Method of diagnosing cerebral infarction
First Claim
1. A method of diagnosing cerebral infarction, comprising the steps of:
- obtaining a set of teaching data on each subject in a group of health subjects and subjects of cerebral infarction, each said teaching data set comprising an age of said subject, measurement of at least one coagulo-fibrinolytic molecular marker for said subject, and an index indicative of cerebral infarction for said subject;
modifying each said measurement of coagulo-fibrinolytic molecular marker in said teaching data in order to cause said measurements to be independent of age;
inputting each set of the modified teaching data into a neural network for use in diagnosing patients and making said neural network learn said teaching data;
obtaining a set of testing data on a patient to be diagnosed, said testing data comprising an age of said patient and measurement of said at least one coagulo-fibrinolytic molecular marker for said patient;
modifying each said measurement of coagulo-fibrinolytic molecular marker in said testing data in order to cause said measurements to be independent of age for purposes of said diagnosing;
inputting the modified testing data into said neural network and obtaining therefrom, as a diagnostic output for said patient, an index indicative of cerebral infarction which is specific to said patient; and
diagnosing cerebral infarction in said patient from said index.
0 Assignments
0 Petitions
Accused Products
Abstract
A novel method of diagnosing cerebral infarction using a neural network, wherein plural sets of data previously obtained from healthy and sick persons, each including an age, measured values of coagulo-fibrinolytic molecular markers ( e.g., D-dimer, TAT and PAP) , an index indicative of the state of cerebral infarction (e.g., 0 for healthy persons and 1 for sick persons) and the like, are repeatedly input into a neural network to let it learn the correlation of these characteristics and, thereafter, a set of data of a person to be diagnosed, including his age, measured values of the coagulo-fibrinolytic molecular markers and the like, are input in the neural network to obtain an index indicative of his state of cerebral infarction as a degree of dangerousness of cerebral infarction. This method is significantly higher in accuracy as compared with the prior art methods using the same data.
28 Citations
2 Claims
-
1. A method of diagnosing cerebral infarction, comprising the steps of:
-
obtaining a set of teaching data on each subject in a group of health subjects and subjects of cerebral infarction, each said teaching data set comprising an age of said subject, measurement of at least one coagulo-fibrinolytic molecular marker for said subject, and an index indicative of cerebral infarction for said subject; modifying each said measurement of coagulo-fibrinolytic molecular marker in said teaching data in order to cause said measurements to be independent of age; inputting each set of the modified teaching data into a neural network for use in diagnosing patients and making said neural network learn said teaching data; obtaining a set of testing data on a patient to be diagnosed, said testing data comprising an age of said patient and measurement of said at least one coagulo-fibrinolytic molecular marker for said patient; modifying each said measurement of coagulo-fibrinolytic molecular marker in said testing data in order to cause said measurements to be independent of age for purposes of said diagnosing; inputting the modified testing data into said neural network and obtaining therefrom, as a diagnostic output for said patient, an index indicative of cerebral infarction which is specific to said patient; and diagnosing cerebral infarction in said patient from said index. - View Dependent Claims (2)
-
Specification