Sessions

The MIE conference has always been a hub for innovation and cutting-edge technology. This year was no exception several demonstrators showcase their unique solutions to healthcare problems. Use the opportunity to take a closer look at some of the most striking demonstrators present at the conference, highlighting their diversity and the potential impact they could have on various healthcare-related challenges

Dana Lewis founded the open-source artificial pancreas movement (known as “OpenAPS”), working to make safe and effective automated insulin delivery (AID) technology available (sooner) for people with diabetes around the world for the past 8 years. She authored the book, "Automated Insulin Delivery: How artificial pancreas “closed loop” systems can aid you in living with diabetes", to help more people understand automated insulin delivery systems, in addition to a series of children's books on various health topics. She is now a researcher and her peer-reviewed publications have been cited more than 1,300 times. She has collected numerous types of individual data and conducted research with it, while also working to support communities of patients and medical and academic researchers to harness the power of real-world shared data for improving healthcare.

We benchmark the influence of four types of noise annotated in the public dataset PTB-XL on the accuracy of a Deep Learning-based method for atrial fibrillation detection in 12-lead ECGs. For this we use the noise metadata provided by human experts as well as a quantitative signal-to-noise ratio for assigning a signal quality to each ECG and analyze the respective DL accuracy. We conclude that the issue of processing noisy electrocardiography data can be addressed successfully by Deep Learning methods.

The European Digital Innovation Hub (EDIH) project Health Data Sweden (HDS), initiated in January 2023, aims to support this development by creating a more effective access to services to regarding digitalisation of the health care system both regionally and nationally, through the use of health data. The HDS connects 17 partners from all over Sweden, who currently offer services in health data and related fields such as digital care and e-health, to various target groups and stakeholders. HDS will also connect with other EDIHs throughout Europe, to transfer knowledge and share best practices concerning the use of health data and related fields, in order to improve healthcare on the EU level.In this panel, we will present some of the main challenges and needs in the health data context identified by the partners behind EDIH-HDS, and discuss how the project will address these obstacles. The five main work packages (the focus of WP1 is primarily administrative) will provide the structure for the presentation. In order to engage the audience and stimulate feedback and discussion, the panel will contain interactive elements throughout.

The aim of this presentation and paper is to identify the underlying obstacles and provide recommendations to promote the dissemination of competency-based learning objectives catalogs for curricular development in health data and information sciences.

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.