Search PubMed⌕ Search

PubMed · 9170971

[Medical practice-supporting system in pulmonary function testing].

Abstract

A pulmonary function testing system which automates measurement, storage and reporting as much possible has been functioning in Mitsui Memorial Hospital since 1992. Data obtained from four measurement apparatus are transferred to the central microcomputer by a local area network (LAN). To facilitate automatic interpretation, we developed a knowledge-based system using 87 production rules called 'PADRES', because the knowledge-based system had the following advantages over other systems; (1) The expression of knowledge is understandable and new pieces of knowledge can be easily added, (2) the process of reasoning can be clearly shown, and (3) the accumulation of many instances of data is not required. Using 'PADRES', it takes 2.6 seconds to interpret one set of data on average. Our system performs about 5,000 routine pulmonary function tests per year without faults. Because the program for interpretation is a separate module written in C language, it is readily portable to other operating systems (OS), although its original target was OS-9, a multitask operating system for microcomputers. In conclusion, the application of a knowledge-based system for microcomputers in the pulmonary function test laboratory was considered successful.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

H Kino. 1997. [Medical practice-supporting system in pulmonary function testing].. https://pubmed.ncbi.nlm.nih.gov/9170971/

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

Automated recognition of lateral from PA chest radiographs: saving seconds in a PACS environment.

Images acquired in a two-view digital chest examination are frequently not electronically distinguishable. As a result the lateral and posterioanterio (PA) images are often improperly positioned on a PACS work station. A series of 1998 chest radiographs (999 lateral, 999 PA or AP) were used to develop a neural network classifier. The images were down-sampled to 16 x 16 matrices, and a feed-forward neural network was trained and tested using the "leave-one-out" method. Using five nodes in the hidden layer, the neural network correctly identified 987 of the 999 test cases (98.8%) (average of six runs). The simple architecture and speed of this technique suggests that it would be a useful addition to PACS work station software. The accumulated time saved by correctly positioning the lateral and PA chest images on the work station monitors in accordance with each radiologist's hanging protocols was estimated to be about 1 week of radiologist time per year.

Electronic Data Processing↗