CI MED-led projects win funding to advance neurological care, analyze health data and reach underprivileged communities

Nine innovative projects launched by the faculty of the Carle Illinois College of Medicine are sharing nearly $1.2 million in grants awarded this spring through the Jump ARCHES (Applied Research through Community Health through Engineering and Simulation) research and development program. The funding supports research involving physicians, engineers and social scientists to rapidly develop technologies and devices that could revolutionize medical education and health care delivery.

Projects of Spring 2023 grant recipients focus on key efforts to improve human health, including: development of new technologies that use health data and data analytics to deliver personalized roadmaps for improving health care; address evolving standards of care to incorporate personalized precision medicine and genomics best practices; improve health care and health literacy of historically disadvantaged populations; assist in the early diagnosis and treatment of neurological disorders; explore the needs of people with disabilities; and address social and behavioral science topics, particularly related to issues involving inequality and poverty, social and behavioral health and the digital revolution, assistive technologies for neuroscience, autism spectrum disorders, and societal influences on the cancer continuum.

Of the 12 projects that will receive funding this spring, nine are co-led by CI MED faculty.

Projects Co-Conducted by the CI MED Faculty:

• Machine learning of standardized DICOM metadata from imaging datasets

Brad Sutton, PhD, CI MED Health Innovation Professor, University of Illinois Urbana-Champaign and Matthew Bramlet, MD, OSF HealthCare

The project aims to develop a machine learning-based algorithm capable of classifying image parameters directly from signal intensity variations of 2D medical images to enable efficient pipelines for medical image segmentation. The proposed algorithm is expected to estimate patient and image acquisition information using machine learning methods in situations where DICOM header fields are incomplete or unreliable, ultimately enabling automated characterization of DICOM imaging datasets Unknown 3D.

• Machine-guided staging of neuroblastic tumors of patient-specific 3D models

Brad Sutton, PhD, CI MED Health Innovation Professor, University of Illinois Urbana-Champaign and Daniel Robertson, MD, OSF HealthCare

OSF HealthCare Children’s Hospital of Illinois uses segmentation services to create 3D models of neuroblastic tumors for presurgical planning. The hospital aims to move from 2D imaging to 3D modeling to increase the reproducibility of staging analysis, set a new standard for segmented models of neuroblastic tumors, and develop self-guided tools that can improve and automate factor staging of risk defined by the recommended image.

• To the measured diameters of the aortic arch with machine learning

Brad Sutton, PhD, CI MED Health Innovation Professor, University of Illinois Urbana-Champaign and Matthew Bramlet, MD, OSF HealthCare

The original project aims to automate the segmentation and clinical measurement of aortic arch diameters from MRI imaging. The researchers leading this project have successfully completed several steps including anonymization and curation of datasets, manual segmentation, and development of a new method for automated analysis of each aortic arch with promising results, indicating the correlation between automated and clinically derived measurements.

• A field trial to evaluate the effectiveness of convenient sanitary kiosks
  

  

Ujjal Mukherjee, PhD, CI MED Health Innovation Professor, UIUC & Ann Willemsen-Dunlap, CRNA, PhD, OSF HealthCare

This proposal outlines a field trial to evaluate the effectiveness of community health worker (CHW)-supported health kiosks in providing frontline preventive health screenings to rural and underprivileged communities. The project intends to lead to the development and large-scale implementation of health kiosks with the aim of having a positive impact on the social determinants of health and the long-term health status of the people served. This project has received more than $100,000 in funding.

• Contextualizing nursing needs for the development of a retention support app
  

  

Ann-Perry Witmer, PhD, CI MED Clinical Assistant Professor, UIUC and Sheryl Emmerling, PhD, RN, NEA-BC, OSF HealthCare

The goal of this project is to address the high turnover rate of new nurses by providing a digital app that offers personalized nursing support. The Contextual Engineering (CE) paradigm will be used to assess the needs and values ​​of first year nurses, including those who have left their positions, to inform app development in the first phase of the project, with the goal of stabilizing the nursing staff, improving the quality of service and reducing operating costs.

• Community Health Café: Engaging digital innovation and community-based resources to improve health equity in underprivileged communities
  

  

Joe Bradley, PhD, MA, CI MED Health Innovation Professor, UIUC and Scott Barrows, MA, OSF HealthCare

The purpose of the Community Health Café is to provide digital access to health and healthcare resources, including links for assistance with the social determinants of health, health education, and links to public health in underprivileged communities. The ultimate goal is a Medicaid telehealth option with OSF OnCall. This proposal aims to address the critical needs of disadvantaged residents in vulnerable communities and is critical to their health.

• AI-based brain tumor segmentation

Zhi-Pei Liang, PhD, CI MED Professor, UIUC and Matthew Bramlet, MD, OSF HealthCare

This project aims to improve the detection and monitoring of brain diseases. Phase 1 of the project focuses on the accurate delineation and segmentation of brain tumors using a combination of structural and molecular multimodal brain imaging data and deep learning. Proposed work includes the development of brain atlases for AI-based brain image analysis, computational tools for automated tumor detection and segmentation, and evaluation of potential clinical applications.

• Optimization of the pharmacological management of behaviors in patients with autism

Ravishankar Iyer, PhD, CI MED Professor, UIUC and Adam Cross, MD, FAAP, OSF HealthCare

This proposal aims to provide clinicians with a machine learning model that aids in the selection of appropriate treatment and dosing strategies for patients with autism spectrum disorder (ASD). Incorporating patient history, genetic information and physician notes, the model will dynamically adjust the treatment protocol as the patient progresses, ensuring optimal choices to improve behavioral symptoms with a high degree of confidence.

• Building Knowledge Graphs with large language models to predict the occurrence and severity of DKA

Jimeng Sun, PhD, CI MED Health Innovation Professor, UIUC and Adam Cross, MD, FAAP, OSF HealthCare

Diabetic ketoacidosis (DKA) hospitalizes more than 50,000 American children each year, with disadvantaged and underprivileged children at higher risk. This proposal aims to develop a predictive model using patient-specific knowledge graphs generated from clinical data extracted through name entity recognition and language modeling. Doctors can use the model to identify high-risk diabetic patients and prevent DKA.

Other funded projects:

• STREAM-ED: Simulation to refine, improve and adapt emergency management

Hyojung Kang, PhD, University of Illinois Urbana-Champaign and William Bond, MD, OSF HealthCare

This study aims to develop practical models that combine machine learning, discrete-event simulation, and optimization techniques to improve Emergency Department (ED) resource utilization and address emergency department overcrowding exacerbated by the COVID-19 pandemic. COVID-19 and staff shortages.

• Prototype: Intelligent Regulatory Change Management System

ChengXiang Zhai, PhD, University of Illinois Urbana-Champaign and Scott Lowry, MHA, CHC, CCEP, OSF HealthCare

This study proposes an Intelligent Regulatory Change Management (IRCM) system that uses natural language processing and artificial intelligence to track and evaluate public policy actions governing OSF HealthCare. This will enable compliance professionals to identify critical changes and determine appropriate actions, reducing manual review and improving quality, security, privacy risk management and efficiency.

• Predicting medication nonadherence in type 2 diabetes

Hyojung Kang, PhD, University of Illinois Urbana-Champaign and Mary Stapel, MD, OSF HealthCare

Medication adherence is critical to diabetes management, but disparities exist, particularly between racial/ethnic minorities and those of lower socioeconomic status. This proposal aims to use data-driven models to identify individuals and areas at high risk for diabetes medication nonadherence, develop and validate prediction models, and implement and evaluate them in clinical practice.

The Jump ARCHES program is a partnership between OSF HealthCare, the University of Illinois Urbana-Champaign (UIUC) and the University of Illinois College of Medicine at Peoria (UICOMP).

Editor’s Note: The original version of this article can be found here.