The Norwegian Knowledge Centre for the Health Services (NOKC) reports 30-day survival as a quality indicator for Norwegian hospitals. The indicators have been published annually since 2011 on the ...website of the Norwegian Directorate of Health (www.helsenorge.no), as part of the Norwegian Quality Indicator System authorized by the Ministry of Health. Openness regarding calculation of quality indicators is important, as it provides the opportunity to critically review and discuss the method. The purpose of this article is to describe the data collection, data pre-processing, and data analyses, as carried out by NOKC, for the calculation of 30-day risk-adjusted survival probability as a quality indicator.
Three diagnosis-specific 30-day survival indicators (first time acute myocardial infarction (AMI), stroke and hip fracture) are estimated based on all-cause deaths, occurring in-hospital or out-of-hospital, within 30 days counting from the first day of hospitalization. Furthermore, a hospital-wide (i.e. overall) 30-day survival indicator is calculated. Patient administrative data from all Norwegian hospitals and information from the Norwegian Population Register are retrieved annually, and linked to datasets for previous years. The outcome (alive/death within 30 days) is attributed to every hospital by the fraction of time spent in each hospital. A logistic regression followed by a hierarchical Bayesian analysis is used for the estimation of risk-adjusted survival probabilities. A multiple testing procedure with a false discovery rate of 5% is used to identify hospitals, hospital trusts and regional health authorities with significantly higher/lower survival than the reference. In addition, estimated risk-adjusted survival probabilities are published per hospital, hospital trust and regional health authority. The variation in risk-adjusted survival probabilities across hospitals for AMI shows a decreasing trend over time: estimated survival probabilities for AMI in 2011 varied from 80.6% (in the hospital with lowest estimated survival) to 91.7% (in the hospital with highest estimated survival), whereas it ranged from 83.8% to 91.2% in 2013.
Since 2011, several hospitals and hospital trusts have initiated quality improvement projects, and some of the hospitals have improved the survival over these years. Public reporting of survival/mortality indicators are increasingly being used as quality measures of health care systems. Openness regarding the methods used to calculate the indicators are important, as it provides the opportunity of critically reviewing and discussing the methods in the literature. In this way, the methods employed for establishing the indicators may be improved.
Feature selection is an essential step in data science pipelines to reduce the complexity associated with large datasets. While much research on this topic focuses on optimizing predictive ...performance, few studies investigate stability in the context of the feature selection process. In this study, we present the Repeated Elastic Net Technique (RENT) for Feature Selection. RENT uses an ensemble of generalized linear models with elastic net regularization, each trained on distinct subsets of the training data. The feature selection is based on three criteria evaluating the weight distributions of features across all elementary models. This fact leads to the selection of features with high stability that improve the robustness of the final model. Furthermore, unlike established feature selectors, RENT provides valuable information for model interpretation concerning the identification of objects in the data that are difficult to predict during training. In our experiments, we benchmark RENT against six established feature selectors on eight multivariate datasets for binary classification and regression. In the experimental comparison, RENT shows a well-balanced trade-off between predictive performance and stability. Finally, we underline the additional interpretational value of RENT with an exploratory post-hoc analysis of a healthcare dataset.
The powerful combination of analytical chemistry and chemometrics and its application to wine analysis provide a way to gain knowledge and insight into the inherent chemical composition of wine and ...to objectively distinguish between wines. Extensive research programs are focused on the chemical characterization of wine to establish industry benchmarks and authentication systems. The aim of this study was to investigate the volatile composition and mid-infrared spectroscopic profiles of South African young cultivar wines with chemometrics to identify compositional trends and to distinguish between the different cultivars. Data were generated by gas chromatography and FTMIR spectroscopy and investigated by using analysis of variance (ANOVA), principal component analysis (PCA), and linear discriminant analysis (LDA). Significant differences were found in the volatile composition of the cultivar wines, with marked similarities in the composition of Pinotage wines and white wines, specifically for 2-phenylethanol, butyric acid, ethyl acetate, isoamyl acetate, isoamyl alcohol, and isobutyric acid. Of the 26 compounds that were analyzed, 14 had odor activity values of >1. The volatile composition and FTMIR spectra both contributed to the differentiation between the cultivar wines. The best discrimination model between the white wines was based on FTMIR spectra (98.3% correct classification), whereas a combination of spectra and volatile compounds (86.8% correct classification) was best to discriminate between the red wine cultivars.
Radiomics can provide in-depth characterization of cancers for treatment outcome prediction. Conventional radiomics rely on extraction of image features within a pre-defined image region of interest ...(ROI) which are typically fed to a classification algorithm for prediction of a clinical endpoint. Deep learning radiomics allows for a simpler workflow where images can be used directly as input to a convolutional neural network (CNN) with or without a pre-defined ROI.
The purpose of this study was to evaluate (i) conventional radiomics and (ii) deep learning radiomics for predicting overall survival (OS) and disease-free survival (DFS) for patients with head and neck squamous cell carcinoma (HNSCC) using pre-treatment
F-fluorodeoxuglucose positron emission tomography (FDG PET) and computed tomography (CT) images.
FDG PET/CT images and clinical data of patients with HNSCC treated with radio(chemo)therapy at Oslo University Hospital (OUS;
= 139) and Maastricht University Medical Center (MAASTRO;
= 99) were collected retrospectively. OUS data was used for model training and initial evaluation. MAASTRO data was used for external testing to assess cross-institutional generalizability. Models trained on clinical and/or conventional radiomics features, with or without feature selection, were compared to CNNs trained on PET/CT images without or with the gross tumor volume (GTV) included. Model performance was measured using accuracy, area under the receiver operating characteristic curve (AUC), Matthew's correlation coefficient (MCC), and the F1 score calculated for both classes separately.
CNNs trained directly on images achieved the highest performance on external data for both endpoints. Adding both clinical and radiomics features to these image-based models increased performance further. Conventional radiomics including clinical data could achieve competitive performance. However, feature selection on clinical and radiomics data lead to overfitting and poor cross-institutional generalizability. CNNs without tumor and node contours achieved close to on-par performance with CNNs including contours.
High performance and cross-institutional generalizability can be achieved by combining clinical data, radiomics features and medical images together with deep learning models. However, deep learning models trained on images without contours can achieve competitive performance and could see potential use as an initial screening tool for high-risk patients.
Radiotherapy (RT) is increasingly being used on dogs with spontaneous head and neck cancer (HNC), which account for a large percentage of veterinary patients treated with RT. Accurate definition of ...the gross tumor volume (GTV) is a vital part of RT planning, ensuring adequate dose coverage of the tumor while limiting the radiation dose to surrounding tissues. Currently the GTV is contoured manually in medical images, which is a time-consuming and challenging task.
The purpose of this study was to evaluate the applicability of deep learning-based automatic segmentation of the GTV in canine patients with HNC.
Contrast-enhanced computed tomography (CT) images and corresponding manual GTV contours of 36 canine HNC patients and 197 human HNC patients were included. A 3D U-Net convolutional neural network (CNN) was trained to automatically segment the GTV in canine patients using two main approaches: (i) training models from scratch based solely on canine CT images, and (ii) using cross-species transfer learning where models were pretrained on CT images of human patients and then fine-tuned on CT images of canine patients. For the canine patients, automatic segmentations were assessed using the Dice similarity coefficient (
), the positive predictive value, the true positive rate, and surface distance metrics, calculated from a four-fold cross-validation strategy where each fold was used as a validation set and test set once in independent model runs.
CNN models trained from scratch on canine data or by using transfer learning obtained mean test set
scores of 0.55 and 0.52, respectively, indicating acceptable auto-segmentations, similar to the mean
performances reported for CT-based automatic segmentation in human HNC studies. Automatic segmentation of nasal cavity tumors appeared particularly promising, resulting in mean test set
scores of 0.69 for both approaches.
In conclusion, deep learning-based automatic segmentation of the GTV using CNN models based on canine data only or a cross-species transfer learning approach shows promise for future application in RT of canine HNC patients.
Simple graphical techniques can be utilized to investigate the performance of individual assessors and to detect individual differences among assessors in a sensory panel. By visualizing different ...type of information in a set of various plots the panel leader can extract relevant information without the need of extensive knowledge in statistics. The joint information content gained from the plots can then be used as a basis for selective training in order to improve performance of single assessors and the panel as a whole.
Artificial neural networks (ANNs) can be a powerful tool for spectroscopic data analysis. Their ability to detect and model complex relations in the data may lead to outstanding predictive ...capabilities, but the predictions themselves are difficult to interpret due to the lack of understanding of the black box ANN models. ANNs and linear methods can be combined by first fitting a linear model to the data followed by a non-linear fitting of the linear model residuals using an ANN. This paper explores the use of residual modelling in high-dimensional data using modern neural network architectures.
By combining linear- and ANN modelling, we demonstrate that it is possible to achieve both good model performance while retaining interpretations from the linear part of the model. The proposed residual modelling approach is evaluated on four high-dimensional datasets, representing two regression and two classification problems. Additionally, a demonstration of possible interpretation techniques are included for all datasets. The study concludes that if the modelling problem contains sufficiently complex data (i.e., non-linearities), the residual modelling can in fact improve the performance of a linear model and achieve similar performance as pure ANN models while retaining valuable interpretations for a large proportion of the variance accounted for.
The paper presents a residual modelling scheme using modern neural network architectures. Furthermore, two novel extensions of residual modelling for classification tasks are proposed. The study is seen as a step towards explainable AI, with the aim of making data modelling using artificial neural networks more transparent.
Display omitted
•Residual shrinking is developed for both regression and classification problems.•The proposed strategy can improve predictions while retaining interpretability.•This contributes to explainable AI by shrinking the black box of ANNs.