Keynote Speech 1

Fuzzy Methods in Medical Research and Patient Care – in Memoriam Lotfi A. Zadeh

Klaus-Peter Adlassnig

Medical University of Vienna, Austria

Abstract To digitize medical knowledge, one needs to discern, formalize, and represent medical entities and their inter-relationships. Medical entities such as fever or hypoxemia are characterized by linguistic uncertainty. The unsharpness of boundaries in these linguistic terms is modeled by fuzzy sets. Relationships between medical entities are characterized by propositional uncertainty, which is due to the incompleteness of medical conclusions. Propositional uncertainty is modeled by truth values between zero and one. When measurements map into fuzzy sets, the results are combined with truth values of medical propositions, and logical conclusions are drawn. One method is the compositional rule of fuzzy inference, in several forms and successively.  Fuzzy automata offer an interesting way to calculate “fuzzy states” of patients in a clear and clinically comprehensible manner. These states represent physiological or pathophysiological states—based on measured patient data—and allow for grades of “health” or “illness”. States are characterized by linguistic terms and state transitions are described by linguistic instructions. If medical devices need to be controlled, but control rules are heuristic, then fuzzy control yields powerful solutions. It might be advisable to follow an open-loop control cycle, with a human physician carefully examining the control output and performing the actual control.  Arden Syntax is a medical knowledge representation and processing language, issued and supported by Health Level Seven (HL7) International, a standard developing organization for health IT standards. In 2013, the Health Level Seven Arden Syntax for Medical Logic Systems, version 2.9, including fuzzy methodologies, was issued by HL7 and approved by the American National Standards Institute.

Biography: Klaus-Peter Adlassnig received his MSc degree in Computer Science from the Technical University of Dresden, Germany, in 1974. He joined the Department of Medical Computer Sciences of the University of Vienna Medical School, Austria, in 1976. In 1983, he obtained his PhD degree in Computer Sciences from the Technical University of Vienna, Austria, with a dissertation on “A Computer-Assisted Medical Diagnostic System Using Fuzzy Subsets”. Dr. Adlassnig was a postdoctoral research fellow with Professor Lotfi A. Zadeh at the Computer Science Division at the Department of Electrical Engineering and Computer Sciences of the University of California at Berkeley, U.S.A., from 1984–86. He received his Venia docendi for Medical Informatics from the University of Vienna in 1988 and became Professor of Medical Informatics in 1992. In 1987, he received the Federal State Prize for excellent research in the area of rheumatology, awarded by the Austrian Federal Ministry for Health and Environmental Protection. From 1988–2015, he was head of the Section on Medical Expert and Knowledge-Based Systems at the Department of Medical Computer Sciences of the University of Vienna Medical School (now: Section for Artificial Intelligence and Decision Support at the Center for Medical Statistics, Informatics, and Intelligent Systems, Medical University of Vienna). In 2014, he has been elected to Fellow of the American College of Medical Informatics (ACMI), and in 2018 to Fellow of the International Academy of Health Sciences Informatics (IAHSI).

Prof. Adlassnig was a Visiting Professor at the Department of Medicine, Section on Medical Informatics, at the Stanford University Medical Center, U.S.A., in summer 1993, and a guest lecturer and guest professor at the Department of Electrical and Biomedical Engineering in the Technical University of Graz, Austria, from 1994 to 2004. He spent the summer 2000 as a visiting scholar at the Department of Electrical Engineering and Computer Sciences, Computer Science Division, Berkeley Initiative in Soft Computing (BISC), University of California, Berkeley, U.S.A., May 2005 as guest researcher at the Department of Computer Science, Meiji University, Kawasaki, Japan, and September 2008 as visiting scientist at the Clinical Decision Making Group, Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), Cambridge/U.S.A.

From 2002 to 2016, Prof. Adlassnig was the Editor-in-Chief of the International Journal “Artificial Intelligence in Medicine”, Elsevier Science Publishers B.V., and was the director of the Ludwig Boltzmann Institute for Expert Systems and Quality Management in Medicine from 2002 until 2005. He is co-founder, CEO, and Scientific Head of Medexter Healthcare GmbH (www.medexter.com), a company established to broadly disseminate intelligent medical systems with clinically proven usefulness. Since its inception in 2002, Medexter succeeded in establishing technical platforms and clinical decision support systems for a number of academic, commercial, and clinical institutions.

Prof. Adlassnig’s research interests focus on computer applications in medicine, especially medical expert and knowledge-based as well as clinical decision support systems and their integration into medical information and web-based health care systems. Prof. Adlassnig is highly interested in formal theories of uncertainty, particularly in fuzzy set theory, fuzzy logic, fuzzy control, and related areas. He is equally interested in the theory and practice of computer systems in medicine. Prof. Klaus-Peter Adlassnig’s sphere of interest includes various aspects of the philosophy of science, particularly the state and future impact of artificial intelligence.

 

Keynote Speech 2:

AI for Safer and Earlier Medicine

Yu-Chuan Li

College of Medical Science and Technology, Taipei

Abstract: Artificial Intelligence (AI) has had a great impact on the healthcare field and will continue to transform health systems radically. Every healthcare professional should arm themselves with the knowledge to face these changes. In light of the AlphaGo program that win over two of the best Go chess players in the world, Artificial Intelligence (AI) is now back to the spotlight again. Given advice and warnings from some of the top minds like Elon Mush and the late Steven Hawkings, it seems inevitable that AI is going into a fast-pace development in the next few years and likely to impact every aspect of our lives very soon. This talk will describe some of the most important AI applications in healthcare, namely, quality and patient safety, early detection of diseases and indivdualized prevention.  We will also discuss how Big Data and AI will go hand-in-hand in the future of health care for all the stakeholders, in terms of high-performance healthcare and precision medicine.

Biography: Prof Dr. Yu-Chuan (Jack) Li has been a pioneer of Medical Informatics research in Asia. He served as a Vice President of Taipei Medical University (TMU) (2009-2011), and he has been the Dean of College of Medical science and Technology since 2011 and Distinguished Professor of the Graduate Institute of Biomedical Informatics since 1998. He obtains his M.D. from TMU in 1991 and his PhD in Medical Informatics from University of Utah in 1994. Due to his achievement in establishing EHR exchange models among hospitals and his dedication to IT applications in patient safety and care, he was awarded as one of the Ten Outstanding Young Persons of the Year in 2001. He has been Principal Investigator of many national and international projects in the domain of Electronic Health Record, Patient Safety Informatics and Medical Big Data. He is author of 279 scientific papers and 3 college-level textbooks. He became an elective fellow of American College of Medical Informatics (FACMI), (2010), Australian College of Health Informatics (FACHI), (2010), founding members of International Academy of Health Sciences Informatics (IAHSI), (2017) and also the President of Asia Pacific Association for Medical Informatics (APAMI) from 2006 to 2009. He is the former Editor-in-Chief of Computer Methods and Programs in Biomedicine (CMPB) (2013-2018), the Editor-in-Chief of International Journal for Quality in Health Care (IJQHC) since 2014, and also the Associate Editor of JCO Clinical Cancer Informatics (JCOCCI). His main areas of expertise are: AI in Medicine, Patient Safety Informatics, Medical Decision Support Systems, and Medical Big Data Analytics.

Keynote Speech 3:

Deep Learning (Partly) Demystified 

Vladik Kreinovich

University of Texas at El Paso, USA

Abstract: Successes of deep learning are partly due to appropriate selection of activation function, pooling functions, etc. Most of these choices have been made based on empirical comparison and heuristic ideas. In this paper, we show that many of these choices — and the surprising success of deep learning in the first place — can be explained by reasonably simple and natural mathematics.

Biography: Vladik Kreinovich received his MS in Mathematics and Computer Science from St. Petersburg University, Russia, in 1974, and PhD from the Institute of Mathematics, Soviet Academy of Sciences, Novosibirsk, in 1979. From 1975 to 1980, he worked with the Soviet Academy of Sciences; during this time, he worked with the Special Astrophysical Observatory (focusing on the representation and processing of uncertainty in radioastronomy). For most of the 1980s, he worked on error estimation and intelligent information processing for the National Institute for Electrical Measuring Instruments, Russia. In 1989, he was a visiting scholar at Stanford University. Since 1990, he has worked in the Department of Computer Science at the University of Texas at El Paso. In addition, he has served as an invited professor in Paris (University of Paris VI), France; Hannover, Germany; Hong Kong; St. Petersburg and Kazan, Russia; and Brazil.

His main interests are the representation and processing of uncertainty, especially interval computations and intelligent control. He has published eight books, 24 edited books, and more than 1,500 papers. Vladik is a member of the editorial board of the international journal “Reliable Computing” (formerly “Interval Computations”) and several other journals. In addition, he is the co-maintainer of the international Web site on interval computations http://www.cs.utep.edu/interval-comp .

Vladik is Vice President of the International Fuzzy Systems Association (IFSA), Vice President of the European Society for Fuzzy Logic and Technology (EUSFLAT), Fellow of International Fuzzy Systems Association (IFSA), Fellow of Mexican Society for Artificial Intelligence (SMIA), Fellow of the Russian Association for Fuzzy Systems and Soft Computing; he served as Vice President for Publications of IEEE Systems, Man, and Cybernetics Society 2015-18, and as President of the North American Fuzzy Information Processing Society 2012-14; is a foreign member of the Russian Academy of Metrological Sciences; was the recipient of the 2003 El Paso Energy Foundation Faculty Achievement Award for Research awarded by the University of Texas at El Paso; and was a co-recipient of the 2005 Star Award from the University of Texas System.

Keynote Speech 4:

Multiagent Smart Communication based on CI Technology

Kaoru HIROTA

Beijing Institute of Technology, China

Abstract: The presenters’ group has been studying on humans-robots interaction based on Computational Intelligence in the frame work of multiagent smart society, where a concept of Fuzzy Atmosfield (FA) is proposed to express the atmosphere in humans-robots communication. The FA is characterized by a 3D fuzzy cubic space with “friendly-hostile”, “lively-calm”, and “casual-formal” based on a cognitive science experiment and PCA. To understand easily such movement of the atmosphere, a graphical representation method is also proposed. To illustrate the FA and its visualization method, a demonstration scenario “enjoying home party by five eye robots and four humans” is introduced/demonstrated. Then, a visualization method of users’ emotion information is proposed for long distance interaction such as telecommuting and distance learning, where 3D emotion vectors in Affinity Pleasure-Arousal space are illustrated by using shape-brightness-size (SBS) figure. It gives users easily understandable emotional profile information, and provides administrator strategic suggestion to improve the interaction between the users and the system. In the matching experiment between 7 basic emotions and 7 SBS figures for 8 subjects, 83.93% matching is achieved, and the administrator finds contents improvement hint in the questionnaire of emotions for 5 reading-text-tasks by 8 subjects. It is planning to be implemented in a language learning application to provide a more comfortable learning experience by contents selection based on user’s emotion.

Biography: Dr. Hirota received Dr. E. degrees from Tokyo Institute of Technology in 1979. He is currently a professor emeritus at Tokyo Institute of Technology, a director of Japan Society for the Promotion of Science Beijing Office, and a professor at Beijing Institute of Technology (in the framework of 1000 global experts program, Chinese government). His research interests include fuzzy systems, intelligent robotics, and image understanding. He experienced president of IFSA (International Fuzzy Systems Association), and president of SOFT (Japan Society for Fuzzy Theory and Systems.) He is currently life members of IEEE, Robotics Society of Japan, Information Processing Society of Japan, and Signal Processing Society of Japan, an honorary member of SOFT, a fellow of IFSA, and a life fellow of ISME (Int. Society of Management Engineering). “Banki Donat Medal, Henri Coanda Medal, Grigore MOISIL Award, SOFT best paper award, Acoustical Society of Japan best paper award, and Chinese Government Friendship Award”, honorary/adjunct professorships from “de La Salle University (Philippine), Changchun Univ. of Science & Technology (China), Harbin University of Science and Technology (China), the University of Nottingham (UK), Beijing Institute of Technology (China), and Chinese University of Geosciences Wuhan (China)”,  and Honoris Causa from “Bulacan state university (Philippine), Budapest Technical University (Hungary), Szechenyi Istvan University (Hungary), and Technical University of Kosice (Slovakia)” were awarded to him. He organized more than 10 international conferences/symposiums as founding/general/program chairs. He has been publishing more than 305 journal papers, 55 books, and 587 conference papers.

Keynote Speech 5:

Artficial Intelligence and Clinical Decision Support

Klaus-Peter Adlassnig

Medical University of Vienna, Austria

Abstract: Health information technology (IT) systems gather, store, transfer, and display the medical data of patients in a computerized and structured form. Examples are patient history data, signs collected during the physical examination, laboratory test results, and findings from clinical investigations (imaging, endoscopy, histology, genetic, and others). These describe the present or previous states of a patient’s health (or illness).

To draw conclusions about patient care based on these data in a partly or fully automated manner, one needs what is generally known as medical knowledge. One also needs this medical knowledge in a computerized and structured form. How to interpret a patient’s symptoms or laboratory data, how to administer medication but avoid adverse drug events, how to detect any worsening of the disease or identify chronic disease, and how to monitor and curb healthcare-associated infections at the medical institution—all of these are examples of smaller or larger cutouts of the large body of medical knowledge.

Combining digitized patient medical data with digitized medical knowledge to generate diagnostic, therapeutic, prognostic, or patient management suggestions is currently referred to as clinical decision support. In former times, such methods or systems were known as computer-assisted diagnosis and therapy, medical expert systems, or artificial intelligence in medicine. Now, the latter also includes machine learning in various forms.

 

Keynote Speech 6:

Artificial Intelligence in Infection Control – Healthcare Institutions Need Intelligent Information and Communication Technologies for Surveillance and Benchmarking

Walter Koller, MD

Medical University of Vienna, Austria

Abstract:   Modern healthcare and medicine depend on the implementation of best practice, which includes surveillance of, and benchmarking with, predefined quality indicators. Given the automated analysis of microbiological findings and automated surveillance of healthcare-associated infections (HAIs), we put forward arguments in favor of the increasing use of intelligent information and communication technologies for the assessment and surveillance of infection. With MOMO, a modern microbiology analytics software, as well as with MONI, a fully automated detection and monitoring system for HAIs, we registered a much greater precision of analytics and surveillance. The time taken by these systems was much less than that needed for conventional surveillance. We registered the need for timely amendments and adaptations concerning new input categories or new reporting outputs as desired by clinicians, administrators, and health authorities. Intelligent information and communication technologies are thus becoming indispensable in the construction of affordable “safety nets” for quality assurance and benchmarking, based on fully automated and intelligent data and knowledge management. These, in turn, constitute the backbone of high-level healthcare, patient safety, and error prevention.

Biography:

Born 1945 in Salzburg, Austria.

1964-1971 Medical student at the Universities in Graz (Austria), Bern (Switzerland) and Vienna;

1971 Graduation to Doctor medicinae universae at Vienna University.

1971-1981 postgraduate training in medical microbiology and hospital hygiene at the Hygiene-Institute of Vienna University (Prof. Flamm, Prof. Rotter).

Professional exchanges and trainings: 1976 and 1979 UK (IPA Colindale, Bristol Royal Informary, Hospital Infection Research Laboratory Birmingham), 1979 Sweden (Linköping and Huddinge), 1980 CDC Atlanta.

1981 Venia docendi for “Hygiene and Microbiology” at Vienna University

Scientific topics and expertise:

Applied microbiological methods in hygiene and clinical medicine,

Validation of hand and surface disinfection,

Microbiology, validation and hygienic management of medical devices, of washer-disinfectors, and of other technical equipment in hospitals,

Epidemiology of antibiotic resistance,

Intelligent IT assistance and applications for hospital epidemiology,

Knowledge transfer in Infection Prevention and Control (IPC)

Affiliations and management positions:

1989 Consultant for the Vienna General Hospital (VGH) for the development of a Hospital Infection Unit,

1994-2008 Professor for Hospital Hygiene at Medical University of Vienna (MUV). Vice-diretor of the Clinical Institute for Hygiene and Medical Microbiology of MUV. Chief infection control officer of VGH.

National and European scientific health projects:

Scientific head and coordinator of the Austrian MRSA-Surveillance project 1994-1998

Austrian representative for EU projects EARSS and HELICS, 2000-2008;

Manager of ANISS, the Austrian Nosocomial Infection Surveillance Service, and Co-Manager (together with Prof. Mittermayer) of the Austrian Reference Center for Nosocomial Infection Prevention, 2003-2008

Manager of the Austrian branch of the EU international BURDEN-project

Austrian delegate to CEN (European Standards Committee) WG 1.

Board member of several IPC and Antimicrobial Resistance Prevention Projects of the Austrian Ministry of Health, 2008-2014

Teaching:

Lectures and seminars for medical students, postgraduates, nurses, laboratory and other medical staff

Training courses and seminars for infection control doctors and nurses.

National and international scientific societies

Austrian Society for Hygiene, Microbiology and Preventive Medicine:

Member since 1975,

1984-1990 secretary, 1998-2000 president, since 2000 Board member

1990-2011 manager of the biannual DOSCH-Symposium for Sterilisation, Disinfection and Hospital Hygiene.

Healthcare Infection Society, member since 1980

German Society for Hospital Hygiene, member since 1990

Hospital hygiene assessments and knowledge transfer:

2007 Prince Court Medical Center, Kuala Lumpur, Malaysia

2007 Al Ain Hospital, Al Ain, Abu Dhabi

2012 Catholic Mission Hospital, Serabu, Sierra Leone

2016 Sonja Kill Memorial Hospital, Kampot, Cambodia

Keynote Speech 7:

Semantic Reasoning based on Grammatical Logic.

Michio Sugeno

Tokyo Institute of Technology, Japan

Biography: Michio Sugeno (LM’18) received the B.Sc. degree from the Department of Physics, University of Tokyo, Tokyo, Japan, in 1962.,He was with the company for three years and then with the Tokyo Institute of Technology, Tokyo, Japan, as a Research Associate, an Associate Professor, and a Professor from 1965 to 2000. After retiring from the Tokyo Institute of Technology, he was a Laboratory Head with the Brain Science Institute, RIKEN, from 2000 to 2005 and then as a Distinguished Visiting Professor with the Doshisha University from 2005 to 2010. Finally, he was an Emeritus Researcher with the European Centre for Soft Computing, Spain, from 2010 to 2015. He is currently an Emeritus Professor with the Tokyo Institute of Technology.,Mr. Sugeno was the President of the Japan Society for Fuzzy Theory and Systems from 1991 to 1993, and also the President of the International Fuzzy Systems Association from 1997 to 1999. He is the first recipient of the IEEE CIS Pioneer Award in Fuzzy Systems with Zadeh in 2000. He was the recipient of the 2010 IEEE Frank Rosenblatt Award. He was also the recipient of the IEEE IEEE International Conference on Systems, Man, and Cybernetics 2017 Lotfi A. Zadeh Pioneer Award.

Keynote Speech 8:

Visualizing and Understanding Neural Networks 

Anh Nguyen

Auburn University, USA

Abstract: Understanding a deep learning model’s inner-workings and decisions is increasingly important, especially for life-critical applications e.g. in medical diagnosis or criminal justice. In this talk, I will discuss our recent findings of some interesting failures of state-of-the-art image classifiers. For example, simply randomly rotating and randomly placing a familiar, training-set object in front of the camera is sufficient to bring the classification accuracy from 77.5% down to 3%. Such notorious brittleness of neural networks, therefore, begs for better explanations of why a model makes a decision. In this quest, I will share some recent work showing that interpretability methods are unreliable, being sensitive to hyperparameters and how harnessing generative models to synthesize counterfactual intervention samples can improve the robustness and accuracy of the attribution methods.

Biography: Anh completed his Ph.D. in 2017 at the University of Wyoming, working with Jeff Clune and Jason Yosinski. He is an Assistant Professor in Computer Science at the Auburn University, USA. His current research focus is Deep Learning, specifically explainable artificial intelligence and generative models. He has also worked as an ML research intern at Apple and Geometric Intelligence (now Uber AI Labs), and Bosch. Anh’s research has won 3 Best Paper Awards at CVPR, GECCO, ICML Visualization workshop, respectively, and 2 Best Research Video Awards at IJCAI and AAAI, respectively.

Keynote Speech 9:

Keynote Speech 9: “Meta heuristic approaches to imputing for Imbalanced Data Set” 

Junzo Watada

Universiti Teknologi PETRONAS, Seri-Iskandar, Perak Malaysia

ABSTRAT: Since 2011, we worked on imbalanced production data to forecast the product deficit without opening products, that is, by using a few features obtained. The sample number is quite large, but deficit products are not so many. The task is to impute some unknow values from imbalanced data set which optimize the result. Almost all the samples are good products. The given data set was imbalanced. In this talk we will report the successful approach to impute or forecast the values of given data.

[1] Lei Ding, Junzo WATADA, LIM Chun Chew, Zuwairie Ibrahim, LEE Wen Jau, Marzuki Khalid, “A SVM-RBF Method for Solving Imbalanced Data Problem,” ICIC EL, vol. 4, no. 6(B), pp. 2419-2424, 2010.12.01

[2] SC Tan, S Wang, J Watada; “A self-adaptive class-imbalance TSK neural network with applications to semiconductor defects detection;” Information sciences 427, 1-17; 2018

[3] SC Tan, J WATADA, Z Ibrahim, M Khalid, “Evolutionary Fuzzy ARTMAP Neural Networks for Classification of Semiconductor Defects,” IEEE Trans.on Neural Networks and Learning Systems, vol. 26, issue 5, pp. 933 – 950, 2015.05.01

[4] Z Sahri, R Yusof, J Watada, “FINNIM: Iterative Imputation of Missing Values in Dissolved Gas Analysis Dataset,” IEEE Trans.on Industrial Informatics, vol. 10, no. 4, pp. 1-10, 2014.08.22


Biography: Prof Junzo Watada received his B.Sc. and M.Sc. degrees in electrical engineering from Osaka City University, Japan, and his Ph.D degree from Osaka Prefecture University, Japan. Currently, he is a professor, the Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, and a Professor Emeritus at Waseda University. He is the president of Forum for Interdisciplinary Mathematics (2019-2021). He is a Life Fellow of the Japan Society for Fuzzy Theory and intelligent informatics (SOFT). Prof Watada is an IEEE senior member, Executive Chair of ISME, WCICME. He is a Co-principal Editor, a Co-Editor and an Associate Editor of various international journals, including IDT journal, ICIC Express Letters, International Journal of Systems and Control Engineering, and Fuzzy Optimization & Decision Making. His professional interests include human centric data mining, soft computing, tracking systems, knowledge engineering, financial engineering and management engineering.