Multi-topic aspects in clinical text classification

Yutaka Sasaki; Brian Rea; Sophia Ananiadou

doi:10.1109/BIBM.2007.23

Multi-topic aspects in clinical text classification

Yutaka Sasaki, Brian Rea, Sophia Ananiadou

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

Abstract

This paper investigates multi-topic aspects in automatic classification of clinical free text. In many practical situations, we need to deal with documents overlapping with multiple topics. Automatic assignment of multiple ICD-9-CM codes to clinical free text in medical records is a typical multi-topic text classification problem. In this paper, we facilitate two different views on multi-topics. The Closed Topic Assumption (CTA) regards an absence of topics for a document as an explicit declaration that this document does not belong to those absent topics. In contrast, the Open Topic Assumption (OTA) considers the missing topics as neutral topics. This paper compares performances of various interpretations of a multi-topic Text Classification problem into a Machine Learning problem. Experimental results show that the characteristics of multi-topic assignments in the Medical NLP Challenge data is OTA-oriented. © 2007 IEEE.

Original language	English
Title of host publication	Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007\|Proc. IEEE Int. Conf. Bioinformatics Biomed., BIBM
Pages	62-67
Number of pages	5
DOIs	https://doi.org/10.1109/BIBM.2007.23
Publication status	Published - 2007
Event	2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007 - Fremont, CA Duration: 1 Jul 2007 → …

Conference

Conference	2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007
City	Fremont, CA
Period	1/07/07 → …

Access to Document

10.1109/BIBM.2007.23

Cite this

@inproceedings{ef1c9f588a3e4c34b408d58221d130a9,

title = "Multi-topic aspects in clinical text classification",

abstract = "This paper investigates multi-topic aspects in automatic classification of clinical free text. In many practical situations, we need to deal with documents overlapping with multiple topics. Automatic assignment of multiple ICD-9-CM codes to clinical free text in medical records is a typical multi-topic text classification problem. In this paper, we facilitate two different views on multi-topics. The Closed Topic Assumption (CTA) regards an absence of topics for a document as an explicit declaration that this document does not belong to those absent topics. In contrast, the Open Topic Assumption (OTA) considers the missing topics as neutral topics. This paper compares performances of various interpretations of a multi-topic Text Classification problem into a Machine Learning problem. Experimental results show that the characteristics of multi-topic assignments in the Medical NLP Challenge data is OTA-oriented. {\textcopyright} 2007 IEEE.",

author = "Yutaka Sasaki and Brian Rea and Sophia Ananiadou",

year = "2007",

doi = "10.1109/BIBM.2007.23",

language = "English",

isbn = "0769530311",

pages = "62--67",

booktitle = "Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007|Proc. IEEE Int. Conf. Bioinformatics Biomed., BIBM",

note = "2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007 ; Conference date: 01-07-2007",

}

Sasaki, Y, Rea, B & Ananiadou, S 2007, Multi-topic aspects in clinical text classification. in Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007|Proc. IEEE Int. Conf. Bioinformatics Biomed., BIBM. pp. 62-67, 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007, Fremont, CA, 1/07/07. https://doi.org/10.1109/BIBM.2007.23

TY - GEN

T1 - Multi-topic aspects in clinical text classification

AU - Sasaki, Yutaka

AU - Rea, Brian

AU - Ananiadou, Sophia

PY - 2007

Y1 - 2007

N2 - This paper investigates multi-topic aspects in automatic classification of clinical free text. In many practical situations, we need to deal with documents overlapping with multiple topics. Automatic assignment of multiple ICD-9-CM codes to clinical free text in medical records is a typical multi-topic text classification problem. In this paper, we facilitate two different views on multi-topics. The Closed Topic Assumption (CTA) regards an absence of topics for a document as an explicit declaration that this document does not belong to those absent topics. In contrast, the Open Topic Assumption (OTA) considers the missing topics as neutral topics. This paper compares performances of various interpretations of a multi-topic Text Classification problem into a Machine Learning problem. Experimental results show that the characteristics of multi-topic assignments in the Medical NLP Challenge data is OTA-oriented. © 2007 IEEE.

AB - This paper investigates multi-topic aspects in automatic classification of clinical free text. In many practical situations, we need to deal with documents overlapping with multiple topics. Automatic assignment of multiple ICD-9-CM codes to clinical free text in medical records is a typical multi-topic text classification problem. In this paper, we facilitate two different views on multi-topics. The Closed Topic Assumption (CTA) regards an absence of topics for a document as an explicit declaration that this document does not belong to those absent topics. In contrast, the Open Topic Assumption (OTA) considers the missing topics as neutral topics. This paper compares performances of various interpretations of a multi-topic Text Classification problem into a Machine Learning problem. Experimental results show that the characteristics of multi-topic assignments in the Medical NLP Challenge data is OTA-oriented. © 2007 IEEE.

U2 - 10.1109/BIBM.2007.23

DO - 10.1109/BIBM.2007.23

M3 - Conference contribution

SN - 0769530311

SN - 9780769530314

SP - 62

EP - 67

BT - Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007|Proc. IEEE Int. Conf. Bioinformatics Biomed., BIBM

T2 - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007

Y2 - 1 July 2007

ER -

Multi-topic aspects in clinical text classification

Abstract

Conference

Access to Document

Fingerprint

Cite this