2012 Fiscal Year Final Research Report
Automatic selection of the adverse reactions caused by multiple specific drug combinations from laboratory and prescription data observation
Project/Area Number |
22500432
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
Medical systems
|
Research Institution | Chiba University |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
SUZUKI Takahiro 千葉大学, 医学部附属病院, 准教授 (40323422)
|
Research Collaborator |
TU Bao・Ho 北陸先端科学技術大学院大学, 知識科学研究科, 教授 (60301199)
土井 俊祐 千葉大学, 医学部附属病院, 客員研究員 (90639072)
|
Project Period (FY) |
2010 – 2012
|
Keywords | 薬剤反応性 / 生体生命情報学 / 人口知能 / 危機管理 |
Research Abstract |
We squeezed the adverse reaction cases from the pattern of laboratory data change in admitted patients. Then checked the drugs used before the change and calculated the occurrence related to the adverse reaction cases for each drug. By comparing the occurrence of the cases with expected occurrence rate of the drug combination, we selected the specific combinations. However, they were considered not as the new unknown combination but the bystanders with other drugs, or treated for provocation or therapy. We concluded that each case must be evaluated by human, though computers can choose the high possibility cases .The approach from text mining of discharge summary failed because of many false positive and false negative cases. For example, only 82.9% was described about drug eruption in the diagnosed cases as drug eruption. Thus we need the education of writing discharge summaries as well as the development of syntactic mining.
|
Research Products
(19 results)
-
[Journal Article] Discussion of "Attitude of physicians towards automatic alerting in computerized physician order entry systems"2013
Author(s)
Bates DW, Baysari MT, Dugas M, Haefeli WE, Kushniruk AW, Lehmann CU, Liu J, Mantas J, Margolis A, Miyo K, Nohr C, Peleg M, de Quiros FG, Slight SP, Starmer J, Takabayashi K, Westbrook JI
-
Journal Title
Methods Inf Med
Volume: 52
Pages: 109-27
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-