Citations

BACKGROUND: Surgeons and ostomy nurses receive a high volume of stoma photos from patients. OBJECTIVE: This study aimed to develop and validate an automated and scalable artificial intelligence pipeline for identification and triage of patient-submitted intestinal ostomy photos. DESIGN: Retrospective derivation and validation study with stakeholder engagement to guide model design. Clinical teams reviewed photos in duplicate and categorized them into: (a) obstructed view, (b) healthy stoma, (c) suitable for conservative management, or (d) requiring in-person review. Pre-trained neural networks including MobileNetV4, ResNet50, ViT and CLIP-ViT were fine-tuned with 5-fold cross-validation. SETTINGS: Nine Mayo Clinic hospitals (2019–2022). PATIENTS: Adult patients (≥18 years) undergoing surgery who submitted images within 30 days after surgery. MAIN OUTCOME MEASURES: Model performance was evaluated with area under the receiver operator curve, precision, recall, and F1-scores. RESULTS: In this study, 538 photos of abdominal ostomies were sent in by 191 patients (median age 52 years, IQR 40–63; 60.4% female). Expert consensus triaged 236 (43.9%) photos as having an obstructed view, 30 (5.6%) as healthy, 177 (32.9%) for conservative management, and 95 (17.7%) for in-person review. All models achieved area under the receiver operator curve >0.97 for identifying stomas. The CLIP-ViT model performed best at triage (macro- area under the receiver operator curve 0.94 ± 0.06; F1 0.77 ± 0.10). End-to-end detection and triage using CLIP-ViT achieved area under the receiver operator curve of 0.99 ± 0.01, precision of 0.87 ± 0.08, recall of 0.93 ± 0.04, and F1 of 0.89 ± 0.07. Attention maps showed that models focused on stomas to determine classification. LIMITATIONS: Low sample size and lack of prospective validation. CONCLUSIONS: A vision language model pipeline accurately detected and triaged patient-submitted ostomy photos. Prospective evaluation is now needed to support integration into multidisciplinary digital workflows. See Video Abstract .

ABSTRACT Pulmonary hypertension (PH) comprises a heterogeneous group of disorders characterized by elevated pressure in the pulmonary arteries. Despite advances in awareness, utilization of non‐invasive screening with echocardiography, increasing number of targeted therapies, and evolving clinical guidelines emphasizing referral to PH specialty centers, barriers to timely diagnosis and treatment persist. Key challenges span patient‐related and system‐level domains that hinder the effective diagnosis, management, and treatment of PH, particularly pulmonary arterial hypertension (PAH). In this article, the obstacles to PH care are examined and actionable recommendations are proposed. By integrating patient‐related and system‐level perspectives, this review provides a framework to bridge persistent gaps in PH care delivery in the United States.

Background Cardiac rehabilitation (CR) leads to increased exercise capacity (VO 2 peak) and risk reduction of major adverse cardiovascular events (MACEs). Women exhibit blunted VO 2 peak improvements following CR. The purpose was to examine sex differences in the clinical predictors of VO 2 peak improvement and odds of MACEs following CR. Methods From 1999 to 2017, all consecutive patients undergoing cardiopulmonary exercise testing before and after CR were included. Sex differences in peak exercise metrics in response to CR were compared. Multiple logistic regression models were fit to assess clinical predictors of VO 2 peak improvement (defined as >0% from pre‐CR) and MACEs following CR for men and women. Results A total of 513 men and 158 women were included. Men had greater increases in VO 2 peak than women following CR ( P =0.001). For men, independent predictors of VO 2 peak improvement following CR included higher CR session attendance (odds ratio [OR], 1.04 [95% CI, 1.02–1.06]), peripheral artery disease (OR, 0.47 [95% CI, 0.25–0.86]), and pre‐CR VO 2 peak (OR, 0.98 [95% CI, 0.97–0.99]) (all, P <0.02). Independent predictors of lower odds of MACEs following CR in men included higher number of CR sessions (OR, 0.97 [95% CI, 0.95–0.99]), pre‐CR VO 2 peak (OR, 0.98 [95% CI, 0.97–0.99]), surgical CR indication (OR, 0.34 [95% CI, 0.18–0.68]), and no history of peripheral artery disease (OR, 2.94 [95% CI, 1.60–5.38]) (all, P <0.02). For women, the selected clinical characteristics were not statistically significant independent predictors of VO 2 peak improvement or odds of MACEs (except for diabetes) following CR. Conclusions These findings suggest that clinical predictors of VO 2 peak improvement and odds of MACEs following CR are sex specific.

Background Hypertensive disorders of pregnancy (HDP) are a leading global cause of maternal and fetal morbidity/mortality. Most estimates of HDP occurrence are reported for composite exposures of HDP or preeclampsia alone, with limited disaggregation by obstetrical subgroup (eg, multi‐fetal deliveries). Consequently, our understanding of HDP prevalence and temporal trends remains limited, and methods for identifying specific diagnoses in administrative data remain underexamined. This population‐based descriptive study assessed how enhanced administrative case‐finding definitions influence prevalence estimates of HDP in pregnancy and postpartum. Methods Included were individuals aged ≥18 years discharged from an Ontario hospital following their first obstetrical delivery between April 1, 2002, and December 31, 2017. We calculated overall and annual prevalence estimates and assessed temporal trends for any HDP and major subtypes by case‐finding definitions, stratified by plurality (singleton versus multi‐fetal deliveries). Results Most subjects had a singleton first delivery (n=781 258; 98%); however, HDP was 2.2 to 2.4 times more prevalent in multi‐fetal deliveries. When pre‐pregnancy hypertension was considered during case‐finding, HDP prevalence increased from 193.6 to 207.6 per 1000 multi‐fetal deliveries and from 79.9 to 92.6 per 1000 singleton deliveries. Gestational hypertension was the most common diagnosis in both populations but was nearly twice as common in those who delivered a multiple gestation (94.4–100.0 versus 49.7–53.4 per 1000 deliveries). Prevalence trends differed by coding strategy and plurality. Conclusions Although informative, data from discharge abstracts alone are insufficient for HDP surveillance, particularly for chronic hypertension in pregnancy. Validation studies should assess the accuracy of our case‐finding definitions against suitable reference standards.

Background The current classification of pulmonary hypertension (PH), based largely on expert opinion, has limitations in prognostication and guiding therapies. We hypothesize that novel PH clusters that predict survival will reveal mechanistic phenotypes associated with biomarkers of vascular health across all PH groups. Methods We first identify novel PH clinical clusters by performing unsupervised clustering analysis on the CC‐PH (Cleveland Clinic PH) registry (N=1529). We develop classification models to predict the new PH clusters and then apply them to the multicenter PVDOMICS (Pulmonary Vascular Diseases Phenomics) cohort (N=853) for validation. We compare transplantation‐free survival across the new PH clusters. We quantify metabolites of the arginine‐nitric oxide pathway and D‐dimer levels and calculate global arginine bioavailability (arginine/[ornithine+citrulline]) to assess endothelial function and activation in the new clusters and link these biomarkers to clinical outcomes. Results Clustering analysis identify 3 clear clusters in CC ‐ PH that are validated in PVDOMICS and outperform conventional classifications in predicting transplantation‐free survival. The phenotype associated with the worst survival is characterized by reduced lung diffusion capacity, decreased arginine bioavailability and nitrate levels, and elevated D‐dimer levels, consistent with loss of pulmonary microcirculation and endothelial dysfunction. Conclusions We identify new informative PH phenotypes associated with mortality and defined by biomarkers of endothelial function and activation. Loss of endothelial health and pronounced pulmonary vascular rarefication contribute more substantially to mortality across the spectrum of PH than right heart function. REGISTRATION: URL: https://www.clinicaltrials.gov ; Unique identifier: NCT02980887.

Background: We had a large-scale measles exposure event affecting 626 patients. Management of exposed patients was urgent, involving quarantine, post-exposure prophylaxis (PEP), and symptom monitoring on a case-by-case basis. Cases were initially tracked and managed using a combination of multiple spreadsheets amongst stakeholders as well as lists within the electronic health record (EHR). Using shared spreadsheets and lists created significant challenges with maintaining and editing multiple copies and updating workbooks simultaneously. Methods: Infection Prevention and Control (IPAC) worked with primary care personnel and EHR developers to create a shared registry that would prioritize communication and follow-up for exposed patients based on age and immunity. Patients are initially added to the shared registry within the EHR by reviewing non-registry reports and tagging patients, identified using exposure timeframes that overlapped with the index measles cases, in a manner that transferred them to the shared registry. From this registry, measles, mumps, and rubella vaccine status can be confirmed, immune status can be identified, and criteria for PEP assigned. High-risk patients are then contacted with recommendations from IPAC and primary care. Communication and follow-up are tracked directly within the shared registry to ensure appropriate patient management. The exposure management registry is further leveraged throughout the measles outbreak timeframe by allowing real-time monitoring of patients that require additional precautions or guidance related to their exposure. Result: The shared registry enhanced documentation accuracy and transparency between stakeholders. It led to availability of real-time status of exposed patients for the duration of the measles outbreak timeframe. Overall, the registry enabled time-sensitive patient communication to all exposed patients and rapid identification of those who needed PEP. Communication could happen rapidly and seamlessly between care teams within the organization, and the necessary information could be shared quickly with public health authorities as required. Conclusion: Large scale exposures are a challenge to manage and ensure appropriate action and communication occurs. Errors can be prevented by having a single shared exposure management registry. A registry enables care teams to quickly identify and prioritize patients for measles follow-up, communication, PEP, and ongoing management across outbreak timeframes. This process reduces both time and operational burdens of exposure follow-up tracking outside of the EHR.

Background: We describe an investigation of a cluster of eight Corynebacterium amycolatum sternal surgical site infections (SSIs) that occurred among cardiac surgery patients from February to October 2025. Although C. amycolatum is a member of the skin microbiota, clinically significant infections caused by this organism may occur in cardiac surgery patients. Methods: The investigation included retrospective reviews of SSIs, clinical cultures and medical records, surgical observations, and operating room (OR) assessment. Line lists of surgical case criteria and infection prevention practices were created to assess common factors among cases (e.g., staffing, instrumentation, equipment, skin preparation and antisepsis, nasal decolonization, antibiotic protocols, and closure). Whole genome sequencing of isolates was performed and analyzed using SNIPPY for single-nucleotide polymorphism (SNP)-based phylogenetic analysis. Results: Phylogenetic analysis indicated isolates from five of eight case patients who had cardiac surgeries occurring over a six-week period from February to April 2025 were genetically related (?7 SNPs across the genome), suggesting a common source of infection. These five isolates were ceftriaxone, meropenem, and penicillin resistant. The other three case patient isolates were unrelated (<3181 to <15,000 SNPs); two were ceftriaxone, meropenem and penicillin resistant (one also doxycycline intermediate resistant), and the third penicillin resistant. Use of sternal tape for closure was identified as a recent practice change. Four of five genetically related cases involved the same surgeons and suture tape for sternal closure (wire for all other cases). Sternal tape was discontinued with three cases occurring afterwards. Seven patients completed chlorhexidine gluconate bathing and nasal decolonization. Hair was removed in the OR with reusable surgical clippers. All received the same skin antiseptic, and antibiotic prophylaxis was appropriate. No trends were identified in instrument or equipment use. Broad infection control measures were implemented, including surgical clipper replacement, OR cleaning and ultraviolet light disinfection, headlamp cleaning, and environmental repairs. Leadership was engaged through frequent meetings and audits. Infection control practices such as minimizing OR traffic, double gloving, glove changes, and strict adherence to hand hygiene and attire were reinforced. Two of eight cases occurred after these recommendations were completed but were not genetically related to the primary cluster. Conclusion: We describe a cluster of invasive C. amycolatum sternotomy SSIs. Only two genetically unrelated cases of C. amycolatum occurred following infection control investigation and interventions, underscoring the effectiveness of a comprehensive, multidisciplinary approach. This organism has rarely been reported as a cause of SSIs and may be an emerging pathogen.

Background: Measles is a highly transmissible virus. A single case can result in significant exposures within a healthcare facility and prompt action is needed to prevent secondary cases. In October 2025, Infection Prevention and Control (IPAC) was notified of a patient being admitted to our facility with recent international travel and symptoms consistent with measles. The patient was unvaccinated and had five healthcare facility visits prior to measles being suspected and subsequently confirmed. Objective: To describe our facility’s effective identification, prioritization, and prophylaxis of individuals exposed to measles. Methods: IPAC leveraged the electronic medical record to identify potentially exposed patients. Patients were quickly assessed for age and immune status, then prioritized and assigned to primary care teams. These teams promptly contacted patients and coordinated PEP administration. Results: Across five encounters, the index patient exposed 539 other patients. Due to delayed notification, our teams had less than four days to administer PEP for those exposed and still within PEP window. PEP administration began within hours of the index case’s positive test and patients received PEP within three days (Table 1). No secondary measles cases occurred within our facility. Conclusion: Timely and coordinated multidisciplinary effort enabled us to rapidly respond to our first measles case and control secondary transmission. Although the index case resulted in a large exposure, patients that were exposed and eligible for PEP were quickly prioritized to prevent secondary transmission.

Background: Advanced planning and adaptable response strategies are essential for preventing measles transmission in healthcare facilities. Objective: To describe a measles management plan and subsequent modifications in response to a cluster of measles cases. Methods: Drawing on previously published work (doi:10.1017/ice.2025.49), the Infection Prevention and Control (IPAC) team initiated a multi-disciplinary team and developed a measles preparedness plan with the following domains: Guidance and education; early detection and testing; isolation and patient movement; contact tracing and exposure management (Table 1). In October 2025, a patient was admitted during their fifth healthcare encounter and was diagnosed with measles. Two family members were later hospitalized with measles. Delayed recognition of the first case prompted enhancements to our preparedness framework (Table 1). Results: The first case resulted in 539 exposed patients. The second resulted in 87 exposures, and the third resulted in no exposure. Despite the extensive exposure, zero secondary measles were reported. Conclusion: Proactive planning enabled rapid response to our first case and controlled secondary transmission. Despite extensive planning, delayed identification of the first case caused significant exposures. As the cluster unfolded, we refined our plan, resulting in zero exposures from the last patient and zero secondary cases, despite over 850 exposures. These efforts may guide other healthcare facilities in improving their measles preparedness and response.

Background: In 2025, 50 measles outbreaks drove 87% of confirmed cases reported in the United States. As a highly infectious virus with an estimated R ranging from 12-18, we sought rapidly scalable and implementable measles preparedness measures for our facilities. Methods: The electronic health record (EHR) has flags that can be placed on patient records to denote the presence of, or concern for, active, transmissible infections. These flags are highly visible in the EHR and represent a good usability heuristic as front line providers are already trained to look for this information. Infection Prevention and Control (IPAC) worked with nursing informatics to develop measles-specific flags for suspected, confirmed and exposed patients in the EHR, expanding flagging functionality in preparation for potential measles cases and exposures. The flagging was tied to registry functionality to allow for tracking of exposed and confirmed cases longitudinally for supporting IPAC investigations in addition to clinical operations. Results: Three different flags were developed in the EHR to address measles. Specific criteria were created for each flag, as shown in Table 1. Table 1: Attached as Image Conclusion: As a highly contagious virus, measles presents unique challenges to healthcare facilities managing both cases and exposures. Measles flags within the EHR can be leveraged to assist facilities with case tracking, exposure management, and infection prevention and control.