Abstract

Screening and diagnosing abdominal aortic aneurysms (AAA) are currently dependent on imaging studies such as ultrasound or computed tomography angiography. All imaging studies offer distinct advantages but also suffer from inherent limitations such as examiner dependency or ionizing radiation. Bioelectrical impedance analysis has previously been investigated with respect to its use in the detection of several cardiovascular and renal pathologies. The present pilot study assessed the feasibility of AAA detection based on bioimpedance analysis. In this single-center exploratory pilot study, measurements were conducted among 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 train four different machine learning models on a randomized training sample (80% of the full dataset). Each model was then evaluated on a test set (20% of the full dataset). 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 for classification when applied to the test sample. Additionally, an exploratory analysis to approximate the maximum AAA diameter was conducted. An association analysis revealed several impedance parameters that might possess predictive ability with respect to aneurysm size. AAA detection via bioelectrical impedance analysis is technically feasible and appears to be a promising technology for large-scale clinical studies and routine clinical screening assessments.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.