Back

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

Margaryan, R.; Della Latta, D.; Bianchi, G.; Martini, N.; Gori, A.; Ripoli, A.; Solinas, M.

2020-12-07 cardiovascular medicine
10.1101/2020.12.05.20243964 medRxiv
Show abstract

ObjectivesDouble (bilateral) mammary artery in situ revascularization seems less attractive to surgeons because of limited mammary length of right mammary artery, scare, or no means of its length estimation. MethodsWeve selected patients who have used bilateral mammary artery for revascularization and divvied them into two groups: in situ and y-graft groups. We have used preoperative chest x-rays to build a predictive model with neural networks that could predict feasibility of in situ bilateral mammary revascularization. ResultsThe predictive model was able to predict a positive outcome with 96% 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. ConclusionsChest x-ray base model can accurately predict the feasibility of in situ bilateral mammary artery revascularization.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.