Objective, computerized video-based rating of blepharospasm severity.
Ontology highlight
ABSTRACT: Objective
To compare clinical rating scales of blepharospasm severity with involuntary eye closures measured automatically from patient videos with contemporary facial expression software.Methods
We evaluated video recordings of a standardized clinical examination from 50 patients with blepharospasm in the Dystonia Coalition's Natural History and Biorepository study. Eye closures were measured on a frame-by-frame basis with software known as the Computer Expression Recognition Toolbox (CERT). The proportion of eye closure time was compared with 3 commonly used clinical rating scales: the Burke-Fahn-Marsden Dystonia Rating Scale, Global Dystonia Rating Scale, and Jankovic Rating Scale.Results
CERT was reliably able to find the face, and its eye closure measure was correlated with all of the clinical severity ratings (Spearman ρ = 0.56, 0.52, and 0.56 for the Burke-Fahn-Marsden Dystonia Rating Scale, Global Dystonia Rating Scale, and Jankovic Rating Scale, respectively, all p < 0.0001).Conclusions
The results demonstrate that CERT has convergent validity with conventional clinical rating scales and can be used with video recordings to measure blepharospasm symptom severity automatically and objectively. Unlike EMG and kinematics, CERT requires only conventional video recordings and can therefore be more easily adopted for use in the clinic.
SUBMITTER: Peterson DA
PROVIDER: S-EPMC5109937 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Existing scales for rating the severity of blepharospasm (BSP) are limited by a number of potential drawbacks. We therefore developed and validated a novel scale for rating the severity of BSP. The development of the scale started with careful examination of the clinical spectrum of the condition by a panel of experts who selected phenomenological aspects thought to be relevant to disease severity. Thereafter, selected items were first checked for reliability, then reliable items were combined to generate the scale, and clinimetric properties of the scale were evaluated. Finally, the confidence with which the scale could be used by people without high levels of movement disorders skill was assessed. The new scale, based on objective criteria, yielded moderate to almost perfect reliability, acceptable internal consistency, satisfactory scaling assumptions, lack of floor and ceiling effects, partial correlations with a prior severity scale and with a quality of life scale, and good sensitivity to change. Despite a few limitations, the foregoing features make the novel scale more suitable than existing scales to assess the severity of BSP in natural history and pathophysiologic studies as well as in clinical trials.
| S-EPMC4878674 | biostudies-literature
Project description:Dyskinesia is a common side effect of prolonged dopaminergic therapy in Parkinson's disease patients. Assessing the severity of dyskinesia could help develop better pharmacological and surgical interventions. We have developed a semi-automatic video-based objective dyskinesia quantifying measure called the severity score (SVS) that was evaluated on 35 patient videos. We present a study to evaluate the utility of our severity score and compare its performance to clinical ratings of neurologists. In addition to the Unified Dyskinesia Rating Scale (UDysRS) score for each video, four neurologists provided three sets of time lapsed ratings and rankings of the 35 videos using a specifically developed protocol. The statistical analysis of our data using Kendall's tau-b and intra-class correlations shows that (a) ranking patient videos based on severity is suitable for studying the utility of the SVS, and (b) SVS exhibits moderate utility to quantify dyskinesia severity when compared to manual assessment of dyskinesia by neurologists using the UDysRS. These results support the effective use of SVS as an objective measure to quantify dyskinesia and the rationale for a ranking system that complements traditional rating scales.
| S-EPMC4105342 | biostudies-literature
Project description:BackgroundThe Modified Rush Video-Based Tic Rating Scale (MRVS) is the most widely used video-based scale for assessing tic severity in patients with Tourette syndrome (TS). However, shortcomings of the MRVS, including a lack of clear instructions, a time-consuming recording procedure, and weak correlations with the gold standard for tic assessment, the Yale Global Tic Severity Scale-Total Tic Score (YGTSS-TTS), limits its use in research settings, although video assessments are generally considered objective, reliable, and time-saving measurements.ObjectivesWe aimed to revise the MRVS (MRVS-R) to simplify and standardize the assessment procedure and improve the correlation with the YGTSS-TTS.MethodsWe used 102 videos of patients with TS or persistent motor tic disorder filmed according to the MRVS. We compared the tic frequency assessed by MRVS with frequencies according to MRVS-R based on a 5-min (instead of a 10-min) video to investigate whether reducing the recording time leads to significant changes. In addition, we adapted the MRVS to the YGTSS and defined new anchor values for motor and phonic tic frequency based on frequency distributions as assessed in our sample. Finally, we compared the MRVS-R and MRVS regarding psychometric properties and correlation with the YGTSS-TTS.ResultsCutting video recording time in half did not significantly affect assessments of motor and phonic tic frequencies. Psychometric properties were acceptable. Most important, proposed revisions of the MRVS improved correlation with the YGTSS-TTS.ConclusionsThe MRVS-R is a simplified version of the MRVS with comparable psychometric qualities, but higher correlations with the YGTSS-TTS.
| S-EPMC10187019 | biostudies-literature
Project description:A large number of studies have analyzed social and sexual interactions between rodents in relation to neural activity. Computerized video analysis has been successfully used to detect numerous behaviors quickly and objectively; however, to date only 2D video recording has been used, which cannot determine the 3D locations of animals and encounters difficulties in tracking animals when they are overlapping, e.g., when mounting. To overcome these limitations, we developed a novel 3D video analysis system for examining social and sexual interactions in rats. A 3D image was reconstructed by integrating images captured by multiple depth cameras at different viewpoints. The 3D positions of body parts of the rats were then estimated by fitting skeleton models of the rats to the 3D images using a physics-based fitting algorithm, and various behaviors were recognized based on the spatio-temporal patterns of the 3D movements of the body parts. Comparisons between the data collected by the 3D system and those by visual inspection indicated that this system could precisely estimate the 3D positions of body parts for 2 rats during social and sexual interactions with few manual interventions, and could compute the traces of the 2 animals even during mounting. We then analyzed the effects of AM-251 (a cannabinoid CB1 receptor antagonist) on male rat sexual behavior, and found that AM-251 decreased movements and trunk height before sexual behavior, but increased the duration of head-head contact during sexual behavior. These results demonstrate that the use of this 3D system in behavioral studies could open the door to new approaches for investigating the neuroscience of social and sexual behavior.
| S-EPMC3813688 | biostudies-literature
Project description:Objectives:The influence of food intake on behavioural disorders was already described in the early 20th century. Elimination of individually allergenic food items from individual diets ["oligoantigenic diet" (OD)] showed promise to improve attention-deficit/hyperactivity disorder (ADHD) symptoms. However, only few of the positive results were evaluated by blinded symptom rating. Therefore the present study's purpose was to evaluate the reliability of a non-blinded rating of the ADHD Rating Scale IV (ARS) for the assessment of OD effects in comparison to a blinded rating of the ARS based on pseudonymized video recordings. Methods:Ten children (8m/2f) aged 8 to 14 with ADHD according to ICD-10 participated in an uncontrolled, open-label dietary intervention study. Food items, commonly related to intolerances, were eliminated for four weeks. Participants with > 40% improvement in the ARS between T1 (before the diet) and T2 (after the diet) were defined as responders. Nutrients with individual relevance to ADHD symptoms were identified in a following reintroduction phase (T3-T4) lasting 8-16 weeks. The ARS was completed by a non-blinded child and adolescent psychiatrist (T0-T4). Sessions were recorded on video, pseudonymized, and evaluated by three blinded raters. Complete data were captured for eight children. The inter-rater reliability between the non-blinded therapist and every blinded rater was determined by the intra-class correlation coefficient (ICC). Correlations according to Pearson and Spearman between the non-blinded and blinded rating were calculated for each rater. Results:Two blinded raters and the non-blinded rater considered 5 of 8 (62.5%) children as responders, whereas one blinded rater disagreed as to the success of one case thus considering only 4 of 8 children as responders to the diet. Inter-rater reliability was assessed after each rater having scored 33 videos: The intra-class coefficients were >.9 for all raters (rater 1: ICC=.997, rater 2: ICC=.996, rater 3: ICC=.996) and the Spearman rho between the raters were high (n=33; rater 1: rho =.989, p<.0001, rater 2: rho=.987, p<.0001, rater 3: rho=.984, p<.0001), respectively. Discussion:As both, blinded and non-blinded ratings of the ARS, revealed relevant significant improvement of ADHD scores in children following an OD in this uncontrolled trial, Randomized controlled trials appear as highly desirable in order to replicate these improvements and to establish reliable and unbiased effect sizes thereby fostering further more objective confirmatory measurements.
| S-EPMC7468497 | biostudies-literature
Project description:BackgroundThe diagnosis of Parkinson's disease (PD) and evaluation of its symptoms require in-person clinical examination. Remote evaluation of PD symptoms is desirable, especially during a pandemic such as the coronavirus disease 2019 pandemic. One potential method to remotely evaluate PD motor impairments is video-based analysis. In this study, we aimed to assess the feasibility of predicting the Unified Parkinson's Disease Rating Scale (UPDRS) score from gait videos using a convolutional neural network (CNN) model.MethodsWe retrospectively obtained 737 consecutive gait videos of 74 patients with PD and their corresponding neurologist-rated UPDRS scores. We utilized a CNN model for predicting the total UPDRS part III score and four subscores of axial symptoms (items 27, 28, 29, and 30), bradykinesia (items 23, 24, 25, 26, and 31), rigidity (item 22) and tremor (items 20 and 21). We trained the model on 80% of the gait videos and used 10% of the videos as a validation dataset. We evaluated the predictive performance of the trained model by comparing the model-predicted score with the neurologist-rated score for the remaining 10% of videos (test dataset). We calculated the coefficient of determination (R2) between those scores to evaluate the model's goodness of fit.ResultsIn the test dataset, the R2 values between the model-predicted and neurologist-rated values for the total UPDRS part III score and subscores of axial symptoms, bradykinesia, rigidity, and tremor were 0.59, 0.77, 0.56, 0.46, and 0.0, respectively. The performance was relatively low for videos from patients with severe symptoms.ConclusionsDespite the low predictive performance of the model for the total UPDRS part III score, it demonstrated relatively high performance in predicting subscores of axial symptoms. The model approximately predicted the total UPDRS part III scores of patients with moderate symptoms, but the performance was low for patients with severe symptoms owing to limited data. A larger dataset is needed to improve the model's performance in clinical settings.
| S-EPMC10552271 | biostudies-literature
Project description:We modified the original Unified Multiple System Atrophy Rating Scale (UMSARS) for remote video-based visits by excluding ocular motor dysfunction, increased tone, and body sway, resulting in a 23-item UMSARS (mUMSARS-23). The mUMSARS-23 demonstrated excellent reliability and strong validity when compared to the original scale, making it a promising tool for conducting video-based virtual assessments in patients with multiple system atrophy.
| S-EPMC10611709 | biostudies-literature
Project description:Accumulating diffusion tensor imaging (DTI) evidence suggests that white matter abnormalities evaluated by local diffusion homogeneity (LDH) or fractional anisotropy (FA) occur in patients with blepharospasm (BSP), both of which are significantly correlated with disease severity. However, whether the individual severity of BSP can be identified using these DTI metrics remains unknown. We aimed to investigate whether a combination of machine learning techniques and LDH or FA can accurately identify the individual severity of BSP. Forty-one patients with BSP were assessed using the Jankovic Rating Scale and DTI. The patients were assigned to non-functionally and functionally limited groups according to their Jankovic Rating Scale scores. A machine learning scheme consisting of beam search and support vector machines was designed to identify non-functionally versus functionally limited outcomes, with the input features being LDH or FA in 68 white matter regions. The proposed machine learning scheme with LDH or FA yielded an overall accuracy of 88.67 versus 85.19% in identifying non-functionally limited versus functionally limited outcomes. The scheme also identified a sensitivity of 91.40 versus 85.87% in correctly identifying functionally limited outcomes, a specificity of 83.33 versus 83.67% in accurately identifying non-functionally limited outcomes, and an area under the curve of 93.7 versus 91.3%. These findings suggest that a combination of LDH or FA measurements and a sophisticated machine learning scheme can accurately and reliably identify the individual disease severity in patients with BSP.
| S-EPMC8155629 | biostudies-literature
Project description:[This corrects the article DOI: 10.1371/journal.pone.0214226.].
| S-EPMC6467391 | biostudies-literature
Project description:Positional preferences, asymmetry of body position and movements potentially indicate abnormal clinical conditions in infants. However, a lack of standardized nomenclature hinders accurate assessment and documentation of these preferences over time. Video tools offer a safe and reproducible method to analyze and describe infant movement patterns, aiding in physiotherapy management and goal planning. The study aimed to develop an objective classification system for infant movement patterns with particular emphasis on the specific distribution of muscle tension, using methods of computer analysis of video recordings to enhance accuracy and reproducibility in assessments. The study involved the recording of videos of 51 infants between 6 and 15 weeks of age, born at term, with an Apgar score of at least 8 points. Based on observations of a recording of infant spontaneous movements in the supine position, experts identified postural-motor patterns: symmetry and typical asymmetry linked to the asymmetrical tonic neck reflex. Deviations from the typical postural-motor system were indicated, and subcategories of atypical patterns were distinguished. A computer-based inference system was developed to automatically classify individual patterns. The following division of motor patterns was used: (1) normal patterns, including (a) typical (symmetrical, asymmetrical: variants 1 and 2); and (b) atypical (variants: 1 to 4), (2) positional preference, and (3) abnormal patterns. The proposed automatic classification method achieved an expert decision mapping accuracy of 84%. For atypical patterns, the high reproducibility of the system's results was confirmed. Lower reproducibility, not exceeding 70%, was achieved with typical patterns. Based on the observation of infant spontaneous movements, it is possible to identify movement patterns divided into typical and atypical patterns. Computer-based analysis of infant movement patterns makes it possible to objectify and satisfactorily reproduce diagnostic decisions.
| S-EPMC11290138 | biostudies-literature