ABSTRACT
Purpose: Radiation-induced dermatitis is one of the most common side effects for breast cancer patients treated with radiation therapy (RT). Acute complications can have a considerable impact on tumor control and quality of life for breast cancer patients. In this study, we aimed to develop a novel quantitative high-accuracy machine learning tool for prediction of radiation-induced dermatitis (grade ≥ 2) (RD 2+) before RT by using data encapsulation screening and multi-region dose-gradient-based radiomics techniques, based on the pre-treatment planning computed tomography (CT) images, clinical and dosimetric information of breast cancer patients. Methods and Materials: 214 patients with breast cancer who underwent RT between 2018 and 2021 were retrospectively collected from 3 cancer centers in China. The CT images, as well as the clinical and dosimetric information of patients were retrieved from the medical records. 3 PTV dose related ROIs, including irradiation volume covered by 100%, 105%, and 108% of prescribed dose, combined with 3 skin dose-related ROIs, including irradiation volume covered by 20-Gy, 30-Gy, 40-Gy isodose lines within skin, were contoured for radiomics feature extraction. A total of 4280 radiomics features were extracted from all 6 ROIs. Meanwhile, 29 clinical and dosimetric characteristics were included in the data analysis. A data encapsulation screening algorithm was applied for data cleaning. Multiple-variable logistic regression and 5-fold-cross-validation gradient boosting decision tree (GBDT) were employed for modeling training and validation, which was evaluated by using receiver operating characteristic analysis. Results: The best predictors for symptomatic RD 2+ were the combination of 20 radiomics features, 8 clinical and dosimetric variables, achieving an area under the curve (AUC) of 0.998 [95% CI: 0.996-1.0] and an AUC of 0.911 [95% CI: 0.838-0.983] in the training and validation dataset, respectively, in the 5-fold-cross-validation GBDT model. Meanwhile, the top 12 most important characteristics as well as their corresponding importance measures for RD 2+ prediction in the GBDT machine learning process were identified and calculated. Conclusions: A novel multi-region dose-gradient-based GBDT machine learning framework with a random forest based data encapsulation screening method integrated can achieve a high-accuracy prediction of acute RD 2+ in breast cancer patients.
ABSTRACT
Purpose: Due to the poor ventilation and air stagnation in the radiation therapy ward, it is easy to cause respiratory disease transmission, which brings about the public health safety problem of infection. In order to alleviate this problem, we propose a research method based on computational fluid dynamics (CFD). Method: A three-dimensional model of a radiation therapy ward is established, and the CFD software framework is used to numerically simulate the air flow field in the constrained radiation therapy ward environment. We computed the influence of the spray speed, particle size, and inlet content of respiratory droplets on the flow and spread of multidrug-resistant bacteria. Results: In the range of the horizontal transmission line X from 0 to 3 meters, when the transmission speed (V) is 35 m/s, the multidrug-resistant bacteria concentration reaches the highest value. In the range of the vertical transmission line Y from 0 to 3 meters, when V is 35 m/s, the multidrug-resistant bacteria concentration reaches the highest value. Conclusion: A large amount of data shows that there is a positive correlation between the respiratory droplet spray velocity, inlet content, and the multidrug-resistant bacteria flow propagation speed and concentration distribution. The respiratory droplet size mainly affects the peak concentration of the multidrug-resistant bacteria flow propagation.
Subject(s)
Computers , Hydrodynamics , Bacteria , Computer Simulation , Humans , Particle SizeABSTRACT
BACKGROUND: As one of the important treatments for lung cancer, chemotherapy not only brings hope for the survival of patients, but also influences their body and mind. Most patients have different degrees of fatigue during chemotherapy and after chemotherapy, and the occurrence and aggravation of fatigue do not necessarily occur during hospitalization, there is a lag, mostly occurs in the interval after chemotherapy, therefore, continuous nursing care is very important for patients with lung cancer undergoing chemotherapy. The purpose of this study was to explore the effect of continuous nursing, based on Omaha System theory, on cancer-related fatigue in patients with lung cancer receiving chemotherapy. METHODS: From April 2018 to May 2019, a total of 102 inpatients with lung cancer at a cancer hospital in Hangzhou, China were selected for chemotherapy. A total of 7patients were lost to follow-up during the intervention, leaving 46 and 49 patients randomly assigned to the experimental and control groups, respectively. Participants in the control group received routine nursing after discharge, while those in the experimental group were nursed according to the Omaha System model. RESULTS: After 4 cycles of chemotherapy, scores for total, physical, cognitive, and emotional fatigue were significantly lower in the intervention group than those in the control group (P<0.05). Repeated analysis of variance (ANOVA) showed that there were significant differences in the time-dependent (<0.001) and intervention-dependent (P<0.001) effects on fatigue score, as well as a significant interaction between time and intervention (P<0.001). CONCLUSIONS: Continuous nursing based on Omaha System theory can ameliorate cancer fatigue in patients with lung cancer undergoing chemotherapy.
