Finding negative symptoms of schizophrenia in patient records

Genevieve Gorrell; Richard Jackson; Angus Roberts; Robert Stewart

Finding negative symptoms of schizophrenia in patient records

Genevieve Gorrell
, Richard Jackson
, Angus Roberts
, Robert Stewart

University of Sheffield

Research output: Chapter in Book/Report/Conference proceeding › Conference paper

13 Citations (Scopus)

Abstract

This paper reports the automatic extraction of eleven negative symptoms of schizophrenia from patient medical records. The task offers a range of difficulties depending on the consistency and complexity with which mental health professionals describe each. In order to reduce the cost of system development, rapid prototypes are built with minimal adaptation and configuration of existing software, and additional training data is obtained by annotating automatically extracted symptoms for which the system has low confidence. The system was further improved by the addition of a manually engineered rule based approach. Rule-based and machine learning approaches are combined in various ways to achieve the optimal result for each symptom. Precisions in the range of 0.8 to 0.99 have been obtained.

Original language	English
Title of host publication	Proceedings of the Workshop on NLP for Medicine and Biology associated with RANLP 2013
Place of Publication	Shoumen, Bulgaria
Publisher	INCOMA Ltd
Pages	9-17
Number of pages	8
Publication status	Published - Sept 2013
Event	Proceedings of the Workshop on NLP for Medicine an Biology associated with RANLP 2013 - Hissar, Bulgaria Duration: 13 Sept 2013 → 13 Sept 2013

Conference

Conference	Proceedings of the Workshop on NLP for Medicine an Biology associated with RANLP 2013
Country/Territory	Bulgaria
City	Hissar
Period	13/09/2013 → 13/09/2013

Access to Document

http://www.aclweb.org/anthology/W/W13/W13-5102.pdfLicence: CC BY-NC-SA

Cite this

@inbook{d2ade4f54f234e2ab1daac91a9366400,

title = "Finding negative symptoms of schizophrenia in patient records",

abstract = "This paper reports the automatic extraction of eleven negative symptoms of schizophrenia from patient medical records. The task offers a range of difficulties depending on the consistency and complexity with which mental health professionals describe each. In order to reduce the cost of system development, rapid prototypes are built with minimal adaptation and configuration of existing software, and additional training data is obtained by annotating automatically extracted symptoms for which the system has low confidence. The system was further improved by the addition of a manually engineered rule based approach. Rule-based and machine learning approaches are combined in various ways to achieve the optimal result for each symptom. Precisions in the range of 0.8 to 0.99 have been obtained. ",

author = "Genevieve Gorrell and Richard Jackson and Angus Roberts and Robert Stewart",

year = "2013",

month = sep,

language = "English",

pages = "9--17",

booktitle = "Proceedings of the Workshop on NLP for Medicine and Biology associated with RANLP 2013",

publisher = "INCOMA Ltd",

note = "Proceedings of the Workshop on NLP for Medicine an Biology associated with RANLP 2013 ; Conference date: 13-09-2013 Through 13-09-2013",

}

Gorrell, G, Jackson, R, Roberts, A & Stewart, R 2013, Finding negative symptoms of schizophrenia in patient records. in Proceedings of the Workshop on NLP for Medicine and Biology associated with RANLP 2013. INCOMA Ltd, Shoumen, Bulgaria, pp. 9-17, Proceedings of the Workshop on NLP for Medicine an Biology associated with RANLP 2013, Hissar, Bulgaria, 13/09/2013. <http://www.aclweb.org/anthology/W/W13/W13-5102.pdf>

TY - CHAP

T1 - Finding negative symptoms of schizophrenia in patient records

AU - Gorrell, Genevieve

AU - Jackson, Richard

AU - Roberts, Angus

AU - Stewart, Robert

PY - 2013/9

Y1 - 2013/9

N2 - This paper reports the automatic extraction of eleven negative symptoms of schizophrenia from patient medical records. The task offers a range of difficulties depending on the consistency and complexity with which mental health professionals describe each. In order to reduce the cost of system development, rapid prototypes are built with minimal adaptation and configuration of existing software, and additional training data is obtained by annotating automatically extracted symptoms for which the system has low confidence. The system was further improved by the addition of a manually engineered rule based approach. Rule-based and machine learning approaches are combined in various ways to achieve the optimal result for each symptom. Precisions in the range of 0.8 to 0.99 have been obtained.

AB - This paper reports the automatic extraction of eleven negative symptoms of schizophrenia from patient medical records. The task offers a range of difficulties depending on the consistency and complexity with which mental health professionals describe each. In order to reduce the cost of system development, rapid prototypes are built with minimal adaptation and configuration of existing software, and additional training data is obtained by annotating automatically extracted symptoms for which the system has low confidence. The system was further improved by the addition of a manually engineered rule based approach. Rule-based and machine learning approaches are combined in various ways to achieve the optimal result for each symptom. Precisions in the range of 0.8 to 0.99 have been obtained.

M3 - Conference paper

SP - 9

EP - 17

BT - Proceedings of the Workshop on NLP for Medicine and Biology associated with RANLP 2013

PB - INCOMA Ltd

CY - Shoumen, Bulgaria

T2 - Proceedings of the Workshop on NLP for Medicine an Biology associated with RANLP 2013

Y2 - 13 September 2013 through 13 September 2013

ER -

Finding negative symptoms of schizophrenia in patient records

Abstract

Conference

Access to Document

Fingerprint

Cite this