Sessions

Why is AI proving more of a challenge in Healthcare than other industries?  AI has been promoted as the saviour of medicine yet has failed to make the difference many predicted. Here in this presentation we will explore how AI has changed the potential for healthcare and the barriers that are still faced.

Women's health technology (femtech) is a burgeoning industry that seeks to develop personalized health solutions for individuals identifying as female. From menstruation and maternal healthcare to longevity and chronic care platforms, the global femtech market is anticipated to be worth over $50 billion by 2025. Yet, most digital health companies entering the femtech market fail to prioritize three crucial aspects to their products and businesses: (i) accuracy, (ii) privacy and security, and (iii) scalability. This presentation provides a roadmap to the key legal and ethical challenges facing women's health companies, and offers solutions to ensure these companies build robust and internationally scalable businesses that are capable of driving long-term innovation in women's health. 

Traditional sample size estimation for sufficient model performance is not applicable for machine learning, especially in the field of electrocardiograms (ECGs). This presentation outlines a sample size estimation strategy for binary classification problems on ECGs. The post-hoc sample size estimations are based on a benchmark across different architectures and different classification targets. The results indicate trends for required sample sizes for given tasks and architectures, which can be used as orientation for future ECG studies or feasibility aspects.

It is of utmost importance to understand better the requirements for a Digital Therapeutics (DTx) design and trial service that supports the design of DTx and their efficient evaluation via feasibility studies, optimization trials (e.g., micro-randomized trials), efficacy or effectiveness trials (e.g., randomized controlled trials). This workshop has, therefore, the objective of gathering such requirements by applying the World Café methodology and discussing several complex care scenarios. We welcome participants with various backgrounds (e.g., technical, regulatory, medical, ethical) who bring in different perspectives.

With the fast progression in AI, its role in healthcare is bound to be ubiquitous in near future. However, creating AI software that is unbiased and trained ethically remains a challenge. In this session, we will evaluate different aspects of what it means for the AI to be biased and how we can evaluate it as a medical device software. Similarly, it is important to understand the fact that ethical AI is a two-way street. We will also look into how the society and the regulatory bodies should play a role for AI to be constructed in an ethical way. 

Women have been historically excluded from healthcare research and women’s health issues still receive inadequate attention, yet women live more years in poor health and with disability.Digital transformation and a rapidly growing global FemTech market provide new opportunities to transform the lives of millions of women globally and contribute to a substantial social impact and economic gains. However, research on FemTech that provide robust evidence on its value is lacking.In this seminar, based on our ongoing research, we will discuss opportunities and challenges of FemTech and why a rigorous research agenda with targeted research funding is needed. We will also address research methods that include multi-stakeholder partnerships, methods of intersectionality research to address health inequities, and co-creation models to engage women in the co-design of technologies to ensure person-centered outcomes.

This study has the overall aim to study physicians’ experiences of VCs, here focusing on their suggestions for future improvements. Twenty-two semi-structured interviews were performed with physicians working for an online healthcare provider in Sweden, and analyzed through inductive content analysis. Two themes emerged related to desired future improvements of VCs; blended care and technical innovation.

Healthcare longitudinal data offers endless opportunities such as diagnostics, and prognostics, to care personalization and improving healthcare quality and efficiency. These can be achieved through Artificial Intelligence (AI), data science, and in specific machine learning (ML). However, lack of inscrutability of the AI/ML-based techniques has hampered pervasive AI in healthcare systems. In this talk, we will introduce graph-based approaches for collecting, storing, visualizing, analyzing, and modeling healthcare data, and discuss how they outperform the other available approaches. We will also discuss challenges around health data and how synthetic data can mitigate them.