Relevance Vector Machine Learning for Neonate Pain Intensity Assessment Using Digital Imaging

被引:58
作者
Gholami, Behnood [1 ]
Haddad, Wassim M. [1 ]
Tannenbaum, Allen R. [2 ,3 ]
机构
[1] Georgia Inst Technol, Sch Aerosp Engn, Atlanta, GA 30332 USA
[2] Georgia Inst Technol, Sch Elect & Comp, Atlanta, GA 30332 USA
[3] Georgia Inst Technol, Sch Biomed Engn, Atlanta, GA 30332 USA
基金
美国国家卫生研究院;
关键词
Digital imaging; facial expression recognition; neonates; pain assessment; relevance vector machine (RVM); support vector machine (SVM); CRITICALLY-ILL; FACIAL EXPRESSION; SCALE; AGREEMENT; AGITATION; FACE;
D O I
10.1109/TBME.2009.2039214
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Pain assessment in patients who are unable to verbally communicate is a challenging problem. The fundamental limitations in pain assessment in neonates stem from subjective assessment criteria, rather than quantifiable and measurable data. This often results in poor quality and inconsistent treatment of patient pain management. Recent advancements in pattern recognition techniques using relevance vector machine (RVM) learning techniques can assist medical staff in assessing pain by constantly monitoring the patient and providing the clinician with quantifiable data for pain management. The RVM classification technique is a Bayesian extension of the support vector machine (SVM) algorithm, which achieves comparable performance to SVM while providing posterior probabilities for class memberships and a sparser model. If classes represent "pure" facial expressions (i.e., extreme expressions that an observer can identify with a high degree of confidence), then the posterior probability of the membership of some intermediate facial expression to a class can provide an estimate of the intensity of such an expression. In this paper, we use the RVM classification technique to distinguish pain from nonpain in neonates as well as assess their pain intensity levels. We also correlate our results with the pain intensity assessed by expert and nonexpert human examiners.
引用
收藏
页码:1457 / 1466
页数:10
相关论文
共 33 条
[1]   Validation of a behavioral pain scale in critically ill, sedated, and mechanically ventilated patients [J].
Aïssaoui, Y ;
Zeggwagh, AA ;
Zekraoui, A ;
Abidi, K ;
Abouqal, R .
ANESTHESIA AND ANALGESIA, 2005, 101 (05) :1470-1476
[2]  
[Anonymous], BIOMETRICS
[3]   Measuring facial grimacing for quantifying patient agitation in critical care [J].
Becouze, Pierrick ;
Hann, Christopher E. ;
Chase, J. Geoffrey ;
Shaw, Geoffrey M. .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2007, 87 (02) :138-147
[4]  
Berger J.O., 1985, Statistical decision theory and Bayesian analysis, V2nd
[5]  
Bishop C., 2006, PATTERN RECOGN, DOI DOI 10.1117/1.2819119
[6]  
Bishop CM., 1995, NEURAL NETWORKS PATT
[7]  
BONROY B, 2008, 3 EUR C US MOD INF C
[8]   Machine recognition and representation of neonatal facial displays of acute pain [J].
Brahnam, S ;
Chuang, CF ;
Shih, FY ;
Slack, MR .
ARTIFICIAL INTELLIGENCE IN MEDICINE, 2006, 36 (03) :211-222
[9]  
BRAHNAM S, 2008, INT C IM PROC COMP V
[10]   Machine assessment of neonatal facial expressions of acute pain [J].
Brahnam, Sheryl ;
Chuang, Chao-Fa ;
Sexton, Randall S. ;
Shih, Frank Y. .
DECISION SUPPORT SYSTEMS, 2007, 43 (04) :1242-1254