Empolis (Germany)

Objectives: Studies evaluating machine learning (ML) algorithms on cross-lingual RadLex® mappings for developing context-sensitive radiological reporting tools are lacking. Therefore, we investigated whether ML-based approaches can be utilized to assist radiologists in providing key imaging biomarkers – such as The Alberta stroke programme early CT score (APECTS). Material and Methods: A stratified random sample (age, gender, year) of CT reports (n=206) with suspected ischemic stroke was generated out of 3997 reports signed off between 2015-2019. Three independent, blinded readers assessed these reports and manually annotated clinico-radiologically relevant key features. The primary outcome was whether ASPECTS should have been provided (yes/no: 154/52). For all reports, both the findings and impressions underwent cross-lingual (German to English) RadLex®-mappings using natural language processing. Well-established ML-algorithms including classification trees, random forests, elastic net, support vector machines (SVMs) and boosted trees were evaluated in a 5 x 5-fold nested cross-validation framework. Further, a linear classifier (fastText) was directly fitted on the German reports. Ensemble learning was used to provide robust importance rankings of these ML-algorithms. Performance was evaluated using derivates of the confusion matrix and metrics of calibration including AUC, brier score and log loss as well as visually by calibration plots. Results: On this imbalanced classification task SVMs showed the highest accuracies both on human-extracted- (87%) and fully automated RadLex® features (findings: 82.5%; impressions: 85.4%). FastText without pre-trained language model showed the highest accuracy (89.3%) and AUC (92%) on the impressions. Ensemble learner revealed that boosted trees, fastText and SVMs are the most important ML-classifiers. Boosted trees fitted on the findings showed the best overall calibration curve. Conclusions: Contextual ML-based assistance suggesting ASPECTS while reporting neuroradiological emergencies is feasible, even if ML-models are restricted to be developed on limited and highly imbalanced data sets.

Abstract“Data is a burden, knowledge is an asset.” Operators and manufacturers of complex equipment often collect data about the equipment they maintain: technical follow-up files, breakdown files, intervention reports, preventive maintenance reports, and records of requests from their clients or distributors. Unfortunately, this information is usually not well exploited. This is due both to the complexity of the equipment itself and to the type of technicians who carry out the maintenance processes. In this chapter, we explore a recipe for this category of problems, with a specific case structure and modeling approach, as well as typical problems for linking the developed maintenance system to both on-board equipment and technical information.KeywordsCase BaseFault TreeModel HierarchyMarine Diesel EngineTypical PieceThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

In this chapter, the basic concepts and, in particular, the terminology of software process modeling are introduced at a level of detail that is sufficient for potential users of the INRECA methodology. The basic terms that were first mentioned in the previous chapter are now explained more precisely.