Programpunkter

Electrodermal activity (EDA) reflects sympathetic nervous system activitythrough sweating-related changes in skin conductance. Decomposition analysisis used to deconvolve the EDA into slow and fast varying tonic and phasicactivity, respectively. In this study, we used machine learning models to comparethe performance of two EDA decomposition algorithms to detect emotions such asamusing, boring, relaxing, and scary. The EDA data considered in this study wereobtained from the publicly available Continuously Annotated Signals of Emotion(CASE) dataset. Initially, we pre-processed and deconvolved the EDA data intotonic and phasic components using decomposition methods such as cvxEDA andBayesianEDA. Further, twelve-time domain features were extracted from the phasiccomponent of EDA data. Finally, we applied machine learning techniques suchas logistic regression (LR) and support vector machine (SVM), to evaluate the performanceof the decomposition method. Our results imply that the BayesianEDAdecomposition method outperforms the cvxEDA. The mean of first derivative featurediscriminated all the considered emotional pairs with high statistical significance(p<0.05). SVM was able to detect emotions better than the LR classifier.We achieved a 10-fold average classification accuracy, sensitivity, specificity, precision,and f1-score of 88.2%, 76.25%, 92.08%, 76.16%, and 76.15% respectively,using BayesianEDA and SVM classifier. The proposed framework can be utilizedto detect emotional states for the early diagnosis of psychological conditions.

Predicting Progression of Type 2 Diabetes using Primary Care Data with the Help of Machine Learning

The workshop aims at improving the completeness and interoperability of data dictionaries through harmonization and standardization. First, the focus lies on the syntactic and semantic level in order to derive concrete technical specifications and implementations: Based on a comprehensive review of existing standards and data dictionaries in common systems, frequently used attributes were identified. In a second step, a "Minimal Information Model" is discussed, in which typical description fields are listed, terminologically cleaned and arranged in a modular system to enable easy use and user-specific expansion. Crosswalks to existing vocabularies and conventions or to international standards are to be discussed.Practical mapping of your Data Dicitonary is possible as a practical exercise!

Patient generated health data (PGHD) integrates patients` values and preferences into decision-making. Digitalization enables the integration of PGHD with electronic patient records. However, the lack of digital tools and applications hampers the use of PGHD. The purpose of this workshop is to gather the current situation in research and to form a transdisciplinary network of researchers.Discussion topics:1.Identification of the researchers, research projects and digital tools and applications for PGHD to build a network of researchers in the field.2.Experiences and perceptions of the research and practice regarding the digital tools and applications for PGHD3.Recommendations for future research topics in the field of PGHD.Keywords. digitalization, shared decision making, patient generated health dataYou are warmly welcome!

With more than a decade of supporting its customers in their healthcare data standardization efforts, B2i Healthcare publicly launched the Snowray Terminology Service to a global audience. This demonstration will introduce the most important functionalities to future users. Users are welcome to follow along with a free account.During the demonstration, we will cover the processes of creating and publishing new standard resources, including Code Systems, Value Sets and Concept Maps.

Sharing our experience of mapping the Swiss Personalized Health Network Dataset to Fast Healthcare Interoperability Resources