Introduction to AI and Machine Learning for Biomedical Research
Basisopleiding voor biomedial onderzoekers, VAIA
Praktische info:
Inschrijven?
- Inschrijvingen: tot 30 sep 2021
- Voorwaarden: No prior knowledge is expected
- Prijs: free
Georganiseerd door:
Leertraject
Tegenwoordig is er steeds meer biomedische data beschikbaar. Deze data komt voor in verschillende vormen zoals afbeeldingen, omics-data, elektronische patiëntendossiers… Machine learning algoritmen kunnen je dan helpen om patronen te vinden in je data, de data te classificeren of je ondersteunen in het maken van weloverwogen beslissingen op basis van deze data. Typisch voorbeelden zijn het analyseren van CT-scans bij het stellen van een kankerdiagnose of het bepalen van een gepaste behandeling voor MS-patiënten. In deze cursus krijg je inzicht in het hedendaags biomedisch onderzoek waarvoor machine learning wordt inzet.
Doelstellingen
- Je leert de mogelijkheden van machine learning kennen, en krijgt belangrijke richtlijnen waar je rekening mee moet houden als je de technieken wilt toepassen in je onderzoek.
- Je kan beoordelen of machine learning nuttig is voor je eigen onderzoek.
- Doordat je op de hoogte bent van de basisterminologie, kun je gemakkelijker een gesprek aanknopen met een AI-expert zodat je een biomedisch probleem kan vertalen naar een AI-toepassing.
Programma
Concepten van Machine Learning (9 u)
Hier worden de theoretische concepten uitgelegd samen met enkele relevante voorbeelden en toepassingen.
- Maandag 11 oktober 2021
Module 1 – 13:00-14:00 Basis van Machine Learning (prof. dr. Jefrey Lijffijt – UGent)
Module 2 – 14:15-16:15 Supervised Learning (prof. dr. Jef Vandemeulebroucke – VUB) - Donderdag 14 oktober 2021
Module 3 – 13:00-15:00 Unsupervised Learning (prof. dr. Celine Vens – KU Leuven) - Maandag 18 oktober 2021
Module 4 – 13:00-15:00 Deep Learning and Neural Networks (dr. Joris Roels – VIB/UGent) - Donderdag 21 oktober 2021
Module 5 – 13:00-15:00 Reinforcement Learning (prof. dr. Pieter Libin – AI Lab VUB)
Toepassingen van Machine Learning (4 u)
Biomedische onderzoekers stellen hun onderzoek voor en geven uitleg over de door hun gebruikte AI-technieken.
- Donderdag 4 november 2021
Module 6 – 13:00-15:15 Use cases uit de biomedische sector (deel 1)- Yvan Saeys (UGent): Machine Learning challenges for single-cell biology
- Liesbet Peeters (UHasselt): Multiple Sclerosis as a use case to show how AI an real world data transform our healthcare system
- Alexandre Arnould & Melanie Nijs (KU Leuven): Dimensionality reduction for (multi-)omics data
- Walter Daelemans (UAntwerpen): Biomedical and Clinical Natural Language Processing
- Pieter Libin (AI Lab VUB): Deep Reinforcement Learning for Epidemic Policy Control
- Ilse Vermeulen (UCLL): ASTMApping, localisation of respiratory hot-spots for asthmatic patients in an urban context through Citizen Science and low-cost sensor technology
- Maandag 8 november 2021
Module 7 – 13:00-15:15 Use cases uit de biomedische sector (deel 2)- Kris Laukens (UAntwerpen): AI for the prediction of adaptive immune response to infection or vaccination
- Axel Geysels (KU Leuven): 2D-segmentation models for ultrasonic images to automate the detection of ovarian cancer
- Alexander Lemm (Amazon AWS): Introduction to AI/ML based biomedical research on AWS
- Tamas Madl (Amazon AWS): Deep-dive into an AI/ML based research project: Munich Leukemia Lab
- Peter De Jaeger (AZ Delta): AI applications today and the road towards a learning hospital
- Nikolay Manyakov (Janssen Pharmaceutical Company): Data science applications in clinical trials
Uitdagingen en ethische kwesties (2 u)
Uitdagingen van het verwerken en verzamelen van data en de ethische kwesties die horen bij het gebruiken van AI.
- Maandag 15 november
Module 8 – 13:00-15:15 Ethiek en data management en bias in data- dr. Patrick De Mazière (UCLL) : Data management en ethics
- Bart Vannieuwenhuyse (J&J) : From Patients to Insights, to Novel Breakthrough Therapies
- Maarten Buyl (UGent): Fairness in AI
Mogelijke vervolgcursussen
Het VIB biedt deze cursussen aan als je zelf hands-on aan de slag wilt gaan met machine learning en AI:
- A tour of Machine Learning: classification – Sven De Groeve
- Deep Learning in Biology – Joris Roels
Lesgevers / sprekers
Jefrey Lijffijt
Jefrey Lijffijt is professor Data Science aan de Universiteit Gent - IDLab en leidt samen met Tijl De Bie de onderzoeksgroep AI & Data Analytics. De onderzoeksgroep AI & Data Analytics ontwerpt, implementeert en analyseert algoritmen en systemen om kennis en inzichten uit data te halen. Vrijwel al onze tools en artikelen zijn open source en open access beschikbaar. Jefrey Lijffijt is voorzitter van de AI-werkgroep aan de Faculteit Ingenieurswetenschappen en Architectuur en lid van de AI-kerngroep aan de Universiteit Gent. Hij draagt actief bij aan het onderwijs over (Gen)AI aan de Universiteit Gent en voorheen aan VAIA.
Zijn expertise omvat: artificiële intelligentie, machine learning, kennisontdekking, datavisualisatie, datamining, data-exploratie, visuele analyse, computationele complexiteitsanalyse, algoritmeontwerp, informatietheorie, statistische hypothesetoetsing, interactiviteit en tools en toepassingen. Voor een overzicht van recent onderzoek, zie https://aida.ugent.be/
Jef Vandemeulebroucke
Expertise: medische beeldanalyse, computer-ondersteunde diagnose and beeldgestuurde interventies.
Celine Vens
Celine Vens is professor at KU Leuven campus Kulak and leading the machine learning and AI subgroup at itec. Her main research interest is the development of machine learning algorithms for applications in health and education. She focuses on non-standard supervised and semi-supervised learning tasks, such as multi-output prediction, time-to-event prediction and interaction prediction. Besides research, she is teaching several courses at the Faculty of Medicine.
Pieter Libin
Prof. Pieter Libin graduated in 2014 at Vrije Universiteit Brussel in Informatics and obtained his PhD in Computer Science at VUB in 2020. After his PhD, he held a postdoctoral position funded by the Flemish science foundation at Hasselt university, at the department of data science. Since October 2021, Pieter is active as an assistant professor at the AI lab of the Vrije Universiteit Brussel. His research involves the use of machine learning to support decision makers by combining machine learning techniques with realistic simulation models and concerns theoretical and applicational AI with a focus on reinforcement learning and Bayesian modeling. He has a broad experience in modeling and analyzing real-world systems ranging from virus diversity, epidemic emergencies, and renewable energy providers. Pieter is a member of the Jonge Academie, an association of young top researchers and artists with an engagement to policy, society, research, and the arts. Pieter is a board member of the Benelux Association for Artificial Intelligence.
Yvan Saeys
Yvan Saeys obtained his PhD in computer science from Ghent University. After spending time abroad at the University of the Basque Country (Spain) and the University of Lyon (France) he returned to Belgium and established the Data Mining and Modeling for Biomedicine (DAMBI) group at the VIB Center for Inflammation Research (IRC) in Gent. As of 2015, he is a professor at Ghent University and a principal investigator (group leader) at VIB, where he is heading an interdisciplinary research team of 21 people, consisting of mathematicians, computer scientists, engineers and bioinformaticians. The Saeys lab studies the design and application of novel data mining and machine learning techniques for high-dimensional single-cell omics data, including methods to model cell developmental trajectories and intercellular communication. At the methodological level, the lab studies the robustness and interpretability of machine learning models.
Walter Daelemans
Walter Daelemans is professor of Artificial Intelligence and Natural Language Processing (NLP) at the University of Antwerp. He helped pioneer the statistical and machine learning revolution in NLP in the nineties with the development of Memory-Based Language Processing and with work on the methodology of machine learning for language processing. He was awarded EurAI and ACL fellowships for this work, and has published influential work on text mining and knowledge extraction from biomedical, clinical, and social media text, and on stylometry and author profiling. With currently 32 supervised PhDs graduated and more than 400 co-authored publications he is one of the most prolific NLP researchers in the Low Countries. In addition, he has been involved in the creation of high profile valorization results with popular open-source software such as TiMBL and Pattern, and has been instrumental in the creation of several spin-offs (textkernel, textgain, fluent.ai).
Ilse Vermeulen
Dr. ir. Ilse Vermeulen is a Bio-engineer in Cell and Gene
Biotechnology with a PhD in Medical Sciences from the Free University of
Brussels (VUB), which she obtained in 2012. During her doctoral
studies, Ilse focused on prediction models and epidemiological studies
in the clinical biology of type I diabetes, which provided her with
extensive experience in data processing and writing research articles
for peer-reviewed journals.
For the past few years, Ilse has been working as a project manager at
the University of Applied Sciences Leuven-Limburg (UCLL), where she was
responsible for the respective focus lines "Environment & Health"
and "Technology Enhanced Care".
In April 2022, Ilse joined the Research Group of Biomedical Data
Sciences of Liesbet Peeters as a Staff Member and Project Manager to
support the MS Data Alliance. Additionally, she leads the follow-up of
other projects within the group, e.g. EBRAINS. Ilse is a vigorous
creator, project enabler, and adept at transforming real-world data into
real-world evidence.
Expertise:
Prediction models, stakeholder management, ...
Kris Laukens
Kris Laukens, who acquired his PhD in 2003, is now a Full Professor in bioinformatics at the University of Antwerp's Adrem Data Lab. His research primarily focuses on developing data science and AI methods to turn biomedical data into actionable insights, supporting a range of (pre-)clinical research projects through innovative data analysis and collaboration with hospitals and research institutes. Laukens founded BIOMINA in 2011, a multidisciplinary hub uniting computational research, life sciences, and clinical expertise, now recognized as a core facility of the University of Antwerp. Additionally, he leads the Tech Transfer consortium "Precision Medicine Technologies" (PreMeT), focusing on converting technology into economic and societal value. In 2022, he received the FWO FNRS AstraZeneca Award for his work on human immune response heterogeneity and he has been acknowledged as a top young innovator in Antwerpen. Further, Laukens has founded two successful spin-off companies. In ImmuneWatch BV, he works on AI technology to make T cell repertoire data actionable in clinical applications.
Patrick De Mazière
Education:
KULeuven MSc Eng Computersciences - Programmatuur 1998
KULeuven PhD Medical Sciences - Computuational Neurosciences 2007
KULeuven LRD Masterclass Hi-Tech Entrepreneurship 2012
Experience:
KULeuven Postdoc Computational Neurosciences 2007 - 2014
UCLL Parttime Research Coordinator Zorgzame IT + partime teaching IT 2013 - 2018
UCLL Head of Research & Expertise Center Digital Solutions 2018 - 2023
UCLL Coordinator Technology Enhanced Healthcare & Social Welfare 2023 - Present
KULeuven IOF Council Member 2021 - 2025
Expertise:
Machine Learning, AI, Textmining, AI4Health, Data Engineering, R, SQL, ...
Maarten Buyl
Postdoctoral researcher at Ghent University
Alex Lemm
As a Business Development Manager for Medical Imaging Innovation I define and execute go-to-market strategies for the adoption and growth of AI/ML in the medical imaging space with customers and partners in EMEA.
I strongly believe in the power of analytics and that they can help businesses gain an edge. Based on my own experience I especially consider self-service analytics for domain experts as a key part of every analytics strategy in the foreseeable future with Machine Learning for researchers and data scientists as the other corner stone. Self-service analytics truly enable companies to scale by using their current employees' skill set and improve the collaboration between domain experts and data science teams.
I have extensive experience bringing ML and advanced time-series analytics to software platforms and further developing the broader vision, product strategy and GTM for advanced analytics.
Tamas Madl
Innovating on behalf of healthcare & life sciences customers in the EMEA public sector, through deep machine learning / AI expertise and a broad range of AWS cloud service offerings
Prior to joining AWS, I worked as a senior data scientist at McKinsey (specializing in leveraging cutting edge AI research to solve real-world problems on very short time scales), founded a healthcare AI startup, led brain-inspired AI research projects, contributed to a major proto-AGI project, and completed a PhD in the machine learning group at the University of Manchester.
Peter De Jaeger
Prof. Peter De Jaeger is director IT & data and the Chief Innovation Officer and leading RADar, the learning and innovation centre of AZ Delta. He holds a position at Hasselt University as a data science professor and a position as adjunct associate professor at University College Dublin. His working experience deals with project management, research & development, product development, clinical studies, data access/use/sharing.
Bart Vannieuwenhuyse
After over 40 years of experience in the pharma/life sciences industry, Bart and his consulting company NeoDoma help with the development of a safe and efficient data ecosystem, allowing reuse of health data (real world data) for research purposes. Bart is the former senior director Health Information Sciences at Janssen Pharmaceutical Companies of Johnson and Johnson
Gerelateerde opleidingen
