Synthetic Data for Biomedical Applications
Before joining SDSC, Arshjot Khehra received his MSc in Artificial Intelligence from USI Lugano, where he completed his thesis on hierarchical graph reinforcement learning. Previously, he worked for 4+ years across India and Singapore gaining data science experience in insurance, logistics, and manufacturing sectors. He also holds a BSc in Industrial Engineering from PEC Chandigarh. Over the course of his career, Arshjot worked on a wide array of projects, such as, handwritten text recognition and generation, voice matching across phone call recordings, policy lapse rate prediction for customer retention, and automated insurance claim processing.
Matthias Galipaud obtained his PhD in evolutionary biology in 2012 from the University of Burgundy in Dijon (France), and held postdoctoral positions as a mathematical biologist at the university of Bielefeld (Germany) and the university of Zurich, where he researched the evolutionary theories of aging and mate choice. In 2020, he became a data scientist, developing machine learning solutions for startups in Switzerland and Australia before joining the SDSC Innovation Team in November 2022.
Valerio started his career working for 7 years as a particle-physics researcher at CERN. In 2016, he moved to consulting, applying data science in several industries. First, he joined the Quant team of Ernst & Young in Geneva. Later, he created his own company, SamurAI sàrl, providing consulting services for his clients. He also has a passion for teaching very complex subjects in simple terms. That is why he particularly enjoys offering training programs to private companies and universities. Valerio joined the SDSC in May 2022 as a Principal Data Scientist with the mission of accompanying industrial partners and other institutions through their data science journey.
Presentation
Overview
Recently, synthetic data has enjoyed growing interest from the biomedical sector. Synthetic patient data helps in leveraging privacy issues. Augmenting datasets with synthetic records helps with increasing classification model training performance in the face of scarce health data and rare minority classes (e.g. rare diseases).
During this one-day workshop, organized by CHUV and SDSC, we will review available tools for synthetic data generation and use cases in the biomedical and pharmaceutical sectors.
Details
Target Audience
Experienced professionals, executives, and data scientists in the biomedical and pharmaceutical sectors wishing to acquire hands-on knowledge on synthetic data generation and usage.
As the workshop involves hands-on sessions, prior experience with the programming language Python is required. The workshop will be held in English.
Programme
Objectives
By the end of the day, participants will:
- Have a grasp of current available methods for synthetic tabular and image data generation.
- Have identified use cases and challenges of synthetic data in the biomedical and pharmaceutical sector.
- Have hands-on experience with generating synthetic data with python and evaluating its quality.
Agenda
09:00
Welcome coffee
09:30
Welcome & introduction
09:40
Synthetic data: How it works and where it is currently used
10:10
GANs, VAEs and diffusion: a deeper dive
10:55
Break
11:15
Applications in healthcare
11:45
Towards the use of synthetic data in biomedical applications: Evaluation of privacy and utility tradeoff
12:15
Lunch
13:15
Applications in the pharmaceutical industry
14:00
Hands-on (part 1): Understanding synthetic data generation (e.g. generating synthetic medical images for image classification)
14:50
Break
15:10
Hands-on (part 2): Understanding synthetic data evaluation (e.g., sharing survival data evaluating the utility and privacy of tabular synthetic data
16:40
Panel discussion
17:10
Concluding remarks, Apéro & Networking
Instructors
Jeremie Despraz, MS, Principal Data Scientist in Clinical AI, CHUV
Matthias Galipaud, PhD, Senior Data Scientist, SDSC, ETHZ
Beyrem Kaabachi, MS, Data Scientist in Health Data Privacy, CHUV
Arshjot Khehra, Data Scientist, SDSC ETHZ
Jean-Louis Raisaro, PhD, Tenure-Track Assistant Professor in Biomedical data science, CHUV
Alena Simalatsar, PhD, Assistant Professor, HES-SO
Practical Information
Price
Non-members: 150/pers
Ongoing collaborations with SDSC or BDSC: free
Availability & Registration
52 registered participants - Registration closed.
Other events
ETH Industry Day 2023
Silvia holds an MSc in Computer Science from EPFL and a PhD in Computer Science from the University of York, UK. She has been a senior research fellow at the University of Trento and later at Politecnico di Milano, Italy. Here, she had the chance to work on Marie Curie and ERC projects relating to natural language processing. From 2012 to 2019, she was a Senior Manager and NLP expert at ELCA Informatique Switzerland, whose AI department she helped create and expand. Silvia joined the Swiss Data Science Center in 2019 and is currently its Chief Transformation Officer, in charge of the team leading organizations to digital transformation.
Contact us
Let’s talk Data Science
Do you need our services or expertise?
Contact us for your next Data Science project!