Helyszín: Nagyvárad téri Elméleti Tömb, 21. emelet, Johan Béla terem, Budapest, Nagyvárad tér 4.
Dátum: 2024.09.27.
{ "name":""Machine learning with a clinical purpose" kurzus", "description":"
INVITATION
A 2-day course (9 hours)
Date: 27-28 September, 2024
Location: Johan Béla room, Department of Preventive Medicine and Public Health, 21st floor, NET Building, 1089 Budapest, Nagyvárad tér 4.
Registration until September 23, at szentgyorgyi.hajnal@semmelweis.hu
Machine learning (ML) and artificial intelligence (AI) are without doubt among the hottest topics in clinical research, a topic that also interests stakeholders and the public. Despite the promise of ML/AI and the vast number of research articles about it in the medical literature (n~80,000 on PubMed in 2023), implementation of AI-based solutions in clinical practice are still sparse. One of the potential reasons is the lack of basic understanding of what problems ML can and what it cannot solve. This is partly due to a knowledge gap and language barrier between data science and clinical research. This course introduces topics in ML/AI through examples from the clinical literature.
• Biostatistics vs. machine learning
• Development and evaluation of clinical prediction models
• Fundamental approaches in ML (e.g. tree-based methods, clustering)
• Introduction to deep learning (e.g. neural networks)
• Image analysis using deep learning
• Large language models and their clinical knowledge
• Perception of AI-based applications in healthcare
• Algorithmic fairness
Topics will be introduced via lectures and guided group discussions.
Learning outcomes
• Understand the differences between traditional statistical methods and ML
• Unravel common misunderstandings about ML/AI
• Cover fundamental concepts in ML/AI (from basic to state-of-the-art) to provide a ‘springboard’ to more complex ML/AI studies
• Critically evaluate clinical studies using ML and AI-based solutions in healthcare
• Discuss ethical and societal considerations of AI-based solutions in healthcare
Adam Hulman (Hulmán Ádám), MSc, PhD
Senior Data Scientist, Steno Diabetes Center Aarhus, Aarhus University Hospital, DK
Associate Professor, Deptartment of Public Health, Aarhus University, DK
Adam has a Masters degree in applied mathematics and a PhD in diabetes epidemiology from the University of Szeged. Currently, he is the leader of the Machine Learning & Clinical Prediction Lab at Steno Diabetes Center Aarhus. His team’s overarching goal is to turn health data into clinical insights and applications by using advanced statistical and machine learning methods. More specifically, the team works on the development and application of deep learning methods to be able to integrate clinical data of different types (tabular, images, time series, audio) in risk prediction of diabetic complications. He is committed to building bridges between the data science community, diabetes researchers and clinicians. Adam is an active academic citizen: steering committee member of the European Diabetes Epidemiology Group, chairman of the Danish Data Science Academy’s Cross-academy Collaboration Committee, and and associate editor of Diabetologia. In 2024, he received the Danish Diabetes & Endocrine Academy Education & Networking Award for his outstanding engagement in diabetes research education and traning of early-career researchers.
Nagyvárad téri Elméleti Tömb, 21. emelet, Johan Béla terem", "startDate":"2024-09-27", "endDate":"2024-09-28", "startTime":"00:00", "endTime":"23:59", "location":", Budapest, Nagyvárad tér 4.", "options":["Apple","Google","iCal","Microsoft365", "MicrosoftTeams", "Outlook.com"], "timeZone":"Europe/Budapest", "iCalFileName":""Machine learning with a clinical purpose" kurzus", "label":"Naptárba"}
INVITATION
A 2-day course (9 hours)
Date: 27-28 September, 2024
Location: Johan Béla room, Department of Preventive Medicine and Public Health, 21st floor, NET Building, 1089 Budapest, Nagyvárad tér 4.
Registration until September 23, at szentgyorgyi.hajnal@semmelweis.hu
Machine learning (ML) and artificial intelligence (AI) are without doubt among the hottest topics in clinical research, a topic that also interests stakeholders and the public. Despite the promise of ML/AI and the vast number of research articles about it in the medical literature (n~80,000 on PubMed in 2023), implementation of AI-based solutions in clinical practice are still sparse. One of the potential reasons is the lack of basic understanding of what problems ML can and what it cannot solve. This is partly due to a knowledge gap and language barrier between data science and clinical research. This course introduces topics in ML/AI through examples from the clinical literature.
• Biostatistics vs. machine learning
• Development and evaluation of clinical prediction models
• Fundamental approaches in ML (e.g. tree-based methods, clustering)
• Introduction to deep learning (e.g. neural networks)
• Image analysis using deep learning
• Large language models and their clinical knowledge
• Perception of AI-based applications in healthcare
• Algorithmic fairness
Topics will be introduced via lectures and guided group discussions.
Learning outcomes
• Understand the differences between traditional statistical methods and ML
• Unravel common misunderstandings about ML/AI
• Cover fundamental concepts in ML/AI (from basic to state-of-the-art) to provide a ‘springboard’ to more complex ML/AI studies
• Critically evaluate clinical studies using ML and AI-based solutions in healthcare
• Discuss ethical and societal considerations of AI-based solutions in healthcare
Adam Hulman (Hulmán Ádám), MSc, PhD
Senior Data Scientist, Steno Diabetes Center Aarhus, Aarhus University Hospital, DK
Associate Professor, Deptartment of Public Health, Aarhus University, DK
Adam has a Masters degree in applied mathematics and a PhD in diabetes epidemiology from the University of Szeged. Currently, he is the leader of the Machine Learning & Clinical Prediction Lab at Steno Diabetes Center Aarhus. His team’s overarching goal is to turn health data into clinical insights and applications by using advanced statistical and machine learning methods. More specifically, the team works on the development and application of deep learning methods to be able to integrate clinical data of different types (tabular, images, time series, audio) in risk prediction of diabetic complications. He is committed to building bridges between the data science community, diabetes researchers and clinicians. Adam is an active academic citizen: steering committee member of the European Diabetes Epidemiology Group, chairman of the Danish Data Science Academy’s Cross-academy Collaboration Committee, and and associate editor of Diabetologia. In 2024, he received the Danish Diabetes & Endocrine Academy Education & Networking Award for his outstanding engagement in diabetes research education and traning of early-career researchers.