Applying Convolutional Neural Networks to Predict the ICD-9 Codes of Medical Records
The International Statistical Classification of Disease and Related Health Problems (ICD) is an international standard system for categorizing and reporting diseases, injuries, disorders, and health conditions. Most previously-proposed disease predicting systems need clinical information collected b...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/24/7116 |
id |
doaj-12d91046fca944b49eded4022143079c |
---|---|
record_format |
Article |
spelling |
doaj-12d91046fca944b49eded4022143079c2020-12-12T00:05:21ZengMDPI AGSensors1424-82202020-12-01207116711610.3390/s20247116Applying Convolutional Neural Networks to Predict the ICD-9 Codes of Medical RecordsJia-Lien Hsu0Teng-Jie Hsu1Chung-Ho Hsieh2Anandakumar Singaravelan3Department of Computer Science and Information Engineering, Fu Jen Catholic University, New Taipei City 242062, TaiwanDepartment of Computer Science and Information Engineering, Fu Jen Catholic University, New Taipei City 242062, TaiwanDepartment of General Surgery, Shin Kong Wu Ho-Su Memorial Hospital, Taipei 111045, TaiwanGraduate Institute of Applied Science and Engineering, Fu Jen Catholic University, New Taipei City 242062, TaiwanThe International Statistical Classification of Disease and Related Health Problems (ICD) is an international standard system for categorizing and reporting diseases, injuries, disorders, and health conditions. Most previously-proposed disease predicting systems need clinical information collected by the medical staff from the patients in hospitals. In this paper, we propose a deep learning algorithm to classify disease types and identify diagnostic codes by using only the subjective component of progress notes in medical records. In this study, we have a dataset, consisting of about one hundred and sixty-eight thousand medical records, from a medical center, collected during 2003 and 2017. First, we apply standard text processing procedures to parse the sentences and word embedding techniques for vector representations. Next, we build a convolution neural network model on the medical records to predict the ICD-9 code by using a subjective component of the progress note. The prediction performance is evaluated by ten-fold cross-validation and yields an accuracy of 0.409, recall of 0.409 and precision of 0.436. If we only consider the “chapter match” of ICD-9 code, our model achieves an accuracy of 0.580, recall of 0.580, and precision of 0.582. Since our diagnostic code prediction model is solely based on subjective components (mainly, patients’ self-report descriptions), the proposed approach could serve as a remote and self-diagnosis assistance tool, prior to seeking medical advice or going to the hospital. In addition, our work may be used as a primary evaluation tool for discomfort in the rural area where medical resources are restricted.https://www.mdpi.com/1424-8220/20/24/7116diagnosis code predictionconvolutional neural networkICD-9medical record |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jia-Lien Hsu Teng-Jie Hsu Chung-Ho Hsieh Anandakumar Singaravelan |
spellingShingle |
Jia-Lien Hsu Teng-Jie Hsu Chung-Ho Hsieh Anandakumar Singaravelan Applying Convolutional Neural Networks to Predict the ICD-9 Codes of Medical Records Sensors diagnosis code prediction convolutional neural network ICD-9 medical record |
author_facet |
Jia-Lien Hsu Teng-Jie Hsu Chung-Ho Hsieh Anandakumar Singaravelan |
author_sort |
Jia-Lien Hsu |
title |
Applying Convolutional Neural Networks to Predict the ICD-9 Codes of Medical Records |
title_short |
Applying Convolutional Neural Networks to Predict the ICD-9 Codes of Medical Records |
title_full |
Applying Convolutional Neural Networks to Predict the ICD-9 Codes of Medical Records |
title_fullStr |
Applying Convolutional Neural Networks to Predict the ICD-9 Codes of Medical Records |
title_full_unstemmed |
Applying Convolutional Neural Networks to Predict the ICD-9 Codes of Medical Records |
title_sort |
applying convolutional neural networks to predict the icd-9 codes of medical records |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2020-12-01 |
description |
The International Statistical Classification of Disease and Related Health Problems (ICD) is an international standard system for categorizing and reporting diseases, injuries, disorders, and health conditions. Most previously-proposed disease predicting systems need clinical information collected by the medical staff from the patients in hospitals. In this paper, we propose a deep learning algorithm to classify disease types and identify diagnostic codes by using only the subjective component of progress notes in medical records. In this study, we have a dataset, consisting of about one hundred and sixty-eight thousand medical records, from a medical center, collected during 2003 and 2017. First, we apply standard text processing procedures to parse the sentences and word embedding techniques for vector representations. Next, we build a convolution neural network model on the medical records to predict the ICD-9 code by using a subjective component of the progress note. The prediction performance is evaluated by ten-fold cross-validation and yields an accuracy of 0.409, recall of 0.409 and precision of 0.436. If we only consider the “chapter match” of ICD-9 code, our model achieves an accuracy of 0.580, recall of 0.580, and precision of 0.582. Since our diagnostic code prediction model is solely based on subjective components (mainly, patients’ self-report descriptions), the proposed approach could serve as a remote and self-diagnosis assistance tool, prior to seeking medical advice or going to the hospital. In addition, our work may be used as a primary evaluation tool for discomfort in the rural area where medical resources are restricted. |
topic |
diagnosis code prediction convolutional neural network ICD-9 medical record |
url |
https://www.mdpi.com/1424-8220/20/24/7116 |
work_keys_str_mv |
AT jialienhsu applyingconvolutionalneuralnetworkstopredicttheicd9codesofmedicalrecords AT tengjiehsu applyingconvolutionalneuralnetworkstopredicttheicd9codesofmedicalrecords AT chunghohsieh applyingconvolutionalneuralnetworkstopredicttheicd9codesofmedicalrecords AT anandakumarsingaravelan applyingconvolutionalneuralnetworkstopredicttheicd9codesofmedicalrecords |
_version_ |
1724385853505011712 |