Coronary Artery Bypass Grafting (CABG) is the most common form of open-heart surgery in the United States and is performed hundreds of thousands of times annually. This surgery can be performed via on-pump, which utilizes a machine to keep the heart beating, or off-pump, where the patient’s heart beats like normal. One of the main complications associated with CABG is acute kidney injury (AKI) which has a high mortality rate, making our research goals to identify the important risk factors behind why a patient would experience acute kidney injury, and to compare the on-pump and off-pump surgical techniques. We used datasets from Mayo Clinic comprised of approximately 2000 patients and several hundred features. We analyzed this dataset using several statistical models, including Random Forest, XGBoost, and Propensity Analysis, with Inverse Probability of Treatment Weighting (IPTW) as our propensity analysis technique. From this analysis, we gathered a list of key features which can predict if a patient will experience AKI when performed with the on-pump method. We also found that there was no statistically significant difference in success rates of the on-pump and off-pump techniques, however the high imbalance in the dataset requires further investigation. Mayo Choice Award: Our project is intended to help patient outcomes by providing physicians with key predictors of whether a patient will experience AKI or not during surgery. The physician will then be able to make a better-informed decision about whether the surgery should be performed given the patient’s characteristics and associated risk factors.
This study proposes an AI driven pipeline that combines, pancreas segmentation outcome for Pancreatic Ductal Adenocarcinoma (PDAC) diagnosis with a large language model (LLM) agent to enhance diagnostic and clinical analysis. Building upon already established deep learning approaches in medical imaging, our project aims to extend traditional UNet segmentation methods by integrating the capabilities of an LLM agent to provide detailed diagnostic information for medical practitioners. Using the Pancreas Decathlon dataset, 3D CT scans are processed and trained over multiple different iterations utilizing attention mechanisms, sparse categorical cross entropy and Tversky loss. The predicted segmentation labels are used by the LLM to infer diagnostic details such as the stage of the disease progression and integrate results with the electronic health records for longitudinal study. Ultimately, this integrated framework aims to assist medical practitioners in diagnosing PDAC more effectively while offering additional supplemental information.
Artificial Intelligence (AI) agents are transforming healthcare by automating tasks, enhancing diagnostic precision, and enabling personalized care. Our project aims to develop an AI-based system to automate the detection of IVC filters and complications, such as extravascular extension, in CT scans. IVC filters are crucial for patients with venous blood clots but are meant to be temporary, and delays in their removal can cause harm. Interventional radiology (IR) practices often rely on manual tracking methods, which are inadequate when patients transfer care. Many patients forget their filter’s presence, leaving new providers unaware. Building on previous research with Mayo Clinic NWWI, we aim to enhance an existing deep learning algorithm for IVC flagging and extend it to detect extravascular extension, flagging patients for closer follow-up. The system will also integrate large language models (LLMs) to process electronic health records (EHRs) and be modular for future expansion. Our goal is to create a reliable AI algorithm for detecting IVC filters and implement it in hospital settings.
In patients with atrial fibrillation, many stroke-causing clots originate in the left atrial appendage. The WATCHMAN Procedure takes a minimally invasive approach by threading a catheter through the left femoral vein and deploying the WATCHMAN device into the left atrial appendage to decrease risk of atrial fibrillation-related strokes. Currently, no tailored surgical models exist for this procedure. This means surgeons who are learning the procedure must perform on patients instead of practice models. This project aims to fill that gap and create an interactive leg and torso model for surgical practice of the WATCHMAN device insertion procedure. Using software within the Materialise Suite, student researchers can convert 2D DICOM files into 3D stereolithography files (3D). These 3D files can be read by the 3D printer software, producing a physical model of the original 2D images. The patient’s leg is printed in a flexible material in the same manner utilizing SolidWorks. Models of customizable patient heart and femoral vein anatomy will be printed in a flexible material for surgical practice. A Raspberry Pi computer and 4 small cameras mimic the fluoroscopy used during surgery, allowing surgeons to practice the surgery with views of the heart that they would use in an actual procedure. Surgical outcomes utilizing the educational model will be compared with previous outcomes for surgeons of various education and experience levels. This project will reveal if customizable practice models are significantly beneficial to surgical practice by observing patient outcomes.
Development of a system that can deploy a stent graft to peripheral artery with a collateral vessel without blocking the collateral vessel has been undertaken to assist in treating different arterial conditions like atherosclerosis. Currently no commercially available system exists that can deploy a stent graft without inhibiting flow to the collateral vessel; surgeons must create a fenestration in the main graft through which to deploy a smaller device. The fabrication of this system involved modifying and combining prefabricated catheters to make a complete system that can deploy the stent with good turnability. The system has a port to both inject dye and insert a wire to probe for correct placement of the device fenestration. The research effort has produced prototypes of a multi-lumen intravascular catheter deployment system for stent graft placement where a stent graft can be placed via the system and proper fenestration alignment to the collateral vessel can be confirmed. This project could improve patient outcomes by providing a cost effective and safe option for inserting stents into major arteries that have a collateral vessel which is currently treated by surgeons using makeshift solutions with existing stents and ablation tools.
Caviar refers to processed salted roe obtained from large fish, and it often requires the sacrifice of a pregnant female. With the increasing global human population, the demand for caviar is rapidly growing, threatening wildlife fish populations everywhere. While many improved versions of caviar analogs have been created, they are unable to mimic natural caviar color, texture, structure, popping (while chewing), and taste. The goal of this project is to develop a scalable method for developing caviar analogs using engineering techniques. For this study, we investigated the use of sodium alginate and calcium chloride (CaCl₂) in the production of engineered caviar analogs that replicate the texture, appearance, and sensory characteristics of natural caviar. Alginate solutions of different concentrations (1-5%) and needles of different gauges were calibrated to achieve structural integrity and mimicry of caviar analog size. Furthermore, CaCl₂ was frozen in liquid nitrogen before soaking in a bath of alginate to form caviar analogs with an outer crusty shell and a softer center, to re-create the popping-effect. Future work will include incorporating our findings within a microfluidic device for a scalable way of producing engineered caviar analogs, furthering the broader pursuit of sustainable food design.
Background: Nursing and packaging professionals play a central role in patient safety. Little is known about how undergraduate students learn about the respective disciplines. Objective: The project aims to promote cross-industry education between packaging and nursing students to contribute to patient safety and improve medical device usability. Nursing student researchers created educational videos for packaging students to be included in a medical packaging course. The videos focused on 1) Nursing competencies, ethics, and principles related to medical packaging in the acute care setting; and 2) Demonstration of nursing sterile and clean procedures. Methods: The Framework for Action on Interprofessional Education and Collaborative Practice, guided the project (World Health Organization, 2010). The videos will be presented in a medical packaging course. Voluntary and anonymous pre and post survey design will be used to determine if changes in packaging student knowledge and confidence occurred. The instrument includes 9 Likert scale questions and one additional open-ended question on the post-test. Likert scale questions will be analyzed with paired samples t-test. Qualitative analysis will be used for the open-ended question. Results: Results will be analyzed in spring 2025. Conclusions: Preliminary work has been promising. It is anticipated that results will show an increase in knowledge and confidence. References: World Health Organization (2010). Framework for action on interprofessional education & collaborative practice.
The research question guiding this review is, in adults with heart failure, how does the use of SGLT-2 inhibitors (Canagliflozin, Dapagliflozin, Empagliflozin, Ertugliflozin) impact nursing care, disease management, and patient education? Heart failure (HF) is a complex disease, with treatments evolving continuously to improve patient outcomes. One such treatment approved in 2022 is SGLT-2 inhibitors, originally used for type 2 diabetes; these drugs have been found to reduce the risk of hospitalization and death of patients with HF. With changes in practice, nurses and healthcare teams need to be updated on information regarding the provision of effective and safe patient care. An integrative literature review was conducted through the EBSCO databases and PubMed using identified key terms. Inclusion criteria were human population, English language, and publication within the last 5 years ensuring inclusion of relevant information. This search strategy identified 136 results with 47 duplicates, resulting in the screening of 89 titles/abstracts. The review is ongoing, and characteristics of included publications will be extracted. Results will provide guidance to nurses on education. We expect topics related to additional monitoring for kidney disease and management in the context of multiple chronic conditions.
Background: Advance care planning (ACP) is critically important to providing consistent patient care. Registered nurses (RN) and Nurse Practitioners (NP) are relied upon to lead ACP discussions with patients; however, they often struggle due to lack of confidence in their abilities to have these discussions, lack of time, and concerns that ACP is outside their scope of practice. Incorporating ACP training into school curriculum would bolster preparedness in leading ACP discussions. Methods: A literature review examined 16 articles that addressed the roles, confidence levels, and training needs of NSs, RNs, NPs in ACP. Key words searched included: ACPs, ACP training programs. The databases CINAHL, MEDLINE, UpToDate, Web of Science, and PubMed were searched. Results: Sixteen articles were identified as eligible for the subject matter. The core theme of improving ACP education was highlighted throughout these articles. Conclusion: Current attitudes of NSs, RNs, and NPs reflect feelings of uncertainty about their role within ACP, how to initiate conversations, and improving confidence in leading these conversations. It was found that ACP training programs have been effective in increasing the number of ACP conversations as they help train NSs and NPs to facilitate these conversations. Keywords: Advance care planning; ACP training; RNs; NPs;
This study aims to investigate the vaping habits and effectiveness of practicing mindfulness techniques and weekly positive framed text messages on vaping behaviors of UW-Eau Claire students. Various studies completed in this realm of mindfulness, stress, and vaping have discovered a correlation between stress and vaping. Researchers utilized direct advertising (referrals, campus resources, recruitment table, and email) to recruit subjects for this study. Participants received an incentive upon completion of the study. 4 participants who currently vape were asked to describe their habits and stress level with a pre-test questionnaire. Next, participants were assigned to an experimental or control group. For privacy, the primary investigator had an identification key. During a 4-week period, the experimental group will be provided vaping pamphlets, mindfulness techniques (4-square breathing, coloring books, meditation, journaling, etc.), and weekly positive text message, while the control group will continue with their normal behaviors. Six weeks after the initial pre-test, participants received questionnaires about their vaping habits and stress levels. From the data collection, we determined mindfulness techniques reduced stress levels but minimal reduction in participants' vaping habits. However, upon completion of the six-week questionnaire, participants reported a 31% decrease in spending on vape products after this study.
Allergen immunotherapy or “allergy shots” are delivered as fast-acting intravenous (IV) injections given to patients suffering from chronic allergies. However, in rural settings, patients must travel long distances for a single injection, significantly adding to patient costs, and costs to an already over-burdened health-care system. We hypothesized that minimally invasive, painless, self-administered 3D (three-dimensional) printed microneedles could be a better alternative in these scenarios and could be provided in conjunction with tele-medicine. For this study, 3D printed microneedles were printed using Formlabs stereolithography (SLA) printers and clear V4 material. Different parameters were calibrated including layer thickness, size, shape, material, and needle orientation, to enable dermal puncture with minimal breakage. Our results show that a Pyramid Needle Model (needle array: 1(L)x1(W)x0.5(H) cm; needle dimensions: 200(L)x200(W)x800(H) µm; 500µm (spacing); 1µm (tip diameter); 45° angle; 0.025mm layer-thickness) was the best microneedle model produced through our experiments. Microscopy and porcine skin puncture testing confirmed the functionality of these needles in the laboratory. Taken together, our results showcase the feasibility of fabrication of transdermal microneedles through 3D printing, providing a fast and effective solution for self-administered painless drug delivery. Future work will focus on improving microneedle design to enable allergy-drug loading and delivery.
Diabetes Mellitus is a chronic condition affecting millions worldwide, associated with factors like age, body mass index, blood pressure, and social determinants such as income level, education, and healthcare access. This study uses a mix of these factors derived from a public health survey to train machine learners for diabetes prediction. The data includes 29 features and 223,022 records. A key goal here is to investigate levels of feature importance in risk factors to assess the impact of social determinants on diabetes. We employ six machine learning models, including XGBoost, AdaBoost, LightGBM, Random Forest, Naive Bayes, and Logistic Regression, and utilize SHapley Additive exPlanations to measure feature importance. Predictive performance metrics include accuracy, precision, recall, and the area under the receiver operating characteristic curve. Empirical results show that five out of six models achieved 85% accuracy, with blood pressure, body mass index, cholesterol, weekly alcohol consumption, and time since the last checkup being the most significant predictive attributes. These initial findings highlight the potential of machine learners to predict diabetes and contribute to early monitoring of the identified risk factors. In related future research, a planned work will investigate whether identifying and incorporating other factors would improve overall predictive performance.
Background: Patient education is linked to better health outcomes and is a core component of Family Medicine, where providers see a variety of patient health problems (Simonsmeier, 2022). Developing and maintaining an evidence-based and inclusive patient education library is a resource-intensive. Content libraries at academic medical centers often are not inclusive of Family Medicine. Moreover, users cannot tailor content to individual patient needs, and accessing content is cumbersome. Objective: We aimed to close this education gap by developing an AI-assisted tool where clinicians can easily generate trustworthy education content for diverse patient needs. Methods: Our tool combines a web-scraper that pulls data from mayoclinic.org, feeds it into a standalone user interface (UI) enabled by a large language model (LLM), which allows users to generate printable education based on inputs, such as disease name, content headers, text size, and patient reading level. We validated the LLM’s accuracy and completeness using volunteer medical students. We plan to evaluate the tool’s usability, time savings, and user satisfaction with a pilot study comparing the traditional workflow to our tool. Results & Future Work: Two times during the development process, output forms were evaluated by multiple different clinicians to confirm medical accuracy and readability. Post-pilot, we will investigate translating the tool into clinical practice. Mayo Choice Award Family medicine providers handle an incredibly large volume of diseases and diagnoses, so having easy-to-access, adjustable educational material is incredibly important as it decreases clerical burden for clinicians and increases patient health literacy (Hart, 2015). Currently, even if providers are able to locate the educational forms without interrupting their workflow to visit the public website, they cannot adjust educational material reading level or text sizes to tailor to individual patient needs without extra steps, which inhibits patients from fully understanding their diagnosis and relevant follow-up, including vital self-care instructions that lead to better patient outcomes (Simonsmeier, 2022). Overall, this tool provides the educational materials for over 400 diagnoses commonly seen in family medicine all in one place, while also allowing providers to tailor the reading level and text size to each patient, which will lead to overall better health outcomes. Works Cited Hart, S., 2015. Patient education accessibility. Medical Writing 24, 190– 194. Simonsmeier BA, Flaig M, Simacek T, Schneider M. What sixty years of research says about the effectiveness of patient education on health: a second order meta-analysis. Health Psychol Rev. 2022 Sep;16(3):450-474. doi: 10.1080/17437199.2021.1967184. Epub 2021 Aug 24. PMID: 34384337.
This project aims to standardize follow-up recommendations for colonoscopies by leveraging Generative AI and Natural Language Processing (NLP) to analyze colonoscopy and pathology reports. Current follow-up guidelines vary based on multiple factors, including polyp type, size, number, and patient history, often leading to inconsistencies in clinical recommendations. The AI system processes unstructured text from medical reports, extracting key diagnostic details and cross-referencing them with established guidelines to generate personalized return date recommendations. By automating this process, the project enhances accuracy, reduces variability in clinical decision-making, and improves workflow efficiency for healthcare providers. The standardized recommendations ensure that patients receive appropriate follow-up care, minimizing the risk of delayed or unnecessary procedures. This initiative demonstrates the potential of AI in streamlining medical decision-making, ultimately contributing to better patient outcomes and more consistent adherence to evidence-based guidelines in gastroenterology.
Within college organizations, very few encompass certifications that promote environmental health, students’ physical well-being, and the community. With the Eau Claire community being 75k+ members, a center that has good quality access to health care is vital to seniors, children and young adults. The UWEC Sonnentag Center has Gold LEED certification, which states the building has outstanding sustainability energy efficiency and environmental design. However, this is not enough to tackle the environmental issues in Eau Claire. Within our research to achieve the WELL certification, we collected data on the clarity of the water (turbidity), total and free chlorine, the pH levels of the water; levels of volatile inorganic compounds (carbon dioxide, carbon monoxide, sulfur dioxide, nitrogen dioxide), ozone levels, and humidity in the air. Interestingly, what our team found was that the turbidity, as well as, free and total chlorine levels were low, and the pH was slightly higher but within range. In addition, the air quality was above and beyond good standards for the WELL Certification, due to the ventilation systems in and around the building. However, nightly cleaning procedures caused a rise in VOC’s and low humidity. Overall, the measures of WELL Certification build upon the LEED certification principles, allowing for the best achievable environmental impact.
Ten kilometers outside Riga, a city located on the northern coast of Latvia, stands a public park that may seem mundane, but beneath the surface lies a dark past. Today the site is known as Mazjumpramuizha Park, but it was once the location of the Jungfernhof concentration camp during WWII. while there is one interpretive sign that acknowledges this history, it does not tell the full story and even locals remain unaware of what happened here. This silenced history is the focus of my research project, which aims to locate the prisoner barracks that once stood on the site and have been described by survivor testimonies. To accomplish this, I worked alongside a team commissioned by The Jews of Latvia Museum, utilizing ground penetrating radar— a non-invasive scanning technology that transmits electromagnetic pulses into the subsurface—to reveal what lies beneath. In conjunction with a Topcon-RL-H4C self-leveling laser to determine ground elevation, our team unearthed evidence of the camp’s barracks, including barbwire and the building’s rock foundation. For survivors, our findings provide evidence to help bring closure and launch memorial efforts via the creation of a steel monument inscribed with the victims’ names known as the Locker of Memory.
Environmental stability is vital to achieving overall health within communities. Where families reside is an important factor in determining whether they can prosper in other aspects of health, such as education, nutrition, and disease prevention. To fulfill communities' needs for a stable, healthy atmosphere, environmental justice must be addressed to provide these essential health requirements. The purpose of this project is to raise awareness of current environmental health challenges faced by community members in Beloit, Wisconsin. University of Wisconsin–Eau Claire students will analyze particulate matter 2.5 reported through PurpleAir Monitors distributed throughout Beloit to help facilitate the awareness needed for positive change. The collaborative process involves meeting with Beloit air quality advocates from the Stateline Clean Air Coalition and the Midwest Environmental Health Advocates group, as well as working alongside past researchers who analyzed similar data. Using PurpleAir Monitors will give researchers access to PM 2.5 trends from 2023 to the present, helping to establish a timeline of possible effects correlated with particulate matter. By analyzing PM 2.5, we can identify key trends that future advocacy groups can use to drive positive change for families in Beloit, Wisconsin.
Water quality plays a crucial role in achieving WELL certification, ensuring a safe and healthy indoor environment. This study assessed the water quality at the newly constructed Sonnentag Center at the University of Wisconsin–Eau Claire, focusing on key parameters such as turbidity, chlorine levels, and microbial contamination. Using the Hanna Instruments HI93414 Turbidity and Chlorine Meter, we observed an unexpected absence of chlorine (0 µg/mL) in all tested samples. A control test with bleached water confirmed the instrument’s accuracy, suggesting a genuine lack of chlorine in the water supply. Additionally, coliform and E. coli tests verified the absence of bacterial contamination, indicating that the water met microbial safety standards. The findings highlight both the strengths and challenges of water quality monitoring in WELL certification. While microbial safety was confirmed, the absence of chlorine raises concerns about potential regulatory non-compliance and long-term water safety. This study underscores the importance of continuous monitoring and evaluating disinfection protocols to maintain WELL standards. Future work will focus on investigating water treatment processes and identifying solutions to ensure consistent compliance with health and safety regulations.
Our project aims to achieve WELL certification, specifically air quality standards at the new Sonnentag Center. My project is important because it emphasizes the importance of human health, even in new buildings. Thousands of people are present in this building at a time, we need to ensure the air quality levels are safe for visitors. Our project offers new knowledge for people who may not know about WELL certification or the air quality parameters involved. We are motivated to investigate the reasoning behind the air quality levels so we can come up with appropriate intervention strategies where needed. Our poster consists of data from the spring semester, focusing on VOCs and Humidity levels at the Sonnentag. The project is still ongoing, so this data has brought new interpretations, which will be discussed to those viewing the poster. We are currently investigating low humidity levels, while not a part of WELL, it is still significant when it comes to human health. Data collection is still ongoing, so this project will be well rounded with fall and spring semester data and interpretation. Our audience shall be informed on what is being done in our local facility, and find comfort in knowing that we care about population health.
Rural residents have lower levels of access to health care and health services, and health insurance coverage rates are lower as well; as a result, the health of rural residents is poorer compared to their urban counterparts. The lack of healthcare providers, longer distances to healthcare facilities, and lower economic status for rural populations place extra burdens on both providers and patients to meet and receive needed care. The COVID-19 pandemic not only highlighted these disparities but also spurred new forms of care delivery. Telehealth, through synchronous and asynchronous remote appointments, provided healthcare providers with opportunities to connect with patients outside of physical office visits. The rise of Telehealth not only increased options for patients but also protected all parties from the spread of the COVID-19 (Hirko et al. 2020). Yet, throughout much of the United States rural broadband options are limited or nonexistent.This project is an extension of a previous collaboration with the Mayo Clinic (please see “A Spatial Analysis of Cellular Singal Strength in Western Wisconsin”). It has been determined that a strength of less than -115 dBm will not produce a viewable telehealth appointment. This poster will discuss one of the outcomes of this project (1) kriging analyses and a probability map of cellar strength for Verizon and AT&T near Menomonie, WI. Such analysis will provide Mayo Clinic with a better understanding of where telehealth opportunities are possible in rural areas for patients who lack internet access.
Our research project addresses health care equity in the Eau Claire Metropolitan Area (ECMA) at a precipitous time. In early 2024 the closure of two hospitals and 19 urgent care clinics in the ECMA eroded access to healthcare. Hospital closures in rural and urban regions exacerbate healthcare barriers for people in minoritized communities, increase ambulance transport times, and worsen morbidity and mortality for time-sensitive conditions (Niewijk 2024). To contextualize the impact of these closures we consolidated news stories into a timeline of events from January 2024 to the present. We also reviewed literature within medical sociology and public health to help us understand barriers to health equity in the ECMA. We will conduct interviews with city, health department, and healthcare-related organizational leaders in Summer 2025, and then analyze the data using MAXQDA, a qualitative software program. Our policy brief will summarize changes to healthcare equity since these closures and strategies for building a more equitable healthcare landscape in the ECMA. In Spring 2026 we will convene a university symposium with stakeholders to discuss health equity in our region.
Fall risk is a growing concern for older adults as balance abilities decrease with age which can lead to injuries, impaired functioning, and a decreased quality of life. Increasing range of motion through stretching can improve balance although the type of stretching that is most effective is inconsistent in previous research. The purpose of this study is to evaluate the acute effects of static, dynamic, and proprioceptive neuromuscular facilitation (PNF) stretching protocols on balance in active older adults. Older adults will gain insight into which type of stretching will positively affect balance, while also learning how to perform self- PNF stretching. This process involved an initial recruitment presentation at the Community Fitness Program, email contact to assign identification numbers, informed consent, balance baseline assessment, and stretching sessions. Participants performed static, dynamic, and PNF stretching on three different days that were randomly assigned. After each stretching protocol sway velocity index was measured using the Biodex Balance System to determine balance changes. This project is currently in progress and the results will be finalized in the near future. It is expected dynamic stretching will promote greater improvements in balance compared to static and PNF stretching protocols which would have no effect.
