RESUMEN
Background: Current EMS stroke screening tools facilitate early detection and triage, but the tools' accuracy and reliability are limited and highly variable. An automated stroke screening tool could improve stroke outcomes by facilitating more accurate prehospital diagnosis and delivery. We hypothesize that a machine learning algorithm using video analysis can detect common signs of stroke. As a proof-of-concept study, we trained a computer algorithm to detect presence and laterality of facial weakness in publically available videos with comparable accuracy, sensitivity, and specificity to paramedics. Methods and Results: We curated videos of people with unilateral facial weakness (n = 93) and with a normal smile (n = 96) from publicly available web-based sources. Three board certified vascular neurologists categorized the videos according to the presence or absence of weakness and laterality. Three paramedics independently analyzed each video with a mean accuracy, sensitivity and specificity of 92.6% [95% CI 90.1-94.7%], 87.8% [95% CI 83.9-91.7%] and 99.3% [95% CI 98.2-100%]. Using a 5-fold cross validation scheme, we trained a computer vision algorithm to analyze the same videos producing an accuracy, sensitivity and specificity of 88.9% [95% CI 83.5-93%], 90.3% [95% CI 82.4-95.5%] and 87.5 [95% CI 79.2-93.4%]. Conclusions: These preliminary results suggest that a machine learning algorithm using computer vision analysis can detect unilateral facial weakness in pre-recorded videos with an accuracy and sensitivity comparable to trained paramedics. Further research is warranted to pursue the concept of augmented facial weakness detection and external validation of this algorithm in independent data sets and prospective patient encounters.
RESUMEN
BACKGROUND: Huntington disease (HD) is an inherited neurodegenerative disorder characterized by motor, psychiatric, and cognitive symptoms. Little is known about the effects of environmental factors on HD symptom onset and severity. OBJECTIVE: To evaluate the relationship between education level and age of diagnosis, symptom onset, and symptom severity in HD. METHODS: This study evaluated 4537 adult-onset, motor-manifest HD participants from the Enroll-HD global registry. Education level was assessed using International Standard Classification of Education categories, stratified into three education groups corresponding to pre-secondary, secondary, and post-secondary educational attainment. Motor and behavioral symptoms of HD, cognition, and functional capacity were measured using baseline Unified Huntington's Disease Rating Scale (UHDRS), Mini-Mental State Exam (MMSE), Symbol Digit Modalities Test (SDMT), verbal fluency, and Stroop assessments. RESULTS: After adjusting for CAG repeats, higher level of education predicted lower age of onset of motor symptoms, depression, irritability, and cognitive impairment (all P-values < 0.001). After adjusting for age of enrollment and CAG repeats, the highest education level predicted the lowest UHDRS motor scores, higher UHDRS total functional capacity and functional assessment scores, and higher SDMT, MMSE, verbal fluency, and Stroop assessment scores (all P-values < 0.001). CONCLUSIONS: HD participants with higher education levels have earlier age of diagnosis and age of symptom onset, but lower motor exam scores and higher functional assessment scores. Earlier recognition of symptoms in more highly educated participants may explain earlier symptom onset and diagnosis. Better performance on motor and functional assessments may be explained by higher cognitive reserve in those with greater education.
RESUMEN
In Strongylocentrotus purpuratus the hyalins are a set of three to four rather large glycoproteins (hereafter referred to as 'hyalin'), which are the major constituents of the hyaline layer, the developing sea urchin embryo's extracellular matrix. Recent research from our laboratories has shown that hyalin is a cell adhesion molecule involved in sea urchin embryo-specific cellular interactions. Other laboratories have shown it to consist of 2-3% carbohydrate and a cloned, sequenced fragment demonstrated repeat domains (HYR) and non-repeat regions. Interest in this molecule has increased because HYR has been identified in organisms as diverse as bacteria, flies, worms, mice and humans, as well as sea urchins. Our laboratories have shown that hyalin appears to mediate a specific cellular interaction that has interested investigators for over a century, archenteron elongation/attachment to the blastocoel roof. We have shown this finding by localizing hyalin on the two components of the cellular interaction and by showing that hyalin and anti-hyalin antibody block the cellular interaction using a quantitative microplate assay. The microplate assay, however, has limitations because it does not directly assess hyalin's effects on the adhesion of the two components of the interaction. Here we have used an elegant direct assay that avoids the limitations, in which we microdissected the two components of the adhesive interaction and tested their re-adhesion to each other, thereby avoiding possible factors in the whole embryos that could confound or confuse results. Using both assays, we found that mild periodate treatment (6 h to 24 h in sodium acetate buffer with 0.2 M sodium periodate at 4 degrees C in the dark) of hyalin eliminates its ability to block the cellular interaction, suggesting that the carbohydrate component(s) may be involved in hyalin's specific adhesive function. This first step is important in identifying the molecular mechanisms of a well known cellular interaction in the NIH-designated sea urchin embryo model, a system that has led to the discovery of scores of physiological mechanisms, including those involved in human health and disease.