Citations

Abstract Echocardiography is the most widely used cardiac imaging modality, yet artificial intelligence-enabled interpretation remains limited by the inability of existing models to integrate visual assessment, quantitative measurement, and clinical reasoning within a unified framework. Here we present EchoAtlas, the first autoregressive vision-language model developed for echocardiographic interpretation. Trained on over 12.9 million question-answer pairs derived from approximately 2 million echocardiogram videos, EchoAtlas achieves 0.966 accuracy on multiple-choice questions in our internal test set and establishes a new state-of-the-art on the public MIMIC-EchoQA benchmark (0.699 vs. 0.508 previously). EchoAtlas also provides accurate quantitative measurements, segment-level regional wall motion assessment, longitudinal comparison, and diagnostic reasoning across diverse question formats — capabilities not previously demonstrated in this domain. These results highlight the potential of autoregressive vision-language models as a foundation for interactive echocardiographic interpretation, representing an early step toward scalable, auditable artificial intelligence systems in cardiology practice.

BACKGROUND: For reasons not fully understood, Black adults experience more socioeconomic disadvantages (SED) than their White counterparts, as well as earlier onset and greater mortality from heart failure (HF). The John Henryism hypothesis predicts that repeated high-effort coping, that is, John Henryism (JH), with socioeconomic adversity can accelerate cardiovascular aging, thus increasing the risk for HF. METHODS: The analysis sample consisted of participants from the JHS (Jackson Heart Study), a cohort of Black adults from the Jackson, Mississippi Metropolitan area. The analysis sample included participants with no cardiovascular disease at baseline (2000–2004) with complete SED and JH scores. Indicators of SED included low household income, low educational attainment, and low maternal educational attainment scores. JH scores (0–36) were categorized as low (<28), moderate (29–32), and high (>32). Effect moderation of JH in the SED and incident HF association was assessed using interaction terms and stratification. Proportional hazards regression determined the hazard ratio and 95% CI, and models adjusted for age, sex, and established lifestyle risk factors. RESULTS: Among 1704 participants (mean age: 52.15 years, 64.3% female), 100 HF events occurred by 2016 (mean follow-up, 10 years). A statistically significant interaction between income and JH was observed for incident HF ( P =0.04). For every 1-unit increase in income disadvantage score, the risk of HF increased 2-fold among those with high JH (hazard ratio, 2.00 [95% CI, 1.39–2.86]) after full adjustment. Among participants with low JH, the corresponding unadjusted association was hazard ratio, 1.40 [95% CI, 1.04–1.90], but this association attenuated after adjusting for age and sex (hazard ratio, 1.19 [95% CI, 0.87–1.63]). CONCLUSIONS: The association between income disadvantage and HF differed by JH level. Because SED and high JH tend to co-occur, both should be considered in future research aiming to decrease the burden of HF in Black Americans.

Foundation models, known as the large-scale, pretrained models capable of generalizing across diverse tasks, have significantly advanced the field of medical image analysis. While most early applications focused on 2D modalities, the unique challenges and opportunities associated with volumetric medical imaging have recently attracted growing interest. This study provides a comprehensive overview of the current landscape of foundation models tailored for volumetric medical image analysis, with a focus on CT, MRI, and PET imaging. We examine key components of these models, including 3D architectures, training strategies, and supported modalities. In addition, we highlight their contribution to major clinical tasks such as classification and prediction, segmentation, image registration, quality enhancement, and visual question answering. Critical challenges of these models, including high computational cost, limited and less diverse 3D datasets, and domain adaptation, are discussed alongside the promising solutions and future research directions. By synthesizing recent advances in volumetric foundation models and outlining key technical and clinical challenges, this review provides a thorough roadmap toward the development of scalable, generalizable, and clinically applicable AI systems for volumetric medical images.

Abstract Creating a People-Centered Organization: 12 Organizational Actions to Reduce Burnout and Foster Professional Fulfillment tells the story of the evolving journey to create a better work environment for health care professionals. It dwells not on the story of occupational distress, burnout, moral injury, and cognitive dissonance but rather on a narrative of hope, well-being, camaraderie, values alignment, and meaning. Achieving this aspiration requires health care professionals and operational leaders working together to create 10 “Ideal Work Elements”: community at work and camaraderie; intrinsic motivation and rewards; control and flexibility; fairness and equity; professional development and mentorship; partnership; safety; trust and respect; gratitude; and work–life Integration. The ultimate aspiration is a people-centered organization with a culture that inspires enthusiasm, loyalty, engagement, and strong regard for the welfare of the team and the best interests of patients. Creating a People-Centered Organization: 12 Organizational Actions to Reduce Burnout and Foster Professional Fulfillment provides a road map for you to create such an environment for your team and organization. The map is paved with information about reliable, thoughtfully designed systems built on a psychologically safe and just culture. The authors drew on their extensive research on the well-being of health care professionals and their executive leadership experience in staff wellness, quality improvement, organization development, and operations management.

Background Primary cutaneous diffuse large B-cell lymphoma, leg type (PCDLBCL-LT), is a rare subset of primary cutaneous lymphoma known for its aggressive behavior, poor prognosis, and limited treatment options, particularly in the relapsed or refractory setting. We report a case of a patient diagnosed with PCDLBCL-LT who achieved a clinically significant response and sustained remission for seven months with acalabrutinib, a covalent inhibitor of Bruton’s tyrosine kinase (BTK), before disease progression. Case presentation An 88-year-old woman presented with a rapidly enlarging ulcerated lesion on the left lower leg. Histopathological and immunohistochemical analyses confirmed the diagnosis of PCDLBCL-LT. She was treated with rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone (R-CHOP) chemoimmunotherapy, followed by external beam radiation therapy (RT). These interventions resulted in only a partial response, and the disease progressed within several months. The patient was receiving direct oral anticoagulant (DOAC) therapy for left lower limb deep vein thrombosis, and she also had a history of hypertension. Considering the increased risk of major bleeding associated with DOAC use and the elevated risk of cardiovascular adverse events previously reported with ibrutinib, an alternative BTK inhibitor was considered. Accordingly, she was initiated on acalabrutinib at a dose of 100 mg orally twice daily. The patient exhibited a rapid and robust clinical response, with complete resolution of cutaneous lesions and sustained remission lasting seven months. Ultimately, the disease progressed, and given her advanced age and overall poor performance status, she was transitioned to hospice care. She subsequently died 14 months after initiating acalabrutinib. Conclusion This report documents the first known case of successful treatment of relapsed/refractory PCDLBCL-LT with acalabrutinib. Despite advanced age and poor performance status, the patient experienced rapid symptom resolution and durable remission without treatment-related adverse events. These findings suggest that BTK inhibitors may represent a promising therapeutic approach for PCDLBCL-LT, either as monotherapy or in combination with anti-CD20 antibodies. Further investigation into novel targeted therapies is urgently needed for this rare and aggressive lymphoma subtype.

ABSTRACT Background Patients with gastroparesis (Gp) can have a variety of symptoms. Apart from use of prokinetics, symptomatic therapies for the predominant symptom (PrS) are used. Aims (1) To classify Gp patients based on their PrS; (2) To determine differences in Gp symptoms, gastric emptying (GE), quality of life (QOL), treatments, and symptom improvement among Gp patients with different PrS. Methods Gp patients were enrolled in a multicenter registry and followed for 96‐weeks. Patients recorded their PrS and completed questionnaires assessing symptoms and QOL at enrollment and at follow up visits. Results Of 1013 Gp patients (361 diabetic, 607 idiopathic, 45 post‐fundoplication), the PrS were nausea (31%), vomiting (20%), abdominal pain (20%), bloating (9%), fullness (4%), GERD (4%), constipation (3%). Abdominal pain was more often a PrS in idiopathics, whereas vomiting was more often a PrS in diabetics. QOL scores were lower in the abdominal pain PrS group. PrS was associated with greater use of directed symptomatic treatment (antiemetic agents and gastric electrical stimulation for nausea and vomiting, prokinetic agents for vomiting and fullness, and constipation medications for constipation). Of 555 patients followed over 48 weeks, GCSI improved by ≥ 1 in 26% overall, more often in patients with initial PrS of nausea (32%) and bloating (35%) and less often for initial PrS of fullness (13%) or abdominal pain (15%). Conclusions In Gp patients, the most common PrS were nausea, vomiting, and abdominal pain. PrS is associated with QOL, treatments utilized, and patient outcomes. Thus, the PrS of a patient with Gp provides useful information about their present condition and future outcome.

Community organisations, alternative schools and business institutions worldwide prepare youth for the workforce. Since the COVID-19 pandemic, changes in work—life decisions and business needs have led to a shortage of talent. To equip students with the skills and mindset needed to be future ready, the power of diversity, equity and inclusion (DEI) must be harnessed through a network of meaningful connections and partnerships. A small group at Mayo Clinic, sharing a common interest in DEI and the local community, explored ways to encourage diverse, young talent to embark on careers in science, technology, education and mathematics. Input from community organisations and professionals indicated that collaborating with educational institutions is vital, which led to the initiation of a pilot programme involving one high school. The group collaborated with the school’s Work Experience Coordinator and students to develop and implement a pilot Career Preparation Programme (CPP) as part of a Work Experience Seminar (WES) course to deepen students’ knowledge of healthcare careers and provide one-on-one and group mentorship. Through discussions about career possibilities, levers of success and a higher purpose, the team sought to help students appreciate available and attainable career opportunities. Student evaluations were conducted after each of the two semesters. A total of 93 students participated in the pilot programme, of whom 85 (91 per cent) reported that the combined offering was engaging and worthwhile. The primary takeaways were ‘the importance of soft skills’, ‘following dreams and passions’ and ‘being a lifelong learner’. Inspired by this experience, the students established a club focused on career mentoring and tutoring. Throughout the process, trust, credibility and role modelling were emphasised. In addition, flexibility, patience and openness to bidirectional learning and creative ideas were identified as the main elements of programme’s success. The team plans to expand the pilot programme to include a non-healthcare focus and implement the programme at additional high schools. This article is also included in The Business & Management Collection which can be accessed at https://hstalks.com/ business/.

ABSTRACT Background Fosaprepitant is non‐inferior to aprepitant in adults receiving highly emetogenic chemotherapy (HEC). We evaluated whether fosaprepitant is non‐inferior to aprepitant in children receiving HEC. Methods In this open‐label, non‐inferiority trial, children aged 5–18 years, receiving their first cycle of HEC, were randomized 1:1 to the fosaprepitant or aprepitant group. The fosaprepitant group received a single intravenous dose of 4 mg/kg (max 150 mg). The aprepitant group received oral aprepitant capsules (weight 15 to <30 kg: 80 mg Days 1–3; weight ≥30 kg, or age ≥12 years: 125 mg Day 1, 80 mg Days 2 and 3). Both groups received ondansetron and dexamethasone. The primary outcome was the complete response (CR) rate of vomiting during the acute phase (AP) with a non‐inferiority margin of 15%. Secondary outcomes included CR rates in the delayed (DP) and overall phases (OP), grade of vomiting, incidence and severity of nausea, and adverse effects. Results A total of 279 children were included in the modified intention‐to‐treat analysis (fosaprepitant group: 140; aprepitant group: 139). In AP, the difference of CR rate between fosaprepitant [76 (54.3%)] and aprepitant groups [84 (60.4%)] was −6.1% [90% CI: −15.7% to +3.6%], with the lower limit exceeding −15%, failing to establish non‐inferiority. The CR rate with fosaprepitant versus aprepitant was 62.1% ( n = 87) versus 65.5% ( n = 91) in DP (difference: –3.4%; 90% CI: –12.7% to 6.1%) and 42.9% ( n = 60) versus 49.6% ( n = 69) in the OP (difference: –6.7%; 90% CI: –16.5% to 3.1%). Grade of vomiting, incidence and severity of nausea, and adverse effects were similar between the two groups. Conclusions Non‐inferiority of fosaprepitant compared to aprepitant was not demonstrated in children undergoing their first cycle of HEC. Trial Registration Clinical Trials Registry, India (CTRI/2019/05/019082).

Abstract Endogenous Cushing syndrome (CS) is a rare disorder resulting from chronic exposure to excessive concentrations of cortisol. It is likely underdiagnosed because many clinical signs and symptoms are non-specific and overlap with those of common conditions. Furthermore, biochemical testing to diagnose CS can be complex and challenging, especially in milder cases. CS is characterized by excessive daily cortisol production, but it is also associated with a disrupted circadian rhythm of cortisol secretion. Traditional cortisol monitoring techniques rely on single-time-point measurements or a cumulation of measurements, which are unable to capture the complete daily rhythm of cortisol fluctuations. Currently, the utility of assessing individual patients’ cortisol circadian rhythm during diagnosis and treatment of CS is not well characterized. In this review, we will discuss how cortisol is measured in clinical practice and the potential benefit of measurement and normalization of the cortisol circadian rhythm.