EP0389992A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Apparatus for automatically analyzing validity of medical examination data
Assignee: Toshiba Corp
•
Filing: 1990-03-23
•
Granted: —
•
Expires: 2010-03-23
Abstract
Abstract An apparatus for automatically analyzing validity of medical examination data capable of accurately assessing a necessity of the re-examination. The apparatus includes a neural network<(2)>for learning human judgements of the necessity of re-examination from previously collected sets of medical examination data accompanied with corresponding teacher data indicating whether re-examination was performed for each set of medical examination data, and for making assessment of the necessity of re-examination for each set of the medical examination data collected, in accordance with the human judgements of the necessity of re-examination learned.
Inventors
- 👤 Akinami Ohhashi
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-10-23 22:42
CPC Classifications
G; G06; G06N; G06N3/00; G06N3/02; G06N3/04; G06N3/0499; G06N3/08; G06N3/09; G16; G16H; G16H15/00; G16H50/00; G16H50/20
Claims Analysis
Total Claims: 9
Claim 1
Independent Claim
98 words
An apparatus for automatically analyzing validity of medical examination data by making an assessment of a necessity of re-examination, comprising: means for collecting the medical examination data; neural network for learning human judgements for the necessity of re-examination from previously collected sets of medical examination data accompanied with corresponding teacher data indicating whether re-examination was performed for each set of medical examination data, and for making an assessment for the necessity of re-examination for each set of the medical examination data collected by the collecting means, in accordance with the human judgements for the necessity of re-examination learned.
Claim 2
Independent Claim
98 words
An apparatus for automatically analyzing validity of medical examination data by making an assessment of a necessity of re-examination, comprising: means for collecting the medical examination data; neural network for learning human judgements for the necessity of re-examination from previously collected sets of medical examination data accompanied with corresponding teacher data indicating whether re-examination was performed for each set of medical examination data, and for making an assessment for the necessity of re-examination for each set of the medical examination data collected by the collecting means, in accordance with the human judgements for the necessity of re-examination learned.
Claim 3
Dependent Claim
24 words
The apparatus of claim 1, wherein the neural network is equipped with units capable of dealing with continuously varying values between 0 and 1.
Claim 4
Dependent Claim
75 words
The apparatus of claim 1, wherein each value of the medical examination data is divided into a plurality of distinct ranges and the neural network is equipped with a plurality of input units capable of dealing with discrete values which are assigned to the distinct ranges for each value of the medical examination data, the plurality of input units indicating which one of the distinct ranges does each value of the medical examination data fall.
Claim 5
Dependent Claim
76 words
The apparatus of claim 1, further comprising: means for correcting the assessment made by the neural network; and means for memorizing the medical examination data and the corresponding teacher data each time the assessment made by the neural network is corrected at the correcting means, and wherein the neural network learns the human judgements for the necessity of re-examination again after new medical examination data and corresponding teacher data are newly memorized in the memorizing means.
Claim 6
Dependent Claim
65 words
The apparatus of claim 4, wherein the memorizing means memorizes the medical examination data and the corresponding teacher data in an order of acquisition of the medical examination data, and wherein newest medical examination data and corresponding teacher data with respect to which the assessment made by the neural network is corrected replace oldest medical examination data and corresponding teacher data in the memorizing means.
Claim 7
Dependent Claim
57 words
The apparatus of claim 1, wherein the medical examination data comprises a plurality of items, and the medical examination data are classified into groups, each group representing a distinct combination of an arbitrary number of the items, and wherein the learning and assessment making by the neural network are carried out with respect to each group separately.
Claim 8
Dependent Claim
35 words
The apparatus of claim 1, wherein the medical examination data are given to the neural network after normalization to convert values of the medical examination data into values within a range between 0 and 1.
Claim 9
Dependent Claim
70 words
The apparatus of claim 7, wherein each value of the medical examination data is divided into a plurality of distinct ranges, the neural network is equipped with a plurality of input units capable of dealing with continuously varying values which are assigned to the distinct ranges for each value of the medical examination data, and the normalization is carried out with respect to each one of the distinct ranges independently.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.