The Effects of Spinal Manipulation Added to Exercise on Pain and Quality of Life in Patients with Thoracic Spinal Pain: A Randomized Controlled Trial.

Background: There are not enough reliable studies available in physiotherapy to determine the effects of spinal manipulative therapy added to exercise on thoracic spinal pain and quality of life. Objective: To investigate the effects of spinal manipulation on pain and quality of life in subjects with thoracic spinal pain. Study Design. It was an open-label "randomized controlled trial." Study Settings. Department of Physiotherapy, Services Hospital, Lahore, Pakistan. Participants. There were one hundred subjects with an age group between 18 and 60 years fulfilling the inclusion criteria. These subjects were divided equally into two groups; an experimental and a control group. Methods: In the experimental group (n = 50), thoracic spinal manipulation was applied along with thoracic muscle strengthening exercises. In the control group (n = 50) thoracic muscle exercises alone were given. Pain was measured by visual analogue scale (VAS) and quality of life with SF-36. Measurements were taken at baseline, immediately after session, after 8th session, and later as follow-ups at 12 weeks. Repeated measure ANOVA and independent sample T-test were used for within and between-group comparisons. Results: Mean age of subjects in control group was 38.56 ± 12.44 and in experimental group was 36.02 ± 11.32. Both groups demonstrated significant improvement in VAS score, and all domains of SF 36 but between-group comparison showed greater improvement in VAS of the experimental group compared to the baseline (P < 0.05), but between-group comparison of 8th session to follow-up has shown that effects of exercise persist while health-related quality of life in spinal manipulation group was significantly reduced after discontinuation of treatment. After the 8th session, spinal manipulation group showed notable results in terms of pain (mean diff 1.14 (0.62, 1.65) 95% CI and all aspects of SF 36 (P value <0.05). However, after week 12 of follow-up, no significant difference (P value >0.05) was observed among the study groups for pain and quality of life. Conclusion: Spinal manipulation added to thoracic exercise was more effective than thoracic exercise alone for improving pain and quality of life at the end of 8th session of care. However, the inclusion of spinal manipulation was not found effective at the 12-week follow-up. This trial is registered with IRCT20190327043125N1.

Comparison of neural mobilization and conservative treatment on pain, range of motion, and disability in cervical radiculopathy: A randomized controlled trial.

OBJECTIVE: The objective of the study was to compare the effectiveness of neural mobilization technique with conservative treatment on pain intensity, cervical range of motion, and disability. METHODS: It was a randomized clinical trial; data was collected from Mayo Hospital, Lahore. Eighty-eight patients fulfilling the sample selection criteria were randomly assigned into group 1 (neural mobilization) and group 2 (conventional treatment). Pain intensity was measured on a numeric pain rating scale, range of motion with an inclinometer, and functional status with neck disability index (NDI). Data were analyzed using SPSS, repeated measure ANOVA for cervical ranges and the Friedman test for NPRS and NDI were used for within-group analysis. Independent samples t-test for cervical ranges and Mann-Whitney U test for NPRS and NDI were used for between-group comparisons. RESULTS: There was a significant improvement in pain, disability, and cervical range of motion after the treatment in both groups compared to the pre-treatment status (p < 0.001), and when both groups were compared neural mobilization was more effective than conventional treatment in reducing pain and neck disability (p < 0.001), but there was no significant difference present in the mean score of cervical range of motion between both groups. (p>0.05). CONCLUSIONS: The present study concluded that both neural mobilization and conservative treatment were effective as an exercise program for patients with cervical radiculopathy, however, neural mobilization was more effective in reducing pain and neck disability in cervical radiculopathy. TRIAL REGISTRATION: RCT20190325043109N1.

Effects of Neurodynamic Mobilization on Health-Related Quality of Life and Cervical Deep Flexors Endurance in Patients of Cervical Radiculopathy: A Randomized Trial.

Purpose: Cervical radiculopathy is disorder of cervical spinal nerve root affecting large number of population. Previously many studies are conducted to design suitable protocol for management of this disorder, but they lack in quality. The purpose of this study was to compare the effects of neural mobilization and cervical isometrics on health-related quality of life and deep flexors endurance in cervical radiculopathy. Methods: A double-blinded randomized clinical trial was conducted at Mayo Hospital, Lahore, Pakistan. Eighty-eight patients within the age range of 35-50 years were included in the study after taking their consent. In the experimental group (n = 44), median nerve mobilization was applied along with cervical isometric exercises. The control group (n = 44) performed cervical isometric exercises alone. Muscle endurance was measured by craniocervical flexion test and quality of life on 36 items short form health survey SF-36 scale. Measurements were taken at baseline, at 2nd week, and at 4th week. For missing data, intention-to-treat analysis was used. Results: Within-group comparison with Friedman test showed a significant difference between pre, mid, and posttreatment scores on craniocervical flexion test and in all domains of SF 36 in both groups. While between-group comparison with Mann-Whitney U test showed all variables were similar at baseline but after 4 weeks there was a statistically significant improvement in craniocervical flexion test scores and all domains of SF 36 in the experimental group. But domain of pain showed mean rank of 49.43 after 4 weeks in the experimental group and 39.57 in the control group with p = 0.065 and d = 0.579, while for all the other 7 domains values were p < .05 and d > 0.25. Conclusion: Neural mobilization combined with cervical isometrics shows significant effects in improving quality of life and deep flexors endurance in patients with cervical radiculopathy than cervical isometrics alone.

Personalized wearable electrodermal sensing-based human skin hydration level detection for sports, health and wellbeing.

Personalized hydration level monitoring play vital role in sports, health, wellbeing and safety of a person while performing particular set of activities. Clinical staff must be mindful of numerous physiological symptoms that identify the optimum hydration specific to the person, event and environment. Hence, it becomes extremely critical to monitor the hydration levels in a human body to avoid potential complications and fatalities. Hydration tracking solutions available in the literature are either inefficient and invasive or require clinical trials. An efficient hydration monitoring system is very required, which can regularly track the hydration level, non-invasively. To this aim, this paper proposes a machine learning (ML) and deep learning (DL) enabled hydration tracking system, which can accurately estimate the hydration level in human skin using galvanic skin response (GSR) of human body. For this study, data is collected, in three different hydration states, namely hydrated, mild dehydration (8 hours of dehydration) and extreme mild dehydration (16 hours of dehydration), and three different body postures, such as sitting, standing and walking. Eight different ML algorithms and four different DL algorithms are trained on the collected GSR data. Their accuracies are compared and a hybrid (ML+DL) model is proposed to increase the estimation accuracy. It can be reported that hybrid Bi-LSTM algorithm can achieve an accuracy of 97.83%.

Machine Learning Based Autism Spectrum Disorder Detection from Videos.

Early diagnosis of Autism Spectrum Disorder (ASD) is crucial for best outcomes to interventions. In this paper, we present a machine learning (ML) approach to ASD diagnosis based on identifying specific behaviors from videos of infants of ages 6 through 36 months. The behaviors of interest include directed gaze towards faces or objects of interest, positive affect, and vocalization. The dataset consists of 2000 videos of 3-minute duration with these behaviors manually coded by expert raters. Moreover, the dataset has statistical features including duration and frequency of the above mentioned behaviors in the video collection as well as independent ASD diagnosis by clinicians. We tackle the ML problem in a two-stage approach. Firstly, we develop deep learning models for automatic identification of clinically relevant behaviors exhibited by infants in a one-on-one interaction setting with parents or expert clinicians. We report baseline results of behavior classification using two methods: (1) image based model (2) facial behavior features based model. We achieve 70% accuracy for smile, 68% accuracy for look face, 67% for look object and 53% accuracy for vocalization. Secondly, we focus on ASD diagnosis prediction by applying a feature selection process to identify the most significant statistical behavioral features and a over and under sampling process to mitigate the class imbalance, followed by developing a baseline ML classifier to achieve an accuracy of 82% for ASD diagnosis.

Predicting ASD Diagnosis in Children with Synthetic and Image-based Eye Gaze Data.

As early intervention is highly effective for young children with autism spectrum disorder (ASD), it is imperative to make accurate diagnosis as early as possible. ASD has often been associated with atypical visual attention and eye gaze data can be collected at a very early age. An automatic screening tool based on eye gaze data that could identify ASD risk offers the opportunity for intervention before the full set of symptoms is present. In this paper, we propose two machine learning methods, synthetic saccade approach and image based approach, to automatically classify ASD given children's eye gaze data collected from free-viewing tasks of natural images. The first approach uses a generative model of synthetic saccade patterns to represent the baseline scan-path from a typical non-ASD individual and combines it with the real scan-path as well as other auxiliary data as inputs to a deep learning classifier. The second approach adopts a more holistic image-based approach by feeding the input image and a sequence of fixation maps into a convolutional or recurrent neural network. Using a publicly-accessible collection of children's gaze data, our experiments indicate that the ASD prediction accuracy reaches 67.23% accuracy on the validation dataset and 62.13% accuracy on the test dataset.

PREDICTING AUTISM DIAGNOSIS USING IMAGE WITH FIXATIONS AND SYNTHETIC SACCADE PATTERNS.

Signs of autism spectrum disorder (ASD) emerge in the first year of life in many children, but diagnosis is typically made much later, at an average age of 4 years in the United States. Early intervention is highly effective for young children with ASD, but is typically reserved for children with a formal diagnosis, making accurate identification as early as possible imperative. A screening tool that could identify ASD risk during infancy offers the opportunity for intervention before the full set of symptoms is present. In this paper, we propose two machine learning methods, synthetic saccade approach and image based approach, to automatically classify ASD given the scanpath data from children on free viewing of natural images. The first approach uses a generative model of synthetic saccade patterns to represent the baseline scan-path from a typical non-ASD individual and combines it with the input scanpath as well as other auxiliary data as inputs to a deep learning classifier. The second approach adopts a more holistic image based approach by feeding the input image and a sequence of fixation maps into a state-of-the-art convolutional neural network. Our experiments indicate that we can get 65.41% accuracy on the validation dataset.