Budiarti, Rizqi Putri Nourma and Sukaridhoto, Sritrusta and Al Hafidz, Ilham Achmad and Satrio, Naufal Adi (2022) Symptoms Identification of ICD-11 Based on Clinical NLP Mobile Apps for Diagnosing the Disease (ICD-11). Bali Medical Journal, 11 (3). pp. 1162-1167. ISSN 2302-2914
|
PDF
Symptoms Identification of ICD-11 Based on Clinical NLP Mobile Apps for Diagnosing the Disease (ICD-11).pdf Download (426kB) | Preview |
|
|
PDF
peer review rizqi putri nourma budiarti.pdf Download (3MB) | Preview |
|
|
PDF
turnitin rizqi putri nourma budiarti.pdf Download (2MB) | Preview |
Abstract
Introduction: There are still many people in Indonesia who are not aware of the importance of information related to the early symptoms that must be experienced when they become patients. Not infrequently, this lack of information disclosure results in misdiagnosis and even leads to unexpected death. Anamnesis is a process where the doctor or medical record nurse gives several questions about the clinical pathway in the form of a narrative to facilitate early identification of the disease, and the results of this history-taking process are stored in the Electronic Medical Record (EMR). EMR narratives often cannot be processed by computers if language literacy is not standardized or ambiguous, so the need to overcome this problem requires the use of technology to minimize misdiagnosis and facilitate the identification process by developing digitization in the form of mobile applications that are integrated with Natural Language Processing technology and ICD-11 in the symptom identification process. This study aims to identify ICD-11 symptoms based on clinical NLP mobile application to diagnose the disease (ICD-11). Methods: The applications of Natural language processing includes literature study, Voice Recognition, Tokenization, Stemming, The process of Stopwords Removal, Named Entity Recognition, Data Translation, Access ICD Data, and Mobile User Interfaces. Results: Named Entity Recognition (NER) is used to identify symptoms of digestive system diseases, with an accuracy rate of 74.3%. In stemming and stopwords processing, the NLP accuracy rates are 95.9% and 97.2%, respectively. Conclusions: This research focuses on the application mobile and development of the Named Entity Recognition (NER) model. The importance of the NLP process in the development of information, especially for word processing, aims as a device that simplifies speech recognition systems to be more helpful.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | ICD-11; NLP mobile apps; disease |
Subjects: | T Technology > T Technology (General) |
Divisions: | Faculty of Technique > Program Study of Information Systems |
Depositing User: | Mr. . Bagas |
Date Deposited: | 10 Jan 2023 02:46 |
Last Modified: | 10 Jan 2023 02:46 |
URI: | http://repository.unusa.ac.id/id/eprint/9152 |
Actions (login required)
![]() |
View Item |