UW Health University Hospital (UW Health, University of Wisconsin Hospital and Clinics or UWHC) is a 515-bed academic regional referral center with 127 outpatient clinics, located on the western edge of the University of Wisconsin–Madison's campus in Madison, Wisconsin. It is an American College of Surgeons designated Level I adult and pediatric trauma center, one of only two in Wisconsin. UW Health University Hospital has seven intensive care units (trauma and life support (TLC), pediatric, neonatal, cardiac, cardiothoracic, burn, neurosurgery). UW Health University Hospital was ranked by U.S. News & World Report as the 16th best hospital in the United States and the #1 hospital in Wisconsin in the publication's 2021-2022 Best Hospitals Honor Roll, earning national rankings in 10 adult and 6 pediatric specialties. Additionally, UW Health University Hospital was ranked as the 22nd best hospital in the United States and #84th Best Hospitals in the world by Newsweek in 2022. UW Health describes itself as "the integrated health system of the University of Wisconsin–Madison." It is the primary teaching affiliate of the University of Wisconsin School of Medicine and Public Health (whose main building, the Health Sciences Learning Center, is connected to UW Health University Hospital). It is also the primary teaching affiliate of the University of Wisconsin–Madison's School of Nursing and School of Pharmacy, and is a teaching affiliate of Edgewood College's Henry Predolin School of Nursing.UW Health University Hospital is home to the University of Wisconsin Carbone Cancer Center, one of 40 National Cancer Institute-designated Comprehensive Cancer Centers. UW Health also operates the American Family Children's Hospital, a 110-bed pediatric hospital located adjacent to University Hospital, as well as UW Health at the American Center, a 59-bed hospital and emergency room located on the Northeast Side of Madison. Additionally, UW Health operates a network of outpatient clinics at over 80 sites throughout southern and central Wisconsin and northern Illinois, and has partnerships with UnityPoint Meriter Hospital in Madison, Beloit Hospital in Beloit, Wisconsin, and Swedish American Hospital in Rockford, Illinois. UW Health also has an affiliated insurance company, Quartz Health Solutions, Inc., operated in partnership with UnityPoint Health and Gundersen Health System. UW Health serves over 800,000 patients per year, and employs over 1,900 physicians and 21,00 staff across seven hospitals, making it the second-largest employer in Madison (after UW–Madison) and in Wisconsin. UW Health University Hospital is home to a helipad that serves UW Med Flight, the hospital's air ambulance and ground ambulance service.S.
BACKGROUND:Ambient artificial intelligence (AI) offers the potential to reduce documentation burden and improve efficiency through clinical note generation. Widespread adoption, however, remains limited due to challenges in electronic health record (EHR) integration, coding compliance, and real-world evaluation. This study introduces a framework and protocols to design, monitor, and deploy ambient AI within routine care. METHODS:We launched an implementation phase to build technical workflows, establish governance, and inform a pragmatic randomized trial. A bidirectional governance model linked operations and research through multidisciplinary workgroups that incorporated the Systems Engineering Initiative for Patient Safety (SEIPS) framework. Integration into the EHR used Fast Healthcare Interoperability Resources (FHIR), and a real-time dashboard tracked utilization and documentation accuracy. To monitor drift, a difference-in-differences analysis was applied to three process metrics: time in notes, work outside work, and utilization. Audits of International Statistical Classification of Diseases and Related Health Problems, Tenth Revision (ICD-10) compliance were performed using an internally developed large language model (LLM), the validity of which was assessed through correlation with certified professional coders. RESULTS:Ambient AI utilization, measured as the proportion of eligible clinical notes completed using the system, had a weighted median of 65.4% (interquartile range, 50.6 to 84.0%). Iterative improvement cycles targeted task-specific adoption. A brief workflow issue related to a note template change initially reduced ICD-10 documentation accuracy from 79% (95% confidence interval [CI], 72 to 86%) to 35% (95% CI, 28 to 42%); accuracy returned to baseline after note template redesign and user training. The internally developed LLM coder achieved a strong correlation with professional coders (Pearson's r=0.97). The trial enrolled 66 providers across eight specialties, powered at 90% for the primary outcome of provider well-being. CONCLUSIONS:We provide a publicly available framework and protocols to help safely implement ambient AI in health care. Innovations include an embedded pragmatic trial design, human factors engineering, compliance-driven feedback loops, and real-time monitoring to support deployment, ensuring fidelity before initiation of the clinical trial. (Funded by the University of Wisconsin Hospital and Clinics and the National Institutes of Health Clinical and Translational Science Award; NIH/ NCATS UL1TR002737; ClinicalTrials.gov number, NCT06517082.).
To determine the efficacy of high-frequency jet ventilation (HFJV) to reduce the effects of respiratory motion on the resultant treatment zone during hepatic histotripsy in an in vivo porcine model. Non-tumor bearing swine (n = 6, 50.1 kg) underwent hepatic histotripsy with both HFJV and conventional ventilation (CV) in separate locations. Treatments were followed by contrast-enhanced magnetic resonance imaging (MRI) and necropsy. Treatment zone size (with emphasis on the cranial-caudal (CC) dimension), volume, and a survey for complications were conducted by MRI and at necropsy. Histopathology was performed to confirm complete cell kill in the treatment zone. Treatment precision was assessed by the width of the transition zone (TZ, zone of partial treatment) with a narrower TZ denoting increased precision. Animals tolerated treatments with no adverse events. Treatment zones created during HFJV were less elongated than during CV (CC dimension during HFJV = 27.8 mm vs. CV = 32.3 mm, p = 0.04). Mean TZ width (treatment precision) was narrower in the HFJV group (HFJV = 4.1 mm, CV = 6.9 mm, p < 0.001), particularly at the cranial margin (HFJV = 4.0 mm, CV = 8.2, p = 0.018). Off-target treatments occurred in the chest wall (n = 2) and spleen (n = 1). High-frequency jet ventilation reduces the craniocaudal elongation of histotripsy treatment zones caused by respiratory motion and improves the precision of histotripsy compared to conventional ventilation in this animal model.
Background: Cardiac magnetic resonance (CMR) is a valuable tool in the assessment of valvular disease. However, its utilization in tricuspid regurgitation (TR) evaluation has been limited. Objectives: The authors sought to compare TR grading with 4D-CMR and transthoracic echocardiography (TTE). Methods: We prospectively recruited patients with ≥ moderate TR on TTE to undergo multiparametric CMR with integrated cardiac function and 4D flow assessments using a 1.5-T scanner (Siemens Somatom Aera). Patients with other severe valvulopathy, end-stage renal disease, or pacemakers were excluded. TR was graded severe on CMR when TR volume ≥45 mL and/or TR fraction ≥50%. The weighted kappa test was used to assess the agreement in overall TR grading on TTE and CMR. Results: Fifty-two patients were enrolled (mean age 78.5 ± 7.6 years, 53.8% men). The median interval between CMR and TTE was 2 days (Q1-Q3: 1-37 days). The agreement between TTE and CMR-derived TR volume was fair (kappa = 0.28, 95% CI: 0.13-0.45), with only 10 of 31 patients (32%) with ≥ severe TR on TTE meeting severe TR volume criterion on CMR (TR volume ≥45 mL). There was no agreement between TTE and CMR-derived TR fraction (kappa = 0.04, 95% CI: 0.13-0.46), with only 3 of 31 patients (13%) with ≥ severe TR on TTE meeting severe TR criterion on CMR (TR fraction ≥50%). Conclusions: Grading of TR was frequently discordant between TTE and 4D magnetic resonance imaging. Further studies are needed to elucidate the clinical impact of concordant/discordant TR grading on multimodality imaging.
