ICHSM 2024

Invited Speakers

 

 

Prof. Dr. Ahmet Murat Ozbayoglu

TOBB University of Economics and Technology, Turkiye

 

A.M. Ozbayoglu graduated from the Department of Electrical Engineering at METU, Ankara, Turkey in 1991, then he got his Msc and PhD degrees from the department of Engineering Management at Missouri University of Science and Technology, USA in 1993 and 1996, respectively. After graduation, he joined MEMC Electronics (now became SunEdison), USA as a software project engineer, programmer and analyst working on silicon wafer manufacturing software and data automation projects. In 2005, he went back to academia by joining the Department of Computer Engineering of TOBB University of Economics and Technology, in Ankara, Turkey. His research interests include machine learning, pattern recognition, deep learning, financial forecasting, computational intelligence, machine vision. He has conducted 20 MSc and 2 PhD theses in theoretical and applied machine learning. He has published more than 40 journal and 100 international conference papers along with numerous white papers and technical reports. He has served in many academic and industrial projects as principal investigator, researcher and consultant. Also, he has been actively involved in social and technical committes both on and off-campus. He is a member of ACM and IEEE Computational Intelligence Society.

 

Speech title "Generative Adversarial Networks in Medical Imaging and Health Informatics"

Abstract-Generative Adversarial Networks (GANs) have emerged as a revolutionary technology in the field of medical imaging and health informatics, offering significant advancements in data augmentation, image reconstruction, and segmentation. Meanwhile, the transformative potential of GANs also have their benefits and drawbacks.
GANs facilitate data augmentation by generating realistic synthetic medical images, thus overcoming the limitations of small datasets and enhancing the training of machine learning models. This capability is particularly vital in medical domains where acquiring large volumes of labeled data is challenging and expensive. Through data augmentation, GANs contribute to improved diagnostic accuracy and robust predictive modeling.
In image reconstruction, GANs excel in restoring high-quality images from low-resolution or corrupted inputs. This has effective implications for enhancing the clarity and detail of medical images such as MRI, CT, and ultrasound scans. The ability to reconstruct images with high fidelity aids clinicians in making more accurate diagnoses and treatment plans, ultimately improving patient outcomes.
Segmentation, a critical task in medical image analysis, also benefits from the application of GANs. These networks can portray anatomical structures and pathological regions with remarkable precision, facilitating tasks such as tumor detection, organ segmentation, and lesion quantification. The improved segmentation accuracy offered by GANs supports better-informed clinical decisions and personalized patient care.
However, the implementation of GANs in medical imaging and health informatics is not without challenges. The training process of GANs is notoriously complex, requiring substantial computational resources and expertise to achieve convergence. Additionally, the synthetic data generated by GANs may occasionally introduce artifacts or biases, potentially impacting clinical interpretations. Ethical considerations surrounding data privacy and the synthetic nature of GAN-generated images also warrant careful examination.
Hence, GANs present a promising avenue for advancing medical imaging and health informatics, offering substantial benefits in data augmentation, image reconstruction, and segmentation. As the technology matures, addressing the associated challenges will be crucial to fully realizing its potential and ensuring its safe and effective integration into clinical practice.
 

 

 

Prof. Dr. Director Lai-Shiun Lai

Taichung Veterans General Hospital, Taiwan

 

Lai-Shiun Lai is currently the Director of the Computer and Communications Center at Taichung Veterans General Hospital in Taichung (TCVGH), Taiwan.
With nearly 30 years of experience in hospital information system management, he has dedicated his career to enhancing healthcare technology and optimizing information systems for better patient care.
He has served as an advisor to the Ministry of Health and Welfare, the Ministry of Education, the National Health Research Institutes, the Hospital Association of Taiwan, and the Taiwan Association for Medical Informatics and providing expert guidance on various initiatives to improve the nation's healthcare infrastructure.
In 2021, he was honored with two prestigious awards: the Outstanding I.T. Elite Award, a national accolade in Taiwan, and the Award of Model Civil Servants from the Veteran Affairs Committee.
His main experiences include serving as the Leader of the Section of the Computer and Communications Center from 2005 to 2016, and as a Programmer and Analyst of the Computer and Communications Center from 1995 to 2005.
 

Speech title "Information System of Smart Hospital"

Abstract-Information System is the key foundation of Smart Hospital. Taichung Veterans General Hospital (TCVGH) has been recognized as the only hospital in Taiwan to be listed in Newsweek's top 300 World's Best Smart Hospitals in 2023 (Ranking #254) and 2024 (Ranking #246).
By the survey of Healthcare Information Management System Society (HIMSS) of United States, Taichung Veterans General Hospital (TCVGH) is the Second Highest Global Ranking of DHI (Digital Healthcare Indicator) Score in 2024. TCVGH was also the first National Medical Center in Taiwan to achieve HIMSS EMRAM Stage 6 and 7 validations in 2023, it takes only 8 months, also created the fastest record in Taiwan.
In the National Recognition of Taiwan, Taichung Veterans General Hospital (TCVGH) is the first hospital in Taiwan to Achieve 3 Times of Smart Hospital Award (2015, 2019 and 2023).
Taichung Veterans General Hospital (TCVGH) also deployed hospital information system to 12 Regional Branch Veterans Hospitals around Taiwan. It created some miracles. First, this work was done During COVID-19 Period (2019-2020). Second, the hospital information system was deployed to 8 Hospitals only in 8 months, which created the fastest record in Taiwan Hospital’s History. Now Taichung Veterans General Hospital (TCVGH) leads one of largest hospital information systems in Taiwan.
In this session, we will introduce Digital Strategy, Hospital Information System, and some innovations of Smart Hospital.
 

 

 

Dr. Ece Uzun

Pathology and Laboratory Medicine, Brown University, USA
 

Dr. Ece (Gamsiz) Uzun, MS, PhD, FAMIA is the founding Director of Clinical Bioinformatics at Lifespan Academic Medical Center, Associate Director of Center for Clinical Cancer Informatics and Data Science (CCIDS) and Associate Professor of Pathology and Laboratory Medicine. She is the Editor-in-Chief at JMIR Bioinformatics and Biotechnology.
Dr.Uzun received B.S in Chemical Engineering at Istanbul Technical University and M.S. in Biological Sciences and Bioengineering at Sabanci University in Istanbul, Turkey. She completed her PhD in Chemical Engineering at Northeastern University, Boston, MA. During her PhD, she studied mathematical modeling of drug delivery systems and focused on oral drug delivery. Upon completion of PhD, she joined Brown University as a postdoctoral fellow. During her postdoctoral studies, she worked on computational biology of neurodevelopmental disorders. In April 2016, Dr. Uzun joined the department of Pathology and Laboratory Medicine. In addition to her clinical work at Molecular Pathology, she has a research group focusing on translational bioinformatics and machine learning based predictive models in cancer and neurodevelopmental disorders. She is the Chair-Elect of the American Medical Informatics Associate (AMIA) Genomics and Translational Bioinformatics Working Group and co-Chair of the Women in AMIA Career Development Committee.

Speech title "Transforming Cancer Recurrence Predictions with Machine Learning Based Models"

Abstract-Cancer is one of the leading causes of morbidity and mortality worldwide, with millions of new cases diagnosed each year. According to World Health Organization (WHO), nearly 10 million people worldwide lost their lives to cancer in 2020. Cancer recurrence remains a significant challenge, as it can occur months or even years after the initial treatment, underscoring the need for effective monitoring and predictive strategies. Understanding a patient’s likelihood of cancer recurrence is crucial for optimizing treatment selection and timing, which can improve overall outcomes, and enhance quality of life. Deep learning (DL) models have shown increasing promise in various medical applications, including predicting disease recurrence. Among all cancer types, low-grade gliomas (LGGs) are primary grade I and grade II brain tumors characterized by slow growth and high recurrence rates. Approximately 62% of patients experience recurrence within five years, and 17%–32% progress from low to high-grade glioma1-4. Due to the slow progression, high recurrence, and relatively long survival associated with LGG, physicians must carefully balance the benefits of intervention against potential treatment related complications. To explore the capability of DL models for predicting recurrence using tabular data in cancers with small datasets, we built LUNAR (Lower-grade glioma recUrreNce clAssifieR), a multilayer perceptron (MLP) designed to predict LGG recurrence based using an existing dataset of over 150 patients with both genomic and clinical data. To assess the performance of LUNAR, we trained six traditional ML models including logistic regression, linear support vector classifier (SVC), stochastic gradient descent (SGD) classifier, random forest, k-nearest neighbors, and decision tree. LUNAR outperformed traditional ML models, demonstrating the effectiveness of DL models in predicting LGG recurrence.

 

 

Prof. William Yu Chung Wang

University of Waikato, New Zealand

 

With the experience of being an IT engineer and corporate consultant, Dr. William Wang has supervised research projects and provided industrial consultancy in Australasia and Asian regions regarding global enterprise planning, process re-engineering, and health information analytics. He has a number of Ph.D. graduates working in universities, research institutes, and the industry. He also has experience in practical projects in Enterprise Systems such as the planning of implementing SAP and MS Dynamics, using Windows Data sever to host Data Analytics research projects with tensor flow & Python. These projects have specifically highlighted the interdisciplinary issues that are related to systems integration, enterprise systems adoption & maintenance, systems architecture for large firms and SMEs, and data analytics in medical institutions. Those are both quantitative and qualitative. He serves on the editorial board/advisory board of several international journals. His papers appear in Information Systems Journal, Industrial Systems and Data Management, Computational and Structural Biotechnology Journal, Journal of Global Information Management, and proceedings of international conferences in Health Informatics and Information Systems.

Speech title "Design Science Research Approach in enhancing clinical decision-making – the prediction of diabetes mellitus complications"

Abstract-Health information systems (HIS) are essential in modern healthcare, transforming data into actionable insights for informed decision-making and improved patient care. Clinical decision support systems (CDSSs) are a key area within HIS, particularly for diagnosing and predicting diseases. Given the global prevalence and severe impact of diabetes, predicting its complications is crucial. This study addresses an issue at Health New Zealand by developing a CDSS to predict complications of diabetes mellitus (CoDM). Despite having a rich dataset, the decision-making involvement needs further development. The study created a CDSS, focusing on design and data analysis. The system design followed design science research methodologies (DSRM), while data analysis used survival analysis methods to address research gaps. The CDSS developed resolves real-world issues and fills research gaps. The design perspective validates the use of DSRM in systematic solution design, and the data analytics perspective confirms the suitability of survival techniques. The CDSS provides a chronological risk percentage for 10 CoDM in a New Zealand cohort, with significant academic and managerial implications. It aids in early warnings, treatment plans, and efficient management of diabetes data repositories. Future research should enhance model accuracy with richer datasets and address interoperability challenges with the hospital information systems and processes performance.

 

 

Dr. Chalong Cheewakriangkrai

Chiang Mai University, Thailand

 

Dr. Chalong Cheewakriangkrai is currently a faculty member and teaching staff in Department of Obstetrics & Gynecology, Faculty of Medicine, Chiang Mai University, Thailand. His research interests are in the area of clinical epidemiology, uterine cancer, chemotherapy and targeted therapy in gynecologic cancer, and gynecological surgery. His experience as guest editor for several issues of Journal of Universal Computer Science (J.UCS) (SCI), Journal of Computing Science and Engineering (Ei/Scopus), International Journal of Computers and Applications (Ei/Scopus), Journal of Data Analysis (ECONLIT). He is currently serving as CO-PIs of the Taiwan MOST Two-year International Project (MOST106-2218-E-040 -001 -MY2) "The Implementation of Evidence-based CDSS for Gynecologic Cancer in Northern Thailand-- Contributions to International Efforts" and CSMU Hospital International Project (CSH-2018-D-002) "Developing evidence-based control programs for women with multiple primary malignantneoplasms (MPMNs): a multilateral-international cooperation."

Speech title "Global Health Challenges: “Bridging AI with global networking for clinical research"

Abstract-Global collaboration in health research has become increasingly critical in addressing complex health challenges that transcend national borders. With the advent of Artificial Intelligence (AI), the potential to enhance global health research has expanded significantly.

AI technologies facilitate the collection, analysis, and sharing of vast amounts of health data from diverse populations, enabling researchers to identify patterns, predict outcomes, and develop targeted interventions more efficiently. Moreover, AI supports the integration of multidisciplinary expertise, bridging gaps between regions and institutions, and fostering a more cohesive global research community. Through AI-driven models, global health initiatives can be more responsive to emerging health threats, ensuring timely and effective interventions.

However, this collaboration also necessitates addressing challenges such as data privacy, ethical considerations, and equitable access to AI technologies across different regions.
In conclusion, the synergy between global collaboration and AI in health research holds promise for advancing public health, improving healthcare delivery, and ultimately achieving better health outcomes worldwide.