Citations

Introduction: Endovascular thrombectomy (EVT) is an effective treatment for basilar artery occlusion (BAO) stroke in select patients. While there is a growing body of literature suggesting that advanced imaging modalities such as computed tomography perfusion (CTP) and magnetic resonance (MR) may not be necessary for selecting anterior circulation large vessel occlusion stroke patients for EVT, whether advanced imaging may be superior to conventional imaging (non-contrast CT and CT angiography) in identifying good treatment candidates among BAO patients is less clear. Patients and methods: This was a multicenter retrospective cohort study of BAO EVT patients treated from 2013 to 2022 in the Stroke Thrombectomy and Aneurysm Registry. Patients selected for EVT by advanced imaging (CTP or MR) were matched with those selected by conventional imaging using propensity score matching (PSM) accounting for possible confounders. Primary outcome was functional independence at 90 days. Other outcomes include bedridden state or death at 90-days and symptomatic intracranial hemorrhage (sICH). Results: 268 patients were included. 150 patients were selected for BAO EVT by conventional imaging, 86 by CTP, and 32 by MR. Patients selected by advanced imaging were significantly older than those selected by conventional imaging (median age 71 vs 64 years, p = 0.001); patient characteristics were otherwise similar between cohorts. After PSM, 90-day outcomes were similar between the two cohorts ( p = 0.56), with similar rates of functional independence (39.4% vs 35.1%, p = 0.65), bedridden state or death (40.4% vs 44.7%, p = 0.66), and sICH (3.3% vs 5.7%, p = 0.49) for conventional and advanced imaging groups, respectively. Results were similar across treatment time windows (all p > 0.05). Conclusions: Selecting patients for basilar EVT using conventional versus advanced imaging did not result in different clinical outcomes, regardless of treatment time windows. Conventional imaging appears sufficient as a first-line tool for selecting basilar EVT patients in routine clinical practice.

Background and objectives Arteriovenous malformations (AVMs) with perinidal aneurysms and single draining vein are associated with an elevated risk of rupture and increased procedural complexity. The role of preoperative embolization in this high-risk anatomical subset remains unclear. This study aimed to evaluate the safety and efficacy of microsurgery with preoperative embolization, compared with microsurgery alone in patients with such AVMs. Methods We conducted a multicenter retrospective analysis of an AVM registry from the MISTA (Multicenter International Study for Treatment of Brain AVMs) consortium and included AVMs with perinidal aneurysms and a single draining vein. Baseline characteristics, angiographic outcomes, functional outcomes, and complication rates were compared. Propensity score weighting (PSW) using the covariate balancing method was applied to adjust for baseline differences. Results Out of a total of 1919 patients, 65 met the inclusion criteria; 45 patients underwent preoperative embolization followed by microsurgery, and 20 underwent microsurgery alone. After adjustment, complete obliteration rates were similar between groups (OR 0.87, 95% CI 0.04 to 16.33, P=0.92), as were rates of functional independence at discharge and follow-up. Overall complication, symptomatic complication, and mortality rates did not differ significantly between groups. However, permanent complications were significantly lower in patients with preoperative embolization (OR 0.06, 95% CI 0.004 to 0.84, P=0.03). Discussion In patients with AVMs featuring perinidal aneurysms and single draining vein, preoperative embolization followed by microsurgery was associated with fewer permanent complications and no increase in adverse outcomes compared with microsurgery alone. However, given the small number of events, this finding should be interpreted cautiously.

Abstract Objective: Electronic Health Record (EHR) data are critical for advancing translational research and AI technologies. The ENACT network offers access to structured EHR data across 57 CTSA hubs. However, substantial information is contained in clinical narratives, requiring natural language processing (NLP) for research. The ENACT NLP Working Group was formed to make NLP-derived clinical information accessible and queryable across the network. Methods: We established the ENACT NLP Working Group with 13 sites selected based on criteria including clinical notes access, IT infrastructure, NLP expertise, and institutional support. We divided sites into five focus groups targeting clinical tasks within disease contexts. Each focus group consisted of two development sites and two validation sites. We extended the ENACT ontology to standardize NLP-derived data and conducted multisite evaluations using the Open Health Natural Language Processing (OHNLP) Toolkit. Results: The working group achieved 100% site retention and deployed NLP infrastructure across all sites. We developed and validated NLP algorithms for rare disease phenotyping, social determinants of health, opioid use disorder, sleep phenotyping, and delirium phenotyping. Performance varied across sites (F1 scores 0.53–0.96), highlighting data heterogeneity impacts. We extended the ENACT common data model and ontology to incorporate NLP-derived data while maintaining Shared Health Research Informatics NEtwork (SHRINE) compatibility. Conclusion: This demonstrates feasibility of deploying NLP infrastructure across large, federated networks. The focus group approach proved more practical than general-purpose approaches. Key lessons include the challenge of data heterogeneity and importance of collaborative governance. This work also provides a foundation that other networks can build on to implement NLP capabilities for translational research.

Abstract Tisagenlecleucel (tisa-cel) is a CD19-directed chimeric antigen receptor T-cell therapy for relapsed/refractory precursor B-cell acute lymphoblastic leukemia (R/R B-ALL). We report infectious complications for 100 days (D100) following tisa-cel therapy in 471 pediatric and young adults (median age 13.8 years) with R/R B-ALL reported from September 2017 to June 2022. By D100, 137 (29%) patients had an infectious event, with an infection density of 0.542 per 100 person-days at risk. D100 cumulative incidences of bacterial, viral, and fungal infections were 14.1%, 11.6%, and 1.3%, corresponding to infection density scores of 0.296, 0.213, and 0.033 per 100 person-days at risk, respectively. In a multivariable analysis, receipt of ≥3 lines of therapy before tisa-cel (hazard ratio [HR], 1.86; 95% confidence interval [CI], 1.13-3.08; P = .015), any-grade cytokine release syndrome (HR, 1.78; 95% CI, 1.17-2.71; P = .007), and lack of neutrophil recovery (HR, 2.63; 95% CI, 1.47-4.69; P = .001) were associated with an increased risk for any infection. Similar associations were observed for bacterial infections, with the addition of younger age as an adverse risk (<6 vs 6-15 years; HR, 2.38; 95% CI, 1.23-4.61; P = .01). Risk factors for viral infections included increasing age (1-year increase; HR, 1.05; 95% CI, 1.01-1.09; P = .016), prior history of any infection (HR, 2.76, 95% CI, 1.40-5.46; P = .004), and prior hematopoietic cell transplant (HR, 2.10; 95% CI, 1.18-3.71; P = .011). D100 infection-related mortality (IRM) rate was low at 0.2% (95% CI, 0.0-0.8). In this multicenter real-world study, we observed a high incidence of infectious complications but a low IRM following tisa-cel for R/R B-ALL.

SummaryIn individuals with high‐count monoclonal B‐cell lymphocytosis (MBL), we investigated if lymphadenopathy or splenomegaly found by imaging was associated with shorter time to first chronic lymphocytic leukaemia (CLL) therapy (TTFT) and overall survival (OS). Individuals with MBL seen at Mayo Clinic (2002–2019) were retrospectively divided into three cohorts based on imaging studies within 1 year of diagnosis: no imaging studies (Cohort A); imaging with no evidence of lymphadenopathy/splenomegaly (Cohort B); imaging with evidence of lymphadenopathy/splenomegaly (Cohort C). We compared baseline characteristics, TTFT and OS across the MBL cohorts to a cohort of individuals with small lymphocytic lymphoma (SLL). A total of 1078 patients were included: 640 with MBL and 438 with SLL. Compared to Cohort B, individuals in Cohort C were more likely to have unmutated immunoglobulin heavy chain variable region (IGHV) (43% vs. 25% p = 0.016), high‐risk fluorescence in situ hybridization (FISH) (del17p and del11q in 15% vs. 4%, p = 0.038) and higher expression of CD38 (31% vs. 16%; p = 0.011). After adjusting for sex and CLL‐International Prognostic Index (IPI), lymphadenopathy/splenomegaly was associated with a shorter TTFT (hazard ratio [HR] = 2.04, 95% confidence interval [CI]: 1.02–4.04, p = 0.042) but not OS (HR = 1.09, 95% CI: 0.62–1.92, p = 0.775). Lymphadenopathy/splenomegaly on imaging in individuals with high‐count MBL is associated with a more unfavourable risk profile and shorter time to first CLL‐directed therapy.

Abstract Introduction: Radiotherapy (RT)-induced acute esophagitis (AE) is a common side effect in lung cancer patients receiving RT, which can significantly impact their quality of life. This highlights the need for a predictive model that can estimate AE risk in advance using pretreatment imaging data. However, collecting sufficient data for model development is often resource-intensive and costly. Additionally, acquiring a homogeneous training dataset (e.g., from a single center or modality) is not always feasible. This study aimed to develop an automated artificial intelligence-based 3D vision foundation model (VFM) combining standard-of-care planning computed tomography (pCT) and planned radiation dose maps to predict grade II or higher AE. Materials and methods: This study included 246 patients with non-small cell lung cancer who underwent either image-guided radiation treatment (IMRT) or proton-beam radiation therapy. The endpoint was grade two or higher AE (33% positive and 67% negative). The IMRT group consisted of 182 patients from a single center, whereas the proton therapy group included 64 patients from the Proton Collaborative Group trial from 11 different institutions. For each patient, pCT, dose maps, and radiotherapy segmentations were available. The VFM was created using a transformer pretrained using a large number of unlabeled volumetric 3D CTs from patients with varied diseases through a self-supervised learning approach, which extracts useful features directly from images. Next, the pretrained encoder was combined with fully connected classification layers and fine-tuned using stratified 5-fold cross-validation with 20 patients set aside for testing. We developed two models: a CT only and CT + dose model. Model performance was assessed using the area under the curve (AUC), specificity, and sensitivity. Results: In cross-validation, adding dose information to CT (CT+Dose) improved model performance, increasing AUC from 0.72 ± 0.08 to 0.76 ± 0.10 and specificity from 0.82 ± 0.09 to 0.87 ± 0.04, while sensitivity remained the same. On the independent test set, CT+Dose showed a marked improvement over CT only (AUC: 0.82 vs. 0.59; sensitivity: 0.57 vs. 0.14), with a slight decrease in specificity (0.77 vs. 1.00). Conclusion: A VFM model combining CT and radiation dose showed the capability to predict AE more accurately with higher specificity. Further studies on larger cohorts of testing patients are planned to assess model generalization. Citation Format: Chloe Min Seo Choi, Jue Jiang, Nikhil Mankuzhy, John Chang, Jing Zeng, Carlos Vargas, James Urbanic, Isabella Choi, Mark Mcdonald, James Gray, Joseph Deasy, Maria Thor, Charles Simone, Harini Veeraraghavan. Prediction of radiotherapy-Induced esophagitis in non-small cell lung cancer using a 3D vision foundation model [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; 2025 Jul 10-12; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(13_Suppl):Abstract nr B022.

Abstract Aims To assess the performance of an artificial intelligence-enabled electrocardiogram (AI-ECG) algorithm in identifying patients with moderate to severe aortic stenosis (AS) in an Asian cohort from a tertiary care centre. Methods and results We identified a randomly selected patients ≥60 years old who underwent echocardiography and ECG within in 31 days between 2012 and 2021 at the Samsung Medical Center in Korea. Patients with previous cardiac surgery, prosthetic valves, or pacemakers were excluded. The AI-ECG model, originally developed and validated by Mayo Clinic in the USA, was applied without fine-tuning. Performance metrics, including the area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy, were calculated to compare AI-ECG predictions with TTE-confirmed AS status. Among 5425 patients, 1095 had moderate to severe AS, and 4330 age- and sex-matched patients without AS were included as controls. The AI-ECG model achieved an AUC of 0.85 (95% CI: 0.84–0.87) in detecting moderate to severe AS. Sensitivity, specificity, PPV, NPV, and accuracy were 0.83, 0.65, 0.37, 0.94, and 68.29%, respectively. The model's performance was consistent across various age and sex subgroups, with sensitivity increasing in older patients. Conclusion The AI-ECG model developed in the USA demonstrated comparable performance in detecting moderate to severe AS in an Asian cohort compared with its original validation population. These findings highlight the potential utility of AI-ECG as a non-invasive screening tool for AS across diverse patient populations.