As we begin a new year at OSF HealthCare, we’re reflecting on 2024 and the major strides in digital transformation to make access to care and health information seamless for our patients. At OSF, we continue to collaborate with our academic and business partners to leverage collective expertise and to responsibly use the power of artificial intelligence, always taking care to use guiding principles of what is fair, appropriate, valid, effective and safe (FAVES).

The efforts are highlighted here in our Top 10 Digital Health and Innovation stories of 2024 in no particular order.

1. OSF Unveils new 55+ primary care service in south suburban Chicago: Called OSF Complete Care 55+, this is a unique collaboration between OSF HealthCare Little Company of Mary Medical Center and OSF OnCall, the digital arm of the health care Ministry. When launched in early 2025, this primary care program will incorporate in-person visits, plus a mix of virtual care, digital health monitoring tools and 24/7 access to a care team focusing on those with chronic conditions.

2. Building an AI prepared workforce: OSF HealthCare leaders took just six weeks to develop mandatory training about generative AI for all 24,000 OSF Mission Partners (employees) because tools were already publicly available. Melissa Knuth, Vice President of Planning, outlines that to rise to the challenge, she worked with OSF Innovation to use mixed media to keep the content interesting and tapped generative AI tools to assist with the content creation.

3. OSF Digital Hospital patients in Rockford area say it’s the best medicine: OSF OnCall expands its digital hospital program to Rockford and receives rave reviews from some of its first patients. In addition, a well-known farm broadcaster shares her story about receiving acute-level care from the comfort of her own home and urges others who are eligible to consider the option.

4. OSF Innovation sets the table for solution to prevent cancelled surgeries: Two OSF HealthCare nurses turned to the OSF Innovation Studio team to help improve their Device Table software that serves as a database for implanted medical devices – offering information needed for surgical teams to reference for safety in surgery planning. We also reported on the creation of a spin-off company, OpenSurg, which will license and promote widespread sales of Device Table and related support features.

5. OSF HealthCare experts: ‘Establish guiding principles when developing digital care strategy’: OSF OnCall was a spotlight vendor and presenter at this year’s American Telemedicine Association’s annual Nexus conference in Phoenix, Arizona. OSF OnCall Senior Vice President Jennifer Junis advised during her presentation that health systems use guiding principles when developing their approach to digital health and to involve clinicians and patients when piloting new programs and digital tools. OSF HealthCare has also become a founding member of an ATA Digital Center of Excellence.

6. Mapping the future for early diagnosis of rare diseases: A Jump ARCHES grant-funded project with the University of Illinois Urbana-Champaign is using generative AI and knowledge graphs that map symptoms to detect rare diseases. Adam Cross, MD, who leads the OSF Children's Innovation Lab in Peoria, Illinois, wants to create a point-of-care tool for primary care providers to help patients get an early diagnosis of a rare disease.

7. Health economist: Connectivity and trust can expand telehealth: OSF OnCall hosted its first-ever digital health symposium which drew nearly 150 clinicians and vendors. Keynote speaker health economist and advisor Jane Sarasohn-Kahn stressed evidence-based digital technologies can improve health outcomes, but health systems need to build trust and expand community partnerships to increase engagements.

8. Fast-Tracking Hope: Rapid Intake at the OSF Cancer Institute: OSF HealthCare began 2024 with the opening of its new comprehensive Cancer Institute, offering advanced radiation therapy such as brachytherapy and proton beam therapy.  It also launched a new rapid intake system, developed by OSF OnCall and OSF Innovation to offer a single point of contact through OSF-HOPE (844- 673-4467) so cancer patients can be immediately connected to treatment and support services.

9. Piloting a smarter colonoscopy: OSF HealthCare St. Joseph Medical Center piloted artificial intelligence-backed colonoscopies, using a company called GI Genius, to improve detection of precancerous polyps. During the pilot, the adenoma detection rate (ADR) averages increased among all patients involved to as high as 12%, while individual physician ADR increased as high as 32.8%. The technology is now being implemented across the OSF Ministry.

10. Testing the path to better concussion diagnosis: An OSF Innovation lab-designed FlightPath app is now being tested by athletes at Illinois State, Bradley and Illinois Wesleyan Universities. The app only takes about two minutes to collect more than a million data points as a person tries to catch a hummingbird within a 3D space on a screen. The clinical trial could last two years. 

Miami Dolphins quarterback Tua Tagovailoa recently suffered his third confirmed concussion in 25 months – just another reminder that football and other contact sports pose the threat of a traumatic brain injury.  Research indicates it’s important to accurately and immediately diagnose a concussion because the consequences of misdiagnosis or faulty management can lead to major disability or death.

Illinois State University senior Cyerra Hibbert knows about concussions. She’s had multiple ones while playing soccer in high school and at ISU, the most recent just a month ago. Hibbert is one of the first athletes to test a new FlightPath concussion app. The lead app developer is *Adam Cross, MD, a pediatric hospitalist and clinical informaticist for OSF HealthCare and director of the OSF Children’s Innovation Lab at Jump Simulation & Education Center in Peoria, Illinois. He is working with co-lead Inki Kim, of the Health Care Engineering Systems Center at the Grainger College of Engineering at the University of Illinois Urbana-Champaign.

The concussion assessment app is a grant-funded project through Jump ARCHES, a research collaborative that partners teams of clinicians and engineers working together to improve patient outcomes and reduce health care costs. The FlightPath app is being tested at Illinois State, Illinois Wesleyan and Bradley Universities as part of a clinical trial and research coalition.  Hibbert used the FlightPath app after receiving instructions from her athletic trainer six days after she received a blow to the head during a game.

Hibbert was able to finish the test. It only takes about two minutes to collect more than a million data points as a person tries to catch a hummingbird within a 3D space on a screen.

“After a while it did bring a little confusion or if I wasn’t aware of where the bird flew on or off the screen, that did trick a little bit of my memory and concentration skills, so I do think it’s definitely approachable," Hibbert explains. “It’s definitely doable. I think just based on your outcome will determine where you are in your concussion level.”

Dr. Cross says the single biggest risk factor for prolonged time to recovery is delayed diagnosis, so FlightPath is his answer with its ability to diagnose a concussion within minutes. His research team has done some internal testing.

“Regarding how well it detects differences in impairments with people – how well they can determine if someone is functioning, acting appropriately, or if there's if there's something else going on. The challenge has been really doing that with individuals that have true concussion,” says Dr. Cross.

Athletes with a suspected concussion are challenged by FlightPath to walk in their environment while trying to keep a hummingbird in a bubble on the screen.

“The players themselves are trying out this app while concussed after having been consented earlier on in the year so that we can get data around how they perform with this app while concussed versus not concussed, and comparing that to the normal, typical present-day evaluation techniques that the trainers perform.”

Dr. Cross stresses, right now, the clinical trial does not involve trainers using the app to help make decisions. He says the research is not that far along and data collection needs to happen first. But, Karan Rai, MD, a sports medicine physician with OSF HealthCare who also serves as the team doctor for ISU Athletics, says eventually, the data from FlightPath could help beyond diagnosis.

“It in turn can help us with making prognoses, coming up with recovery timelines, implementing certain vestibular therapy. Other than diagnostic purposes, we can extrapolate that data to help us come up with a better treatment plan as well.”

Takes the pressure off
Both Hibbert and Dr. Rai are excited to be part of what they consider ground-breaking research that has the potential for helping athletes in the future. Hibbert, who plans to go into medical sales, says it’s helpful to have an objective tool for an evaluation. She thinks it takes the pressure off athletes.

“Because as athletes, we’re always eager to be on the field or play the game and to have that mindset to be better and get back on your feet as quickly as you can. I think this app will allow you to really settle and to really take your time with your symptoms.”

The clinical trial is looking at whether FlightPath can do as good or better as traditional methods in diagnosing a concussion.  So far, Dr. Rai says nearly 15 athletes who have suffered a concussion have completed a FlightPath assessment and it’s been performing well.

“Results are early so far but in our sample size we found some associations at least where FlightPath has shown some abnormalities similar to what other examinations have found as well, whether that’s the SCAT test or the ImPACT test.”

There are other concussion applications commercially available, but Dr. Cross suggests none are as robust as FlightPath.

“There aren't any, as far as I've seen, that use this mixed reality approach to gather the kinds of data that we're gathering. This is very rich data in a very short time in our app. One of the things that makes it so unique and sets it apart is that we get so much data about so many different manifestations of concussion in such a short time.”

Testing is expected to take at least two years. After testing, the app will be submitted to the FDA for clinical approval.

Here is a video demonstrating how the app works.

*Dr. Adam Cross also holds these positions:
Assistant Professor, University of Illinois College of Medicine Peoria, Division of Pediatric Hospital Medicine
Adjunct Professor, University of Illinois at Urbana-Champaign, Health Care Engineering Systems Center (HCESC)
Clinical Research Informatician, OSF HealthCare | Jump Trading Simulation & Education Center (JTSEC) 

Dr. Adam Cross, ISU soccer player Cyerra Hibbert and Dr. Karan Rai

B-roll of ISU soccer player Cyerra Hibbert on soccer field

B-roll of FlightPath app demonstration

Rare diseases might seem individually uncommon but collectively 1 in 10 people across the globe have a rare disease according to the World Health Organization. Undiagnosed rare diseases pose a significant challenge in health care, often leading to delayed treatment and poorer patient outcomes.

When specialists or primary care providers are confounded by a patient’s symptoms, it can send them back to their medical books. But, Adam Cross, MD, a pediatric hospitalist and clinical informaticist who leads the Children’s Innovation Lab at the Jump Trading Simulation & Education Center, is collaborating on research to better help primary care providers make a rare disease diagnosis quickly. The goal is to create an AI-backed, point-of-care support tool that can prompt testing for confirmation for the most relevant diagnoses.

Dr. Cross says typically genetic testing is the only way to confirm a rare disease. That testing is expensive and not readily available in primary care settings, particularly in rural communities. Patients have long waits and often must travel in hopes of getting a diagnosis.

A Jump ARCHES grant is funding a collaborative effort with the University of Illinois Urbana-Champaign (UIUC), with co-lead researcher Jimeng Sun, PhD, to use generative AI and medical knowledge graphs to improve diagnosis of rare diseases.

“We are trying to create a model that will take the notes that are already being written by primary care physicians and look for unique sets of signs and symptoms that might suggest a patient has an undiagnosed rare disease.” Dr. Cross adds, “That approach can empower the physician with information regarding those diseases and prompt further testing if they choose to do so.”

Dr. Cross believes rare diseases, despite their complexity, leave identifiable patterns within electronic medical records. The project introduces Automated Rare Disease Mining (AutoRD) to help unearth patterns when analyzed using machine learning models and mapped using knowledge graphs. He believes the Auto RD method can potentially enable the early detection of these diseases. These patterns could be drawn from clinical signs and symptoms and medical history, in addition to demographic features such as race/ethnicity, age and geographic location.

Researchers are making progress

In one year, researchers have been able to develop robust machine learning models to extract signs and symptoms of rare diseases from notes within electronic medical records that have been stripped of personal, identifying information. They’ve also been constructing comprehensive knowledge graphs to visually map the relationships between various medical conditions and symptoms of rare diseases from existing resources. 

“We did this so that we could give people a better visual example of just how complex these diseases are and how they're all connected,” Dr. Cross observes while viewing an early version of a knowledge graph created by researchers that looks like a celestial constellation. “It's kind of beautiful when you see the simplicity and the complexity of all the different symptoms, but the simplicity of the structure. It gives you a sense of just how incredible these new technologies really are in terms of helping us find patterns in the chaos.”

The effort involves sophisticated machine learning approaches that have changed with lightning speed, even since Dr. Cross and his UIUC colleagues began their work.

“Even in that year, there have been more advanced and more powerful methods that have come out that we've since adopted, and we continue to improve our own methods based on what's being developed globally.”

The research is leveraging the abilities of a supercomputer at UIUC which has a federal health privacy compliant section for secure data storage and processing of massive amounts of health care data. The next focus is to work on the predictive ability of the models. Dr. Cross is convinced that dynamically linking patient-specific data with the broader context of medical knowledge on rare diseases can uncover patterns and correlations that might otherwise remain hidden.

As the approach is refined and improved, he also doesn’t rule out the possibility of discovering new rare diseases.

“As we go along, it is certainly possible with the technology that we've created, maybe we'll start to see patterns of signs and symptoms that don't have a known diagnosis. Or maybe there are subtypes of diseases that are out there that really seem to have their own unique progression, and we could also maybe discover those in subsequent phases of the project.”

Dr. Cross, who also serves as an assistant professor at the University of Illinois College of Medicine in Peoria (UICOMP) and is an adjunct professor at UIUC, says he and his fellow researchers have already published one scientific paper, and another has been submitted, showing the results of their research so far.

Video clips with Dr. Adam Cross

B-roll of knowledge graphs for rare disease diagnosis

OSF HealthCare and Bradley University are focusing on cancer prevention and treatment, as well as improving overall cardiac imaging plus pulmonary lung monitoring for babies and young children. The grants are the result of a partnership announced earlier this year between the Peoria, Illinois-based health system and the city’s premiere private university. The awards be given twice a year with joint funding from each organization.

This first round of grants, totaling nearly $200,000, have been awarded to four projects for research into rapidly developing the best, innovative approaches to medical training and health care delivery. The IFH grant awards include co-investigators from both Bradley University and OSF HealthCare.

Here are the Innovation for Health projects for spring 2023:

Toward Automation of a 4D Heart from Retrospectively Gated Cardiac CT Scans

Lead researchers
Matthew Bramlet, MD, OSF HealthCare
Samuel Hawkins, PhD, Bradley University

The goal of this project is to determine the feasibility automating the segmentation of the 18 phases of gated cardiac CT scans to generate patient-specific, 4D beating hearts and that these 4D animations can be placed into and analyzed in a digital stereoscopic format such as virtual reality.

Pulmonary Acoustic Sensor Telemetry Array (PASTA)

Lead researchers
Adam Cross, MD, FAAP, OSF HealthCare
Suruz Miah, PhD, Bradley University
Connor Davey, BA, OSF HealthCare
Reid Jockisch, BS, OSF HealthCare

This venture is an expansion of the Pulmonary Acoustic Sensor Telemetry Array (PASTA) project which is focused on developing a device for use with an algorithm to remotely monitor lung sounds in pediatric patients. The primary deliverable of this phase is a physical device that is easily replicable and records eight channels of audio simultaneously without losing quality due to compression with minimal quality loss due to compression.

Characterization of Changes in Biomechanical Properties and Cell Aggression in Ovarian Cancer Stem Cells Following Exposure to Chemotherapy

Lead researchers
Kalyani Nair, PhD, Bradley University
Craig Cady PhD, Bradley University
Daniel Chan, MD, PhD, OSF HealthCare

The objective of this concept is to determine whether treatment with a chemotherapeutic agent will induce identifiable changes in the biomechanical properties of cancer stem cells which can be correlated with an increase in cancer stem cell aggression. Identifying biomechanical properties linked to an increase in aggression may suggest alternative approaches to suppressing cancer stem cell activation and reducing the recurrence of cancer.

Humanizing Breast Cancer Prevention: A Community-Based Approach to Increase Health Literacy and Address Breast Cancer Health Disparities among Local Underserved Women

Lead researchers
Heather Ford, MFA, Bradley University
Scott Barrows MA, FAMI, OSF HealthCare
Tianjiao (Grace) Wang, PhD, Bradley University|
Rachelle Pavelko PhD, Bradley University
Mary Stapel, MD, OSF HealthCare

This project aims to address health disparities among underserved groups by developing a community-based solution to effectively increase breast cancer health literacy and raise awareness of breast cancer prevention among local ethnic minority women.