Artificial intelligence measuring the aortic diameter assist in identifying adverse blood pressure status including masked hypertension

Wang, Yaolin; Bai, Lijuan; Yang, Jinrong; Lu, Yichen; Fan, Wenliang; Nie, Zhuang; Yu, Jie; Wen, Kai; Wang, Ruiyun; He, Linfeng; Yang, Fan; B, Qi

doi:10.1080/00325481.2021.2003150

Cited by 8 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We further identified, indexed aorta volume to be an independent multivariate predictor for each of the arterial hemodynamic variables examined (i.e., PWV, systolic, diastolic, and pulse BP), contrary to FDG-PET and clinical variables, and to outperform the prediction provided by age for systolic BP, a key indicator of cardiovascular risk (Flint et al 2019 ). This strong association between indexed aorta volume and systolic-BP may be explained by the wall stress variations induced by systolic BP which impacts the lumen of the thoracic aorta in the short term (i.e., the systolic BP-aorta diameter association) (Stefanadis et al 1995 ; Toutouzas et al 2000 ), but also in the longer term, as previously shown in populations of patients with hypertension (Cesareo et al 2021 ; Wang et al 2022 ; Tadic et al 2022 ) or various cardiovascular risk factors (Chen et al 2022 ), and Marfan syndrome (Brooke et al 2008 ).…”

Section: Discussionmentioning

confidence: 52%

Volume of the proximal half of the thoracic aorta is the most comprehensive FDG-PET/CT indicator of arterial aging throughout adulthood

Hurstel

Joly

Imbert

et al. 2023

European J Hybrid Imaging

View full text Add to dashboard Cite

Introduction 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) and computed tomography (CT) features of the proximal and more elastic half of the thoracic aorta are known to correlate with aorta stiffness in older populations. This prospective study aimed to analyze the changes in these FDG-PET/CT features between young, middle-aged, and older adults, and investigate associations with arterial stiffness and blood pressure (BP). Methods Young (< 40 years), middle-aged (40-to-60 years), and older (> 60 years) adults, who underwent an FDG-PET/CT, were prospectively recruited. FDG-PET/CT features of the proximal half of the thoracic aorta were analyzed relative to the age categories, BP and carotid-femoral pulse wave velocity (PWV), a reference indicator of aorta stiffness. Results We included 79 patients (38 women; 22 young, 19 middle-aged, and 38 older adults). An increase in age category was associated with increases in mean standardized uptake values (SUVs) of blood and aorta and most significantly in aorta SUV heterogeneity, represented by SUV standard deviation (SUV-SD), aorta calcification volume, and the aorta volume indexed to body surface area. However, this indexed aorta volume was the sole variable: (i) exhibiting a stepwise increase from young (median: 25 cm3/m2 [interquartile range: 20–28 cm3/m2]), to middle-aged (41 [30–48] cm3/m2, p < 0.001 vs. Young), and older (62 [44–70] cm3/m2, p < 0.001 vs. middle-age) adults, and (ii) selected in the multivariate predictions of systolic, diastolic, and pulse BP. Indexed aorta volume was also a multivariate predictor of PWV but in association with SUV-SD and hypertension. Conclusion In a population of patients referred to an FDG-PET/CT investigation, the indexed volume of the proximal and more elastic half of the thoracic aorta is the most comprehensive indicator of arterial aging. This imaging parameter exhibits a stepwise increase from young to middle-aged and older adults, is strongly linked to inter-individual changes in both arterial stiffness and BP, and thus, could help assess the early phases of arterial aging. Trial registration ClinicalTrial.gov, NCT03345290. Registered 17 November 2017, https://clinicaltrials.gov/ct2/show/NCT03345290?term=NCT03345290&draw=2&rank=1

show abstract

Section: Discussionmentioning

confidence: 52%

Volume of the proximal half of the thoracic aorta is the most comprehensive FDG-PET/CT indicator of arterial aging throughout adulthood

Hurstel

Joly

Imbert

et al. 2023

European J Hybrid Imaging

View full text Add to dashboard Cite

show abstract

“…[37] In echocardiography, we found that the AAOD of MH/ MUCH patients was larger. Wang et al [38] used a machine learning approach to perform automatic aorta measurement in thoracic CT images at nine key positions of 801 patients to predict MH. Better results were also finally obtained (AUC = 0.78).…”

Section: Discussionmentioning

confidence: 99%

Nomogram based on clinical features at a single outpatient visit to predict masked hypertension and masked uncontrolled hypertension: A study of diagnostic accuracy

et al. 2022

View full text Add to dashboard Cite

Patients with masked hypertension (MH) and masked uncontrolled hypertension (MUCH) are easily overlooked, and both cause target organ damage. We propose a prediction model for MH and MUCH patients based on clinical features at a single outpatient visit. Data collection was planned before the index test and reference standard were after. Thus, we retrospectively collect analyzed 804 subjects who underwent ambulatory blood pressure monitoring (ABPM) at Renmin Hospital of Wuhan University. These patients were divided into normotension/controlled hypertension group (n = 121), MH/MUCH (n = 347), and sustained hypertension (SH)/sustained uncontrolled hypertension group (SUCH) (n = 302) for baseline characteristic analysis. Models were constructed by logistic regression, a nomogram was visualized, and internal validation by bootstrapping. All groups were performed according to the definition proposed by the Chinese Hypertension Association. Compared with normotension/controlled hypertension, patients with MH/MUCH had higher office blood pressure (BP) and were more likely to have poor liver and kidney function, metabolic disorder and myocardial damage. By analysis, [office systolic blood pressure (OSBP)] (P = .004) and [office diastolic blood pressure (ODBP)] (P = .007) were independent predictors of MH and MUCH. By logistic regression backward stepping method, office BP, body mass index (BMI), total cholesterol (Tch), high-density lipoprotein cholesterol (HDL-C), and left ventricular mass index are contained in this model [area under curve (AUC) = 0.755] and its mean absolute error is 0.015. Therefore, the prediction model established by the clinical characteristics or relevant data obtained from a single outpatient clinic can accurately predict MH and MUCH.

show abstract

Segment aorta and localize landmarks simultaneously on noncontrast CT using a multitask learning framework for patients without severe vascular disease

Yang

Cheng

et al. 2023

Computers in Biology and Medicine

View full text Add to dashboard Cite

Artificial intelligence measuring the aortic diameter assist in identifying adverse blood pressure status including masked hypertension

Cited by 8 publications

References 24 publications

Volume of the proximal half of the thoracic aorta is the most comprehensive FDG-PET/CT indicator of arterial aging throughout adulthood

Volume of the proximal half of the thoracic aorta is the most comprehensive FDG-PET/CT indicator of arterial aging throughout adulthood

Nomogram based on clinical features at a single outpatient visit to predict masked hypertension and masked uncontrolled hypertension: A study of diagnostic accuracy

Segment aorta and localize landmarks simultaneously on noncontrast CT using a multitask learning framework for patients without severe vascular disease

Contact Info

Product

Resources

About