As the clinical applications of immune checkpoint inhibitors (ICIs) expand, our knowledge of the potential adverse effects of these drugs continues to broaden. Emerging evidence supports the association between ICI therapy with accelerated atherosclerosis and atherosclerotic cardiovascular (CV) events. We discuss the biological plausibility and the clinical evidence supporting an effect of inhibition of these immune checkpoints on atherosclerotic CV disease. Further, we provide a perspective on potential diagnostic and pharmacological strategies to reduce atherosclerotic risk in ICI-treated patients. Our understanding of the pathophysiology of ICI-related atherosclerosis is in its early stages. Further research is needed to identify the mechanisms linking ICI therapy to atherosclerosis, leverage the insight that ICI therapy provides into CV biology, and develop robust approaches to manage the expanding cohort of patients who may be at risk for atherosclerotic CV disease.

Manganese (Mn)‐enhanced MRI (MEMRI) has found a growing number of applications in anatomical and functional imaging in small animals, based on the cellular uptake of Mn ions in the brain, heart, and other organs. Previous studies have relied on endogenous mechanisms of paramagnetic Mn ion uptake and enhancement. To genetically control MEMRI signals, we reverse engineered a major component of the molecular machinery involved in Mn uptake, the divalent metal transporter, DMT1. DMT1 provides positive cellular enhancement in a manner that is highly sensitive and dynamic, allowing greater spatial and temporal resolution for MRI compared to previously proposed MRI reporters such as ferritin. We characterized the MEMRI signal enhancement properties of DMT1‐expressing cells, both in vitro and in vivo in mouse models of cancer and brain development. Our results show that DMT1 provides an effective genetic MRI reporter for a wide range of biological and preclinical imaging applications. Magn Reson Med 70:842–850, 2013.

PURPOSE: Current approaches to accurately identify immune-related adverse events (irAEs) in large retrospective studies are limited. Large language models (LLMs) offer a potential solution to this challenge, given their high performance in natural language comprehension tasks. Therefore, we investigated the use of an LLM to identify irAEs among hospitalized patients, comparing its performance with manual adjudication and International Classification of Disease (ICD) codes. METHODS: Hospital admissions of patients receiving immune checkpoint inhibitor (ICI) therapy at a single institution from February 5, 2011, to September 5, 2023, were individually reviewed and adjudicated for the presence of irAEs. ICD codes and an LLM with retrieval-augmented generation were applied to detect frequent irAEs (ICI-induced colitis, hepatitis, and pneumonitis) and the most fatal irAE (ICI-myocarditis) from electronic health records. The performance between ICD codes and LLM was compared via sensitivity and specificity with an α = .05, relative to the gold standard of manual adjudication. External validation was performed using a data set of hospital admissions from June 1, 2018, to May 31, 2019, from a second institution. RESULTS: Of the 7,555 admissions for patients on ICI therapy in the initial cohort, 2.0% were adjudicated to be due to ICI-colitis, 1.1% ICI-hepatitis, 0.7% ICI-pneumonitis, and 0.8% ICI-myocarditis. The LLM demonstrated higher sensitivity than ICD codes (94.7% v 68.7%), achieving significance for ICI-hepatitis ( P < .001), myocarditis ( P < .001), and pneumonitis ( P = .003) while yielding similar specificities (93.7% v 92.4%). The LLM spent an average of 9.53 seconds/chart in comparison with an estimated 15 minutes for adjudication. In the validation cohort (N = 1,270), the mean LLM sensitivity and specificity were 98.1% and 95.7%, respectively. CONCLUSION: LLMs are a useful tool for the detection of irAEs, outperforming ICD codes in sensitivity and adjudication in efficiency.