Evaluating and predicting the Efficiency Index for Stereotactic Radiosurgery Plans using RapidMiner GO(JAVA) Based Artificial Intelligence Algorithms

TL;DR

This study evaluates machine learning algorithms within RapidMiner GO to predict the Efficiency Index for SRS plans, finding that the Generalized Linear Regression model offers high accuracy and speed, aiding treatment plan quality assurance.

Contribution

It compares multiple machine learning algorithms for predicting the Efficiency Index in SRS, identifying the most effective model for clinical application.

Findings

GLR achieved 0.974 squared correlation with RMSE of 0.01.

All models performed well with RMSE between 0.01 and 0.021.

GLR was the fastest and most accurate model for EI prediction.

Abstract

Evaluation the prediction of Efficiency index by DVH parameter for SRS treatment plans using Supervised Machine learning and the performance of predictive model algorithms of RapidMiner GO in the parameter prediction are investigated. Dose volume histogram (DVH) based Efficiency index was calculated for 100 clinical SRS plans generated by Leksell Gamma plan, and the results were compared to predicted values produced by machine learning toolbox of RapidMiner Go, algorithms are namely, Generalized linear model (GLR), Decision Tree Model, Support Vector Machine (SVM), Gradient Boosted Trees (GBT), Random Forest (RF) and Deep learning Model (DL). Root mean square error (RMSE), Average absolute error, Absolute relative error, squared correlation and model building time were determined to evaluate the performance of each algorithm. The GLR algorithm model had square correlation of 0.974 with the smallest RMSE of 0.01, relatively high prediction speed, and fast model building time with 2.812 s, according to the results. The RMSE values for all models were between 0.01 upto 0.021, all algorithms performed well. The RMSE of the Gradient Boosted Tree, Random Forest, and Decision Tree regression algorithms was found to be greater than 0.01, suggesting that they are not appropriate for predicting EI in this analysis. RapidMiner GO machine learning models can be used to predict DVH parameters like EI in SRS treatment planning QA. To effectively evaluate the parameter, it is necessary to choose a suitable machine learning algorithm.