Programpunkter

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.

Digital healthcare technologies (DTHs), including health apps, have brought with them a great potential to further develop healthcare services, but their introduction should follow the same criteria as other healthcare methods. The health technology assessment (HTA) supports decision-makers by producing the unbiased assessments of different type of health technologies. In Finland, the Digi-HTA process supports HTA activities for all types of DHTs, such as health apps, artificial intelligence and robotic solutions. In order to ensure that Digi-HTA would be as compatible as possible with other recognized assessment methods, the Finnish Coordinating Center for Health Technology Assessment (FinCCHTA) has carried out a comparison work that includes the DiGA and NordDEC assessment models and the CEN/ISO TS 82304-2:2021 technical specification.

The Norwegian project "Safer health apps" has looked at how Norway can increase the uptake of health apps in the society – as part of the national, public health service – and developed a "how-to" guide for quality assessment of health apps and similar technologies.

In this talk a brief overview of cybersecurity challenges with integrated IT/OT medical devices will be provided, along with current best practices for addressing them and open issues. Realistic attack scenarios will be used as examples to discuss the possible impact of the attack; ease of detection; risk of cascade effects; assets likely to be affected; stakeholders involved; security measures to prevent such attacks; handling the incident.

Nursing Organizations are expected to make contributions to Innovation. How do nursing organizations know how Innovation Ready they are? What should nursing organizations do to become more Innovation Ready? As contribution to the discussion around Nurse-Led Innovation, the Innovation Readiness Inventory is delivered to help answer these questions.During the presentation you will also meet Nursing Directors who will take you through how they use the tool and how it is connected to their work on how to establish Frontline Innovation as a part of their day to day operations.

Presentation of the six years of experience in using mixed reality applications in planning liver and heart surgery at Oslo University Hospital. Description of research, development and implementation of clinical applications from image data to surgical strategies in 3D. It was initiated by clinicians based on clinical challenges to be fully compatible with clinical reality. Efficient workflow, fully integrated with hospital infrastructures cloud/browser-based with no need for specialized workstations.Ample experience is derived from surgical planning sessions for colorectal liver cancers and structural heart diseases. Not only limited to the most complex surgical cases. In pediatric heart surgery, holographic visualization brings enhanced 3D anatomical understanding of complex heart defects. It provides insight that reduces the risk of damaging critical structures in the surgical area. Holographic information impacts surgical plans in about half of the tested cases.In liver cancer surgery, holographic visualization brings anatomical overview and improves spatial understanding of internal anatomical structures in relation to the tumour. This is important when planning intricate surgical paths within the liver. Additionally, it better utilizes already available preoperative data to be used in surgical planning as an adjunct to the standard of care.Industrial collaboration has been vital in the establishment of minimum viable products as well as in establishing a start-up. This paved a path towards regulatory approvals and the distribution of applications for clinical use outside our hospital. We will present published and unpublished results from our department - where we have failed and succeeded and what we have learned in the process.Finally, we will provide a glimpse of the future trend in the current project and what is coming next. 

“The Nordic Welfare Model is not sustainable!”, they said, ”Too much focus on healthcare and too little on preventative care will break the system going forward. We need to get the citizens more involved, not only in the care process but also in preventative care. The question is just – how?”

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.