Sessions

May 21 – 24, 2023
Connect4Health via NordXDataspace at Vitalis
The Connect4Health healthcare connectathon using NordxDataspace aims to promote digital wallets and Solid pods as a data intermediary through a trusted data intermediation service to enable organisations to become part of the European Health Data Space while ensuring data privacy, human-centric use of personal data and digital rights. 

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.

We present a study comparing two mediums that can be used to communicate with allophone patients: a speech-enabled phraselator (BabelDr) and telephone interpreting. 

The automatic de-identification of clinical narrative text offers efficient patient data privacy protection and eases reuse of clinical data. CliniDeID applies an ensemble method combining deep and shallow machine learning with rule-based algorithms and is released as free and open-source solution to de-identify unstructured clinical text with high accuracy. It was recently evaluated with a selection of clinical text corpora and reached high sensitivity and positive predictive value.

Deep learning models for radiology are typically deployed either through cloud-based platforms, through on-premises infrastructures, or though heavyweight viewers. This tends to restrict the audience of deep learning models to radiologists working in state-of-the-art hospitals, which raises concerns about the democratization of deep learning for medical imaging, most notably in the context of research and education. We show that complex deep learning models can be applied directly inside Web browsers, without resorting to any external computation infrastructure, thanks to the use of WebAssembly, and we release our code as free and open-source software. This opens the path to the use of teleradiology solutions as an effective way to distribute, teach, and evaluate deep learning architectures.

Within Nordic cooperation and with funding from the Nordic Council of Ministers, a number of projects are underway as part of the Nordic Vision 2030 goals; The Nordic region will become the most sustainable and integrated region in the world. Some examples of ongoing and completed projects are presented during this session. Integrated Healthcare and care (iHAC) 2021-2024 is run by the Centre for Rural Medicine in Storuman Sweden and the Nordic Welfare centre. The project focuses on the citizen perspective in national and regional models for integrated management of healthcare and social care including the data management. Nordforsk runs the more research-oriented project Nordic Commons with a focus on secondary use of health data for research. Nordic Innovation has additional investments related to health data promotion from an innovation perspective.THL in Finland runs the Finnish presidency project 2021-2023, World's Smoothest Cross-Border Mobility and Daily Life Through Digitalisation with a focus on e-prescriptions and Patient Summary. In 2021, the project published the report Baseline study of cross-border data exchange in the Nordic and Baltic countries. The project is partly a continuation of the project the Swedish E-health authority carried out in the Nordic project Care and care at a distance (VOPD) 2018-2021 with a focus on cross border e-prescriptions and patient summaries.This session can be seen as a brief introduction related to what happens within the Nordic Cooperation related to health data.

This presentation is about an important challenge in change management: how to motivate, move and activate people? Based on her scientific research and extensive consulting experience in healthcare, Marieke tells about the importance of social contagion and informal leadership when changing or transforming healthcare or implementing improvements and innovations. Get inspired and go home with new insights and tips. 

Successful digitalization requires bold and courageous leadership – with extensive skills in change management and fully understanding Return on Investment (ROI) – “bang for the buck”. This lecture will address the challenges to all healthcare leaders in digitalization, with the objective that all decision making must be based on facts to ensure that a change always is an improvement.