期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2017
卷号：17
期号：7
页码：148-160
出版社：International Journal of Computer Science and Network Security
摘要：In medical domain, usually one disease is identified by looking at the patient��s data, but it may be possible that the data of an individual patient may have more than one disease at the same time. It is also possible that the diagnosed disease is not correctly identified. Our proposed system aims to identify different possible diseases present in patient��s data and on the basis of certain parameters it will identify most likely disease. Our proposed method will work in two steps:
1- In the first step, it will list out all the possible diseases prioritized with respect to certain parameters, may be shown in the form of percentages. E.g. List of possible diseases on the basis of symptoms (Percentages show possibility of disease)
? Disease A:60% ? Disease B:20% ? Disease C:10% ? No Disease Detected in Medical Database:5% ? Inaccurate Data (No proper relations exist between symptoms):5% 2- In case of multiple diseases of patient, it will be able to identify more than one possible disease. The proposed study involve more than one domain experts for the validation of results.
关键词：De-identification patient records NLP prioritize mental diseases health DSM V
