Neonatal pain facial expression: Evaluating the primal face of pain

Face-based automatic pain assessment: challenges and perspectives in neonatal intensive care units

OBJECTIVE

To describe the challenges and perspectives of the automation of pain assessment in the Neonatal Intensive Care Unit.

DATA SOURCES

A search for scientific articles published in the last 10 years on automated neonatal pain assessment was conducted in the main Databases of the Health Area and Engineering Journal Portals, using the descriptors: Pain Measurement, Newborn, Artificial Intelligence, Computer Systems, Software, Automated Facial Recognition.

SUMMARY OF FINDINGS

Fifteen articles were selected and allowed a broad reflection on first, the literature search did not return the various automatic methods that exist to date, and those that exist are not effective enough to replace the human eye; second, computational methods are not yet able to automatically detect pain on partially covered faces and need to be tested during the natural movement of the neonate and with different light intensities; third, for research to advance in this area, databases are needed with more neonatal facial images available for the study of computational methods.

CONCLUSION

There is still a gap between computational methods developed for automated neonatal pain assessment and a practical application that can be used at the bedside in real-time, that is sensitive, specific, and with good accuracy. The studies reviewed described limitations that could be minimized with the development of a tool that identifies pain by analyzing only free facial regions, and the creation and feasibility of a synthetic database of neonatal facial images that is freely available to researchers.

What Facial Features Does the Pediatrician Look to Decide That a Newborn Is Feeling Pain?

OBJECTIVE

 The study aimed to analyze the gaze fixation of pediatricians during the decision process regarding the presence/absence of pain in pictures of newborn infants.

STUDY DESIGN

 Experimental study, involving 38 pediatricians (92% females, 34.6 ± 9.0 years, 22 neonatologists) who evaluated 20 pictures (two pictures of each newborn: one at rest and one during a painful procedure), presented in random order for each participant. The Tobii-TX300 equipment tracked eye movements in four areas of interest of each picture (AOI): mouth, eyes, forehead, and nasolabial furrow. Pediatricians evaluated the intensity of pain with a verbal analogue score from 0 to 10 (0 = no pain; 10 = maximum pain). The number of pictures in which pediatricians fixed their gaze, the number of gaze fixations, and the total and average time of gaze fixations were compared among the AOI by analysis of variance (ANOVA). The visual-tracking parameters of the pictures' evaluations were also compared by ANOVA according to the pediatricians' perception of pain presence: moderate/severe (score = 6-10), mild (score = 3-5), and absent (score = 0-2). The association between the total time of gaze fixations in the AOI and pain perception was assessed by logistic regression.

RESULTS

 In the 20 newborn pictures, the mean number of gaze fixations was greater in the mouth, eyes, and forehead than in the nasolabial furrow. Also, the average total time of gaze fixations was greater in the mouth and forehead than in the nasolabial furrow. Controlling for the time of gaze fixation in the AOI, each additional second in the time of gaze fixation in the mouth (odds ratio [OR]: 1.26; 95% confidence interval [CI]: 1.08-1.46) and forehead (OR: 1.16; 95% CI: 1.02-1.33) was associated with an increase in the chance of moderate/severe pain presence in the neonatal facial picture.

CONCLUSION

 When challenged to say whether pain is present in pictures of newborn infants' faces, pediatricians fix their gaze preferably in the mouth. The longer duration of gaze fixation in the mouth and forehead is associated with an increase perception that moderate/severe pain is present.

KEY POINTS

· Neonatal pain assessment is intrinsically subjective.. · Visual tracking identifies the focus of attention of individuals.. · Adults' gaze in neonates' mouth and forehead is associated with pain perception..

Detecting discomfort in infants through facial expressions

OBJECTIVE

Detecting discomfort status of infants is particularly clinically relevant. Late treatment of discomfort infants can lead to adverse problems such as abnormal brain development, central nervous system damage and changes in responsiveness of the neuroendocrine and immune systems to stress at maturity. In this study, we exploit deep convolutional neural network (CNN) algorithms to address the problem of discomfort detection for infants by analyzing their facial expressions.

APPROACH

A dataset of 55 videos about facial expressions, recorded from 24 infants, is used in our study. Given the limited available data for training, we employ a pre-trained CNN model, which is followed by fine-tuning the networks using a public dataset with labeled facial expressions (the shoulder-pain dataset). The CNNs are further refined with our data of infants.

MAIN RESULTS

Using a two-fold cross-validation, we achieve an area under the curve (AUC) value of 0.96, which is substantially higher than the results without any pre-training steps (AUC  =  0.77). Our method also achieves better results than the existing method based on handcrafted features. By fusing individual frame results, the AUC is further improved from 0.96 to 0.98.

SIGNIFICANCE

The proposed system has great potential for continuous discomfort and pain monitoring in clinical practice.

What Faces Reveal: A Novel Method to Identify Patients at Risk of Deterioration Using Facial Expressions

OBJECTIVES

To identify facial expressions occurring in patients at risk of deterioration in hospital wards.

DESIGN

Prospective observational feasibility study.

SETTING

General ward patients in a London Community Hospital, United Kingdom.

PATIENTS

Thirty-four patients at risk of clinical deterioration.

INTERVENTIONS

A 5-minute video (25 frames/s; 7,500 images) was recorded, encrypted, and subsequently analyzed for action units by a trained facial action coding system psychologist blinded to outcome.

MEASUREMENTS AND MAIN RESULTS

Action units of the upper face, head position, eyes position, lips and jaw position, and lower face were analyzed in conjunction with clinical measures collected within the National Early Warning Score. The most frequently detected action units were action unit 43 (73%) for upper face, action unit 51 (11.7%) for head position, action unit 62 (5.8%) for eyes position, action unit 25 (44.1%) for lips and jaw, and action unit 15 (67.6%) for lower face. The presence of certain combined face displays was increased in patients requiring admission to intensive care, namely, action units 43 + 15 + 25 (face display 1, p < 0.013), action units 43 + 15 + 51/52 (face display 2, p < 0.003), and action units 43 + 15 + 51 + 25 (face display 3, p < 0.002). Having face display 1, face display 2, and face display 3 increased the risk of being admitted to intensive care eight-fold, 18-fold, and as a sure event, respectively. A logistic regression model with face display 1, face display 2, face display 3, and National Early Warning Score as independent covariates described admission to intensive care with an average concordance statistic (C-index) of 0.71 (p = 0.009).

CONCLUSIONS

Patterned facial expressions can be identified in deteriorating general ward patients. This tool may potentially augment risk prediction of current scoring systems.

Prenatal opioid exposure heightens sympathetic arousal and facial expressions of pain/distress in term neonates at 24-48 hours post birth

Purpose: The rising issue of opioid use during pregnancy poses an increased risk of fetal exposure to opioids in-utero and the development of neonatal abstinence syndrome (NAS). The cessation of exposure to opioids upon birth causes elevated levels of norepinephrine in the circulation enhancing sympathetic arousal. Skin conductance (SC) detects sympathetic-mediated sweating while the Neonatal Facial Coding System (NFCS) depicts facial expressions of stress and pain. We hypothesize that there will be a direct correlation between SC and NFCS scores, such that neonates with prenatal opioid exposure will have higher SC and facial responses to pain/stress as compared with healthy neonates without prenatal opioid exposure.Objective: This study evaluates the utility of SC and the NFCS in the objective assessment of early postnatal pain response in opioid-exposed and non-opioid exposed neonates.Methods: This prospective, single-center, pilot study enrolled opioid-exposed term neonates (>37 weeks) and healthy controls. Subjects were observed within 24-48 hours post-birth (and prior to opioid withdrawal) for pain at baseline, during, and post-heel lance/squeeze (HLS) with simultaneously measured SC and videotaped facial expressions. SC data included electro-dermal responses over time (EDR/second) and the average amplitude of responses (mean of peaks [MP]). Video data were scored using the NFCS by two trained coders with inter-rater agreement >85%.Results: SC and NFCS scores were significantly associated with both groups. The opioid-exposed neonates had significantly higher skin conductance indices, EDR/sec for the HLS phase, and MP for HLS and post phases as compared with controls (p < .05). Opioid-exposed neonates demonstrated higher NFCS at baseline (p = .003).Conclusions: Prenatal opioid exposure was associated with heightened sympathetic arousal during both pain and recovery phases and higher facial expressions of pain/distress at baseline only. A multimodal system of assessment may be useful in understanding the complexity and severity of opioid withdrawal associated with NAS.

Scope of physiological and behavioural pain assessment techniques in children - a review

Pain is an unpleasant subjective experience. At present, clinicians are using self-report or pain scales to recognise and monitor pain in children. However, these techniques are not efficient to observe the pain in children having cognitive disorder and also require highly skilled observers to measure pain. Using these techniques it is also difficult to choose the analgesic drug dosages to the patients after surgery. Thus, this conceptual work explains the demand for automatic coding techniques to evaluate pain and also it documents some evidence of techniques that act as an alternative approach for objectively determining pain in children. In this review, some good indicators of pain in children are explained in detail; they are facial expressions from an RGB image, thermal image and also feature from well proven physiological signals such as electrocardiogram, skin conductance, body temperature, surgical pleth index, pupillary reflex dilation, analgesia nociception index, photoplethysmography, perfusion index etc.

Objectively measuring pain using facial expression: is the technology finally ready?

Currently, clinicians observe pain-related behaviors and use patient self-report measures in order to determine pain severity. This paper reviews the evidence when facial expression is used as a measure of pain. We review the literature reporting the relevance of facial expression as a diagnostic measure, which facial movements are indicative of pain, and whether such movements can be reliably used to measure pain. We conclude that although the technology for objective pain measurement is not yet ready for use in clinical settings, the potential benefits to patients in improved pain management, combined with the advances being made in sensor technology and artificial intelligence, provide opportunities for research and innovation.

Neonatal procedural pain can be assessed by computer software that has good sensitivity and specificity to detect facial movements

AIM

The difficulty in assessing pain during the neonatal period is one of the main obstacles for appropriate analgesia in intensive care units. The aim of this study was to develop and validate computer software to monitor neonatal facial movements of pain in real time.

METHODS

The software was developed in the Delphi integrated development environment and provides real-time image analysis during monitoring, based on image recognition of pain-related facial actions. To validate the software performance, facial images were obtained during the monitoring of 30 neonates who were subjected to painful procedures related to daily care management. Of the 5644 images identified and analysed by the software, 360 images - 12 per infant - were randomly selected and assessed by six healthcare professionals with experience of recognising neonatal pain.

RESULTS

The agreement between the examiners and the software assessment was excellent (κ = 0.975). The software exhibited 85% sensitivity and 100% specificity in detecting neutral facial expressions in the resting state and 100% sensitivity and specificity in detecting pain during painful procedures.

CONCLUSION

It is possible to assess neonatal procedural pain using computer software that has good sensitivity and specificity to detect facial movements.

Postoperative Pain in Children After Dentistry Under General Anesthesia

The objective of this study was to determine the prevalence, severity, and duration of postoperative pain in children undergoing general anesthesia for dentistry. This prospective cross-sectional study included 33 American Society of Anesthesiology (ASA) Class I and II children 4-6 years old requiring multiple dental procedures, including at least 1 extraction, and/or pulpectomy, and/or pulpotomy of the primary dentition. Exclusion criteria were children who were developmentally delayed, cognitively impaired, born prematurely, taking psychotropic medications, or recorded baseline pain or analgesic use. The primary outcome of pain was measured by parents using the validated Faces Pain Scale-Revised (FPS-R) and Parents' Postoperative Pain Measure (PPPM) during the first 72 hours at home. The results showed that moderate-to-severe postoperative pain, defined as FPS-R ≥ 6, was reported in 48.5% of children. The prevalence of moderate-to-severe pain was 29.0% by FPS-R and 40.0% by PPPM at 2 hours after discharge. Pain subsided over 3 days. Postoperative pain scores increased significantly from baseline (P < .001, Wilcoxon matched pairs signed rank test). Moderately good correlation between the 2 pain measures existed 2 and 12 hours from discharge (Spearman rhos correlation coefficients of 0.604 and 0.603, P < .005). In conclusion, children do experience moderate-to-severe pain postoperatively. Although parents successfully used pain scales, they infrequently administered analgesics.

Measurement of Acute Pain in Infants

Background:

The use of non-validated pain measurement tools to assess infant pain represents a serious iatrogenic threat to the developing neonatal nervous system. One partial explanation for this practice may be the contradictory empirical data from studies that use newborn pain management tools constructed for infants of different developmental stages or exposed to different environmental stressors.

Purpose:

The purpose of this review is to evaluate the evidence regarding the physiologic and behavioral variables that accurately assess and measure acute pain response in infants.

Methodology:

A literature search was conducted using PUBMED and CINAHL and the search terms infant, neonate/neonatal, newborn, pain, assessment, and measurement to identify peer-reviewed studies that examined the validity and reliability of behavioral and physiological variables used for investigation of infant pain. Ten articles were identified for critical review. Principal findings: Strong evidence supports the use of the behavioral variables of facial expressions and body movements and the physiologic variables of heart rate and oxygen saturation to assess acute pain in infants.

Conclusion:

It is incumbent upon researchers and clinical nurses to ensure the validity, reliability, and feasibility of pain measures, so that the outcomes of their investigations and interventions will be developmentally appropriate and effective pain management therapies.

A Quantitative Examination of Extreme Facial Pain Expression in Neonates: The Primal Face of Pain across Time

Many pain assessment tools for preschool and school-aged children are based on facial expressions of pain. Despite broad use, their metrics are not rooted in the anatomic display of the facial pain expression. We aim to describe quantitatively the patterns of initiation and maintenance of the infant pain expression across an expressive cycle. We evaluated the trajectory of the pain expression of three newborns with the most intense facial display among 63 infants receiving a painful stimulus. A modified "point-pair" system was used to measure movement in key areas across the face by analyzing still pictures from video recording the procedure. Point-pairs were combined into "upper face" and "lower face" variables; duration and intensity of expression were standardized. Intensity and duration of expression varied among infants. Upper and lower face movement rose and overlapped in intensity about 30% into the expression. The expression reached plateau without major change for the duration of the expressive cycle. We conclude that there appears to be a shared pattern in the dynamic trajectory of the pain display among infants expressing extreme intensity. We speculate that these patterns are important in the communication of pain, and their incorporation in facial pain scales may improve current metrics.

Exploring the association between pain intensity and facial display in term newborns

BACKGROUND

Facial expression is widely used to judge pain in neonates. However, little is known about the relationship between intensity of the painful stimulus and the nature of the expression in term neonates.

OBJECTIVES

To describe differences in the movement of key facial areas between two groups of term neonates experiencing painful stimuli of different intensities.

METHODS

Video recordings from two previous studies were used to select study subjects. Four term neonates undergoing circumcision without analgesia were compared with four similar male term neonates undergoing a routine heel stick. Facial movements were measured with a computer using a previously developed 'point-pair' system that focuses on movement in areas implicated in neonatal pain expression. Measurements were expressed in pixels, standardized to percentage of individual infant face width.

RESULTS

Point pairs measuring eyebrow and eye movement were similar, as was the sum of change across the face (41.15 in the circumcision group versus 40.33 in the heel stick group). Point pair 4 (horizontal change of the mouth) was higher for the heel stick group at 9.09 versus 3.93 for the circumcision group, while point pair 5 (vertical change of the mouth) was higher for the circumcision group (23.32) than for the heel stick group (15.53).

CONCLUSION

Little difference was noted in eye and eyebrow movement between pain intensities. The mouth opened wider (vertically) in neonates experiencing the higher pain stimulus. Qualitative differences in neonatal facial expression to pain intensity may exist, and the mouth may be an area in which to detect them. Further study of the generalizability of these findings is needed.

Operant conditioning of facial displays of pain

OBJECTIVE

The operant model of chronic pain posits that nonverbal pain behavior, such as facial expressions, is sensitive to reinforcement, but experimental evidence supporting this assumption is sparse. The aim of the present study was to investigate in a healthy population a) whether facial pain behavior can indeed be operantly conditioned using a discriminative reinforcement schedule to increase and decrease facial pain behavior and b) to what extent these changes affect pain experience indexed by self-ratings.

METHODS

In the experimental group (n = 29), the participants were reinforced every time that they showed pain-indicative facial behavior (up-conditioning) or a neutral expression (down-conditioning) in response to painful heat stimulation. Once facial pain behavior was successfully up- or down-conditioned, respectively (which occurred in 72% of participants), facial pain displays and self-report ratings were assessed. In addition, a control group (n = 11) was used that was yoked to the reinforcement plans of the experimental group.

RESULTS

During the conditioning phases, reinforcement led to significant changes in facial pain behavior in the majority of the experimental group (p < .001) but not in the yoked control group (p > .136). Fine-grained analyses of facial muscle movements revealed a similar picture. Furthermore, the decline in facial pain displays (as observed during down-conditioning) strongly predicted changes in pain ratings (R(2) = 0.329).

CONCLUSIONS

These results suggest that a) facial pain displays are sensitive to reinforcement and b) that changes in facial pain displays can affect self-report ratings.

The expression and assessment of emotions and internal states in individuals with severe or profound intellectual disabilities

The expression of emotions and internal states by individuals with severe or profound intellectual disabilities is a comparatively under-researched area. Comprehensive or standardized methods of assessing or understanding the emotions and internal states within this population, whose ability to communicate is significantly compromised, do not exist. The literature base will be discussed and compared to that applicable to the general population. Methods of assessing broader internal states, notably depression, anxiety, and pain within severe or profound intellectual disabilities are also addressed. Finally, this review will examine methods of assessing internal states within genetic syndromes, including hunger, social anxiety, and happiness within Prader-Willi, Fragile-X and Angelman syndrome. This will allow for identification of robust methodologies used in assessing the expression of these internal states, some of which may be useful when considering how to assess emotions within individuals with intellectual disabilities.

Measurement of self-reported pain intensity in children and adolescents

Acute and chronic pain is a common experience in children and youth. A thorough assessment is fundamental to understand this experience and to assess and monitor treatment responses. The intensity of pain is the parameter most commonly assessed. In this article, we describe the different methods employed to assess pediatric pain intensity and review well-validated and commonly used self-report measures of pain. This review is based on the recent systematic reviews conducted for the Pediatric Initiative on Methods, Measurement, and Pain Assessment in Clinical Trials Consensus Group and the Society of Pediatric Psychology. Amongst the several types of pediatric pain measures, self-report, when available, is regarded as the primary source of information about pain intensity, to be complemented by observation and knowledge of the context. There is a large number of self-report measures of pediatric pain intensity; and there is some agreement that professionals in the clinical and research practice should assess pain intensity using the Pieces of Hurt Tool, the Faces Pain Scale, the Oucher, or Visual Analogue Scales because these measures have shown to have sound psychometric properties and clinical utility. Despite the increased number of age-appropriate self-report measures of pediatric pain intensity over the last years, we report several research gaps and priorities of future research.

Relevance vector machine learning for neonate pain intensity assessment using digital imaging

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.

Children's self-report of pain intensity: what we know, where we are headed

The present paper provides a short, practical introduction to children's self-report measures of pain intensity, followed by an overview of principles and issues. Details on individual self-report scales were previously reported in a landmark systematic review in 2006 and will not be repeated here. Broader measurement issues discussed here include interpretation of pain scores over time, across individuals and in relation to contextual factors; special considerations affecting children younger than six years of age; social communicative functions of pain reports; cognitive developmental factors in understanding pain scales and their anchors; screening for the ability to use self-report scales and training for children who do not have this skill; level of measurement (interval versus ordinal); estimating clinically significant change for groups and individuals; and measurement of aspects of pain other than intensity. Also highlighted are areas in which there has been progress and a lack of progress since the last time this topic was featured at the International Forum on Pediatric Pain in 1996. The present article closes with an outline of key areas for further research on children's self-report of pain and a brief summary of recommendations for clinicians.

Assessing pain by facial expression: facial expression as nexus

The experience of pain is often represented by changes in facial expression. Evidence of pain that is available from facial expression has been the subject of considerable scientific investigation. The present paper reviews the history of pain assessment via facial expression in the context of a model of pain expression as a nexus connecting internal experience with social influence. Evidence about the structure of facial expressions of pain across the lifespan is reviewed. Applications of facial assessment in the study of adult and pediatric pain are also reviewed, focusing on how such techniques facilitate the discovery and articulation of novel phenomena. Emerging applications of facial assessment in clinical settings are also described. Alternative techniques that have the potential to overcome barriers to the application of facial assessment arising out of its resource intensiveness are described and evaluated, including recent work on computer- based automatic assessment.

Cultural influences on the assessment of children's pain

Culture is commonly regarded as a factor in pain behaviour and experience, but the meaning of the term is often unclear. There is little evidence that pain perception is modified by cultural or ethnic factors, but pain expression by children and interpretation by caregivers may be affected by the culture of the patient or the caregiver. The present paper examines some of the research regarding cultural influences on children's pain assessment, and addresses directions for future research. A focus on cultural influences should not distract clinicians from the need to be sensitive to individual beliefs and attitudes.