Multilevel Pain Assessment with Functional Near-Infrared Spectroscopy: Evaluating ΔHBO2 and ΔHHB Measures for Comprehensive Analysis.

Assessing pain in non-verbal patients is challenging, often depending on clinical judgment which can be unreliable due to fluctuations in vital signs caused by underlying medical conditions. To date, there is a notable absence of objective diagnostic tests to aid healthcare practitioners in pain assessment, especially affecting critically-ill or advanced dementia patients. Neurophysiological information, i.e., functional near-infrared spectroscopy (fNIRS) or electroencephalogram (EEG), unveils the brain's active regions and patterns, revealing the neural mechanisms behind the experience and processing of pain. This study focuses on assessing pain via the analysis of fNIRS signals combined with machine learning, utilising multiple fNIRS measures including oxygenated haemoglobin (ΔHBO2) and deoxygenated haemoglobin (ΔHHB). Initially, a channel selection process filters out highly contaminated channels with high-frequency and high-amplitude artifacts from the 24-channel fNIRS data. The remaining channels are then preprocessed by applying a low-pass filter and common average referencing to remove cardio-respiratory artifacts and common gain noise, respectively. Subsequently, the preprocessed channels are averaged to create a single time series vector for both ΔHBO2 and ΔHHB measures. From each measure, ten statistical features are extracted and fusion occurs at the feature level, resulting in a fused feature vector. The most relevant features, selected using the Minimum Redundancy Maximum Relevance method, are passed to a Support Vector Machines classifier. Using leave-one-subject-out cross validation, the system achieved an accuracy of 68.51%±9.02% in a multi-class task (No Pain, Low Pain, and High Pain) using a fusion of ΔHBO2 and ΔHHB. These two measures collectively demonstrated superior performance compared to when they were used independently. This study contributes to the pursuit of an objective pain assessment and proposes a potential biomarker for human pain using fNIRS.

"Where does it hurt?": Exploring EDA Signals to Detect and Localise Acute Pain.

Pain is a highly unpleasant sensory experience, for which currently no objective diagnostic test exists to measure it. Identification and localisation of pain, where the subject is unable to communicate, is a key step in enhancing therapeutic outcomes. Numerous studies have been conducted to categorise pain, but no reliable conclusion has been achieved. This is the first study that aims to show a strict relation between Electrodermal Activity (EDA) signal features and the presence of pain and to clarify the relation of classified signals to the location of the pain. For that purpose, EDA signals were recorded from 28 healthy subjects by inducing electrical pain at two anatomical locations (hand and forearm) of each subject. The EDA data were preprocessed with a Discrete Wavelet Transform to remove any irrelevant information. Chi-square feature selection was used to select features extracted from three domains: time, frequency, and cepstrum. The final feature vector was fed to a pool of classification schemes where an Artificial Neural Network classifier performed best. The proposed method, evaluated through leave-one-subject-out cross-validation, provided 90% accuracy in pain detection (no pain vs. pain), whereas the pain localisation experiment (hand pain vs. forearm pain) achieved 66.67% accuracy.Clinical relevance- This is the first study to provide an analysis of EDA signals in finding the source of the pain. This research explores the viability of using EDA for pain localisation, which may be helpful in the treatment of noncommunicable patients.

Validation of an instrumented mouthguard in rugby union-a pilot study comparing impact sensor technology to video analysis.

Background: To better understand the biomechanical profile of direct head impacts and the game scenarios in which they occur in Rugby Union, there is a need for an on-field validation of a new instrumented mouthguard (IMG) against the reference standard. This study considers the potential of a combined biomechanical (IMG) and video analysis approach to direct head impact recognition, both of which in isolation have limitations. The aim of this study is to assess the relationship between an instrumented mouthguard and video analysis in detection of direct head impacts in rugby union. Design: Pilot Study - Observational Cohort design. Methods: The instrumented mouthguard was worn by ten (3 backs, 7 forwards) professional Rugby Union players during the 2020-21 Gallagher Premiership (UK) season. Game-day video was synchronized with timestamped head acceleration events captured from the instrumented mouthguard. Direct Head Impacts were recorded in a 2 × 2 contingency table to determine sensitivity. Impact characteristics were also collected for all verified head impacts to further the understanding of head biomechanics during the game. Results: There were 2018 contact events that were reviewed using video analysis. Of those 655 were categorized as direct head impacts which also correlated with a head acceleration event captured by the IMG. Sensitivity analysis showed an overall sensitivity of 93.6% and a positive predictive value (PPV of 92.4%). When false positives were excluded due to ball out of play, mouthguard removal or handling after a scoring situation or stoppage, PPV was improved (98.3%). Most verified head impacts occurred in and around the ruck contest (31.2%) followed by impacts to the primary tackler (28.4%). Conclusion: This pilot validation study demonstrates that this IMG provides a highly accurate measurement device that could be used to complement video verification in the recognition of on-field direct head impacts. The frequency and magnitude of direct head impacts derived from specific game scenarios has been described and allows for greater recognition of high-risk situations. Further studies with larger sample sizes and in different populations of Rugby Union players are required to develop our understanding of head impact and enable strategies for injury mitigation.

Multimodal physiological sensing for the assessment of acute pain.

Pain assessment is a challenging task encountered by clinicians. In clinical settings, patients' self-report is considered the gold standard in pain assessment. However, patients who are unable to self-report pain are at a higher risk of undiagnosed pain. In the present study, we explore the use of multiple sensing technologies to monitor physiological changes that can be used as a proxy for objective measurement of acute pain. Electrodermal activity (EDA), photoplethysmography (PPG), and respiration (RESP) signals were collected from 22 participants under two pain intensities (low and high) and on two different anatomical locations (forearm and hand). Three machine learning models were implemented, including support vector machines (SVM), decision trees (DT), and linear discriminant analysis (LDA) for the identification of pain. Various pain scenarios were investigated, identification of pain (no pain, pain), multiclass (no pain, low pain, high pain), and identification of pain location (forearm, hand). Reference classification results from individual sensors and from all sensors together were obtained. After feature selection, results showed that EDA was the most informative sensor in the three pain conditions, 93.2±8% in identification of pain, 68.9±10% in the multiclass problem, and 56.0±8% for the identification of pain location. These results identify EDA as the superior sensor in our experimental conditions. Future work is required to validate the obtained features to improve its feasibility in more realistic scenarios. Finally, this study proposes EDA as a candidate to design a tool that can assist clinicians in the assessment of acute pain of nonverbal patients.

A systematic review of neurophysiological sensing for the assessment of acute pain.

Pain is a complex and personal experience that presents diverse measurement challenges. Different sensing technologies can be used as a surrogate measure of pain to overcome these challenges. The objective of this review is to summarise and synthesise the published literature to: (a) identify relevant non-invasive physiological sensing technologies that can be used for the assessment of human pain, (b) describe the analytical tools used in artificial intelligence (AI) to decode pain data collected from sensing technologies, and (c) describe the main implications in the application of these technologies. A literature search was conducted in July 2022 to query PubMed, Web of Sciences, and Scopus. Papers published between January 2013 and July 2022 are considered. Forty-eight studies are included in this literature review. Two main sensing technologies (neurological and physiological) are identified in the literature. The sensing technologies and their modality (unimodal or multimodal) are presented. The literature provided numerous examples of how different analytical tools in AI have been applied to decode pain. This review identifies different non-invasive sensing technologies, their analytical tools, and the implications for their use. There are significant opportunities to leverage multimodal sensing and deep learning to improve accuracy of pain monitoring systems. This review also identifies the need for analyses and datasets that explore the inclusion of neural and physiological information together. Finally, challenges and opportunities for designing better systems for pain assessment are also presented.

Interpretation of Depression Detection Models via Feature Selection Methods.

Given the prevalence of depression worldwide and its major impact on society, several studies employed artificial intelligence modelling to automatically detect and assess depression. However, interpretation of these models and cues are rarely discussed in detail in the AI community, but have received increased attention lately. In this study, we aim to analyse the commonly selected features using a proposed framework of several feature selection methods and their effect on the classification results, which will provide an interpretation of the depression detection model. The developed framework aggregates and selects the most promising features for modelling depression detection from 38 feature selection algorithms of different categories. Using three real-world depression datasets, 902 behavioural cues were extracted from speech behaviour, speech prosody, eye movement and head pose. To verify the generalisability of the proposed framework, we applied the entire process to depression datasets individually and when combined. The results from the proposed framework showed that speech behaviour features (e.g. pauses) are the most distinctive features of the depression detection model. From the speech prosody modality, the strongest feature groups were F0, HNR, formants, and MFCC, while for the eye activity modality they were left-right eye movement and gaze direction, and for the head modality it was yaw head movement. Modelling depression detection using the selected features (even though there are only 9 features) outperformed using all features in all the individual and combined datasets. Our feature selection framework did not only provide an interpretation of the model, but was also able to produce a higher accuracy of depression detection with a small number of features in varied datasets. This could help to reduce the processing time needed to extract features and creating the model.

Help-seeker expectations and outcomes of a crisis support service: Comparison of suicide-related and non-suicide-related contacts to lifeline Australia.

Lifeline Australia aims to prevent suicide and support community members in personal crisis via the provision of free anonymous telephone, online chat and text message services. This study aimed to identify the expectations and outcomes of Lifeline help-seekers, including whether there are differences between suicide-related and non-suicide-related contacts. Help-seekers (N = 553) who had previously contacted Lifeline via telephone, online chat, or text message crisis services were recruited via social media and a link provided after Lifeline service use, who completed an online survey about their awareness, expectations and outcomes of Lifeline's services. The responses from help-seekers who self-reported suicide-related and non-suicide-related reasons for contact were compared. Participants were highly aware of Lifeline's services, particularly the phone service. The main expectations of all help-seekers were to feel heard and listened to, feel less upset and feel understood. There were 59.5% of the sample that reported suicidality as a reason for contact. Suicide-related contacts endorsed more reasons for contact than non-suicide-related contacts. Expectations of suicide-related help-seekers were greater, but they were less likely to report that their expectations were met. The high expectations and complexity of suicide-related contacts reveal the challenges in meeting the needs of this high-priority group, particularly within the context of the multiple demands on crisis support services.

Exoskeleton robots for lower limb assistance: A review of materials, actuation, and manufacturing methods.

The field of robot-assisted physical rehabilitation and robotics technology for providing support to the elderly population is rapidly evolving. Lower limb robot aided rehabilitation and assistive technology have been a focus for the engineering community during the last three decades as several robotic lower limb exoskeletons have been proposed in the literature as well as some being commercially available. Numerous manufacturing techniques and materials have been developed for lower limb exoskeletons during the last two decades, resulting in the design of a variety of robot exoskeletons for gait assistance for elderly and disabled people. One of the most important aspects of developing exoskeletons is the selection of the most appropriate proper material. The material selection strongly influences the overall weight and performance of the exoskeleton robot. The most suitable fabrication method for material is also an important parameter for the development of lower limb robot exoskeletons. In addition to the materials and manufacturing methods, the actuation method plays a vital role in the development of these robot exoskeletons. Even though various materials, manufacturing methods and actuators are reported in the literature for these lower limb robot exoskeletons, there are still avenues of improvement in these three domains. In this review, we have examined various lower limb robotic exoskeletons, concentrating on the three main aspects of material, manufacturing, and actuation. We have focused on the advantages and drawbacks of various materials and manufacturing practices as well as actuation methods. A discussion on future directions of research is provided for the engineering community covering the material, manufacturing and actuation methods.

Deeply Supervised Discriminative Learning for Adversarial Defense.

Deep neural networks can easily be fooled by an adversary with minuscule perturbations added to an input image. The existing defense techniques suffer greatly under white-box attack settings, where an adversary has full knowledge of the network and can iterate several times to find strong perturbations. We observe that the main reason for the existence of such vulnerabilities is the close proximity of different class samples in the learned feature space of deep models. This allows the model decisions to be completely changed by adding an imperceptible perturbation to the inputs. To counter this, we propose to class-wise disentangle the intermediate feature representations of deep networks, specifically forcing the features for each class to lie inside a convex polytope that is maximally separated from the polytopes of other classes. In this manner, the network is forced to learn distinct and distant decision regions for each class. We observe that this simple constraint on the features greatly enhances the robustness of learned models, even against the strongest white-box attacks, without degrading the classification performance on clean images. We report extensive evaluations in both black-box and white-box attack scenarios and show significant gains in comparison to state-of-the-art defenses.

Quinine Ingestion During the Latter Stages of a 3,000-m Time Trial Fails to Improve Cycling Performance.

The ingestion of quinine, a bitter tastant, improves short-term (30 s) cycling performance, but it is unclear whether this effect can be integrated into the last effort of a longer race. The purpose of this study was to determine whether midtrial quinine ingestion improves 3,000-m cycling time-trial (TT) performance. Following three familiarization TTs, 12 well-trained male cyclists (mean ± SD: mass = 76.6 ± 9.2 kg, maximal aerobic power = 390 ± 50 W, maximal oxygen uptake = 4.7 ± 0.6 L/min) performed four experimental 3,000-m TTs on consecutive days. This double-blind, crossover design study had four randomized and counterbalanced conditions: (a) Quinine 1 (25-ml solution, 2 mM of quinine); (b) Quinine 2, replicate of Quinine 1; (c) a 25-ml sweet-tasting no-carbohydrate solution (Placebo); and (d) 25 ml of water (Control) consumed at the 1,850-m point of the TT. The participants completed a series of perceptual scales at the start and completion of all TTs, and the power output was monitored continuously throughout all trials. The power output for the last 1,000 m for all four conditions was similar: mean ± SD: Quinine 1 = 360 ± 63 W, Quinine 2 = 367 ± 63 W, Placebo = 364 ± 64 W, and Control = 367 ± 58 W. There were also no differences in the 3,000-m TT power output between conditions. The small perceptual differences between trials at specific 150-m splits were not explained by quinine intake. Ingesting 2 mM of quinine during the last stage of a 3,000-m TT did not improve cycling performance.

Automated Measurement of Head Movement Synchrony during Dyadic Depression Severity Interviews.

With few exceptions, most research in automated assessment of depression has considered only the patient's behavior to the exclusion of the therapist's behavior. We investigated the interpersonal coordination (synchrony) of head movement during patient-therapist clinical interviews. Our sample consisted of patients diagnosed with major depressive disorder. They were recorded in clinical interviews (Hamilton Rating Scale for Depression, HRSD) at 7-week intervals over a period of 21 weeks. For each session, patient and therapist 3D head movement was tracked from 2D videos. Head angles in the horizontal (pitch) and vertical (yaw) axes were used to measure head movement. Interpersonal coordination of head movement between patients and therapists was measured using windowed cross-correlation. Patterns of coordination in head movement were investigated using the peak picking algorithm. Changes in head movement coordination over the course of treatment were measured using a hierarchical linear model (HLM). The results indicated a strong effect for patient-therapist head movement synchrony. Within-dyad variability in head movement coordination was found to be higher than between-dyad variability, meaning that differences over time in a dyad were higher as compared to the differences between dyads. Head movement synchrony did not change over the course of treatment with change in depression severity. To the best of our knowledge, this study is the first attempt to analyze the mutual influence of patient-therapist head movement in relation to depression severity.

Evaluating and Validating Emotion Elicitation Using English and Arabic Movie Clips on a Saudi Sample.

With the advancement of technology in both hardware and software, estimating human affective states has become possible. Currently, movie clips are used as they are a widely-accepted method of eliciting emotions in a replicable way. However, cultural differences might influence the effectiveness of some video clips to elicit the target emotions. In this paper, we describe several sensors and techniques to measure, validate and investigate the relationship between cultural acceptance and eliciting universal expressions of affect using movie clips. For emotion elicitation, a standardised list of English language clips, as well as an initial set of Arabic video clips are used for comparison. For validation, bio-signal devices to measure physiological and behavioural responses associated with emotional stimuli are used. Physiological and behavioural responses are measured from 29 subjects of Arabic background while watching the selected clips. For the six emotions' classification, a multiclass SVM (six-class) classifier using the physiological and behavioural measures as input results in a higher recognition rate for elicited emotions from Arabic video clips (avg. 60%) compared to the English video clips (avg. 52%). These results might reflect that using video clips from the subjects' culture is more likely to elicit the target emotions. Besides measuring the physiological and behavioural responses, an online survey was carried out to evaluate the effectiveness of the selected video clips in eliciting the target emotions. The online survey, having on average 220 respondents for each clip, supported the findings.

Sway Risk Analysis Based on Age Group Classification.

Human postural sway is the horizontal movement, which is generated to control a person's balance while walking or standing. Changes in postural sway patterns are a reflection of changes in brain signals and in physical health affected by a person's aging process. This increases the likelihood of falling. In this paper, we propose a method to estimate the age groups of elderly people based on the extracted sway measurements. These measurements are computed based on learning the postural sway signal from video footage only. Then, we use the person's real age and the estimated age group to define a risk of a fall for the elderly people becoming more likely. This may lead to an early intervention and help them to prevent serious falls or injuries by putting countermeasures in place, e.g. physical exercise regimes. The conducted experiments show the reliability of the proposed method to produce a risk analysis tool for elderly based on their estimated sway signals.

Gait Estimation and Analysis from Noisy Observations.

People's walking style - their gait - can be an indicator of their health as it is affected by pain, illness, weakness, and aging. Gait analysis aims to detect gait variations. It is usually performed by an experienced observer with the help of different devices, such as cameras, sensors, and/or force plates. Frequent gait analysis, to observe changes over time, is costly and impractical. This paper initiates an inexpensive gait analysis based on recorded video. Our methodology first discusses estimating gait movements from predicted 2D joint locations that represent selected body parts from videos. Then, using a long-short-term memory (LSTM) regression model to predict 3D (Vicon) data, which was recorded simultaneously with the videos as ground truth. Feet movements estimated from video are highly correlated with the Vicon data, enabling gait analysis by measuring selected spatial gait parameters (step and cadence length, and walk base) from estimated movements. Using inexpensive and reliable cameras to record, estimate and analyse a person's gait can be helpful; early detection of its changes facilitates early intervention.

Facial feature tracking: a psychophysiological measure to assess exercise intensity?

The primary aim of this study was to determine whether facial feature tracking reliably measures changes in facial movement across varying exercise intensities. Fifteen cyclists completed three, incremental intensity, cycling trials to exhaustion while their faces were recorded with video cameras. Facial feature tracking was found to be a moderately reliable measure of facial movement during incremental intensity cycling (intra-class correlation coefficient = 0.65-0.68). Facial movement (whole face (WF), upper face (UF), lower face (LF) and head movement (HM)) increased with exercise intensity, from lactate threshold one (LT1) until attainment of maximal aerobic power (MAP) (WF 3464 ± 3364mm, P < 0.005; UF 1961 ± 1779mm, P = 0.002; LF 1608 ± 1404mm, P = 0.002; HM 849 ± 642mm, P < 0.001). UF movement was greater than LF movement at all exercise intensities (UF minus LF at: LT1, 1048 ± 383mm; LT2, 1208 ± 611mm; MAP, 1401 ± 712mm; P < 0.001). Significant medium to large non-linear relationships were found between facial movement and power output (r2 = 0.24-0.31), HR (r2 = 0.26-0.33), [La-] (r2 = 0.33-0.44) and RPE (r2 = 0.38-0.45). The findings demonstrate the potential utility of facial feature tracking as a non-invasive, psychophysiological measure to potentially assess exercise intensity.

Cross-Cultural Detection of Depression from Nonverbal Behaviour.

Millions of people worldwide suffer from depression. Do commonalities exist in their nonverbal behavior that would enable cross-culturally viable screening and assessment of severity? We investigated the generalisability of an approach to detect depression severity cross-culturally using video-recorded clinical interviews from Australia, the USA and Germany. The material varied in type of interview, subtypes of depression and inclusion healthy control subjects, cultural background, and recording environment. The analysis focussed on temporal features of participants' eye gaze and head pose. Several approaches to training and testing within and between datasets were evaluated. The strongest results were found for training across all datasets and testing across datasets using leave-one-subject-out cross-validation. In contrast, generalisability was attenuated when training on only one or two of the three datasets and testing on subjects from the dataset(s) not used in training. These findings highlight the importance of using training data exhibiting the expected range of variability.

Facial Performance Transfer via Deformable Models and Parametric Correspondence.

The issue of transferring facial performance from one person's face to another's has been an area of interest for the movie industry and the computer graphics community for quite some time. In recent years, deformable face models, such as the Active Appearance Model (AAM), have made it possible to track and synthesize faces in real time. Not surprisingly, deformable face model-based approaches for facial performance transfer have gained tremendous interest in the computer vision and graphics community. In this paper, we focus on the problem of real-time facial performance transfer using the AAM framework. We propose a novel approach of learning the mapping between the parameters of two completely independent AAMs, using them to facilitate the facial performance transfer in a more realistic manner than previous approaches. The main advantage of modeling this parametric correspondence is that it allows a "meaningful" transfer of both the nonrigid shape and texture across faces irrespective of the speakers' gender, shape, and size of the faces, and illumination conditions. We explore linear and nonlinear methods for modeling the parametric correspondence between the AAMs and show that the sparse linear regression method performs the best. Moreover, we show the utility of the proposed framework for a cross-language facial performance transfer that is an area of interest for the movie dubbing industry.