Data4SmartHealth 2023
Friday, November 10, 2023, 14:00 – 18:00
NOI Techpark Bozen – Bolzano, Building A2, Auditorium
Talk abstracts
Gianluigi Greco
Invited Talk: AI Algorithms for Digital Therapeutics
Digital therapeutics tackle diverse medical conditions, and AI algorithms, encompassing machine learning, natural language processing, and computer vision, are central to their success. They enable personalized, data-driven treatments, improving patient outcomes while potentially reducing healthcare costs. This talk explores AI’s pivotal role in digital therapeutics, where software interventions are reshaping healthcare.
Speaker’s short bio: Gianluigi Greco is a Full Professor of Computer Science at the University of Calabria, where he has held the position of Department Director of Mathematics and Computer Science since 2018. Since January 2022, he has been the President of the Italian Association for Artificial Intelligence (AIxIA), a leading scientific association in the field, founded in 1988, with more than 1500 professors and researchers from public and private universities and research centers. He is also a member of the Board of Directors of the Italian Society for the Ethics of Artificial Intelligence (SIpEIA).
With over 200 scientific publications in the field of Artificial Intelligence, he has received numerous awards and recognitions, including the AAIA Fellowship (2022), the EurAI Fellowship (2020), the IJCAI Distinguished Paper Award (2018), the Kurt Gödel Fellowship Award (2014), the Marco Somalvico Award (2009), and the IJCAI-JAIR Best Paper Award (2008). He is a member of the editorial boards of numerous computer science journals and, in particular, serves as an Associate Editor of the Artificial Intelligence Journal.
In addition to his scientific activities, he has coordinated numerous initiatives in partnership with industry, focusing on the use of Artificial Intelligence technologies, and has promoted several start-up initiatives. He participated in the AGENAS working group for the definition of the national Artificial Intelligence platform for primary care, and is currently a member of the ethical committee of the PRO.DI.GI.T project of the Ministry of Economy and Finance (MEF) for the adoption of innovative tools for tax judges’ activities. He is responsible for the digital transformation and technology transfer activities of the Tech4You ecosystem for innovation in Calabria and Basilicata, and is a member of the scientific committee and advisory board of various innovation hubs and investment funds focused on digital technologies.
(slides)
Chiara Masci and Davide Montesin
Talk 1: Software testing for remote proof of concept studies of digital therapies
Digital therapies are evidence-based therapeutic interventions that use software to prevent, manage, or treat a medical disorder or disease. Not only they require carefully planned clinical studies, but they require also a suitable technical infrastructure not to lose or compromise relevant information. Consequently, careful software testing and monitoring is necessary to ensure that the technical infrastructure is working correctly during the study. In this talk we will describe the entire process used for the analysis of the effectiveness of Nearine, a digital therapy for the management of depressive symptoms based on interoceptive stimulation through vibrations applied on the wrist. We will start with the description of the remote proof of concept study used for the assessment of the effectiveness and potential adverse effects. After that, the technical infrastructure necessary for the study will be outlined.
Finally we will show how the usage of CatchSolve for software testing has decreased the risk of potential loss of information during the study. The talk is the result of a joint collaboration between CatchSolve, software testing startup based in NOI Techpark, and Nearine, a new digital health and neurotechnology startup based in Bolzano.
Speakers’ short bio: Chiara Masci is the founder of Nearine, a startup that develops a digital therapy for the management of depressive symptoms that uses neuroscientifically proven vibrations to simulate the anti-depressive effects of affective touch. In addition, she actively collaborates with CatchSolve, a software and data quality testing startup, for the business strategy and the management of internal operations. She obtained her Bachelor’s Degree in Computer Science at the Free University of Bolzano in 2020. After that, she continued her studies in Biomedical Engineering, which has given her the skills necessary to understand the latest innovative research in the neurotechnology sector.
And finally, she completed her Executive Master’s in Management and Innovation of Lifesciences at H-FARM in June 2023, which has given her the tools and skills to plan and launch medical startups. She has collaborated with research institutions such as the Tokyo Institute of Technology, IULM, and Politecnico delle Marche in the fields of Brain-Computer Interface and Computer Vision.
Davide Montesin is the CEO of a Start-up called Catch Solve, which is situated in NOI Techpark in Bolzano Bozen, South Tyrol. The Start-up – founded in 2019 – is an integrated platform that monitors the quality of apps, websites and digital services and to find useful resources to solve software bugs easily, quickly and time efficiently. The South Tyrol native, currently living in Bolzano – Bozen, has a great passion for programming and open source / free software and has a 20 year-long experience in participating and leading software projects for the public administration, private companies and the tourism sector.
(slides)
Daniele Gobbetti
Talk 2: Gimme! Gimme! Gimme! (Some good algorithms)
Gadgetbridge, a free and open source project, has existed since 2015 to allow wearable device customers to use their hardware without being tied to the online services of the manufacturers. The small but very focused and capable technical community working on the basic functionalities such as retrieving the various data from the wearables (detected activities, sleep, pulse per minute, peripheral oxygen saturation, …) lacks the expertise on specialised algorithms that could help to perform advanced analysis/diagnostics. The goal of this talk is to explore a potential collaboration between our communities: Gadgetbridge provides local-only support for an extensive list of wearable devices and a community of engineers and privacy minded users, Data4SmartHealth might contribute advanced algorithms and AI on edge devices.
Speaker’s short bio: Daniele Gobbetti is a freelancer who works with small and medium-sized IT companies to help them manage complex technical projects. He’s an information engineer with several years of experience in CTO and CEO roles. A passionate open source developer and curious person, he’s happy to be called a hacker. He is an active member of the Gadgetbridge core development team and co-ordinated the project response to a DMCA complaint.
(slides)
Luca Nardelli
Talk 3: Home4Me – IoT and AI at service of disability
Home4Me is an innovative social project that tries to help disabled people at home (and not only at home). The projects tries to keep in mind concrete problems that a person with disabilities lives at home and try to resolve them using IoT ad-hoc devices and a backend to access to the power of Cognitive and AI services.
Speaker’s short bio: My objective is to acquire even more competence in the field of IT. I like very much every technology, that I use with passion. I have a robust experience on backend development (.Net Core, Node/Express/Nestjs) and cloud technologies (Azure/AWS), but I also love the mobile and web development (Xamarin, Angular, React, Electron, Node.js, Tizen, etc). I have a base know-how in Docker, Google GCP and AWS services (eg S3 and Cognito). I started to experiment with Tensorflow.js, Microsoft Cognitive Services and Flutter, as well with Arduino. I love traveling, reading, the history, the art, knowing new people and do sports One of my dreams is the possibility to apply my knowledges in the social field.
(slides)
Alan Ianeselli
Talk 4: Machine learning driven simulation of protein folding atomistic trajectories
The folding of proteins is an important biological process that determines the structure, role and functionality of proteins. It is often studied by molecular dynamics (MD) simulations, in order to obtain the folding trajectory of all the atoms in the system. To date, pure MD simulations require huge computational resources and are still unable to access the timescales of folding processes that have biological relevance. In my work, I am exploiting machine learning techniques and one recent AI milestone, Deepmind’s Alphafold, in order to create an advanced algorithm able to explore the folding trajectories within short computational times. It becomes possible to extract atomistic conformations from the folding pathways, and identify folding intermediates and long-lived states. This method can be used to facilitate the identification of biologically relevant protein conformations, later to be used for pharmacological targeting or biophysical studies.
Speaker’s short bio: Alan Ianeselli is a researcher in computer science at the Free University of Bozen-Bolzano. He graduated (110 cum laude) in molecular biotechnology at the University of Trento (Italy), and received his PhD (summa cum laude) in physics at the Ludwig-Maximilian University of Munich (Germany). Alan’s research focuses on studying biological processes by means of advanced computational techniques, machine learning methods and chemometrics. Alan has a high-rank record of publications in journals such as Nature Chemistry, Nature Physics and Angewandte Chemie.
(slides)
Giuseppe di Fatta
Talk 5: Data-driven knowledge discovery from Brain Imaging of Alzheimer’s disease patients
Alzheimer’s disease (AD) is a chronic neurodegenerative disease which is largely responsible for dementia in around 6% of the population aged 65 and above. The availability of human brain data generated by imaging techniques, such as Magnetic Resonance Imaging, have resulted in a growing interest in data-driven approaches for the diagnosis of neurological disorders and for the identification of new biomarkers. The knowledge discovery process typically involves complex data workflows that combine pre-processing techniques, statistical methods, machine learning algorithms, post-processing and visualisation techniques. This talk presents specific research efforts in this direction, promising results, open issues and challenges.
Speaker’s short bio: Giuseppe Di Fatta is a full professor at the Faculty of Engineering of the Free University of Bozen-Bolzano. From 2006 to 2021, he was with the University of Reading (UK), where he served as Head of the Department of Computer Science from 2016 to 2021. From 2004 to 2006, he was with the University of Konstanz (Germany), where he contributed to the development of the first release of the Data Science and Machine Learning platform KNIME. From 2000 to 2004, he was with ICAR-CNR (Italy). In 1999, he was a research fellow at the International Computer Science Institute (ICSI) in Berkeley (CA, USA). His research interests include data science and machine learning algorithms, Big Data analytics, distributed and parallel computing, and data-driven multidisciplinary applications for Industry and Science.
Michele Finelli
Talk 6: Management of large genomic data with free software
The suite of free software tools created within the OpenCB (Open Computational Biology – https://github.com/opencb) initiative makes possible to efficiently manage large genomic databases. These tools are not widely used, since there is quite a steep learning curve for their adoption, thanks to the complexity of the software stack, but they may be really cost-effective for hospitals, research institutions etcetera. The objective of the talk is showing the potential of the OpenCB suite, the information to start using it and the advantages for the end users. BioDec is currently deploying a large OpenCGA installation for the Genetic Unit of one of the main Italian Hospitals, where data in the order of the hundreds of TBs will be managed and analyzed by bioinformaticians.
Speaker’s short bio: Michele Finelli is a consultant and founder of BioDec – the first Italian bioinformatics company. He is server shepherd and dungeon master.
(slides)
