OSF HealthCare

Previous research has empirically demonstrated that personal resilience and organizational level interventions are important considerations when studying workplace adversity such as burnout and excessive workloads in the context of a pandemic. To explore interest in participating in a wellness initiative program designed specifically for advanced practice registered nurses (APRNs) and physician associates (PAs), with a voluntary option for participation in research. An anonymous, brief, online survey with Likert-response type items and one free-text question was delivered with passive informed consent via email to all APRNs and PAs (N = 312 participants) within one health care system. A positive correlation between likelihood of seeking well-being care and having sufficient time (0.36, p < .01) was found, which indicates that APRNs or PAs who felt they had sufficient time to get counseling were actually more likely to seek counseling services. Results from the path model show that the comfort-level of seeking counseling completely mediates the relationship between fear of negative perceptions of receiving counseling and the likelihood of participating in a wellness program. Well-being strategies are important for organizations to engage in to support their employees; however, confidentiality concerns and competing priorities for time may influence engagement. Interest among APRNs and PAs for participation in research exists if enough information is provided and anonymity can be assured. Organizations should focus on finding innovative ways to integrate wellness into APRN and PA practice that mitigates the belief around the burden of time commitment and seeks ways to provide psychological safety for its employees.

Cryptococcal meningitis is classically associated with immunocompromised hosts but can also occur in individuals without identifiable immune dysfunction. Its nonspecific and often indolent presentation may delay diagnosis, particularly when early neuroimaging suggests alternative etiologies. We report a case of a 49-year-old immunocompetent man who presented with progressive headaches, sensory changes such as transient hearing loss, visual changes, and balance issues. Initial imaging showed a hyperdense area on CT, which was interpreted as a possible cerebrovascular accident, delaying recognition of an infectious process. Cerebrospinal fluid (CSF) evaluation ultimately confirmed cryptococcal meningitis, and the patient improved with targeted antifungal therapy and intracranial pressure (ICP)-directed management. This case highlights diagnostic challenges in immunocompetent hosts and underscores the importance of maintaining suspicion for fungal meningitis even without classic risk factors.

Recent advances in Artificial Intelligence (AI) have started disrupting the healthcare industry, especially medical imaging, and AI devices are increasingly being deployed into clinical practice. Such classifiers have previously demonstrated the ability to discern a range of protected demographic attributes (like race, age, sex) from medical images with unexpectedly high performance, a sensitive task which is difficult even for trained physicians. In this study, we motivate and introduce a general explainable AI (XAI) framework called DREAM (DiscoveRing and Explaining AI Mechanisms) for interpreting how AI models trained on medical images predict protected attributes. Focusing on two modalities, radiology and dermatology, we are successfully able to train high-performing classifiers for predicting race from chest x-rays (ROC-AUC score of ~0.96) and sex from dermoscopic lesions (ROC-AUC score of ~0.78). We highlight how incorrect use of these demographic shortcuts can have a detrimental effect on the performance of a clinically relevant downstream task like disease diagnosis under a domain shift. Further, we employ various XAI techniques to identify specific signals which can be leveraged to predict sex. Finally, we propose a technique, which we call ‘removal via balancing’, to quantify how much a signal contributes to the classification performance. Using this technique and the signals identified, we are able to explain ~15% of the total performance for radiology and ~42% of the total performance for dermatology. We envision DREAM to be broadly applicable to other modalities and demographic attributes. This analysis not only underscores the importance of cautious AI application in healthcare but also opens avenues for improving the transparency and reliability of AI-driven diagnostic tools.

Diagnostic uncertainty is a reality of clinical care, particularly in emergency medicine. The ability to communicate this uncertainty to patients and families, however, remains underdeveloped in medical education curricula. Traditional simulation training is regarded as the gold standard for teaching difficult conversations, but resource constraints can limit access, especially for larger cohorts of learners. Faced with this challenge, we turned to a tool our team developed: the Uncertainty Communication mobile application (app). With over 200 medical students entering their fourth year of training, we used this app to deliver real-time, large-scale, skill-based learning, without simulation rooms, standardized patients, or small-group role-play. Students practiced communicating diagnostic uncertainty to patients, received immediate feedback, and reflected on patient-centered communication strategies. Their responses were generally positive. While not a formal study or intended to replace the role of traditional simulation training, our experience reaffirms how the intentional integration of mobile tools into medical training can introduce complex skills, like communicating diagnostic uncertainty, into scalable and practical learning solutions. As we train the next generation of physicians, such tools may offer educators some degree of flexibility when training large cohorts of students.

BackgroundTeaching the management of pediatric sedation-related airway concerns is challenging due to the time-sensitive interventions required and their infrequent occurrence. Recognizing this educational gap in the sedation experience, virtual reality (VR) was utilized to prepare learners and provide an immersive training experience in a controlled environment.MethodsWe describe simulation-based training using a VR environment, Enduvo Inc., an innovative software for medical trainees. This two-hour course creates a problem-based learning experience, allowing learners to apply their knowledge and develop a framework for managing these stressful and less commonly encountered situations.ResultsFrom 2019 to 2022, 35 learners participated in the sedation course. After completing the VR modules, all learners completed a blinded survey on their experience and preparation for sedation-related situations. Based on our initial data, self-reported confidence and preparedness in handling complex situations during pediatric sedation rated high, with an overall response rate of 100%. Learners reported improved confidence and self-preparedness after completing the modules.ConclusionVR for pediatric sedation training creates a distinctive learning environment due to its immersive nature and has been well-received. VR could be an effective method for educating residents and physicians in this specialized field.

The concept of inclusion within diversity, equity, and inclusion has broad meanings and implications and has not been explored in nursing through a World Café. To describe the process and experiences of 9 nurse scientists who hosted a World Café focused on inclusion, to share participants' insights, and to offer considerations to advance inclusion in nursing. We hosted and encouraged active participation in a World Café that focused on 7 inclusion topics in nursing during the 2024 Midwestern Nursing Research Society Annual Research Conference. During the 90-min World Café, 40 participants ("members") engaged in iterative rounds of small group dialogue, moving from table to table every 10 min and randomly changing groups. Table hosts welcomed new members, provided background information, and asked probing questions about topics related to inclusion. Members shared insights verbally and through creative expression using colored markers/pencils or craft supplies and creating images on paper tablecloths. Table hosts used notes, photographs of words and images from the paper tablecloths, and collective post-Café reflections to synthesize insights regarding inclusion. Across all topics, members stated that inclusion requires connecting as human beings, creating welcoming spaces, being open to others, and actively listening. Table hosts described the World Café process as engaging, invoking, and inspiring. Hosts found the World Café process itself to be inclusive, inviting diverse perspectives, and gleaning insights about inclusion in nursing. Considerations generated from this World Café offer tangible behaviors to promote inclusion across various nursing topics, roles, and settings.

This paper presents the pulmonary acoustic sensor telemetry array, a novel hardware prototype developed for remote pulmonary monitoring, diagnosis, and prognostication of pulmonary sounds in clinical settings. The proposed hardware prototype employs an array of acoustic sensors strategically positioned at standard auscultation sites on the patient’s chest and back, enabling real-time acquisition and analysis of pulmonary sounds with an edge computing device. This task is beyond the capabilities of existing commercially available digital stethoscopes. The hardware prototype presented herein addresses critical challenges in pulmonary care by providing continuous, high-fidelity, multi-site acoustic data collection. This functionality is pivotal for enhancing diagnostic accuracy and enabling early detection of respiratory abnormalities, potentially reducing treatment delays in acute respiratory conditions. The pulmonary acoustic sensor telemetry array (PASTA) integrates a compact design, multi-channel monitoring, and real-time telemetry, distinguishing itself from existing commercial medical devices. Performance evaluations against established digital stethoscopes, conducted using a high-fidelity medical simulation training manikin, demonstrate adequate sensitivity and signal quality. The potential applications of the pulmonary acoustic sensor telemetry array extend beyond inpatient care, making it suitable for remote monitoring in outpatient environments such as hospital-at-home and outpatient hospice programs. By bridging a significant gap in current medical device offerings, the pulmonary acoustic sensor telemetry array sets a new standard in pulmonary auscultation and serves as a foundational platform for future advancements in Internet-of-Things enabled healthcare solutions.