| Project/Area Number |
18H03336
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 62010:Life, health and medical informatics-related
|
|---|
| Research Institution | St. Luke's International University |
|---|
Principal Investigator |
WONG Shui Yee 聖路加国際大学, 専門職大学院公衆衛生学研究科(公衆衛生大学院), 准教授 (70791599)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
林 邦好 聖路加国際大学, 専門職大学院公衆衛生学研究科(公衆衛生大学院), 講師 (00793217)
笹野 遼平 名古屋大学, 情報学研究科, 准教授 (70603918)
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Project Status |
Completed (Fiscal Year 2021)
|
| Budget Amount *help |
¥17,290,000 (Direct Cost: ¥13,300,000、Indirect Cost: ¥3,990,000)
Fiscal Year 2020: ¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2019: ¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2018: ¥7,410,000 (Direct Cost: ¥5,700,000、Indirect Cost: ¥1,710,000)
|
|---|
| Keywords | WHO Patient Safety / Artificial Intelligence / Incident reports / NLP / NER / Adverse drug events / Deep learning / adverse drug events / deep learning (DL) / Patient Safety / Artifical Intelligence / Incident Reports / Named Entity Recognition / Adverse Drug Events / Named entity recognition / Adverse Drug Event / Deep learning (DL) / Adverse drug events (ADEs) / Named entity / Natural language processing / Named Entities / Deep Learning |
|---|
| Outline of Final Research Achievements |
Our research team has successfully completed all three specific research tasks (including 1. developed and validated annotation guidelines for medication errors incident reports, 2. developed and evaluated AI models for named entity recognistion for incident reports and 3. created prototype of AI-empowered incident report system). The FY 2018-2022 Kakenhi B team has successfully achieved optimal research outcomes and the fund has directly (as of today) resulted in 15 major international peer-reviewed publications, supported 5 Ph.D./master students (locally and globally), built our team’s significant roles in global patient safety informatics research, and our work has also drawn attention at the Health AI Acceleration Consortium (Ministry of Health, Labor and Welfare). Furthermore, our team members have disseminated to the WHO Global Patient Safety Network and many global patient safety meetings, such as WHO meeting in Florence (Dec 2019), WHO Policy Makers’ Forum (Feb 2022).
|
| Academic Significance and Societal Importance of the Research Achievements |
Our study innovates the way to collect, utilize and retrieve incident reports using the recent advances in AI/NLP methods. Our outcome is beneficial to local and global authorities/hospitals to enhance patient safety through enabling robust medication error detection and effective incident learning.
|
