Speaker
Description
Clinical decision-support systems (CDSS) can support experts’ decision-making by exploiting big data. For example, a classification integrated into the CDSS can provide a statistical proposition of which hearing device a patient would benefit from; or data-driven, unsupervised approaches can characterize patient groups available in the data, showing different profiles of audiological test outcome combinations and different prevalence. The main challenge is to base such a CDSS on international, really “big data”, since local clinical-audiological databases comprise different audiological tests and test conditions, data structure and formats, expert knowledge, or patient populations.Latent variable approaches help deal with these differences by transforming and summarizing diverse input data into a common, harmonized representation that can be derived by experts, machine learning, or auditory models. This presentation focuses on the comparability of speech test data across languages, speech material complexity (words, sentences), and conditions (in quiet, in noise). Results from a model-based approach applied to different international datasets will be discussed. In the future, the proposed approach can be used to transform between different speech tests, to enable combined analysis of various datasets from research and clinics.