Detection of Abdominal Aortic Aneurysms via Bioelectrical Impedance Analysis – a pilot study

Abstract

Objective: To assess the feasibility of abdominal aortic aneurysm (AAA) detection based on parameters obtained from segmental bioimpedance measurements. Design: Pilot study Methods: In this single center exploratory pilot study, measurements were conducted in three different cohorts: patients with AAA, end stage renal disease patients without AAA, and healthy controls. The device used in the study, CombynECG, is an open market accessible device for segmental bioelectrical impedance analysis. The data was preprocessed and used to establish 4 different machine learning models on a randomized training sample. Each model was then evaluated on a test sample. Results: The total sample included 22 patients with AAA, 16 chronic kidney disease patients, and 23 healthy controls. All four models showed strong predictive performance in the test partitions. Specificity ranged from 71.4 to 100 %, while sensitivity ranged from 66.7 to 100 %. The best performing model had 100% accuracy during classification on a test sample. Additionally, an exploratory analysis to approximate the maximum AAA diameter was conducted. An association analysis revealed potential variables that might hold predictive ability for aneurysm extent. Conclusion: AAA detection via bioelectrical impedance analysis is technically feasible and appears to be a promising technology for large scale clinical studies as well as routine clinical screening assessment.