Translate and Summarize Complaints of Patient to Electronic Health Record by BiLSTM-CNN Attention model

Haowei Song; Gangmin Li; Size Hou; Yuan Ying Qu; Hai Ning Liang; Xuming Bai

doi:10.1109/CISP-BMEI48845.2019.8965711

Translate and Summarize Complaints of Patient to Electronic Health Record by BiLSTM-CNN Attention model

Haowei Song, Gangmin Li, Size Hou, Yuan Ying Qu, Hai Ning Liang, Xuming Bai

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

3 Citations (Scopus)

Abstract

Auto-generation of Electronic Health Record (EHR) is a difficult problem in intelligent medical diagnose and health care. This paper proposes a BiLSTM-CNN attention model which directly reads patients' complaints and generates EHRs. The BiLSTM-CNN attention model is a combination of BiLSTM and CNN model with attention. The attention is achieved through the Encode-Decode model. With the coded input text the BiLSTM-CNN model is trained and used to generate EHRs. The model is validated against reference EHRs which shows satisfactory result. The ROUGE is also used as the evaluation metrics to compare with other baseline models. A brief discussion about the limitations, weakness and the future work of the proposed mode are given.

Original language	English
Title of host publication	Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019
Editors	Qingli Li, Lipo Wang
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728148526
DOIs	https://doi.org/10.1109/CISP-BMEI48845.2019.8965711
Publication status	Published - Oct 2019
Event	12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019 - Huaqiao, China Duration: 19 Oct 2019 → 21 Oct 2019

Publication series

Name	Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019

Conference

Conference	12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019
Country/Territory	China
City	Huaqiao
Period	19/10/19 → 21/10/19

Keywords

BiLSTM-CNN
Encoder-Decoder model
Natural Language Processing
Text Summarization

Access to Document

10.1109/CISP-BMEI48845.2019.8965711

Cite this

Song, H., Li, G., Hou, S., Qu, Y. Y., Liang, H. N., & Bai, X. (2019). Translate and Summarize Complaints of Patient to Electronic Health Record by BiLSTM-CNN Attention model. In Q. Li, & L. Wang (Eds.), Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019 Article 8965711 (Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CISP-BMEI48845.2019.8965711

Song, Haowei ; Li, Gangmin ; Hou, Size et al. / Translate and Summarize Complaints of Patient to Electronic Health Record by BiLSTM-CNN Attention model. Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019. editor / Qingli Li ; Lipo Wang. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019).

@inproceedings{ad1c83f164b24155945f9e5dfb331d38,

title = "Translate and Summarize Complaints of Patient to Electronic Health Record by BiLSTM-CNN Attention model",

abstract = "Auto-generation of Electronic Health Record (EHR) is a difficult problem in intelligent medical diagnose and health care. This paper proposes a BiLSTM-CNN attention model which directly reads patients' complaints and generates EHRs. The BiLSTM-CNN attention model is a combination of BiLSTM and CNN model with attention. The attention is achieved through the Encode-Decode model. With the coded input text the BiLSTM-CNN model is trained and used to generate EHRs. The model is validated against reference EHRs which shows satisfactory result. The ROUGE is also used as the evaluation metrics to compare with other baseline models. A brief discussion about the limitations, weakness and the future work of the proposed mode are given.",

keywords = "BiLSTM-CNN, Encoder-Decoder model, Natural Language Processing, Text Summarization",

author = "Haowei Song and Gangmin Li and Size Hou and Qu, {Yuan Ying} and Liang, {Hai Ning} and Xuming Bai",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019 ; Conference date: 19-10-2019 Through 21-10-2019",

year = "2019",

month = oct,

doi = "10.1109/CISP-BMEI48845.2019.8965711",

language = "English",

series = "Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Qingli Li and Lipo Wang",

booktitle = "Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019",

}

Song, H, Li, G, Hou, S, Qu, YY, Liang, HN & Bai, X 2019, Translate and Summarize Complaints of Patient to Electronic Health Record by BiLSTM-CNN Attention model. in Q Li & L Wang (eds), Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019., 8965711, Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019, Institute of Electrical and Electronics Engineers Inc., 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019, Huaqiao, China, 19/10/19. https://doi.org/10.1109/CISP-BMEI48845.2019.8965711

Translate and Summarize Complaints of Patient to Electronic Health Record by BiLSTM-CNN Attention model. / Song, Haowei; Li, Gangmin; Hou, Size et al.
Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019. ed. / Qingli Li; Lipo Wang. Institute of Electrical and Electronics Engineers Inc., 2019. 8965711 (Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - Translate and Summarize Complaints of Patient to Electronic Health Record by BiLSTM-CNN Attention model

AU - Song, Haowei

AU - Li, Gangmin

AU - Hou, Size

AU - Qu, Yuan Ying

AU - Liang, Hai Ning

AU - Bai, Xuming

PY - 2019/10

Y1 - 2019/10

N2 - Auto-generation of Electronic Health Record (EHR) is a difficult problem in intelligent medical diagnose and health care. This paper proposes a BiLSTM-CNN attention model which directly reads patients' complaints and generates EHRs. The BiLSTM-CNN attention model is a combination of BiLSTM and CNN model with attention. The attention is achieved through the Encode-Decode model. With the coded input text the BiLSTM-CNN model is trained and used to generate EHRs. The model is validated against reference EHRs which shows satisfactory result. The ROUGE is also used as the evaluation metrics to compare with other baseline models. A brief discussion about the limitations, weakness and the future work of the proposed mode are given.

AB - Auto-generation of Electronic Health Record (EHR) is a difficult problem in intelligent medical diagnose and health care. This paper proposes a BiLSTM-CNN attention model which directly reads patients' complaints and generates EHRs. The BiLSTM-CNN attention model is a combination of BiLSTM and CNN model with attention. The attention is achieved through the Encode-Decode model. With the coded input text the BiLSTM-CNN model is trained and used to generate EHRs. The model is validated against reference EHRs which shows satisfactory result. The ROUGE is also used as the evaluation metrics to compare with other baseline models. A brief discussion about the limitations, weakness and the future work of the proposed mode are given.

KW - BiLSTM-CNN

KW - Encoder-Decoder model

KW - Natural Language Processing

KW - Text Summarization

UR - http://www.scopus.com/inward/record.url?scp=85079198576&partnerID=8YFLogxK

U2 - 10.1109/CISP-BMEI48845.2019.8965711

DO - 10.1109/CISP-BMEI48845.2019.8965711

M3 - Conference Proceeding

AN - SCOPUS:85079198576

T3 - Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019

BT - Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019

A2 - Li, Qingli

A2 - Wang, Lipo

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019

Y2 - 19 October 2019 through 21 October 2019

ER -

Song H, Li G, Hou S, Qu YY, Liang HN, Bai X. Translate and Summarize Complaints of Patient to Electronic Health Record by BiLSTM-CNN Attention model. In Li Q, Wang L, editors, Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8965711. (Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019). doi: 10.1109/CISP-BMEI48845.2019.8965711

Translate and Summarize Complaints of Patient to Electronic Health Record by BiLSTM-CNN Attention model

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this