Rxivist logo

Double Mammary In Situ: Predicting Feasibility of Right Mammary Artery In Situ for Circumflex Coronary Artery System

By Rafik Margaryan, Daniele Della Latta, Giacomo Bianchi, Nicola Martini, Andrea Gori, Andrea Ripoli, Marco Solinas

Posted 07 Dec 2020
medRxiv DOI: 10.1101/2020.12.05.20243964

Arterial revascularization of the myocardium is well established and it is the gold standard. Double mammary artery in situ revascularisation seems less attractive to surgeons because of limited mammary length, scare, or no means of its length estimation. Here we hypothesized that the right mammary artery length is relative to chest anatomy, mainly to its type. We sought to estimate the feasibility, hence the mammary artery length using machine learning (neural networks). The predictive model was able to predict a positive outcome with 95% percent accuracy. (p < 0.01). Models' sensitivity and specificity were 96% and 95% respectively. Neural networks can be used to predict double mammary feasibility using chest x-rays. Model is capable of predicting positive outcomes with 95% accuracy.

Download data

  • Downloaded 116 times
  • Download rankings, all-time:
    • Site-wide: 141,182
    • In cardiovascular medicine: 439
  • Year to date:
    • Site-wide: 112,466
  • Since beginning of last month:
    • Site-wide: 76,154

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide