BIOSTEC 2023

Toward the Virtual Human Simulator – Giovanni Saggio, University of Tor Vergata, Rome, Italy

The new technologies make it possible to acquire big data considerably. As a result, it is possible to have the necessary and useful elements to characterize even rather complex systems. Moreover, the acquisition, even prolonged, and characterization of data from a certain source (object, component, system, etc.) make it possible to create a virtual copy of this source, which is a digital twin (DT). DTs are already successfully adopted in electronics, mechanics, and chemistry, but how far is the realization of digital twins of entire human bodies, and which possibilities are opened to realize virtual human simulators?

Academia and Industry: Partners in Leveraging Engineering, Science, and Medicine for Clinical Translation – Elazer Edelman, Massachusetts Institute of Technology, United States

Any list of the most influential medical innovations over the past century highlights the basic premise that ideas are often conceived and brought to proof-of-concept in universities and clinical and communal realization by industry. The translation from academia to industry is the path to the impact of ideas. The optimization of this translation speaks to the operational efficiency of novel concepts, especially in medical care. We have learned that one can stimulate and teach such translation, and increasing collaboration between academia and industry in Portugal and the United States heralds the next major innovations. We will discuss the history of such linkages in appreciating the mechanistic basis of acute diseases and devising new therapies and how active binational collaboration has brought together partners from across science, engineering, and medicine in the basic and applied aspects of academia and industry.

Ground-Truthing in the European Health Data Space – Mireille Hildebrandt, Vrije Universiteit Brussel, Belgium

In this keynote, I will discuss the use of health-related training data for medical research in light of the EU Health Data Space. If such data is deployed as a proxy for ‘the truth on the ground,’ we need to address the issue of proxies. Ground truth in machine learning is the pragmatic stand-in or proxy for whatever is considered to be the case or should be the case. Developing a ground truth dataset requires curation, that is, several translations, constructions, and cleansing. What if the resulting proxies misrepresent what they stand for, and what if the interoperability of health data across the EU affects the quality of the data and their relationship to what they stand for? I will argue that ground-truthing is an act rather than a given, that this act is key to machine learning, and assert that this act can have potentially fatal implications for the reliability of the output. Deciding on the ground truth is what philosophers may call a speech act with performative effects. Emphasizing these effects will allow us to better address the constructive nature of the datasets used in medical informatics. Furthermore, it should help the EU legislature to take a precautionary approach to medical informatics.

Machine Learning Applied to Electronic Health Record Data: Opportunities and Challenges – Riccardo Bellazzi, Universita di Pavia, Italy

The increasing success of the application of machine and deep learning in many areas of medicine, particularly in imaging diagnostics, is pushing toward implementing AI-based approaches to extract knowledge from other data sources, such as health records data (EHR). Examples include COVID-19 cooperative international efforts, such as the 4CE initiative. However, EHR data are particularly complex due to their multifaceted nature and inherent relationship with the healthcare organizations generating the data. These challenges will be discussed in this talk through some examples, and a few suggestions will be given for future research in this area.