| Summary: | 碩士 === 國立高雄科技大學 === 電子工程系 === 107 === Purpose : To assess the dose-volume factors analysis of radiation - induced hepatic toxicity (RIHT) in patients with hepatocellular carcinoma (HCC) after radiotherapy.
Materials and methods : The study is retrospectively collected between 2014 and 2017, 114 patients with HCC underwent intensity modulation radiation therapy (IMRT). Of those, liver dose - volume receiving of less than 700 cc and extreme value excluded with remain only 69 patients and to use the bootstrapping of reached 138 samples. Assess blood draw rises level during the course of the patient's treatment RIHT was scored using the Common Terminology Criteria for Adverse Events (CTCAE). The predictor's analysis, we use patient’s dose - volume factors the may cause RIHT, And two kinds of selection algorithm by least absolute shrinkage and selection operator (LASSO), bayesian network (BN) to select the risk predictors. Furthermore, the classification models of the selected risk predictors, all risk predictors were established two kinds of algorithms by logistic regression (LR), naive bayes (NB). Finally, uses the area under the receiver operating characteristic curve (AUC), accuracy (ACC) and negative predictive value (NPV) was compared.
Results : The patients predicted risk dose-volume factors of classification models with AUC, ACC and NPV. First, LASSO select on LR models：normal liver volume receiving 30 Gy (NLV30), 0.76, 0.65, 0.72. Second LASSO select on LR models：total liver volume receiving 30 Gy (TLV30), 0.84, 0.72, 0.72. Third BN select on NB models：total liver volume receiving 45 & 20 Gy (TLV45&20), 0.72, 0.76, 0.73.
Conclusions : The results of this study showed should be limited to the NLV30 Gy, TLV30 Gy, TLV20 Gy as risk predictors of RIHT after IMRT for unresectable HCC, and could reach liver organ with low tolerance for radiation. The advantage of selection factors can be provided to physicians for better decision-making.
|
|---|
