%0 Journal Article
%T Brachytherapy outcome modeling in cervical cancer patients: A predictive machine learning study on patient-specific clinical, physical and dosimetric parameters.
%A Abdalvand N
%A Sadeghi M
%A Mahdavi SR
%A Abdollahi H
%A Qasempour Y
%A Mohammadian F
%A Birgani MJT
%A Hosseini K
%J Brachytherapy
%V 21
%N 6
%D Nov-Dec 2022
%M 35933272
%F 2.441
%R 10.1016/j.brachy.2022.06.007
%X <B>OBJECTIVE: </B>To predict clinical response in locally advanced cervical cancer (LACC) patients by a combination of measures, including clinical and brachytherapy parameters and several machine learning (ML) approaches.<BR><B>METHODS: </B>Brachytherapy features such as insertion approaches, source metrics, dosimetric, and clinical measures were used for modeling. Four different ML approaches, including LASSO, Ridge, support vector machine (SVM), and Random Forest (RF), were applied to extracted measures for model development alone or in combination. Model performance was evaluated using the area under the curve (AUC) of receiver operating characteristics curve, sensitivity, specificity, and accuracy. Our results were compared with a reference model developed by simple logistic regression applied to three distinct clinical features identified by previous papers.<BR><B>RESULTS: </B>One hundred eleven LACC patients were included. Nine data sets were obtained based on the features, and 36 predictive models were built. In terms of AUC, the model developed using RF applied to dosimetric, physical, and total BT sessions features were found as the most predictive [AUC; 0.82 (0.95 confidence interval (CI); 0.79 -0.93), sensitivity; 0.79, specificity; 0.76, and accuracy; 0.77]. The AUC (0.95 CI), sensitivity, specificity, and accuracy for the reference model were found as 0.56 (0.52 ...0.68), 0.51, 0.51, and 0.48, respectively. Most RF models had significantly better performance than the reference model (Bonferroni corrected p-value < 0.0014).<BR><B>CONCLUSIONS: </B>Brachytherapy response can be predicted using dosimetric and physical parameters extracted from treatment parameters. Machine learning algorithms, including Random Forest, could play a critical role in such predictive modeling.