FROM REPORTS TO KNOWLEDGE FOR PATIENT SAFETY IMPROVEMENT THROUGH ADVANCEMENTS IN ARTIFICIAL INTELLIGENCE
Japan Society for the Promotion of Science (JSPS) Grant-in-Aid for Scientific Research B
Unsafe medication practices and errors can potentially be overcome through incident learning. This research attempts to develop a scalable approach to extract actionable data from unstructured textual reports to facilitate incident learning. This research will change the ways how we utilize massive collections of incident reports for preventing adverse events and promoting patient safety.
Dr Zoie SY Wilkins-WONG, Associate Professor, Division of Biostatistics and Bioinformatics,
Graduate School of Public Health, St. Luke's International University
5/F, 3-6-2 Tsukiji, Chuo-ku, Tokyo, 104-0045 Japan
‘Big Data’ Analytics for Health, Patient Safety Informatics, Health Informatics, Infectious Disease Modelling
Associate Editor of npj Digital Medicine (Impact factor: 11.653) - a highly influential Nature partner journal focusing on digital medicine advancement (https://www.nature.com/npjdigitalmed/)
Roster of Expert, WHO Digital Health Technical Advisory Group (DHTAG)
Active Member of IMIA Working Group on Technology Assessment and Quality Development in Health Informatics, International Medical Informatics Association (IMIA) (one of the 10 global members), 2017-Present.
Scientific Program Committee (SPC) & Local Organizing Committee (LOC) of Context Sensitive Health Informatics Conference (CSHI) 2017 (Pre-Medinfo conference)
Special issue editor: International Journal of Medical Informatics (IJMI)
Reviewers: Journal of Medical Internet Research (JMIR), International Journal of Medical Informatics (IJMI), Health Informatics Journal, MedInfo, CSHI, Medical Decision Making, Artificial Intelligence in Medicine
This study aims to develop an innovative information retrieval solution to extract actionable data from incident reports for patient safety improvement. The research objectives are to develop:
Annotation methods for Incident Reports
Named Entity Recognition via AI methods
Next Generation Incident Report System
AI-empowered Incident Reporting and Learning
Welcome to the trial version of the 'AI-enabled Incident Reporting and Learning System'. This system is being developed by the 'AI for Patient Safety' team led by Dr. Zoie Wong at St. Luke's International University.
What's the purpose of this system?
The aim of our team is to facilitate learning from past patient safety incidents and ultimately improve patient safety.
What can this system do?
We have been investigating how to automatically capture information from unstructured, free-text incident reports and present it as structured data.
Once an incident report has been 'structured', it can be analyzed automatically with advanced clinical AI, drawing from vast medical databases to provide the user with similar past incidents and relevant learning resources.
How does it work?
We use natural language processing to automatically extract named entities, i.e., the 'things' of interest, from incident reports. By extracting and analyzing the named entities, we can infer what type of incident occurred and other relevant details. This allows underlying reasons for medical incidents to be explored automatically on a large scale.
Context Sensitive Health Informatics: Redesigning Healthcare Work. Studies in Health Technology and Informatics. Edited by C. E. Kuziemsky C. Nøhr, Z. S. Y. Wong. Amsterdam: IOS Press, 2017.
Referred Journal Papers
Wong ZSY and Rigby M. Identifying and addressing digital health risks associated with emergency pandemic response: Problem identification, scoping review, and directions toward evidence-based evaluation. International Journal of Medical Informatics (2022) Vol 157. https://doi.org/10.1016/j.ijmedinf.2021.104639.
Liu J, Wong ZSY, So HY (2021). Automatic Patient Fall Outcome Extraction using Narrative Incident Reports. Studies in health technology and informatics. Accepted for publication.
Wong ZSY, Qiao Y, Sasano R, Zhang H, Taneda K, Ushiro S. (2021). Annotation Guidelines for Medication Errors in Incident Reports: Validation through A Mixed Methods Approach. Studies in health technology and informatics. Accepted for publication.
Su W., Fu W., Kato K., Wong ZSY. (2021). “Japan LIVE Dashboard” for COVID-19: A Scalable Solution to Monitor Real-Time and Regional-Level Epidemic Case Data. Context Sensitive Health Informatics: The Role of Informatics in Global Pandemics. doi:10.3233/SHTI210629.
Liu, J., Wong Z.S.Y., So H. Y., Tsui K. L. (2021). “Evaluating resampling methods and structured features to improve fall incident report identification by the severity level.” Journal of the American Medical Informatics Association. Volume 28, Issue 8, August 2021, Pages 1756–1764, https://doi.org/10.1093/jamia/ocab048.
Magrabi, F., Ammenwerth, E., Craven, C. K., Cresswell K., De Keizer, N. F., Medlock S. K., Scott P. J., Wong, Z.S.Y., Georgiou, A. (2021). “Managing Pandemic Responses with Health Informatics – Challenges for Assessing Digital Health Technologies.” IMIA Yearbook of Medical Informatics 2021. 2021 Apr 21. doi: 10.1055/s-0041-1726490.
Wong ZSY, Siy B, Lopes K, Georgiou A. (2020). Improving Patients’ Medication Adherence and Outcomes in Non-Hospital Settings through eHealth: A Systematic Review of Randomized Controlled Trials. International Journal of Medical Research. 2020 Aug 20;22(8):e17015. doi: 10.2196/17015.
Wong, Z. S., So, H. Y., Kwok, B. S., Lai, M. W., & Sun, D. T. (2019). Medication-rights detection using incident reports: A natural language processing and deep neural network approach. Health Informatics J, 1460458219889798.
Shiima, Y., & Wong, Z. S.-Y. (2019). Classification Scheme for Incident Reports of Medication Errors. Studies in health technology and informatics, 265, 113-118.
Magrabi, F., Ammenwerth, E., McNair, J. B., De Keizer, N. F., Hypponen, H., Nykanen, P., Rigby, M., Scott P. J., Vehko, T., Wong Z. S. Y., Georgiou, A. (2019). Artificial Intelligence in Clinical Decision Support: Challenges for Evaluating AI and Practical Implications. Yearb Med Inform.
Wong ZSY, Zhou J, Zhang QP (2018). Artificial Intelligence for infectious disease Big Data Analytics. Infection, disease & Health. 2018, 1-5.
Georgiou A, Magrabi F, Hypponen H, Wong ZS, Nykanen P, Scott PJ, et al. The Safe and Effective Use of Shared Data Underpinned by Stakeholder Engagement and Evaluation Practice. Yearbook of medical informatics. 2018.
Zhao Y, Wong ZS-Y, Tsui KL. A Framework of Rebalancing Imbalanced Healthcare Data for Rare Events Classification: A Case of Look-Alike Sound-Alike Mix-Up Incident Detection. Journal of Healthcare Engineering. 2018;2018:11.
Wang H, Zhang Q, So HY, Kwok A, Wong ZS. Temporal prediction of in-hospital falls using tensor factorisation. BMJ innovations. 2018;4(2):75-83.
Wong ZS, Chan WM, Wong EL, Chau PY, Tsui KL, Fung H. Uncovering Hidden Topics in Hong Kong Clinical Research Through Hospital Authority Convention Publications. Studies in health technology and informatics. 2017;245:624-8.
Wong ZS, Nohr C, Kuziemsky CE, Leung E, Chen F. Context Sensitive Health Informatics: Delivering 21st Century Healthcare - Building a Quality-and-Efficiency Driven System. Studies in health technology and informatics. 2017;241:1-5.
Wong ZS. Statistical classification of drug incidents due to look-alike sound-alike mix-ups. Health informatics journal. 2014(Nov 11):1-17.
Wong S-Y, Chin K-S. Organizational innovation management: An organization-wide perspective. Industrial management & data systems. 2007;107(9):1290-315.
Kurii, M., Fujita, K., Wong Z. S. Y. Prediction of Incident Report Severity Level for Medication Error Using Natural Language Processing. (自然言語処理を用いた医療インシデント報告の患者影響度推定). The 82nd National Convention of IPSJ. 5-7 March 2020, Kanazawa, Japan.
Zhang, H., Sasano, R., Koichi, T., Wong Z. S. Y. Developing a Medical Incident Report Corpus with Intention and Factuality Annotation. LREC 2020. 11-16 May 2020, Marseille, France.
Liu, J., Wong, Z. S., Tsui, K. L., So, H. Y., & Kwok, A. (2019). Exploring Hidden In-Hospital Fall Clusters from Incident Reports Using Text Analytics. Stud Health Technol Inform, 264, 1526-1527.
Dr Zoie SY WONG, Associate Professor, Graduate School of Public Health, St. Luke’s International University
Dr. Ryohei SASANO, Associate Professor, Graduate School of Informatics, Nagoya University
Dr. Kuniyoshi HAYASHI, Lecturer, Graduate School of Public Health, St. Luke’s International University
Prof. Kenjiro TAURA, Professor, Graduate School of Information Science and Technology, University of Tokyo
Dr. Kenichiro TANEDA, Chief Senior Researcher, Department of International Health and Collaboration, National Institute of Public Health
Prof. Shin USHIRO, Professor and Director, Division of Patient Safety, Kyushu University, Japan Council for Quality Health Care (JQ)
Prof. Osamu TAKAHASHI, Professor, Graduate School of Public Health, St. Luke’s International University
Dr. Takashi NINOMIYA, Professor, Graduate School of Science and Engineering, Ehime University
Dr. Katsuhide FUJITA, Associate Professor, Faculty of Engineering, Tokyo University of Agriculture and Technology
Truly inter-disciplinary research collaboration
This research involves close collaboration of multidisciplinary researchers from health informatics, NLP, AI, information science, pharmacists, physician, nurses, and PS policy makers.
This research was supported by the Japan Society for the Promotion of Science KAKENHI (Grant No. 18H03336)
We strive to advance AI methods for patient safety improvement and are experience in design studies with the aid of Big Data analytics.
If you are interested in our research or wish to get connected, please feel free to stay connected at Twitter (@zoiesywong)!