Development of computer-assisted system for laboratory diagnosis based on a large collection of case records with well defined clinical diagnoses
| Project/Area Number |
10672193
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Laboratory medicine
|
|---|
| Research Institution | KAWASAKI MEDICAL SCHOOL |
|---|
Principal Investigator |
ICHIHARA Kiyoshi Kawasaki Medical School, Medicine, Associate Professor, 医学部, 助教授 (10144495)
|
|---|
| Project Period (FY) |
1998 – 2000
|
| Project Status |
Completed (Fiscal Year 2000)
|
| Budget Amount *help |
¥2,400,000 (Direct Cost: ¥2,400,000)
Fiscal Year 2000: ¥700,000 (Direct Cost: ¥700,000)
Fiscal Year 1999: ¥700,000 (Direct Cost: ¥700,000)
Fiscal Year 1998: ¥1,000,000 (Direct Cost: ¥1,000,000)
|
|---|
| Keywords | laboratory epidemiology / evidence based laboratory medicine / computer-assisted laboratory interpretation / database / laboratory diagnosis / log-likelihood dynamic graphics / dynamic graphics / コンピュータ / データベース / evidence based / 病態検査情報 |
|---|
| Research Abstract |
To promote evidence-based practice and education of laboratory medicine, we created a database of 1951 typical case records consisting of 37 common diseases. Cases without therapy or major complication were carefully selected from our archive of hospital admission records. Characteristic clinical symptoms and signs to judge the severity or subtypes of each diagnostic group were recorded together with general and specific laboratory test results. A user friendly computer system for interpretive laboratory diagnosis was also created. It features (1) automatic graphics for visualizing distributions of laboratory values and/or prevalence of the clinical symptoms and signs for any diagnostic group, (2) simultaneous display of distribution of essential test results for any combinations of diagnostic groups, (3) dynamic partitioning of cases within a diagnostic group with regard to a specified clinical characteristics, (4) guidance of diagnosis by dynamic calculation of a novel similarity index or sum of log-likelihood, which represents matching of a given set of signs/values with those of typical cases in the database, (5) capability to automatically re-scale any laboratory test value by supplying information on the linear relationship between values of ours and any other laboratory's.
|
Report
(4 results)
Research Products
(20 results)
