![histogram maker physics histogram maker physics](https://media.physics.hmc.edu/static/img/one_dev.png)
Model explanation analysis showed that the model relies on clinically valid logic when making predictions. The trained model achieved satisfactory accuracy and can be used by medical physicists in a data-driven quality assurance program as well as by radiation oncologists to support their decision-making process in terms of treatment plan approval and potential plan modifications. The least important feature was ΔD MAX for the left and right cochleae. The SHAP analysis indicated that the ΔD 99% metric for PTV had the greatest influence on the model predictions. Under Input, select the input range (your data), then select. Click Data > Data Analysis > Histogram > OK. On a worksheet, type the input data in one column, and the bin numbers in ascending order in another column. The highest-performing model was Logistic Regression achieving an accuracy of 93.8 ± 4.1% and AUC of 0.98 ± 0.02 on the testing data. Make sure you load the Analysis ToolPakto add the Data Analysis command to the Data tab. The model predictions were explained with Shapely additive explanation (SHAP) interaction values.
![histogram maker physics histogram maker physics](https://www.frontiersin.org/files/Articles/315665/feduc-03-00008-HTML/image_m/feduc-03-00008-g010.jpg)
Each process is represented by a different colour. The 4 processes displayed in Histogram Analyser are H WW, WW, t t and Z. For simply drawing a branch of a TTree (. It is useful to have a good understanding of the physics processes involved when applying cuts. Several models were evaluated using double-nested cross-validation and an area-under-the-curve (AUC) metric, with the highest performing one selected for further investigation. The creation of the TFile and t->Write() seem superfluous for just creating and plotting the histogram. The model aimed to classify the target variable that included class-0 corresponding to plans for which the PTV treatment planning objective was met and class-1 that was associated with plans for which the PTV objective was not met due to the priority trade-off to meet one or more organs-at-risk constraints. Structures considered for analysis included planning target volume (PTV), brainstem, cochleae, and optic chiasm. The ML model was developed based on 79 radiotherapy plans of brain tumor patients that were prescribed a total dose of 60 Gy delivered with volumetric-modulated arc therapy (VMAT). To create and investigate a novel, clinical decision-support system using machine learning (ML).