Arooshi Kumar, MD
@ArooshiK

Bathla G, Liu Y, Zhang H, Sonka M, Derdeyn C. Computed Tomography Perfusion–Based Prediction of Core Infarct and Tissue at Risk: Can Artificial Intelligence Help Reduce Radiation Exposure? Stroke. 2021;52:e755–e759.

It is well accepted that advanced CT perfusion (CTP) technology can help select patients who could benefit from endovascular treatment (EVT).¹ However, CTP imaging is arterial input dependent, requires higher radiation than CT angiography, and utilizes timely and costly post-processing software.^2,3 Authors Bathla et al. in this study explored if a machine learning algorithm, a convolutional neural network, which establishes complex relationships between many layers of visual imagery, could estimate cerebral blood flow and area-at-risk similar to the standard arterial dependent prediction method (RAPID).

Retrospective CTP data from 57 patients was split into training/validation (60%/40%) sets. The authors devised and validated separate U-net models, allowing for imaging segmentation, to predict core infarct (CBF) and tissue at risk (Tmax). Once trained, the full sets of 28 input images were sequentially reduced to equitemporal 14, 10, and 7 time points (tp) to further investigate if suboptimal arterial capture could be overcome by this predictive algorithm. The averaged structural similarity index measure (SSIM), a measure of similarity between two images, between the model-derived images and true perfusion maps was compared. For reference, the higher the SSIM, the better the reconstruction technique.

Kevin O’Connor, MD

Bhat A, Mahajan V, Chen HHL, Gan GCH, Pontes-Neto OM, Tan TC. Embolic Stroke of Undetermined Source: Approaches in Risk Stratification for Cardioembolism. Stroke. 2021;52:e820-e836.

Embolic strokes of undetermined source (ESUS) account for about a fifth of all ischemic strokes and comprise pathologies including cardioembolic sources, undiagnosed malignancy, and arteriogenic emboli. There is no single strategy for investigating suspected cardioembolic strokes, and initiating empiric anticoagulation for these patients may result in more harm than benefit.

Cardiac monitoring — whether implanted or external — is an important part of a cardioembolic workup, but the ideal timeframe for monitoring is unclear. In the CRYSTAL AF trial, the median time for atrial fibrillation (AF) detection via implanted cardiac monitor (ICM) was 8.4 months. A meta-analysis of ICM use in patients monitored for AF reported detection rates of 5% for <6 months, 26% for 12-24 months, and 34% for >24 months of monitoring. Although prolonged monitoring appears beneficial, the utility may be limited by patient adherence, accurate interpretation of captured rhythms, and patient cost.

Wern Yew Ding, MBChB

Kuck KH, Lebedev DS, Mikhaylov EN, Romanov A, Gellér L, Kalējs O, Neumann T, Davtyan K, On YK, Popov S, et al. Catheter ablation or medical therapy to delay progression of atrial fibrillation: the randomized controlled atrial fibrillation progression trial (ATTEST). Europace. 2021;23:362-369.

Atrial fibrillation (AF) is closely linked to atrial cardiomyopathy and associated with structural and electrical remodelling that develops as the condition progresses. Currently, AF is classified based on a crude assessment of the estimated duration of each episode. Progression of AF is often signalled by an increase in AF burden, which is related to poorer outcomes, including excess thromboembolism. Therefore, halting (or even reversing) AF progression is of clinical importance.

In this study by Kuck and colleagues, the authors investigated whether catheter AF ablation could delay the progression of AF compared with drug therapy. To this end, they performed a study among patients aged equal or over 60 years old with symptomatic paroxysmal AF who were randomized to either radio frequency catheter ablation (RFCA) or anti-arrhythmic drug (AAD) therapy. The study was terminated prematurely due to slow enrolment; at the time of termination, 255 (79%) of the planned 322 patients were enrolled. Over a follow-up period of 3 years, the primary endpoint for the rate of persistent AF or atrial tachycardia was significantly lower with RFCA compared to AAD therapy (2.4% vs. 17.5%). The rate of any recurrent AF or atrial tachycardia was also significantly lower with RFCA over AAD therapy (49.2% vs. 84.8%). Serious adverse events occurred in 12 (11.8%) patients in the radiofrequency ablation arm.

Dixon Yang, MD

Horn JW, Feng T, Mørkedal B, Strand LB, Horn J, Mukamal K, Janzsky I. Obesity and Risk for First Ischemic Stroke Depends on Metabolic Syndrome: The HUNT Study. Stroke. 2021;52:3555–3561.

Obesity is thought to be an important modifiable risk factor for ischemic stroke, especially given its high prevalence in certain European countries and the United States. However, obesity relationship to ischemic stroke may be more complex as there is still uncertainty on whether obesity itself or metabolic consequences of obesity are drivers of stroke risk. Horn et al. sought to assess the long-term association of weight, metabolic health, and ischemic stroke risk in the HUNT study (Trøndelag Health Study), a large prospective population-based cohort investigation based in Norway.

The present analysis included 35105 participants from HUNT who were free of stroke at baseline and had complete information on demographics, metabolic risk factors, and relevant covariates. Body weight categories were determined by standard body-mass index (BMI) thresholds (normal weight: 18.5 to <25 kg/m², overweight: 25 to 29.9 kg/m², obese: ≥30 kg/m²). The authors used a modified definition of metabolic syndrome from the International Diabetes Federation. Metabolically unhealthy was defined as the presence of increased waist circumference (WC) (≥102 cm in men, ≥88 cm in women) and 2 or more of the following: increased non-fasting triglycerides (≥1.7 mmol/L), decreased high-density lipoprotein (<1.03 mmol/L in men, <1.29 mmol/L in women), increased blood pressure (≥130/85 mmHg) or use of blood pressure medication, increased non-fasting glucose (≥11.1 mmol/L), or diabetes diagnosis. Outcomes were stroke diagnosis based on ICD codes in administrative hospital system data.