Gait disorder classification based on effective feature selection and unsupervised methodology.

In gait stability analysis, patients suffering from dysfunction problems are impacted by shifts in their dynamic balance. Monitoring the patients' progress is important for allowing physicians and patients to observe the rehabilitation process accurately. In this study, we designed a new methodology for classifying gait disorders to quantify patients' progress. The dataset in this study includes 84 measurements of 37 patients based on a physician's opinion. In this study, the system, which includes a Kinect camera to observe and store the frames of patients walking down a hallway, a key-point detector to detect the skeletal key points, and an encoder transformer classifier network integrated with generator-discriminator networks (ET-GD), is designed to evaluate the classification of gait dysfunction. The detector extracts the skeletal key points of patients. After feature engineering, the selected high-level features are fed into the proposed neural network to analyse patient movement and perform the final evaluation of gait dysfunction. The proposed network is inspired by the 1D encoder transformer, which is integrated with two main networks: a network for classification and a network to generate fake output data similar to the input data. Furthermore, we used a discriminator structure to distinguish between the actual data (input) and fake data (generated data). Due to the multi-structural networks in the proposed method, multi-loss functions need to be optimised; this increases the accuracy of the encoder transformer classifier.

Head-shaking-induced nystagmus reflects dynamic vestibular compensation: A 2-year follow-up study.

Purpose: We aimed to assess the ability of a head-shaking test (HST) to reflect vestibular compensation in patients after unilateral peripheral vestibular loss and to provide missing evidence and new insights into the features of head-shaking-induced nystagmus (HSN) over a 2-year follow-up. Background: HSN may occur after a prolonged sinusoidal oscillation of the head. HSN is frequently observed in subjects with vestibular function asymmetry; it usually beats toward the functionally intact or "stronger" ear and can be followed by a reversal of its direction. Study design: A prospective observational case-control study. Settings: A tertiary academic referral center. Methods: A total of 38 patients after acute unilateral vestibular loss (22 patients with vestibular neuronitis and 16 patients after vestibular neurectomy) and 28 healthy controls were followed for four consecutive visits over a 2-year period. A complex vestibular assessment was performed on all participants, which included spontaneous nystagmus (SPN), the caloric test, the head-shaking test (HST), the video head impulse test (vHIT), the Timed Up and Go (TUG) test, and the Dizziness Handicap Inventory (DHI) questionnaire. We established the criteria for the poorly compensated group to assess different compensatory behaviors and results. Results: We found a time-related decrease in HSN (ρ < -0.84, p < 0.001) after unilateral vestibular loss. After 2 years of follow-up, HSN intensity in compensated patients reached the level of the control group; TUG and DHI also improved to normal; however, the caloric and vHIT tests remained abnormal throughout all follow-ups, indicating a chronic vestibular deficit. Besides, poorly compensated patients had a well-detectable HSN throughout all follow-ups; TUG remained abnormal, and DHI showed at least a moderate deficit. Conclusions: Our study showed that, after a unilateral peripheral vestibular loss, the intensity of HSN decreased exponentially over time, reflecting an improvement in dynamic ability and self-perceived deficit. HSN tended to decline to the value of the control group once vestibular compensation was satisfactory and sufficient for a patient's everyday life. In contrast, well-detectable HSN in poorly compensated patients with insufficient clinical recovery confirmed the potential of HSN to reflect and distinguish between adequate and insufficient dynamic compensation. HSN could serve as an objective indicator of stable unilateral vestibular loss.

Estimated Vestibulogram (EVEST) for Effective Vestibular Assessment.

BACKGROUND: The availability and development of methods testing the vestibuloocular reflex (VOR) brought a broader view into the lateral semicircular canal (L-SCC) function. However, the higher number of evaluated parameters makes more difficult the specialist's diagnose-making process. PURPOSE: To provide medical specialists, a new diagnostic-graphic tool, Estimated Vestibulogram- EVEST, enabling a quick and easy-to-read visualization and comparison of the VOR test results within the L-SCC. METHODS: The development of EVEST involved 148 participants, including 49 healthy volunteers (28 female and 21 male) and 99 (58 female and 41 male) patients affected by different degrees of peripheral vestibular deficit. The corresponding L-SCC VOR test results, from patients meeting the diagnostic criteria, were used to create the EVEST. RESULTS: Based on the test results, we depicted and calculated the EVEST vestibular function asymmetry (VFA) in all the groups. To assess a feasibility of EVEST to describe a vestibular function deficit, we calculated sensitivity and specificity of VFA using a receiver operating characteristic curve (ROC) and compared it to single tests. In all the tests, we determined the cutoff value as the point with the highest sensitivity and specificity. For discrimination of any vestibular deficit, the VFA with cutoff 6.5% was more sensitive (91%) and specific (98%) than single tests. Results showed that EVEST is a beneficial graphic tool for quick multifrequency comparison and diagnosis of different types of the peripheral vestibular loss. CONCLUSIONS: EVEST can help to easily evaluate various types of peripheral vestibular lesion.

Advanced Statistical Analysis of 3D Kinect Data: Mimetic Muscle Rehabilitation Following Head and Neck Surgeries Causing Facial Paresis.

An advanced statistical analysis of patients' faces after specific surgical procedures that temporarily negatively affect the patient's mimetic muscles is presented. For effective planning of rehabilitation, which typically lasts several months, it is crucial to correctly evaluate the improvement of the mimetic muscle function. The current way of describing the development of rehabilitation depends on the subjective opinion and expertise of the clinician and is not very precise concerning when the most common classification (House-Brackmann scale) is used. Our system is based on a stereovision Kinect camera and an advanced mathematical approach that objectively quantifies the mimetic muscle function independently of the clinician's opinion. To effectively deal with the complexity of the 3D camera input data and uncertainty of the evaluation process, we designed a three-stage data-analytic procedure combining the calculation of indicators determined by clinicians with advanced statistical methods including functional data analysis and ordinal (multiple) logistic regression. We worked with a dataset of 93 distinct patients and 122 sets of measurements. In comparison to the classification with the House-Brackmann scale the developed system is able to automatically monitor reinnervation of mimetic muscles giving us opportunity to discriminate even small improvements during the course of rehabilitation.

A Continuous Glucose Monitoring System (CGMS) - a promising approach for improving metabolic control in persons with type 1 Diabetes mellitus treated by insulin pumps.

This pilot study deals with the possibilities of a Continuous Glucose Monitoring System (CGMS, Minimed- Medtronic) to optimize insulin substitution. Ten persons with type 1 diabetes mellitus treated by means of an insulin pump entered the study and eight of them completed the protocol. CGMS was introduced for a period of 5 days. The standard dinner (60 g of carbohydrates) and overnight fasting were designed to ensure standard night conditions in all persons in the study while maintaining their usual daily eating routine, physical exercise and assessment of prandial insulin boluses. The only adaptation of basal rates of insulin pump was performed on day 3. Comparison of the mean plasma glucose concentration (0:00-24:00 hrs) between day 2 (before adaptation) and day 4 (following adaptation) was made. An independent comparison of the mean plasma glucose concentration between the night from day 2 till day 3 (22:00-6:00 hrs) and the night from day 4 till day 5 (22:00-6:00 hrs) was performed. The mean plasma glucose investigated by means of CGMS improved in the 24-hour period in 5 out of 8 persons and in the night fasting period (22:00 to 6 hrs) in 6 out of 8 persons. The CGMS is a useful means for assessment of the effectiveness of basal rate and prandial insulin doses in persons with type 1 diabetes treated by means of an insulin pump. However, further studies are necessary to improve the algorithm for insulin substitution.