Citations

Background: Discharge summaries are essential for safe transitions of care, but writing the hospital course narrative is time intensive. Large language models can generate plausible clinical narratives, yet prior approaches often rely on static inputs and remain vulnerable to omissions and factual inconsistencies. Methods: We developed an electronic health record (EHR)-integrated agentic artificial intelligence (AI) system that uses Gemini 2.5 Pro and Model Context Protocol tools to retrieve clinical notes, diagnostic reports, diagnoses, medications, and appointments on demand. In this retrospective, blinded, paired study, 50 inpatient cardiology encounters were randomly selected from admissions July 13 to 27, 2024, at Mayo Clinic, Rochester, Minnesota. Five physicians rated AI-generated and clinician-authored hospital course narratives for each encounter (250 ratings) on 0-to-10 scales for overall quality, clarity, completeness, accuracy, and readability and indicated a preference. The primary outcome was the paired difference in overall quality (linear mixed-effects model with crossed random intercepts for encounter and reviewer). Secondary domains were analyzed similarly with Bonferroni adjustment, and preference with a crossed random-effects logistic model. Results: Clinician-authored narratives were preferred in 132 ratings (52.8%) and AI-generated narratives in 118 (47.2%) (odds ratio for clinician-authored preference, 1.12; 95% CI, 0.71 to 1.78). Overall quality did not differ significantly (mean, 7.27 AI-generated versus 7.42 clinician-authored; difference, -0.15; 95% CI, -0.86 to 0.56; p=0.627). AI-generated narratives were rated higher for clarity (0.36; 95% CI, 0.07 to 0.65) and readability (0.72; 95% CI, 0.20 to 1.24) but lower for completeness (-0.84; 95% CI, -1.36 to -0.32) and accuracy (-0.35; 95% CI, -0.66 to -0.05). After Bonferroni correction, only lower completeness remained significant (adjusted p=0.012). Conclusions: Hospital course narratives generated by the EHR-integrated agentic AI system did not differ significantly from clinician-authored narratives in physician-rated overall quality or preference. Lower completeness supports continued clinician review before use in the medical record.

BACKGROUND: Pulsed field ablation is now widely used for atrial fibrillation (AF) ablation, but atrial tachyarrhythmia recurrence remains common and postablation risk tools are limited. We assessed whether a validated sinus‑rhythm artificial intelligence— enabled ECG AF probability score, and its early postablation change, predicts recurrence after pulsed field ablation. METHODS: We studied consecutive patients undergoing index pulsed field ablation across 3 Mayo Clinic sites (February 2024–March 2025) with ≥1 sinus‑rhythm ECG within 180 days preprocedure. Baseline artificial intelligence—enabled ECG AF score (range 0–1) was the mean across baseline ECGs. Recovery indices (RI30/60/90), defined as mean postprocedure artificial intelligence—enabled ECG score within days 1–30/60/90 minus baseline, predicted post‑blanking recurrence using corresponding 30‑, 60‑, and 90‑day blanking windows. The primary outcome was time to first documented AF/atrial flutter/atrial tachycardia episode >30 seconds, ascertained via clinic ECGs, ambulatory monitoring, and device interrogations. Cox regression adjusted for prespecified clinical and echocardiographic covariates assessed associations; Harrell C‑statistic quantified discrimination. RESULTS: Among 1052 patients (67±10 years; 33% women), median baseline score was 0.35; 320 (30%) recurred over 188 days. Higher baseline score independently predicted recurrence (hazard ratio per 0.1 increase, 1.08 [95% CI, 1.03–1.14]). Scores rose on day 0 after ablation, then declined over subsequent weeks, with persistently higher, less‑improving trajectories among patients who recurred (time×recurrence interaction P <0.001). Day 0 score was not independently associated with recurrence after adjustment. Attenuated early recovery (higher recovery index) was independently associated with recurrence, most robustly for RI-90 (hazard ratio per 0.1 increase, 1.15 [95% CI, 1.07–1.24]), and improved discrimination beyond baseline and covariates (C‑statistic, 0.63–0.67; ΔC=0.04). Findings were consistent in a historical thermal ablation cohort. CONCLUSIONS: Baseline and early postablation dynamics of a sinus‑rhythm artificial intelligence—enabled ECG AF probability score are associated with pulsed field ablation recurrence and may aid multivariable risk stratification; prospective validation is warranted.

Background Bicuspid aortic valve (BAV) is the most common congenital heart defect, associated with a lifetime morbidity burden exceeding 80% and an estimated 7% probability of transmission to first-degree relatives. Hence, echocardiographic screening of relatives is recommended. The aim of our study is to develop an artificial intelligence-enabled electrocardiogram (AI-ECG) model for the detection of BAV. Methods Between January 1, 1990, and June 30, 2023, the Mayo Clinic healthcare system database was searched for patients aged ≥18 years with echocardiograms performed for family history of BAV, abnormal auscultation, a BAV-related diagnosis, or to rule out the condition, and with an electrocardiogram (ECG) obtained within 6 months. Cases were patients with a confirmed BAV diagnosis, and controls were those with normal aortic valves. ECGs were randomly assigned into training (80%), internal validation (10%), and test (10%) groups. The AI-ECG model was built using Keras under TensorFlow. Results A total of 13,065 valid ECG–echocardiogram pairs were included (mean [SD] age, 58 [17] years; 44% women), with a median time of 1 day (interquartile range, 0–3 days) between studies. With a 45% BAV prevalence in the test group ( n = 1301), the area under the curve was 0.704, positive predictive value (PPV) 60.1%, and negative predictive value (NPV) 69.4%. At a prevalence of 7%, the NPV increased to 96.1%, but the PPV decreased to 12.2%. Conclusions In this retrospective cohort and using the current AI-ECG model, BAV detection showed modest diagnostic performance and limited standalone clinical utility, suggesting that ECG-only screening for BAV may require additional modalities or more refined phenotyping.

Background Diastolic dysfunction is common in patients with aortic stenosis and may influence outcomes following surgical aortic valve replacement. We aimed to examine the association of preoperative artificial intelligence (AI)‐generated diastolic function grades with early and late outcomes following aortic valve replacement and how postoperative progression influence prognosis. Methods We identified 5503 patients undergoing aortic valve replacement between 2000 and 2023. Diastolic function was assessed using a validated deep‐learning AI model applied to 12‐lead ECGs done preoperatively and on postoperative follow‐up. Diastolic grades were classified by AI into Grades 1 to 3. Longitudinal trend analyses and multivariable regression models were used to assess study end points. Results Among 5503 patients (mean age 72.4±10.8 years; 39% female), higher AI ECG diastolic grades were associated with greater comorbidity burden, including diabetes, renal disease, and heart failure. AI ECG diastolic Grade 3 was independently associated with higher in‐hospital mortality (odds ratio, 2.5; P =0.007) and other complications. At 5‐year follow‐up, patients with Grade 3 showed the least improvement in diastolic function by both ECG and echocardiography. Grades 2 and 3 diastolic function at baseline were independently associated with increased late mortality (hazard ratio, 1.3 and 2.45, respectively; both P <0.001). Additionally, lack of improvement in AI ECG diastolic grade by 1 year was also independently associated with late mortality. Conclusions AI ECG–derived diastolic function grades strongly correlates with early complications and long‐term mortality and diastolic progression after aortic valve replacement. AI ECG provides a powerful, noninvasive tool for risk stratification and longitudinal monitoring of patients with aortic stenosis.

Importance Timely identification of aortic stenosis (AS) is essential for appropriate clinical management, yet screening remains limited by dependence on comprehensive echocardiography and trained imaging personnel. Objective To develop and validate a deep learning algorithm for detection of moderate or greater AS and prospectively evaluate its performance using artificial intelligence (AI)–guided focused cardiac ultrasound (FoCUS) acquired by novice operators. Design, Setting, and Participants This diagnostic study included retrospective algorithm development and validation and prospective evaluation of AI-guided FoCUS across Mayo Clinic sites in the Midwest, Arizona, and Florida. The model was developed using 6753 patients and evaluated in internal validation (n = 852), internal test (n = 844), and validation (n = 1912) cohorts. Performance was assessed on FoCUS acquired by experienced sonographers (n = 602) and prospectively by novice operators (n = 1302). The retrospective model development and validation cohorts comprised studies performed from January 2005 through September 2022. Prospective study was conducted in 2 enrollment periods from June to August 2024 and from June to September 2025. Participants from both periods were combined to comprise the final prospective cohort. Exposure AI-guided FoCUS acquisition and automated deep learning–based assessment for detection of moderate or greater AS. Main Outcomes and Measures Detection of moderate or greater AS. Performance was assessed using area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and positive predictive value. Results The model demonstrated excellent discrimination in the internal test cohort (AUROC, 0.99; 95% CI, 0.98-1.00) and geographically distinct validation cohorts in Arizona (AUROC, 0.99; 95% CI, 0.97-1.00) and Florida (AUROC, 0.99; 95% CI, 0.96-1.00). Among FoCUS examinations acquired by experienced sonographers, sensitivity was 95% (95% CI, 82-99) and specificity was 97% (95% CI, 95-98). In the prospective novice-operator cohort, 1258 of 1302 examinations (96.6%) were suitable for automated analysis. Sensitivity was 93% (95% CI, 82-99) and specificity was 96% (95% CI, 95-97). Expert review of AI-positive and uninterpretable examinations increased the positive predictive value from 49.4% to 91.1%, with sensitivity of 85.4%. Conclusions and Relevance A deep learning algorithm accurately detected moderate or greater AS across validation cohorts in this study. In prospective evaluation, novice operators were able to acquire AI-guided FoCUS examinations that enabled accurate detection of moderate or greater AS. These findings support a scalable strategy that may expand access to AS detection in settings with limited echocardiography resources.

This study examines the patient- and hospital-level variation in time to initiation of inpatient management among patients admitted to general medical services.

The NCCN Guidelines for Survivorship offer guidance for health care providers who care for survivors of adult-onset cancer. These guidelines include screening, evaluation, and treatment recommendations for common physical and psychosocial problems resulting from cancer and its treatment and provide a framework for care coordination. They also present guidance for helping cancer survivors to enhance their wellness and maintain a healthy lifestyle. This article summarizes the panel’s current recommendations and recent updates regarding anxiety, depression, distress, and trauma in cancer survivors.

Abstract Background Vagally mediated syncope and functional bradyarrhythmias can cause recurrent symptoms, injury and a need for permanent pacing, yet standard therapies do not address the underlying autonomic reflex. Cardioneuroablation (CNA) targets this mechanism, but adoption has been limited by uncertainty about patient selection, procedural endpoints and durable outcomes. Methods We studied 95 consecutive patients with vagally mediated syncope (n=78) or functional bradyarrhythmia (n=17) who underwent CNA at a single center by a single lead operator under a uniform, prospectively maintained protocol. Extracardiac vagal stimulation (ECVS) was performed before and after ablation to confirm vagally mediated sinus or atrioventricular (AV) nodal responses and to verify their attenuation. Outcomes through 1 year included clinical recurrence, quality of life, pacing burden and pacemaker extraction. Results Before ablation, ECVS provoked sinus pauses in 95.8% of patients and AV block in 91.6%; after ablation, sinus pauses were abolished in every patient and residual AV block was present in 4.2%. One-year freedom from recurrent syncope and from bradyarrhythmia-related events was 93.8% and 94.1%. Syncope burden fell from a median of 2.7 episodes per year to none, and disease-specific quality of life improved substantially (P<0.001). Among patients with pre-existing devices, atrial pacing burden fell from a median of 22% to 0%. There were no strokes, deaths or myocardial infarctions. Conclusions In this single-center cohort, physiology-guided CNA was associated with durable symptom control, improved quality of life and reduced pacing across vagally mediated bradyarrhythmia syndromes. Multicenter controlled studies are needed to confirm these findings.

Abstract Introduction The lifetime risk for colorectal cancer (CRC) in the United States is approximately 4%. Individuals with Inflammatory Bowel Disease, including Ulcerative Colitis and Crohn’s Disease, have a substantially increased risk of developing colorectal cancer. Siglecs (sialic acid immunoglobulin lectin-like proteins) are a family of receptors that regulates the immune response. Siglec-E is a mouse inhibitory receptor that is primarily expressed by innate cells. While others have demonstrated that Siglec-E KO mice reject tumors faster in multiple tumor models, we have found that colorectal cancer is accelerated in Siglec-E KO mice. Here we aim to investigate the role of Siglec-E in immune homeostasis, inflammation and colorectal cancer development. Methods We used two models of colorectal cancer to assess the role of Siglec-E in tumorigenesis: TS4-cre LSL KRASG12D APClox468/wt (TAR mice) and the DSS/AOM model of colitis-associated cancer. Colons were prepared by separating lamina propria (LP) and epithelial (EP) fractions for flow cytometry. 2cm sections were taken from the middle of colons to generate lysates for ELISA. DSS was administered to WT and Siglec-E KO mice to assess the susceptibility to intestinal inflammation. H&E and IHC for PCNA were performed on colonic tissue from experiments. Results We have found that in both the spontaneous and DSS induced models of CRC, Siglec-E KO mice grow more tumors than WT mice. Siglec-E KO mice have an exquisite susceptibility to DSS induced inflammation and reduced number and proportion of neutrophils after treatment. Lastly, we have found that Siglec-E KO mice at baseline have increased VEGF-A in the colon. Conclusion Siglec-E has a critical role in regulating immune homeostasis in the colon. Siglec-E functions as a brake for intestinal inflammation which protects from the development of colorectal cancer. Funding Source This research was funded by NIH grant CA243545-01A1 (VSS), NIH T32 AI170478 (VSS/BM), and and grant R25 GM055252-26 Deans fellowship: Initiative for maximizing student development (IMSD). Topic Categories Cellular Adhesion, Migration, and Inflammation (CAM)

Temozolomide (TMZ) remains the cornerstone of chemotherapeutic agent for glioblastoma (GBM), yet intrinsic and acquired resistance severely limits its clinical benefit. While O6-methylguanine-DNA methyltransferase (MGMT)–mediated repair of TMZ-induced O6-methylguanine (O6-meG) lesions has been extensively studied, the DNA mismatch repair (MMR) pathway is increasingly recognized as a key determinant of TMZ cytotoxicity. Canonical MMR, mediated by MutSα (MSH2–MSH6) and MutLα (MLH1–PMS2) complexes, recognizes O6-meG: thymine mispairs generated during replication and initiates futile repair cycles that culminate in replication stress, replication fork collapse, and apoptotic signaling; intact canonical MMR is, therefore, required for TMZ-induced cell death. Disruption of canonical MMR, frequently via acquired MSH6 mutations, confers TMZ tolerance and drives hypermutated recurrent GBM. Beyond mismatch correction, MMR proteins perform non-canonical functions in DNA damage signaling, replication stress responses, transcriptional regulation, chromatin dynamics, and immune modulation. These activities may shift the outcome from cytotoxic futile repair toward replication stress adaptation, Translesion synthesis (TLS)-mediated lesion tolerance, immune remodeling, and therapeutic resistance. Notably, partial attenuation or functional diversion of MMR may decouple lesion recognition from cytotoxic signaling, enabling TLS-mediated lesion tolerance without complete loss of MMR activity. This review integrates current insights into canonical and non-canonical MMR functions in GBM, defines their distinct contributions to TMZ sensitivity and resistance, and highlights therapeutic opportunities to exploit MMR-associated dependencies, including synthetic lethal strategies and immunotherapeutic vulnerabilities linked to MMR deficiency-driven hypermutation.