Two-Dimensional Aortic Size Normalcy: A Novelty Detection Approach

Abstract

Background: To develop a tool for assessing normalcy of the thoracic aorta (TA) by echocardiography, based on either a linear regression model (Z-score), or a machine learning technique, namely one-class support vector machine (OC-SVM) (Q-score). Methods: TA diameters were measured in 1112 prospectively enrolled healthy subjects, aging 5 to 89 years. Considering sex, age and body surface area we developed two calculators based on the traditional Z-score and the novel Q-score. The calculators were compared in 198 adults with TA > 40 mm, and in 466 patients affected by either Marfan syndrome or bicuspid aortic valve (BAV). Results: Q-score attained a better Area Under the Curve (0.989; 95% CI 0.984–0.993, sensitivity = 97.5%, specificity = 95.4%) than Z-score (0.955; 95% CI 0.942–0.967, sensitivity = 81.3%, specificity = 93.3%; p < 0.0001) in patients with TA > 40 mm. The prevalence of TA dilatation in Marfan and BAV patients was higher as Z-score > 2 than as Q-score < 4% (73.4% vs. 50.09%, p < 0.00001). Conclusions: Q-score is a novel tool for assessing TA normalcy based on a model requiring less assumptions about the distribution of the relevant variables. Notably, diameters do not need to depend linearly on anthropometric measurements. Additionally, Q-score can capture the joint distribution of these variables with all four diameters simultaneously, thus accounting for the overall aortic shape. This approach results in a lower rate of predicted TA abnormalcy in patients at risk of TA aneurysm. Further prognostic studies will be necessary for assessing the relative effectiveness of Q-score versus Z-score.

Aortic Dilatation in Pediatric Patients with Bicuspid Aortic Valve: How the Choice of Nomograms May Change Prevalence

“…Two-dimensional (2D) echocardiographic measurements of the aortic root were performed from the parasternal long-axis view at 4 different levels perpendicular of the long axis of aorta: the aortic annulus, measured in end-systole using the inner-to-inner technique at the hinge points of the leaflets and the sinuses of Valsalva, the sinotubular junction, and the ascending aorta, which are measured in end-diastole using the leading-edge to leading-edge technique [ 14 ]. A conventional pediatric Z-score and the new Q-score (based on a machine-learning algorithm that uses a vector representing age, sex, BSA, and single or all 4 aortic diameters, thus obtaining a regional Q-score or a global Q-score, respectively) were then applied and compared [ 8 , 10 ]. Since the Q-score is a continuous quantity expressing percentiles, pathological Q-score values were assumed when < 2% [ 10 ].…”

“…A conventional pediatric Z-score and the new Q-score (based on a machine-learning algorithm that uses a vector representing age, sex, BSA, and single or all 4 aortic diameters, thus obtaining a regional Q-score or a global Q-score, respectively) were then applied and compared [ 8 , 10 ]. Since the Q-score is a continuous quantity expressing percentiles, pathological Q-score values were assumed when < 2% [ 10 ].…”

“…Recently, a new tool for aortic normalcy at the 4levels (aortic annulus, sinus of Valsalva, sinotubular junction, and proximal ascending aorta), the Q-score, has been developed in a large healthy population including > 250 children and adolescents older than 5 years [ 10 ]. The Q-score is based on a machine-learning algorithm and diameters do not depend linearly on anthropometric measurements.…”

Bicuspid Aortic Valve in Children and Adolescents: A Comprehensive Review

“…Recently, a new tool based on a machine learning algorithm (Q score) has been proposed for assessing normalcy of the thoracic aorta [ 27 ]. The Q score was developed on a cohort of healthy subjects comprising a subgroup of children aged > 5 years.…”

“…Recently, a new tool based on a machine learning algorithm (Q score) h posed for assessing normalcy of the thoracic aorta [27]. The Q score was dev cohort of healthy subjects comprising a subgroup of children aged > 5 yea score potentially provides a more comprehensive evaluation of aortic geomet over-diagnosis of 'aortopathy', which may have negative consequences in term of life, especially in adolescents.…”