Spirometry is used for evaluating lung function, playing a crucial role in assessing lung health and monitoring treatment effectiveness. Numerous studies demonstrate the potential of Machine Learning algorithms to match human experts in spirometry classification, although most approaches depend on custom data pre-processing and complex model architectures. Therefore, we apply efficient Time Series (TS) classifiers to quickly and computationally assure spirometry signal quality, enabling realtime deployment. Seven classifiers were implemented to classify spirometry curves as ‘Acceptable’ or ‘Not Acceptable’, with performance referenced against results from similar studies. The bestperforming classifier was FreshPRINCE, a TS method combining TSFresh feature extraction with Rotation Forest classifier. The FreshPRINCE model achieved an accuracy of 0.9449, precision, recall and $F 1$ Score of $0.9745,0.9586$ and 0.9665, consistently matching and sometimes outperforming more complex models. These findings suggest models, such as FreshPRINCE, could streamline spirometry analysis, reducing computational burden, whilst maintaining classification performance.

The EmoPain 2020 Challenge is the first international competition aimed at creating a uniform platform for the comparison of multi-modal machine learning and multimedia processing methods of chronic pain assessment from human expressive behaviour, and also the identification of pain-related behaviours. The objective of the challenge is to promote research in the development of assistive technologies that help improve the quality of life for people with chronic pain via real-time monitoring and feedback to help manage their condition and remain physically active. The challenge also aims to encourage the use of the relatively underutilised, albeit vital bodily expression signals for automatic pain and pain-related emotion recognition. This paper presents a description of the challenge, competition guidelines, bench-marking dataset, and the baseline systems' architecture and performance on the Challenge's three sub-tasks: pain estimation from facial expressions, pain recognition from multimodal movement, and protective movement behaviour detection.

Although clinical best practice suggests that affect awareness could enable more effective technological support for physical rehabilitation through personalisation to psychological needs, designers need to consider what affective states matter, and how they should be tracked and addressed. In this article, we set the standard by analysing how the major affective factors in chronic pain (pain, fear/anxiety, and low/depressed mood) interfere with everyday physical functioning. Further, based on discussion of the modality that should be used to track these states to enable technology to address them, we investigated the possibility of using movement behaviour to automatically detect the states. Using two body movement datasets on people with chronic pain, we show that movement behaviour enables very good discrimination between two emotional distress levels (F1=0.86), and three pain levels (F1=0.9). Performance remained high (F1=0.78 for two pain levels) with a reduced set of movement sensors. Finally, in an overall discussion, we suggest how technology-provided encouragement and awareness can be personalised given the capability to automatically monitor the relevant states, towards addressing the barriers that they pose. In addition, we highlight movement behaviour features to be tracked to provide technology with information necessary for such personalisation.

Early detection of mental health changes in individuals with serious mental illness is critical for effective intervention. CrossCheck is the first step towards the passive monitoring of mental health indicators in patients with schizophrenia and paves the way towards relapse prediction and early intervention. In this paper, we present initial results from an ongoing randomized control trial, where passive smartphone sensor data is collected from 21 outpatients with schizophrenia recently discharged from hospital over a period ranging from 2-8.5 months. Our results indicate that there are statistically significant associations between automatically tracked behavioral features related to sleep, mobility, conversations, smart-phone usage and self-reported indicators of mental health in schizophrenia. Using these features we build inference models capable of accurately predicting aggregated scores of mental health indicators in schizophrenia with a mean error of 7.6% of the score range. Finally, we discuss results on the level of personalization that is needed to account for the known variations within people. We show that by leveraging knowledge from a population with schizophrenia, it is possible to train accurate personalized models that require fewer individual-specific data to quickly adapt to new users.

Pain-related emotions are a major barrier to effective self rehabilitation in chronic pain. Automated coaching systems capable of detecting these emotions are a potential solution. This paper lays the foundation for the development of such systems by making three contributions. First, through literature reviews, an overview of how pain is expressed in chronic pain and the motivation for detecting it in physical rehabilitation is provided. Second, a fully labelled multimodal dataset (named `EmoPain') containing high resolution multiple-view face videos, head mounted and room audio signals, full body 3D motion capture and electromyographic signals from back muscles is supplied. Natural unconstrained pain related facial expressions and body movement behaviours were elicited from people with chronic pain carrying out physical exercises. Both instructed and non-instructed exercises were considered to reflect traditional scenarios of physiotherapist directed therapy and home-based self-directed therapy. Two sets of labels were assigned: level of pain from facial expressions annotated by eight raters and the occurrence of six pain-related body behaviours segmented by four experts. Third, through exploratory experiments grounded in the data, the factors and challenges in the automated recognition of such expressions and behaviour are described, the paper concludes by discussing potential avenues in the context of these findings also highlighting differences for the two exercise scenarios addressed.

Mobile sensing systems have made significant advances in tracking human behavior. However, the development of personalized mobile health feedback systems is still in its infancy. This paper introduces MyBehavior, a smartphone application that takes a novel approach to generate deeply personalized health feedback. It combines state-of-the-art behavior tracking with algorithms that are used in recommendation systems. MyBehavior automatically learns a user's physical activity and dietary behavior and strategically suggests changes to those behaviors for a healthier lifestyle. The system uses a sequential decision making algorithm, Multi-armed Bandit, to generate suggestions that maximize calorie loss and are easy for the user to adopt. In addition, the system takes into account user's preferences to encourage adoption using the pareto-frontier algorithm. In a 14-week study, results show statistically significant increases in physical activity and decreases in food calorie when using MyBehavior compared to a control condition.

Despite its importance in social interactions, laughter remains little studied in affective computing. Intelligent virtual agents are often blind to users’ laughter and unable to produce convincing laughter themselves. Respiratory, auditory, and facial laughter signals have been investigated but laughter-related body movements have received less attention. The aim of this study is threefold. First, to probe human laughter perception by analyzing patterns of categorisations of natural laughter animated on a minimal avatar. Results reveal that a low dimensional space can describe perception of laughter “types”. Second, to investigate observers’ perception of laughter (hilarious, social, awkward, fake, and non-laughter) based on animated avatars generated from natural and acted motion-capture data. Significant differences in torso and limb movements are found between animations perceived as laughter and those perceived as non-laughter. Hilarious laughter also differs from social laughter. Different body movement features were indicative of laughter in sitting and standing avatar postures. Third, to investigate automatic recognition of laughter to the same level of certainty as observers’ perceptions. Results show recognition rates of the Random Forest model approach human rating levels. Classification comparisons and feature importance analyses indicate an improvement in recognition of social laughter when localized features and nonlinear models are used.

Physical activity is essential in chronic pain rehabilitation. However, anxiety due to pain or a perceived exacerbation of pain causes people to guard against beneficial exercise. Interactive rehabiliation technology sensitive to such behaviour could provide feedback to overcome such psychological barriers. To this end, we developed a Support Vector Machine framework with the feature level fusion of body motion and muscle activity descriptors to discriminate three levels of pain (none, low and high). All subjects underwent a forward reaching exercise which is typically feared among people with chronic back pain. The levels of pain were categorized from control subjects (no pain) and thresholded self reported levels from people with chronic pain. Salient features were identified using a backward feature selection process. Using feature sets from each modality separately led to high pain classification F1 scores of 0.63 and 0.69 for movement and muscle activity respectively. However using a combined bimodal feature set this increased to F1 = 0.8.

Despite the importance of laughter in social interactions it remains little studied in affective computing. Respiratory, auditory, and facial laughter signals have been investigated but laughter-related body movements have received almost no attention. The aim of this study is twofold: first an investigation into observers' perception of laughter states (hilarious, social, awkward, fake, and non-laughter) based on body movements alone, through their categorization of avatars animated with natural and acted motion capture data. Significant differences in torso and limb movements were found between animations perceived as containing laughter and those perceived as nonlaughter. Hilarious laughter also differed from social laughter in the amount of bending of the spine, the amount of shoulder rotation and the amount of hand movement. The body movement features indicative of laughter differed between sitting and standing avatar postures. Based on the positive findings in this perceptual study, the second aim is to investigate the possibility of automatically predicting the distributions of observer's ratings for the laughter states. The findings show that the automated laughter recognition rates approach human rating levels, with the Random Forest method yielding the best performance.

Many real world datasets occur or can be arranged into multi-modal structures. With such datasets, the tasks to be learnt can be referenced by multiple indices. Current multitask learning frameworks are not designed to account for the preservation of this information. We propose the use of multilinear algebra as a natural way to model such a set of related tasks. We present two learning methods; one is an adapted convex relaxation method used in the context of tensor completion. The second method is based on the Tucker decomposition and on alternating minimization. Experiments on synthetic and real data indicate that the multilinear approaches provide a significant improvement over other multitask learning methods. Overall our second approach yields the best performance in all datasets.

Plantar lesions induced by biomechanical dysfunction pose a considerable socioeconomic health care challenge, and failure to detect lesions early can have significant effects on patient prognoses. Most of the previous works on plantar lesion identification employed the analysis of biomechanical microenvironment variables like pressure and thermal fields. This paper focuses on foot kinematics and applies kernel principal component analysis (KPCA) for nonlinear dimensionality reduction of features, followed by Fisher's linear discriminant analysis for the classification of patients with different types of foot lesions, in order to establish an association between foot motion and lesion formation. Performance comparisons are made using leave-one-out cross-validation. Results show that the proposed method can lead to approximately 94% correct classification rates, with a reduction of feature dimensionality from 2100 to 46, without any manual preprocessing or elaborate feature extraction methods. The results imply that foot kinematics contain information that is highly relevant to pathology classification and also that the nonlinear KPCA approach has considerable power in unraveling abstract biomechanical features into a relatively low-dimensional pathology-relevant space.

Time-to-event analysis is important in a wide range of applications from clinical prognosis to risk modeling for credit scoring and insurance. In risk modeling, it is sometimes required to make a simultaneous assessment of the hazard arising from two or more mutually exclusive factors. This paper applies to an existing neural network model for competing risks (PLANNCR), a Bayesian regularization with the standard approximation of the evidence to implement automatic relevance determination (PLANNCR-ARD). The theoretical framework for the model is described and its application is illustrated with reference to local and distal recurrence of breast cancer, using the data set of Veronesi (1995).

This paper describes the evaluation of a regularized Bayesian neural network model in prognostic applications. A total sample size of 5442 subjects treated with ocular melanoma in two centers; Liverpool and Paris was used to carry out external validation analysis of the model. The performance of the model was benchmarked against the traditional Cox regression model and a clinically accepted TNM staging system. The cumulative hazards curve for the neural network model was much closer to the empirical curve in the test data than the one produced by the Cox model. The neural network model showed equal performance to Cox's model in terms of discrimination. However, the neural network model was better than Cox's model in terms of calibration. The paper proposes an alternative staging system based on the model, which takes into account histopathological information. The new system has many advantages over the existing staging system.

The evaluation of generic non-linear models for censored data needs to address the two complementary requirements in the software development life-cycle, of validation and verification. The former involves making a rigorous assessment of predictive accuracy in prognostic modelling and the latter is interpreted in this paper as comprising two different stages, namely model selection and rule-based interpretation of the composition of prognostic risk groups. With reference to prognostic performance is survival modelling the well-known ROC framework has recently been extended to a threshold independent, time-dependent performance index to quantify the predictive accuracy of censored data models, termed the C' index, which is briefly described. The rule-based framework for direct validation of risk group allocation against expert domain knowledge, uses low-order Boolean rules to approximate the response surfaces generated by analytical inference models. In the case of censored data, this approach serves to characterise the allocation of patients into risk groups generated by a risk staging index. Furthermore, the low-order rules define low-dimensional sub-spaces where individual data points can be directly visualised in relation to the decision boundaries for their risk group. Taken together, the quantitative performance index, Boolean explanatory rules and direct visualisation of the data, define a consistent and transparent validation framework based on triangulation of information. This information can be included in decision support systems.

This paper presents an analysis of censored survival data for breast cancer specific mortality and disease free survival. There are three stages to the process, namely time-to-event modelling, risk stratification by predicted outcome and model interpretation using rule extraction. Model selection was carried out using the benchmark linear model, Cox regression but risk staging was derived with Cox regression and with Partial Logistic Regression Artificial Neural Networks regularised with Automatic Relevance Determination (PLANN-ARD). This analysis compares the two approaches showing the benefit in using the neural network framework is better specificity for patients at high risk. The neural network model also has results in a smooth model of the hazard without the need for limiting assumptions of proportionality. The model predictions were verified using out-of-sample testing and by comparing marginal estimates of the predicted and actual cumulative hazards. The analysis was extended with automatic rule generation using Orthogonal Search Rule Extraction (OSRE). This methodology translates analytical risk scores into the language of the clinical domain, enabling direct validation of the operation of the Cox or neural network model.