SARAspeech-Feasibility of automated assessment of ataxic speech disturbance.

Ataxias are a group of movement disorders that are characterized by progressive loss of balance, impaired coordination and speech disturbance, which together lead to markedly reduced quality of life. Speech disturbance is clinically diagnosed, but methods for objective assessment of severity are lacking. Using 71 sets of speech recordings from ataxia patients, we developed an automated classification system. With a tolerance of ±1 point, this classification system correctly predicted experts' ratings of speech disturbance according to item 4 of the Scale for Assessment and rating of ataxia (SARA) in 80% of cases. We thereby demonstrate feasibility of computer-assisted voice analysis for automated assessment of severity of speech disturbance.

Comparison of different radiographic scores with associated echocardiographic measurements and prediction of heart enlargement in dogs with and without myxomatous mitral valve disease.

INTRODUCTION: Staging of myxomatous mitral valve disease (MMVD) requires an echocardiographic examination along with thoracic radiographs. The aims of this study were to calculate mean values for radiographic scores vertebral heart size (VHS), left atrial width (LAWidth), radiographic left atrial dimension (RLAD), and vertebral left atrial size (VLAS) in conventional and grayscale inverted images in healthy dogs and dogs with different stages of MMVD, and to find cutoff values for a stage assignment. ANIMALS: One hundred fifty dogs in different stages of MMVD and 50 unaffected dogs were evaluated. METHODS: Radiographic scores, echocardiographic left atrium-to-aorta ratio and normalized left ventricular internal dimension at end-diastole, and results of a clinical examination were obtained. Analyses were performed to evaluate the correlation between radiographic scores and echocardiographic values, to determine cutoff values for a radiographic stage assignment, and to compare measurements in conventional and inverted radiographs. RESULTS: After excluding breed-specific higher VHS, the means of VHS, LAWidth, RLAD, and VLAS were similar in the control group and stage B1. All radiographic scores increased in stages B2 and C. The cutoff values identifying heart enlargement, and therefore differentiating stages B1 and B2, were 11.0 for VHS, 1.8 for LAWidth, 2.0 for RLAD, and 2.3 for VLAS. Besides RLAD, scores were similar in conventional and inverted radiographs. CONCLUSION: Cutoff values for the different radiographic scores for stage assignment were calculated. Radiographic cardiac scores using either conventional or inverted grayscale could be a tool to differentiate between different stages of MMVD when echocardiography is unavailable.