KFU. Card publication. KFU at CLEF eHealth 2017 Task 1: ICD-10 coding of English death certificates with recurrent neural networks

KAZAN
FEDERAL UNIVERSITY

- RUS
- 中文
- ES

KFU AT CLEF EHEALTH 2017 TASK 1: ICD-10 CODING OF ENGLISH DEATH CERTIFICATES WITH RECURRENT NEURAL NETWORKS

Form of presentation

Articles in international journals and collections

Year of publication

2017

��

��

Authors, employees of KFU

Miftakhutdinov Zulfat Shaykhinurovich, author

Tutubalina Elena Viktorovna, author

Bibliographic description in the original language

Miftahutdinov Z, Tutubalina E., KFU at CLEF eHealth 2017 Task 1: ICD-10 coding of English death certificates with recurrent neural networks//CEUR Workshop Proceedings. - 2017. - Vol.1866, Is.. - .

Annotation

This paper describes the participation of the KFU team in the CLEF eHealth 2017 challenge. Specifically, we participated in Task 1, namely “Multilingual Information Extraction - ICD-10 coding” for which we implemented recurrent neural networks to automatically assign ICD- 10 codes to fragments of death certificates written in English. Our system uses Long Short-Term Memory (LSTM) to map the input sequence into a vector representation, and then another LSTM to decode the target sequence from the vector. We initialize the input representations with word embeddings trained on user posts in social media. The encoder- decoder model obtained F-measure of 85.01% on a full test set with significant improvement as compared to the average score of 62.2% for all participants' approaches. We also obtained significant improvement from 26.1% to 44.33% on an external test set as compared to the average score of the submitted runs.

Keywords

ICD coding, deep learning, neural networks, recurrent neural networks, medical concept normalisation

The name of the journal

CEUR Workshop Proceedings

URL

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85034788154&partnerID=40&md5=78facae035f322db6f0b19e3b5dab366

Please use this ID to quote from or refer to the card

https://repository.kpfu.ru/eng/?p_id=170212&p_lang=2

Resource files

File name	Size (MB)	Format
paper_64.pdf	0,16	pdf	show / download

Full metadata record

Field DC	Value	Language
dc.contributor.author	Miftakhutdinov Zulfat Shaykhinurovich	ru_RU
dc.contributor.author	Tutubalina Elena Viktorovna	ru_RU
dc.date.accessioned	2017-01-01T00:00:00Z	ru_RU
dc.date.available	2017-01-01T00:00:00Z	ru_RU
dc.date.issued	2017	ru_RU
dc.identifier.citation	Miftahutdinov Z, Tutubalina E., KFU at CLEF eHealth 2017 Task 1: ICD-10 coding of English death certificates with recurrent neural networks//CEUR Workshop Proceedings. - 2017. - Vol.1866, Is.. - .	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/eng/?p_id=170212&p_lang=2	ru_RU
dc.description.abstract	CEUR Workshop Proceedings	ru_RU
dc.description.abstract	This paper describes the participation of the KFU team in the CLEF eHealth 2017 challenge. Specifically, we participated in Task 1, namely “Multilingual Information Extraction - ICD-10 coding” for which we implemented recurrent neural networks to automatically assign ICD- 10 codes to fragments of death certificates written in English. Our system uses Long Short-Term Memory (LSTM) to map the input sequence into a vector representation, and then another LSTM to decode the target sequence from the vector. We initialize the input representations with word embeddings trained on user posts in social media. The encoder- decoder model obtained F-measure of 85.01% on a full test set with significant improvement as compared to the average score of 62.2% for all participants' approaches. We also obtained significant improvement from 26.1% to 44.33% on an external test set as compared to the average score of the submitted runs.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	ICD coding	ru_RU
dc.subject	deep learning	ru_RU
dc.subject	neural networks	ru_RU
dc.subject	recurrent neural networks	ru_RU
dc.subject	medical concept normalisation	ru_RU
dc.title	KFU at CLEF eHealth 2017 Task 1: ICD-10 coding of English death certificates with recurrent neural networks	ru_RU
dc.type	Articles in international journals and collections	ru_RU