Predicting ICD-9 Codes Using Self-Report of Patients

The International Classification of Diseases (ICD) is a globally recognized medical classification system that aids in the identification of diseases and the regulation of health trends. The ICD framework makes it easy to keep track of records and evaluate medical data for evidence-based decision-ma...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Anandakumar Singaravelan, Chung-Ho Hsieh, Yi-Kai Liao, Jia-Lien Hsu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	ICD-9 medical record LSTM GRU Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/114cf85e20c34bc9b3a20eb0d53cab50
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:114cf85e20c34bc9b3a20eb0d53cab50
record_format	dspace
spelling	oai:doaj.org-article:114cf85e20c34bc9b3a20eb0d53cab502021-11-11T15:07:29ZPredicting ICD-9 Codes Using Self-Report of Patients10.3390/app1121100462076-3417https://doaj.org/article/114cf85e20c34bc9b3a20eb0d53cab502021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10046https://doaj.org/toc/2076-3417The International Classification of Diseases (ICD) is a globally recognized medical classification system that aids in the identification of diseases and the regulation of health trends. The ICD framework makes it easy to keep track of records and evaluate medical data for evidence-based decision-making. Several methods have predicted ICD-9 codes based on the discharge summary, clinical notes, and nursing notes. In our study, our approach only utilizes the subjective component to predict ICD-9 codes. Data cleaning and segmentation, and Natural Language Processing (NLP) techniques are applied on the subjective component during the pre-processing. Our study builds the Long Short-Term Memory (LSTM) and the Gated Recurrent Unit (GRU) to develop a model for predicting ICD-9 codes. The ICD-9 codes contain different ICD levels such as chapter, block, three-digit code, and full code. The GRU model scores the highest recall of 57.91% in the chapter level and the top-10 experiment has a recall of 67.37%. Based on the subjective component, the model can help patients in the form of a remote assistance tool.Anandakumar SingaravelanChung-Ho HsiehYi-Kai LiaoJia-Lien HsuMDPI AGarticleICD-9medical recordLSTMGRUTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10046, p 10046 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	ICD-9 medical record LSTM GRU Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	ICD-9 medical record LSTM GRU Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Anandakumar Singaravelan Chung-Ho Hsieh Yi-Kai Liao Jia-Lien Hsu Predicting ICD-9 Codes Using Self-Report of Patients
description	The International Classification of Diseases (ICD) is a globally recognized medical classification system that aids in the identification of diseases and the regulation of health trends. The ICD framework makes it easy to keep track of records and evaluate medical data for evidence-based decision-making. Several methods have predicted ICD-9 codes based on the discharge summary, clinical notes, and nursing notes. In our study, our approach only utilizes the subjective component to predict ICD-9 codes. Data cleaning and segmentation, and Natural Language Processing (NLP) techniques are applied on the subjective component during the pre-processing. Our study builds the Long Short-Term Memory (LSTM) and the Gated Recurrent Unit (GRU) to develop a model for predicting ICD-9 codes. The ICD-9 codes contain different ICD levels such as chapter, block, three-digit code, and full code. The GRU model scores the highest recall of 57.91% in the chapter level and the top-10 experiment has a recall of 67.37%. Based on the subjective component, the model can help patients in the form of a remote assistance tool.
format	article
author	Anandakumar Singaravelan Chung-Ho Hsieh Yi-Kai Liao Jia-Lien Hsu
author_facet	Anandakumar Singaravelan Chung-Ho Hsieh Yi-Kai Liao Jia-Lien Hsu
author_sort	Anandakumar Singaravelan
title	Predicting ICD-9 Codes Using Self-Report of Patients
title_short	Predicting ICD-9 Codes Using Self-Report of Patients
title_full	Predicting ICD-9 Codes Using Self-Report of Patients
title_fullStr	Predicting ICD-9 Codes Using Self-Report of Patients
title_full_unstemmed	Predicting ICD-9 Codes Using Self-Report of Patients
title_sort	predicting icd-9 codes using self-report of patients
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/114cf85e20c34bc9b3a20eb0d53cab50
work_keys_str_mv	AT anandakumarsingaravelan predictingicd9codesusingselfreportofpatients AT chunghohsieh predictingicd9codesusingselfreportofpatients AT yikailiao predictingicd9codesusingselfreportofpatients AT jialienhsu predictingicd9codesusingselfreportofpatients
_version_	1718437102489698304

Predicting ICD-9 Codes Using Self-Report of Patients

Ejemplares similares