Development of Machine Learning Model for Selecting the 1st Coil in the Treatment of Cerebral Aneurysms by Coil Embolization.

ABSTRACT

To achieve good treatment outcomes in coil embolization for cerebral aneurysms, it is important to select an appropriate 1st coil for each aneurysm since it serves as a frame to support the subsequent coils to be deployed. However, its selection as appropriate size and length from a wide variety of lineups is not easy, especially for inexperienced neurosurgeons. We developed a machine learning model (MLM) to predict the optimal size and length of the 1st coil by learning information on patients and aneurysms that were previously treated with coil embolization successfully. The accuracy rates of the MLM for the test data were 86.3% and 83.4% in the prediction of size and length, respectively. In addition, the accuracy rates for the 30 cases showed good prediction by the MLM when compared with two different skilled neurosurgeons. Although the accuracy rate of the well-experienced neurosurgeon is similar to MLM, the inexperienced neurosurgeon showed a worse rate and can benefit from the method.Clinical Relevance- The developed MLM has the potential to assist in the selection of the 1st coil for aneurysms. A technically and cost efficient supply chain in the treatment of aneurysms may also be achieved by MLM application.