the socio-economic and racial disparities in cancer screening and mortality, specifically with breast cancer. Through the use of data science, this project will explore the most effective ways to deploy digital interventions for the promotion of cancer screening among populations with historically low screening rates and high mortality rates. Data analysis will also help optimize the DHW program to maximize screening rates, and provide an understanding of how to apply these practices to other types of cancers—especially among underserved populations.
A TRAINING SIMULATOR FOR CLINICAL BREAST EXAMINATION (CBE)
Investigators: Anusha Muralidharan, UIUC; Dr. Sarah de Ramirez, MD, OSF HealthCare, UICOMP; Thenkurussi Kesavadas, PhD, UIUC; Rohit Bhargava, PhD, UIUC; Dr. Sandhya Pruthi, MD, Mayo Clinic; Kimberly Michelle Bolin, National Consortium of Breast Centers
This project proposes to develop a high-fidelity training simulator to train health professionals on clinical breast examination techniques. It will also provide clinical evaluation to result in diagnosis of breast cancer at earlier stages, resulting in improved outcomes when followed with timely and appropriate treatment. The project uses current state-of-the-art technology to improve training using real-time performance analysis and mimics a realistic environment, giving medical professionals the flexibility of practicing as many times as they want in order to master the skill.
7-TESLA MRI IMAGING OF SEVERE TRAUMATIC BRAIN INJURY
Investigators: Paul M. Arnold, MD, FACS, Carle Foundation Hospital; Andrew Webb, PhD, Carle Foundation Hospital; Ravishankar Iyer, PhD, UIUC; Brad Sutton, PhD, UIUC; George Heintz, MSPH, MSE, UIUC; Dzung Dinh, MD, UICOMP, OSF HealthCare
The goal of this study is to image patients with traumatic brain injuries (TBI) by using high-field MRI, specifically the 7-Tesla. This type of imaging is expected to provide rich, previously unavailable information about lesions to diagnose what the effect of TBI could be. Better understanding of lesions can provide more detailed information about the extent of an injury and the cognitive processes that might be affected six months after injury. This will aid in the development of analytic tools to guide clinicians in decision-making and prognosis.
A RAPID AND AFFORDABLE VIRUS TEST FOR EARLY WARNING OF A PANDEMIC
This initiative will develop a test kit that extracts nucleic acid sequences from a sample of blood or saliva which are amplified with primers and new technology that can look for biomarkers of the virus using colorimetry so detection by naked eyes is possible. Researchers hope to develop an all-in-one test kit costing no more than $5 USD.
CONVERTING A MICROWAVE OVEN INTO A MASK STERILIZATION UNIT
This proposal will investigate the effectiveness for sterilization and disinfection to offer additional research to initial reports that indicate microwaves can be an effective microbicide.
DATA DRIVEN ANALYTICS TO PREDICT THE DYNAMICS OF THE COVID 19 OUTBREAK AND THE IMPACT ON HEALTHCARE PROVIDERS, RESOURCES, AND COMMUNITIES
This project proposes to use a novel analytical approach which incorporates artificial intelligence, data analytics, and machine learning to drive solutions to improve outcomes of the COVID-19 virus.
RAPID, CONTACTLESS VITAL SIGNS COLLECTION USING COMPUTER VISION AND CONSUMER TECHNOLOGIES
The goal of the proposal is to develop a computer vision algorithm for rapidly assessing an individual’s key vital signs (temperature, heart rate, respiratory rate, and blood pressure) relevant to COVID-19 utilizing a consumer grade camera.
SECURE FEDERATED LEARNING FOR COLLABORATIVE DIAGNOSTICS
This proposal leverages modern cryptographic tools to introduce a computational and software features for securely training predictive models using huge data sets distributed over several medical establishments; while ensuring patient privacy.
TESTING THE FILTRATION EFFICIENCY OF N95 RESPIRATORS FOR HEALTH-CARE EMPLOYEES AND PROTECTING PUBLIC HEALTH IN PANDEMIC FLU EMERGENCIES
This project proposes to solve the problem of quality assurance testing for Do-It-Yourself or rapidly made personal protective equipment (PPE).
THE COVID-19 KEEPING SAFE PROGRAM
To help communities open back up in the safest way possible, this platform will expand on the OSF Pandemic Health Worker Program for more extensive monitoring of individuals before, during, and after exposure to COVID-19.
VENTILATOR DUPLICATION KIT
Aims to develop a rapidly deployable kit for using a single ventilator among multiple patients with varying ventilation needs by tailoring the delivered breaths to each individual.
View Full Project briefs from all 17 Jump ARCHES Projects
JANUARY 2020
A HUMAN FACTORS APPROACH TO FOOD SECURITY
Collaborators: Dr. Sarah Stewart de Ramirez, OSF HealthCare and Abigail R. Wooldridge, University of Illinois Grainger College of Engineering
Thirty-seven million Americans have food insecurity which results in poor health and increases health care costs. This project will use a human-centered approach to identify barriers for individuals who are food insecure and challenges for service providers who are trying to meet needs in rural communities. That research will support design of technology-based solutions to reduce food insecurity in rural areas.
A-EYE: AUTOMATED RETINOPATHY OF PREMATURITY DETECTION AND ANALYSIS
Collaborators: Dr. C. Reddy, OSF HealthCare and Thomas Huang, U of I Beckman Institute for Advanced Science and Technology
Early detection of retinopathy in premature infants is important for early interventions to prevent blindness. With a shortage of specialists, it’s critically important to develop an AI diagnostic system that autonomously analyzes images of the retina to detect retinopathy. The team will also consider how to integrate the tool into portable, user-friendly equipment with the possibility future expanded uses for such a medical device.
ACTIVATE CAPTURE AND DIGITAL COUNTING (AC+DC) TECHNOLOGY FOR ULTRASENSITIVE AND RAPID CHARACTERIZATION OF MIRNA BLOOD BORNE BIOMARKERS FOR ALS
Collaborators: Dr. Vahid Tohidi, OSF HealthCare and Brian Cunningham, U of I Grainger College of Engineering
ALS is a devastating condition that leads to gradual muscle decline caused by loss of motor neurons in the brain and spinal cord. It’s in urgent need of new treatments. The goal of this proposal is to develop and validate nanoparticle technology that can use a small amount of blood plasma to identify miRNA biomarkers of ALS. The team will also develop an instrument using just a drop of blood to detect statistically significant circulating biomarkers to identify genetic indicators of ALS.
AI AUGMENTED PORTABLE PHOTOACOUSTIC IMAGING SYSTEM FOR EARLY DIAGNOSIS OF BREAST CANCER
Collaborators: Dr. Kent Hoskins, OSF HealthCare and Yun-Sheng Chen, U of I Beckman Institute for Advanced Science and Technology
This research aims to harness artificial intelligence (AI) to develop an affordable, portable imaging solution for breast cancer screening and diagnosis that could be more accessible to residents in rural communities. The team is proposing to use photoacoustic (PA) imaging techniques that combine optical (photo) and ultrasound (acoustic) approaches to produce high-contrast, molecular images of breast blood vessel and lymphatic systems for early breast cancer diagnosis.
AUTONOMOUS MORPHING BED MATTRESS FOR ALS PATIENTS WITH LIMITED MOVEMENT ABILITY
Collaborators: Dr. Christopher Zallek, OSF HealthCare/University of Illinois College of Medicine Peoria and Elizabeth Hsiao-Wecksler, U of I Grainger College of Engineering
This project will address complications from limited to no movement ability of adults while lying in bed, including patients with ALS who have weak muscles and loss of ability to control them. The team will develop an innovative bed mattress consisting of an array of soft air cells that will autonomously pressurize and depressurize specific areas to provide site-specific pressure relief, tilted repositioning and assistance with transferring while the patient is lying flat or has their head elevated.
AUTOMATED ANEURYSM SEGMENTATION AND MEASUREMENT
Collaborators: Dr. Jeff Klopfenstein, OSF HealthCare and Thomas Huang, U of I Beckman Institute for Advanced Science and Technology
Cerebral aneurysms are among the most deadly types. This group will build a large-scale dataset to create an algorithm to identify and segment the bulging blood vessels based on size and blood flow. This will be used for future medical imaging instruction and to develop computer programs to help with treatment decisions.
DESIGN AND VALIDATION OF A SOFT ROBOTIC CARDIAC TRANSSEPTAL PUNCTURE SIMULATOR
Collaborators: Dr. Abraham Kocheril, OSF HealthCare and Girish Krishnan, U of I Grainger College of Engineering
This project continues work on a realistic soft heart simulator that allows early-career cardiologists and surgeons to feel what it’s like to poke and prod cardiac tissues during a common surgery for patients with an irregular heartbeat. Phase II will enhance the level of realism by fine-tuning the materials used and incorporating image-based guidance.
DEVELOPMENT OF A DIGITAL FALL RISK ASSESSMENT AND PREVENTION TOOL FOR RURAL OLDER ADULTS
Collaborators: Dr. Sarah Stewart de Ramirez, OSF HealthCare and Jacob Sosnoff, U of I Beckman Institute for Advanced Science and Engineering
Falls are the number one cause of accidental injury in older adults. This project will use a machine learning algorithm for a fall risk assessment and prevention strategy application as part of a community health worker's digital toolkit. Researchers will also assess the usability of the “Steady” tool.
DIGITIZING THE NEUROLOGICAL SCREENING EXAMINATION
Collaborators: Dr. Christopher Zallek, OSF HealthCare/UICOMP and George Heintz, U of I Health Care Engineering Systems Center
There’s a projected 19% shortage of neurologists nationally by 2025 and yet nine percent of primary care visits are with patients who have neurological issues. This project will pilot an integrated Digital Neurological Examination (DNE) system and develop a platform using data for an AI-informed decision support assistant. The assistant will help physicians triage and care for patients with neurological symptoms regardless of exam location.
IMPROVING FEEDBACK AND EFFICIENCY: AUTOMATED GRADING OF POST SIMULATION WRITTEN CHART NOTES
Collaborators: Dr. William Bond, OSF HealthCare and Suma Bhat, U of I Grainger College of Engineering
Immediate feedback fosters the best learning and this project aims to improve Automated Short Answer Grading (ASAG) using Natural Language Processing (NLP) methods from previously collected and graded chart notes following simulations using standard participants (actor-based simulations). The tools developed will also reduce faculty grading demands and can be applied to trainings for other topics including use of opiates, telehealth use and patient counseling.
IMPROVING OUTCOMES AND TRAINING OF PECTUS EXCAVATUM
Collaborators: Dr. Paul Jeziorczak, OSF HealthCare and Inki Kim, U of I’s Grainger College of Engineering
This team will develop a process using virtual and augmented reality to improve patient education, resident training and placement of an internal metal chest brace for patients with pectus excavatum or sunken chest which can impact the function of the heart and lungs. The team will build on work already done with pediatric hearts, and build a training model using 3D printed chest walls as well as a virtual reality module for self-study as well as pre-operative planning.
OPTIMIZING DEPLOYMENT OF COMMUNITY HEALTH WORKERS
Collaborators: Dr. Sarah Stewart de Ramirez, OSF HealthCare and Hyojung Kang, U of I College of Applied Health Sciences
Community Health Workers are effective for improving health and lowering health care costs for vulnerable populations, such as those living in rural areas where access to health care is limited and health outcomes are poor. The project will create data-driven algorithms to support optimal deployment of precision guided, digitally enabled CHWs in rural settings.
SKILL ASSESSMENT IN SURGERY AND MICROSURGERY
Collaborators: Dr. Heidi Phillips, U of I College of Veterinary Medicine and T. Kesavadas, U of I Health Care Engineering Systems Center
We propose applying advanced engineering and data science to develop a high-fidelity virtual simulator to provide thorough and validated microsurgical training and assessment. The team will develop an evidence-supported, automated, robust, real-time, comprehensive and quantitative (ARRCQ) assessment system by building data sets and creating algorithms for optimum learning including accuracy and cost.
VIRTUAL REALITY TO DELIVER PSYCHOTHERAPY TO LUNG CANCER PATIENTS WITH DEPRESSION
Collaborators: Dr. Rhonda L. Johnson, OSF HealthCare and Rosalba Hernandez, U of I School of Social Work
More than half of all lung cancer patients experience depression which impacts their compliance with treatment, increases hospitalization and ultimately decreases survival rates. With a shortage of psychotherapists across the country, especially in rural areas, this project’s virtual reality (VR) platform could fill the void. For example, VR programs could transport users to relaxing environments with guided meditation. If successful, this treatment could be used as patients receive chemotherapy before or after radiation.
