Citations

ABSTRACTBackground and ObjectiveThe diagnosis of interstitial lung diseases (ILDs) often relies on the integration of various clinical, radiological, and histopathological data. Achieving high diagnostic accuracy in ILDs, particularly for distinguishing usual interstitial pneumonia (UIP), is challenging and requires a multidisciplinary approach. Therefore, this study aimed to develop a multimodal artificial intelligence (AI) algorithm that combines computed tomography (CT) and histopathological images to improve the accuracy and consistency of UIP diagnosis.MethodsA dataset of CT and pathological images from 324 patients with ILD between 2009 and 2021 was collected. The CT component of the model was trained to identify 28 different radiological features. The pathological counterpart was developed in our previous study. A total of 114 samples were selected and used for testing the multimodal AI model. The performance of the multimodal AI was assessed through comparisons with expert pathologists and general pathologists.ResultsThe developed multimodal AI demonstrated a substantial improvement in distinguishing UIP from non‐UIP, achieving an AUC of 0.92. When applied by general pathologists, the diagnostic agreement rate improved significantly, with a post‐model κ score of 0.737 compared to 0.273 pre‐model integration. Additionally, the diagnostic consensus rate with expert pulmonary pathologists increased from κ scores of 0.278–0.53 to 0.474–0.602 post‐model integration. The model also increased diagnostic confidence among general pathologists.ConclusionCombining CT and histopathological images, the multimodal AI algorithm enhances pathologists' diagnostic accuracy, consistency, and confidence in identifying UIP, even in cases where specialised expertise is limited. image

Background and Aims: Angiotensin-converting enzyme inhibitors (ACEi) and angiotensin receptor blockers (ARB) prevent fibrosis progression in a preclinical model of steatotic liver disease. Our objective was to assess the impact of ACEi/ARB use on clinical outcomes in patients with metabolic dysfunction–associated steatotic liver diseases. Approach and Results: Using TriNetX, a nationwide database, we identified all patients with metabolic dysfunction–associated steatotic liver diseases from January 1, 2011, to December 31, 2019. Using a target trial emulation framework, ACEi/ARB users were matched with calcium channel blocker (CCB) users using propensity score matching (PSM). Patients were followed up to 10 years after the index date. Cox proportional hazards regression was used to determine the risk of mortality, major adverse liver outcomes, major adverse cardiac events, and incident cancers. Of the 35,988 eligible patients, 28,423 were ACEi/ARB users, and 7565 were CCB users. After PSM, 7238 pairs were well-balanced. ACEi/ARB use was associated with a significantly decreased mortality risk (HR: 0.59, 95% CI: 0.51–0.68). ACEi/ARB was associated with a significantly reduced risk of developing major adverse liver outcomes (HR: 0.70, 95% CI: 0.61–0.80), including ascites (HR: 0.78, 95% CI: 0.63–0.98) and HE (HR: 0.67, 95% CI: 0.57–0.78). ACEi/ARB use was also associated with a lower risk of major adverse cardiac events (HR: 0.82, 95% CI: 0.76–0.90) but not incident cancer (HR: 0.97, 95% CI: 0.86-1.10) compared with CCB. Conclusions: ACEi/ARB use in patients with metabolic dysfunction–associated steatotic liver diseases was associated with a reduced risk of mortality, major adverse liver outcomes, and major adverse cardiac events compared with CCB use. A large prospective study is needed for external validation.

Abstract Aims Artificial intelligence (AI) has the potential to transform cardiac electrophysiology (EP), particularly in arrhythmia detection, procedural optimization, and patient outcome prediction. However, a standardized approach to reporting and understanding AI-related research in EP is lacking. This scientific statement aims to develop and apply a checklist for AI-related research reporting in EP to enhance transparency, reproducibility, and understandability in the field. Methods and results An AI checklist specific to EP was developed with expert input from the writing group and voted on using a modified Delphi process, leading to the development of a 29-item checklist. The checklist was subsequently applied to assess reporting practices to identify areas where improvements could be made and provide an overview of the state of the art in AI-related EP research in three domains from May 2021 until May 2024: atrial fibrillation (AF) management, sudden cardiac death (SCD), and EP lab applications. The EHRA AI checklist was applied to 31 studies in AF management, 18 studies in SCD, and 6 studies in EP lab applications. Results differed between the different domains, but in no domain reporting of a specific item exceeded 55% of included papers. Key areas such as trial registration, participant details, data handling, and training performance were underreported (<20%). The checklist application highlighted areas where reporting practices could be improved to promote clearer, more comprehensive AI research in EP. Conclusion The EHRA AI checklist provides a structured framework for reporting AI research in EP. Its use can improve understanding but also enhance the reproducibility and transparency of AI studies, fostering more robust and reliable integration of AI into clinical EP practice.

Background and Aims: Immunotherapy has emerged as an effective treatment for advanced HCC. We aimed to investigate the real-world effectiveness of immunotherapy compared to lenvatinib in HCC. Approach and Results: From the TriNetX database, we used a target trial emulation framework and identified patients with HCC who received first-line treatment with immunotherapy (atezolizumab/bevacizumab or tremelimumab/durvalumab) or lenvatinib between or between August 2018 and December 2023. OS was compared using Kaplan-Meier analysis and Cox proportional hazards regression. After propensity score matching, 1203 patients were included in each group. Immunotherapy was associated with improved OS versus lenvatinib (median survival: 545 vs. 425 d; HR: 0.86, 95% CI: 0.76–0.97). Regarding treatment type, atezolizumab plus bevacizumab showed improved survival compared to lenvatinib (n=1070 in each group; HR: 0.87, 95% CI: 0.77–0.99), while the point estimate favored durvalumab plus tremelimumab versus lenvatinib (HR: 0.81, 95% CI: 0.59–1.12), though this difference was not statistically significant, likely due to small sample size. Regarding etiology, immunotherapy had improved OS compared to lenvatinib in viral hepatitis (n=510 in each group; HR: 0.74, 95% CI: 0.61–0.89) and alcohol-associated liver disease (n=190 in each group; HR: 0.65, 95% CI: 0.49–0.87), but not in metabolic dysfunction–associated steatotic liver diseases (n=156 in each group; HR: 0.96, 95% CI: 0.70–1.31). Conclusions: In this real-world analysis, immunotherapy was associated with improved OS compared to lenvatinib in advanced HCC, with consistent benefit across most subgroups. These findings support the use of immunotherapy as a first-line treatment for advanced HCC.

Abstract INTRODUCTION Loss‐of‐function variants of the ABCA7 gene are associated with an increased risk of Alzheimer's disease (AD). How neuronal ABCA7 contributes to AD pathogenesis is unknown. METHODS Using neuron‐specific Abca7 KO mice (n Abca7 −/− ) with or without 5×FAD amyloid model background and post mortem AD brains, we investigated AD‐related phenotypes through comprehensive approaches including transcriptomics and lipidomics. RESULTS Lipidomics analysis detected altered lipid profiles in the brains and synaptosomes of 5×FAD; n Abca7 −/− mice compared to controls. Transcriptomics profiling revealed that neuronal ABCA7 deficiency altered the expression of genes and pathways related to mitochondrial homeostasis and apoptosis, particularly in excitatory neurons. Consistently, synaptosomes isolated from 5×FAD; n Abca7 −/− mice showed diminished mitochondria respiration and reduced synaptic protein levels, which is further supported by results from human AD brains. DISCUSSION Our findings reveal that neuronal ABCA7 plays a critical role in mitochondrial homeostasis important for neuronal function and survival in the presence of AD pathology. Highlights Neuronal ABCA7 deficiency exacerbates Aβ pathology and neuronal damage in 5×FAD mice. Neuronal ABCA7 deficiency alters brain transcriptomes and lipidomes of 5×FAD mice. Neuronal ABCA7 deficiency disturbs mitochondria functions in synaptosomes from 5×FAD mice. Neuronal ABCA7 expression associates with genes and pathways related to mitochondrial homeostasis in AD brains.

Background/Objectives: This study aimed to establish the clinical utility of a therapeutic drug monitoring (TDM)-supported, model-informed precision dosing (MIPD) approach (precision-guided dosing [PGD]) by assessing the impact of pharmacokinetic (clearance [CL]) and clinical laboratory parameters on adalimumab (ADA) dosage adjustments during maintenance therapy for inflammatory bowel disease (IBD). Methods: In the EMPOWER study, blood was collected at any time post-ADA injection. Pharmacokinetic (PK) testing was conducted in an accredited lab. Inputs for the PGD test included ADA concentrations, antibodies to ADA, albumin levels, and the current dosing regimen. CL was calculated using nonlinear mixed-effect models. Results were reported to health care providers (HCPs) within 3 days. HCPs’ treatment decisions were recorded and classified as treatment reduction, continuation, intensification, or ADA discontinuation. The physician global assessment (PGA) of disease activity was collected. Relationships between drug concentrations, CL, disease activity, and physician decision-making were assessed using logistic regression. Results: A total of 213 cases were assessed by 21 HCPs. ADA treatment was intensified in 24% and discontinued in 13% of cases. An ADA concentration ≤ 10 μg/mL was associated with a 23.7-fold and 3.0-fold higher likelihood of therapy intensification and PGA > 0, respectively, compared to concentrations > 10 μg/mL. An ADA concentration < 5 μg/mL was associated with a 3.3-fold higher likelihood of treatment discontinuation. CL ≥ 0.318 L/day was associated with a 10.4-fold higher likelihood of therapy intensification. Higher CL (>0.8 L/day) was associated with a 3.5-fold and 4.2-fold higher likelihood of treatment discontinuation and PGA > 0, respectively. Conclusions: PGD enables earlier and precise optimization of ADA dosing by predicting trough levels at any time during the therapy cycle. Optimized dosing to achieve target ADA concentrations and low clearance is crucial to mitigate therapy discontinuation and active disease in IBD patients.

BACKGROUND: Patients presenting with cervical artery dissection (CAD) are at risk for subsequent ischemic events. We aimed to identify characteristics that are associated with increased risk of ischemic stroke after initial presentation of CAD and to evaluate the differential impact of anticoagulant versus antiplatelet therapy in these high-risk individuals. METHODS: This was a preplanned secondary analysis of the STOP-CAD study (Antithrombotic Treatment for Stroke Prevention in Cervical Artery Dissection), a multicenter international retrospective observational study (63 sites from 16 countries in North America, South America, Europe, Asia, and Africa) that included patients with CAD predominantly between January 2015 and June 2022. The primary outcome was subsequent ischemic stroke by day 180 after diagnosis. Clinical and imaging variables were compared between those with versus without subsequent ischemic stroke. Significant factors associated with subsequent stroke risk were identified using stepwise Cox regression. Associations between subsequent ischemic stroke risk and antithrombotic therapy type (anticoagulation versus antiplatelets) among patients with identified risk factors were explored using adjusted Cox regression. RESULTS: In all, 4023 patients (mean age was 47.4 years; 44.5% were women) were included. By day 180, subsequent ischemic stroke occurred in 5.3% of the cohort. In adjusted Cox regression, factors associated with increased risk of subsequent ischemic stroke were prior history of ischemic stroke (adjusted hazard ratio [aHR], 7.31 [95% CI, 1.61–33.13]; P =0.010), presentation within 7 days from first symptoms (aHR, 3.04 [95% CI, 1.04–8.91]; P =0.043), infarct on baseline imaging (aHR, 9.85 [95% CI, 3.65–26.58]; P <0.001), and occlusive dissection (aHR, 2.34 [95% CI, 1.03–5.34]; P =0.043). Only patients with occlusive dissection demonstrated a reduced risk of subsequent ischemic stroke when treated with anticoagulation versus antiplatelets (aHR, 0.36 [95% CI, 0.16–0.80]; P =0.01). CONCLUSIONS: In this post hoc analysis of the STOP-CAD study, several factors associated with subsequent ischemic stroke were identified among patients with CAD. Furthermore, we identified a potential benefit of anticoagulation in patients with CAD with occlusive dissection. These findings require validation by meta-analyses of prior studies to formulate optimal treatment strategies for specific high-risk CAD subgroups.

Abstract Emphysema’s significant morbidity and mortality underscore the need for reliable outcome metrics in clinical trials. However, commonly accepted chronic obstructive pulmonary disease outcome measures do not adequately capture emphysema severity or progression. Computed tomography (CT) metrics have been validated as accurate indicators of pathological emphysema and predictors of chronic obstructive pulmonary disease progression, exacerbations, and mortality. This position paper reviews the evidence supporting CT densitometry as a biomarker for emphysema, establishes implementation standards, and highlights areas for future research. A systematic literature review addressed three key questions: whether CT densitometry can be used as a diagnostic biomarker of emphysema, whether CT densitometry can be used as a prognostic biomarker, and whether longitudinal change in densitometry can be used as a disease progression monitoring biomarker. Emphysema metrics, such as the percentage of low attenuation areas below −950 Hounsfield units, are validated, highly reproducible diagnostic and prognostic biomarkers. Volume-adjusted lung density is recommended for disease monitoring. Both metrics demonstrate a scan–rescan intraclass correlation coefficient of 0.99 with proper technique. The paper also discusses relevant CT physics, techniques, and sources of variation, including technical factors, physiological changes, and software analysis. Key recommendations for clinical trials include using standardized CT techniques, proper subject selection, and longitudinal evaluation with volume-adjusted lung density.