Although atrial fibrillation (AF) guidelines indicate that pharmacological blockade of the renin-angiotensin system may be considered for primary AF prevention in hypertensive patients, previous studies have yielded conflicting results. We sought to determine whether randomization to lisinopril reduces incident AF or atrial flutter (AFL) compared with chlorthalidone in a large clinical trial cohort with extended post-trial surveillance. We performed a secondary analysis of the ALLHAT (Antihypertensive and Lipid-Lowering Treatment to Prevent Heart Attack Trial), a randomized, double-blind, active-controlled clinical trial that enrolled hypertensive individuals ≥55 years of age with at least one other cardiovascular risk factor. Participants were randomly assigned to receive amlodipine, lisinopril, or chlorthalidone. Individuals with elevated fasting low-density lipoprotein cholesterol levels were also randomized to pravastatin versus usual care. The primary outcome was the development of either AF or AFL as diagnosed by serial study ECGs or by Medicare claims data. Among 14 837 participants without prevalent AF or AFL, 2514 developed AF/AFL during a mean 7.5±3.2 years of follow-up. Compared with chlorthalidone, randomization to either lisinopril (hazard ratio, 1.04; 95% confidence interval, 0.94-1.15; P=0.46) or amlodipine (hazard ratio, 0.93; 95% confidence interval, 0.84-1.03; P=0.16) was not associated with a significant reduction in incident AF/AFL. Compared with chlorthalidone, treatment with lisinopril is not associated with a meaningful reduction in incident AF or AFL among older adults with a history of hypertension. URL: http://www.clinicaltrials.gov. Unique identifier: NCT00000542.

Background

Prehospital automated large vessel occlusion (LVO) detection in Mobile Stroke Units (MSUs) could accelerate identification and treatment of patients with LVO acute ischemic stroke. Here, we evaluate the performance of a machine learning (ML) model on CT angiograms (CTAs) obtained from 2 MSUs to detect LVO.

Methods

Patients evaluated on MSUs in Houston and Los Angeles with out-of-hospital CTAs were identified. Anterior circulation LVO was defined as an occlusion of the intracranial internal carotid artery, middle cerebral artery (M1 or M2), or anterior cerebral artery vessels and determined by an expert human reader. A ML model to detect LVO was trained and tested on independent data sets consisting of in-hospital CTAs and then tested on MSU CTA images. Model performance was determined using area under the receiver-operator curve statistics.

Results

Among 68 patients with out-of-hospital MSU CTAs, 40% had an LVO. The most common occlusion location was the middle cerebral artery M1 segment (59%), followed by the internal carotid artery (30%), and middle cerebral artery M2 (11%). Median time from last known well to CTA imaging was 88.0 (interquartile range, 59.5-196.0) minutes. After training on 870 in-hospital CTAs, the ML model performed well in identifying LVO in a separate in-hospital data set of 441 images with area under receiver-operator curve of 0.84 (95% CI, 0.80-0.87). ML algorithm analysis time was under 1 minute. The performance of the ML model on the MSU CTA images was comparable with area under receiver-operator curve 0.80 (95% CI, 0.71-0.89). There was no significant difference in performance between the Houston and Los Angeles MSU CTA cohorts.

Conclusions

In this study of patients evaluated on MSUs in 2 cities, a ML algorithm was able to accurately and rapidly detect LVO using prehospital CTA acquisitions.