Risk stratification in symptomatic intracranial atherosclerotic disease with conventional vascular risk factors and cerebral haemodynamics

Angiography‑based quantitative flow ratio for functional assessment of intracranial atherosclerotic disease

BACKGROUND

Intracranial atherosclerotic stenosis (ICAS), an important cause of stroke, is associated with a considerable stroke recurrence rate despite optimal medical treatment. Further assessment of the functional significance of ICAS is urgently needed to enable individualised treatment and, thus, improve patient outcomes.

AIMS

We aimed to evaluate the haemodynamic significance of ICAS using the quantitative flow ratio (QFR) technique and to develop a risk stratification model for ICAS patients.

METHODS

Patients with moderate to severe stenosis of the middle cerebral artery, as shown on angiography, were retrospectively enrolled. For haemodynamic assessment, the Murray law-based QFR (μQFR) was performed on eligible patients. Multivariate logistic regression models composed of μQFR and other risk factors were developed and compared for the identification of symptomatic lesions. Based on the superior model, a nomogram was established and validated by calibration.

RESULTS

Among 412 eligible patients, symptomatic lesions were found in 313 (76.0%) patients. The μQFR outperformed the degree of stenosis in discriminating culprit lesions (area under the curve [AUC]: 0.726 vs 0.631; DeLong test p-value=0.001), and the model incorporating μQFR and conventional risk factors also performed better than that containing conventional risk factors only (AUC: 0.850 vs 0.827; DeLong test p-value=0.034; continuous net reclassification index=0.620, integrated discrimination improvement=0.057; both p<0.001). The final nomogram showed good calibration (p for Hosmer-Lemeshow test=0.102) and discrimination (C-statistic 0.850, 95% confidence interval: 0.812-0.883).

CONCLUSIONS

The μQFR was significantly associated with symptomatic ICAS and outperformed the angiographic stenosis severity. The final nomogram effectively discriminated symptomatic lesions and may provide a useful tool for risk stratification in ICAS patients.

Machine Learning for Onset Prediction of Patients with Intracerebral Hemorrhage

Objective: Intracerebral hemorrhage (ICH) has a high mortality and long-term morbidity and thus has a significant overall health–economic impact. Outcomes are especially poor if the exact onset is unknown, but reliable imaging-based methods for onset estimation have not been established. We hypothesized that onset prediction of patients with ICH using artificial intelligence (AI) may be more accurate than human readers. Material and Methods: A total of 7421 computed tomography (CT) datasets between January 2007–July 2021 from the University Hospital Basel with confirmed ICH were extracted and an ICH-segmentation algorithm as well as two classifiers (one with radiomics, one with convolutional neural networks) for onset estimation were trained. The classifiers were trained based on the gold standard of 644 datasets with a known onset of >1 and <48 h. The results of the classifiers were compared to the ratings of two radiologists. Results: Both the AI-based classifiers and the radiologists had poor discrimination of the known onsets, with a mean absolute error (MAE) of 9.77 h (95% CI (confidence interval) = 8.52–11.03) for the convolutional neural network (CNN), 9.96 h (8.68–11.32) for the radiomics model, 13.38 h (11.21–15.74) for rater 1 and 11.21 h (9.61–12.90) for rater 2, respectively. The results of the CNN and radiomics model were both not significantly different to the mean of the known onsets (p = 0.705 and p = 0.423). Conclusions: In our study, the discriminatory power of AI-based classifiers and human readers for onset estimation of patients with ICH was poor. This indicates that accurate AI-based onset estimation of patients with ICH based only on CT-data may be unlikely to change clinical decision making in the near future. Perhaps multimodal AI-based approaches could improve ICH onset prediction and should be considered in future studies.

Artificial Intelligence in Hypertension Management: An Ace up Your Sleeve

Arterial hypertension (AH) is a progressive issue that grows in importance with the increased average age of the world population. The potential role of artificial intelligence (AI) in its prevention and treatment is firmly recognized. Indeed, AI application allows personalized medicine and tailored treatment for each patient. Specifically, this article reviews the benefits of AI in AH management, pointing out diagnostic and therapeutic improvements without ignoring the limitations of this innovative scientific approach. Consequently, we conducted a detailed search on AI applications in AH: the articles (quantitative and qualitative) reviewed in this paper were obtained by searching journal databases such as PubMed and subject-specific professional websites, including Google Scholar. The search terms included artificial intelligence, artificial neural network, deep learning, machine learning, big data, arterial hypertension, blood pressure, blood pressure measurement, cardiovascular disease, and personalized medicine. Specifically, AI-based systems could help continuously monitor BP using wearable technologies; in particular, BP can be estimated from a photoplethysmograph (PPG) signal obtained from a smartphone or a smartwatch using DL. Furthermore, thanks to ML algorithms, it is possible to identify new hypertension genes for the early diagnosis of AH and the prevention of complications. Moreover, integrating AI with omics-based technologies will lead to the definition of the trajectory of the hypertensive patient and the use of the most appropriate drug. However, AI is not free from technical issues and biases, such as over/underfitting, the "black-box" nature of many ML algorithms, and patient data privacy. In conclusion, AI-based systems will change clinical practice for AH by identifying patient trajectories for new, personalized care plans and predicting patients' risks and necessary therapy adjustments due to changes in disease progression and/or therapy response.

Comparison of thrombosis risk in an abdominal aortic dissection aneurysm with a double false lumen using computational fluid dynamic simulation method

BACKGROUND: Aneurysms are associated with a mortality rate of 81% or more in cases of rupture. OBJECTIVE: To analyse the haemodynamic indices and compare the thrombosis risk in a double false lumen abdominal aortic dissection aneurysm using computational fluid dynamics (CFD). METHODS: Computer tomography angiography (CTA) imaging data were collected from a patient with a double false lumen abdominal aortic dissection aneurysm, and three different lesion morphology aneurysm models were established, double false lumen abdominal aortic dissection aneurysm, single false lumen abdominal aortic dissection aneurysm and saccular abdominal aortic aneurysm, in order to analyse the flow velocity, time-averaged shear stress (TAWSS), oscillatory shear index (OSI), relative residence time (RRT) of blood flow, and endothelial cell activation potential (ECAP). RESULTS: All three aneurysms were in a low-flow state within the body, and the low-flow velocity flow in the proximal vessel wall extended to the right common iliac artery; the vortex intensity was more intense in the abdominal aortic dissection aneurysm than in the saccular abdominal aortic aneurysm. The risk area for thrombosis was concentrated in the expansion part of the aneurysm and the false lumen. The RRT and ECAP maxima of the double false lumen abdominal aortic dissection aneurysm were much greater than those of the single false lumen dissection aneurysm and saccular aortic aneurysm. CONCLUSION: Low-velocity blood flow, high OSI, low TAWSS, high RRT, and high ECAP regions correlate with the risk of thrombosis. The double false lumen type of abdominal aortic dissection aneurysm had some specificity in this case. The risk of thrombosis in the patient was extremely high, and the largest risk zone was within the smaller false lumen, which could be because the smaller false lumen was connected to the true lumen by only one breach. The results of the study provide some guidance in the early screening and development of treatment plans.

Elevated stress hyperglycemia and the presence of intracranial artery stenosis increase the risk of recurrent stroke

BACKGROUND

Stress hyperglycemia has served as a reliable biomarker to predict poor outcomes after ischemic stroke. However, recent studies have reported some contrary conclusions. Different stroke subtypes may respond inconsistently to stress hyperglycemia. The progression of intracranial atherosclerotic stenosis (ICAS) is tightly related to hyperglycemia. Thus, this study aims to determine the relationship between stress hyperglycemia and recurrent stroke in ischemic stroke patients with or without intracranial atherosclerotic stenosis.

METHODS

This is a multicenter retrospective observational cohort study. Patients with acute minor ischemic stroke and eligible computed tomography and magnetic resonance imaging data were enrolled. The severity of stress hyperglycemia is measured by the stress hyperglycemia ratio (SHR). SHR was calculated based on fasting plasma glucose (FPG) and hemoglobin A1c (HbA1c) levels. The primary outcome was stroke recurrence during hospitalization. The interaction of SHR levels with the presence of ICAS on the primary outcome was investigated using univariable and multivariable Cox proportional hazards models. Restricted cubic splines were applied to determine the nonlinear relationship between SHR and primary outcome. A two-piecewise linear regression model was used to identify the threshold of SHR.

RESULTS

A total of 610 participants were included in the study. The average age of the patients was 61.4 ± 12.9 years old, and approximately 70% of participants were males. A total of 189 (30.98%) patients had ICAS. The patients were categorized into 3 groups based on the tertiles of SHR. Compared with the group with a lower SHR, a higher SHR was significantly associated with the risk of stroke recurrence in the ICAS group (hazard ratio [HR], 8.52, 95% confidence interval [CI], 3.16-22.96, P<0.001). When SHR was treated as a continuous variable, each 0.1-unit increase in SHR in the ICAS group was associated with a 1.63-fold increase in the risk of recurrence (HR, 1.63, 95% CI, 1.39-1.9, P<0.001) with a threshold of 0.75. FPG but not HbA1c was associated with stroke recurrence in ICAS patients (HR, 1.17, 95% CI, 1.08-1.26, P<0.001). Sensitive analyses showed consistent results after adjusting for previous diabetes mellitus, oral hypoglycemic agents and insulin injection.

CONCLUSIONS

SHR represents a better biomarker to predict the risk of stroke recurrence in patients with ICAS than FPG and HbA1c regardless of previous diabetes mellitus.

TRIAL REGISTRATION

https://www.chictr.org.cn/showproj.aspx?proj=125817; Identifier, [ChiCTR2100046958].