Pain is a symptom of many disorders associated with actual or potential tissue damage in human body. Managing pain is not only a duty but also highly cost prone. The most primitive state of pain management is the assessment of pain. Traditionally it was accomplished by self-report or visual inspection by experts. However, automatic pain assessment systems from facial videos are also rapidly evolving due to the need of managing pain in a robust and cost effective way. Among different challenges of automatic pain assessment from facial video data two issues are increasingly prevalent: first, exploiting both spatial and temporal information of the face to assess pain level, and second, incorporating multiple visual modalities to capture complementary face information related to pain. Most works in the literature focus on merely exploiting spatial information on chromatic (RGB) video data on shallow learning scenarios. However, employing deep learning techniques for spatio-temporal analysis considering Depth (D) and Thermal (T) along with RGB has high potential in this area. In this paper, we present the first state-of-the-art publicly available database, 'Multimodal Intensity Pain (MIntPAIN)' database, for RGBDT pain level recognition in sequences. We provide a first baseline results including 5 pain levels recognition by analyzing independent visual modalities and their fusion with CNN and LSTM models. From the experimental evaluation we observe that fusion of modalities helps to enhance recognition performance of pain levels in comparison to isolated ones. In particular, the combination of RGB, D, and T in an early fusion fashion achieved the best recognition rate.

Gait rehabilitation by Functional Electrical Stimulations (FESs) requires a reliable trigger signal to start the stimulations. This could be obtained by a simple switch under the heel or by means of an inertial sensor system. This study provides an algorithm to detect gait events in differential acceleration signals of the foot. The key feature of differential measurements is that they compensate the impact of gravity. The real time detection capability of a rule based algorithm in healthy and hemiparetic individuals was investigated. Detection accuracy and precision compared to signals from foot switches were evaluated. The algorithm detected curve features of the vectorial sum of radial and tangential accelerations and mapped those to discrete gait states. The results showed detection rates for healthy and hemiparetic gait ranging form 84.2% to 108.5%. The sensitivity was between 0.81 and 1, and the specificity between 0.85 and 1, depending on gait phase and group of subjects. The algorithm detected gait phase changes earlier than the reference. Differential acceleration signals combined with the proposed algorithm have the potential to be implemented in a future FES system.

The aim of this study was to investigate the modulation and topography of the nociceptive withdrawal reflex elicited by painful electrical stimulation of the foot sole during gait. Fifteen healthy volunteers participated in this study. Cutaneous electrical stimulation was delivered on five locations of the foot sole after heel-contact, during foot-flat, after heel-off, and during the mid-swing phase of the gait cycle during treadmill walking. Reflexes were recorded from muscles of the ipsilateral and contralateral legs. Furthermore, the kinematic responses in the sagittal plane of the ipsilateral ankle, knee, and hip joints were recorded. Reflexes in the distal muscles showed a site-dependant modulation. The largest responses in tibialis anterior were evoked at the arch of the foot and the smallest at the heel ( P < 0.05). The largest soleus responses were also elicited at the arch of the foot ( P < 0.04). The EMG responses in flexors and extensors of the knee and extensors of the contralateral leg were generally not dependent on the stimulation site. The response at the three joints showed site dependency, especially during the swing phase where maximal flexion was obtained by stimulation at the arch of the foot ( P < 0.05). The withdrawal reflex was modulated during the gait cycle and presented distinctive characteristics for the different muscles studied. Minimal kinematic responses were observed during stance in contrast to swing phase. Modulation of the reflex probably ensures an appropriate withdrawal but primarily secures balance and continuity of movement.

Brain computer interface is an emerging technology to treat the sequelae of stroke. The purpose of this study was to explore the motor imagery related desynchronization of sensorimotor rhythms of stroke patients and to assess the efficacy of an upper limb neurorehabilitation therapy based on functional electrical stimulation controlled by a brain computer interface. Eight severe chronic stroke patients were recruited. The study consisted of two stages: screening and therapy. During screening, the ability of patients to desynchronize the contralateral oscillatory sensorimotor rhythms by motor imagery of the most affected hand was assessed. In the second stage, a therapeutic intervention was performed. It involved 20 sessions where an electrical stimulator was activated when the patient's cerebral activity related to motor imagery was detected. The upper limb was assessed, before and after the intervention, by the Fugl–Meyer score (primary outcome). Spasticity, motor activity, range of movement and quality of life were also evaluated (secondary outcomes). Desynchronization was identified in all screened patients. Significant post-treatment improvement (p < 0.05) was detected in the primary outcome measure and in the majority of secondary outcome scores. The results suggest that the proposed therapy could be beneficial in the neurorehabilitation of stroke individuals.

Gait deficits are very common after stroke and improved therapeutic interventions are needed. The objective of this study was therefore to investigate the therapeutic use of the nociceptive withdrawal reflex to support gait training in the subacute post-stroke phase.