Open Access
Subscription or Fee Access
A Combined Classification Model for Chinese Clinical Notes
Jun Liang, XiaoWei Zheng, MeiFang Xu, XiaoJun He, YaWen Xing
Abstract
Patient's drinking played an important role in a variety of health problems research and diagnostic. A small amount of alcohol information usually hidden in the mass of unstructured narrative EMR text, which required sophisticated techniques for extraction and classification. This article described the extraction and classification methods of patient’s drinking that combined with rule-based and machine-learning-techniques-based, and assessed the performance of the system. System got a 87.30% F measure on the training dataset and an 82.60% F measure on the test dataset, using the macro-average F-score, the common evaluation metric used in NLP areas and medical statistics areas. The experimental result shows that we can use machine-learning-models to replace labor-intensive steps in the rule-based system, in addition, the hybrid system retained some of the advantages of rule-based system, for example, high performance. Therefore, this system can be applied to drinking risk factors screening of which the study people is based on massive EMR data in epidemiological studies.
Keywords
Natural language processing, Feature selection, Electronic medical records, Documentation, Health care
Full Text:
PDF
Disclaimer/Regarding indexing issue:
We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.
