Machine assessment of neonatal facial expressions of acute pain

Sheryl Brahnam; Chao Fa Chuang; Randall S. Sexton; Frank Y. Shih

doi:10.1016/j.dss.2006.02.004

Machine assessment of neonatal facial expressions of acute pain

Sheryl Brahnam, Chao Fa Chuang, Randall S. Sexton, Frank Y. Shih

Computer Science

Research output: Contribution to journal › Article › peer-review

92 Scopus citations

Abstract

We propose that a machine assessment system of neonatal expressions of pain be developed to assist clinicians in diagnosing pain. The facial expressions of 26 neonates (age 18-72 h) were photographed experiencing the acute pain of a heel lance and three nonpain stressors. Four algorithms were evaluated on out-of-sample observations: PCA, LDA, SVMs and NNSOA. NNSOA provided the best classification rate of pain versus nonpain (90.20%), followed by SVM with linear kernel (82.35%). We believe these results indicate a high potential for developing a decision support system for diagnosing neonatal pain from images of neonatal facial displays.

Original language	English (US)
Pages (from-to)	1242-1254
Number of pages	13
Journal	Decision Support Systems
Volume	43
Issue number	4
DOIs	https://doi.org/10.1016/j.dss.2006.02.004
State	Published - Aug 2007

All Science Journal Classification (ASJC) codes

Management Information Systems
Information Systems
Developmental and Educational Psychology
Arts and Humanities (miscellaneous)
Information Systems and Management

Keywords

Linear discriminant analysis
Medical face classification
Neonate pain recognition
Neural network simultaneous optimization algorithm
Principal component analysis
Support vector machines

Access to Document

10.1016/j.dss.2006.02.004

Cite this

@article{f70d7f76cb47488fb9baf942606d4d77,

title = "Machine assessment of neonatal facial expressions of acute pain",

abstract = "We propose that a machine assessment system of neonatal expressions of pain be developed to assist clinicians in diagnosing pain. The facial expressions of 26 neonates (age 18-72 h) were photographed experiencing the acute pain of a heel lance and three nonpain stressors. Four algorithms were evaluated on out-of-sample observations: PCA, LDA, SVMs and NNSOA. NNSOA provided the best classification rate of pain versus nonpain (90.20%), followed by SVM with linear kernel (82.35%). We believe these results indicate a high potential for developing a decision support system for diagnosing neonatal pain from images of neonatal facial displays.",

keywords = "Linear discriminant analysis, Medical face classification, Neonate pain recognition, Neural network simultaneous optimization algorithm, Principal component analysis, Support vector machines",

author = "Sheryl Brahnam and Chuang, {Chao Fa} and Sexton, {Randall S.} and Shih, {Frank Y.}",

note = "Funding Information: The authors gratefully acknowledge the partial funding of this project by Missouri State University faculty grant #1015-22-2181. ",

year = "2007",

month = aug,

doi = "10.1016/j.dss.2006.02.004",

language = "English (US)",

volume = "43",

pages = "1242--1254",

journal = "Decision Support Systems",

issn = "0167-9236",

publisher = "Elsevier",

number = "4",

}

TY - JOUR

T1 - Machine assessment of neonatal facial expressions of acute pain

AU - Brahnam, Sheryl

AU - Chuang, Chao Fa

AU - Sexton, Randall S.

AU - Shih, Frank Y.

N1 - Funding Information: The authors gratefully acknowledge the partial funding of this project by Missouri State University faculty grant #1015-22-2181.

PY - 2007/8

Y1 - 2007/8

N2 - We propose that a machine assessment system of neonatal expressions of pain be developed to assist clinicians in diagnosing pain. The facial expressions of 26 neonates (age 18-72 h) were photographed experiencing the acute pain of a heel lance and three nonpain stressors. Four algorithms were evaluated on out-of-sample observations: PCA, LDA, SVMs and NNSOA. NNSOA provided the best classification rate of pain versus nonpain (90.20%), followed by SVM with linear kernel (82.35%). We believe these results indicate a high potential for developing a decision support system for diagnosing neonatal pain from images of neonatal facial displays.

AB - We propose that a machine assessment system of neonatal expressions of pain be developed to assist clinicians in diagnosing pain. The facial expressions of 26 neonates (age 18-72 h) were photographed experiencing the acute pain of a heel lance and three nonpain stressors. Four algorithms were evaluated on out-of-sample observations: PCA, LDA, SVMs and NNSOA. NNSOA provided the best classification rate of pain versus nonpain (90.20%), followed by SVM with linear kernel (82.35%). We believe these results indicate a high potential for developing a decision support system for diagnosing neonatal pain from images of neonatal facial displays.

KW - Linear discriminant analysis

KW - Medical face classification

KW - Neonate pain recognition

KW - Neural network simultaneous optimization algorithm

KW - Principal component analysis

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=34547666978&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547666978&partnerID=8YFLogxK

U2 - 10.1016/j.dss.2006.02.004

DO - 10.1016/j.dss.2006.02.004

M3 - Article

AN - SCOPUS:34547666978

SN - 0167-9236

VL - 43

SP - 1242

EP - 1254

JO - Decision Support Systems

JF - Decision Support Systems

IS - 4

ER -

Machine assessment of neonatal facial expressions of acute pain

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this