Improved Strabotomy Surgical Decision Model with Experts Neural Networks

The ensemble method called Mixture of Experts, based on the Divide-and-Conquer principle was proposed to model a new Strabotomy Surgical Decision system, in which an extra gating component is used to compute weights dynamically according to the inputs. The aim is to develop a new operation quantity planning decision model (OQPDM) to predict the corrective quantity of lateral and medial rectus in strabotomy to instruct practice. The corrective rate of strabotomy from OQPDM (98.4%) is better than past experience (81.6%) and shows effective prediction. improved OQPDM can offer robustness for potential application in other clinical decision support system, which can develop a system for minisized instrument of eye checking and operation planning.