ICHSM 2024

Keynote Speakers

 

Prof. Dr. Osman Hayran

Istanbul Medipol University Faculty of Medicine, Turkiye

 

He graduated from Hacettepe University School of Medicine as a Medical Doctor and then specialized in Public Health at Hacettepe University Institute of Community Medicine. After completing compulsory service in Kocaeli Health Directorate of the Ministry of Health, he started academic life. He became Associate Professor at Marmara University School of Medicine in 1988 and Full Professor in 1994. In the same university, he served as the Head of the Department of Public Health, Director of the Vocational School of Health Services, Dean of the Faculty of Health Education and Director of the Health Policy Research Center. In addition, he held part-time positions at the World Health Organization and the University of Miami Medical School. He retired from Marmara University at the end of 2007 and started to work as the founder Dean of the Yeditepe University School of Health Sciences. After the establishment of this faculty, he served as its dean until 2013. He is currently working as the head of the Department of Public Health at Istanbul Medipol University Faculty of Medicine and also Director of Healthcare Systems and Policies Research Center at the same university. He has many scientific articles published in various local and foreign journals, congress papers and books.

 

Speech title "Infodemiology, Metascience and Healthcare Services"

Abstract-Infodemiology and metascience are newly emerging disciplines of the Information Age that have gained importance especially following the COVID-19 pandemics.
Misinformation and disinformation are important threats to public health. Infodemiological methods, which were initially developed for the analysis and management of false, erroneous and harmful information, later became widespread as methods for making predictions about important public health problems. The methods developed for infodemic studies are also used by the discipline called digital epidemiology or e-epidemiology. Digital epidemiology uses part of the Big Data that is collected for non-research purposes.
Findings of the research conducted with non-scientific methods is another significant problem that has become widespread during the pandemic period. It has been known for a long time that many studies published in reputable scientific journals are not scientific, even though they are written by people with the title of scientists. During the pandemic period, due to academic ambition to discover something rapidly the patience and rigor required by scientific research processes were pushed to the background, and many publications with extremely weak methodology and controversial findings invaded reputable journals. This has led to the importance of metascience methods.
Metascience, also known as Meta-Research, means "the science of science" or "the study of research". With the development of information technologies, research methods and results that were previously questionable long after they were published can now be questioned as soon as they are published.
While misinformation spread by the infodemic misleads ordinary people, publications based on non-scientific methods mislead scientists and healthcare providers. Both must be prevented.
In this presentation, the advantages of infodemiology and metascience in healthcare delivery will be summarized in the light of the current literature and the points to be considered will be emphasized.

 

Prof. Yu-Chuan Jack Li

Taipei Medical University

President of the International Medical Informatics Association

 

Yu-Chuan Jack Li is a leading expert in AI in medicine and translational biomedical informatics, ranked in the top 2% of scientists worldwide. He has been actively involved in international collaborations and has led numerous national projects focused on advancing the use of AI in disease prevention, patient safety, and "earlier medicine". Li's research on temporal phenomic stochastic models has evolved into the largest model ever constructed based on medical data elements.
He has been recognized for his outstanding achievements with fellowships in the Australian College of Health Informatics, the American College of Medical Informatics, and the International Academy of Health Science Informatics. He has also received numerous awards for his remarkable contributions.
Position
• Distinguished Professor, Taipei Medical University
• Dermatologist, Taipei Municipal Wanfang Hospital
• Editor-in-Chief, BMJ Health and Care Informatics
Education
• Ph.D., Medical Informatics, University of Utah School of Medicine
• M.D., Medicine, Taipei Medical University

 

Speech title "AI and a Safer Future of Healthcare"

Abstract-Artificial Intelligence (AI) is likely to be one of the technologies that will reshape the future of medicine and healthcare in unimaginable ways. As Stephen Hawking put it, "Our future is a race between the growing power of technology and the wisdom with which we use it." How we understand, develop, and use AI will largely determine what happens to our healthcare ecosystem and the overall well-being of humanity. In the realm of healthcare, AI's transformative potential is immense, particularly in enhancing early disease detection, minimizing medical errors, and bolstering patient safety. These advancements promise not just incremental improvements but a fundamental reshaping of healthcare practices.
To explore the depths of AI's impact and its promising future in healthcare, let's turn to the insights of Prof. Yu Chuan (Jack) Li, a distinguished figure in biomedical informatics. His expertise and vision will guide us through an understanding of how AI can be harnessed to revolutionize healthcare for the betterment of society.

 

 

Prof. Przemysław Biecek

Warsaw University of Technology, Poland

 

Przemysław Biecek is a full professor in computer science who for more than 15 years has been conducting research applying the latest data science developments to the field of healthcare, particularly oncology. To this end, he has built the mi2.ai group stretched between the mathematics and computer science departments of the Warsaw University of Technology and the University of Warsaw. His personal mission is to enhance human capabilities by supporting them through access to data-driven and knowledge-based predictions. I execute it by developing methods and tools for responsible machine learning, trustworthy artificial intelligence, and reliable software engineering.

He currently serves as associate dean for development at the Faculty of Mathematics and Information Sciences at Warsaw University of Technology and is a member of the Global Partnership on AI (GPAI), an international group of experts working on issues related to the responsibility of AI algorithms. He leads the xLungs project, which develops and maintains the largest publicly available database of CT examinations and trains AI models on it in tasks of classification, segmentation, and lesion detection. Algorithms are enriched with techniques of explainable, safe, and trustworthy AI so as to more effectively support doctors' decisions. This collaboration has resulted in numerous articles, books, software packages as well as the implementation of algorithms in healthcare.

 

Speech title "Explainable AI - Latest Advances and New Opportunities for Computational Oncology and Beyond"

Abstract-Advanced machine learning and artificial intelligence models offer the hope of increasing efficiency in treating diseases, supporting medical decisions and optimizing medical services.
However, ML/AI models are increasingly complex and resemble impenetrable black boxes in their nature. So when a model's recommendation differs from a human's intuition, the question arises as to whether they have noticed an important regularity, or whether they may have missed something important after all.
Explainable artificial intelligence is a rapidly growing field creating solutions to look inside complex models and see how they work and based on what they make decisions. During this talk, I will present examples in which XAI has supported interesting discoveries of new relationships as well as allowed the discovery and correction of malfunctioning predictive models. I will also present three examples of how XAI techniques have been applied to real-world decision-making processes.