Abstract: Plan adaptation during the course of (chemo)radiotherapy of H&N cancer requires repeat CT scanning to capture anatomy changes such as parotid gland shrinkage. Hydration, applied to prevent nephrotoxicity from cisplatin, could temporarily alter the hydrogen balance and hence the captured anatomy. The aim of this study was to determine geometric changes of parotid glands as function of hydration during chemoradiotherapy compared to a control group treated with radiotherapy only.
LINK
Background: Modern modeling techniques may potentially provide more accurate predictions of dichotomous outcomes than classical techniques. Objective: In this study, we aimed to examine the predictive performance of eight modeling techniques to predict mortality by frailty. Methods: We performed a longitudinal study with a 7-year follow-up. The sample consisted of 479 Dutch community-dwelling people, aged 75 years and older. Frailty was assessed with the Tilburg Frailty Indicator (TFI), a self-report questionnaire. This questionnaire consists of eight physical, four psychological, and three social frailty components. The municipality of Roosendaal, a city in the Netherlands, provided the mortality dates. We compared modeling techniques, such as support vector machine (SVM), neural network (NN), random forest, and least absolute shrinkage and selection operator, as well as classical techniques, such as logistic regression, two Bayesian networks, and recursive partitioning (RP). The area under the receiver operating characteristic curve (AUROC) indicated the performance of the models. The models were validated using bootstrapping. Results: We found that the NN model had the best validated performance (AUROC=0.812), followed by the SVM model (AUROC=0.705). The other models had validated AUROC values below 0.700. The RP model had the lowest validated AUROC (0.605). The NN model had the highest optimism (0.156). The predictor variable “difficulty in walking” was important for all models. Conclusions: Because of the high optimism of the NN model, we prefer the SVM model for predicting mortality among community-dwelling older people using the TFI, with the addition of “gender” and “age” variables. External validation is a necessary step before applying the prediction models in a new setting.
The building industry is a major target for resource-efficiency developments, which are crucial in European Union’s roadmaps. Using renewable materials impacts the sustainability of buildings and is set as urgent target in current architectural practice. The building industry needs renewable materials positively impacting the CO2 footprint without drawbacks. The use of wood and timber as renewable construction materials has potentials, but also drawbacks because trees need long time to grow; producing timber generates considerable waste; and the process from trees to applications in buildings requires transportation and CO2 emission. This research generates new scientific knowledge and a feasibility study for a new wood-like bio-material - made of cellulose and lignin from (local) residual biomass via i.e. 3D printing - suitable for applications in the building industry. It contributes to a sustainable built environment as it transforms waste from different sectors into a local resource to produce a low carbon-footprint bio-material for the construction sector. Through testing, the project will study the material properties of samples of raw and 3D printed material, correlating different material recipes that combine lignin and cellulose and different 3D printing production parameters. It will map the material properties with the requirements of the construction industry for different building products, indicating potentials and limits of the proposed bio-material. The project will produce new knowledge on the material properties, a preliminary production concept and an overview of potentials and limits for application in the built environment. The outcome will be used by industry to achieve a marketable new bio-material; as well as in further scientific academic research.
