Search

Abstract Background Thyroid-associated ophthalmopathy (TAO) is an autoimmune disorder. It has discriminable appearance. This study was conducted to dig the clinical significance of demographic characteristics and ophthalmologic diagram features in TAO diagnosis and stage/severity evaluation. Results We included 320 males and 633 females, with an average age of 41.75 ± 13.75. A majority of TAO patients had hyperthyroidism, and most of them were in the inactive stage and at the moderate level. The thyroid function type, stage and severity were closely associated with hypopsia, eyelid congestion, conjunctival congestion, corneal ulcer, ocular motility disorder, best corrected visual acuity, and extraocular muscle thickening. Using these features, we established different logistic regression models to predict thyroid function subtypes, abnormal thyroid function, stage, and severity, in which the AUC of the ROC curve and accuracies were satisfactory. Conclusion Together, TAO subtype, stage and severity can be diagnosed by auxiliary references including demographic factors, symptoms from complains, and image features. These non-invasive indices can be applied in a timely manner in clinical estimating TAO status.

Thyroid-associated ophthalmopathy (TAO) is a complicated orbitopathy related to dysthyroid, which severely destroys the facial appearance and life quality without medical interference. The diagnosis and management of thyroid-associated ophthalmopathy are extremely intricate, as the number of professional ophthalmologists is limited and inadequate compared with the number of patients. Nowadays, medical applications based on artificial intelligence (AI) algorithms have been developed, which have proved effective in screening many chronic eye diseases. The advanced characteristics of automated artificial intelligence devices, such as rapidity, portability, and multi-platform compatibility, have led to significant progress in the early diagnosis and elaborate evaluation of these diseases in clinic. This study aimed to provide an overview of recent artificial intelligence applications in clinical diagnosis, activity and severity grading, and prediction of therapeutic outcomes in thyroid-associated ophthalmopathy. It also discussed the current challenges and future prospects of the development of artificial intelligence applications in treating thyroid-associated ophthalmopathy.

IntroductionHuntington's disease (HD) is a rare neurodegenerative disease characterized by cognitive, behavioral and motor symptoms that progressively worsen with time. Cognitive and behavioral signs of HD are generally present in the years prior to a diagnosis; however, manifest HD is typically assessed by genetic confirmation and/or the presence of unequivocal motor symptoms. Nevertheless, there is a large variation in symptom severity and rate of progression among individuals with HD.MethodsIn this retrospective study, longitudinal natural history of disease progression was modeled in individuals with manifest HD from the global, observational Enroll-HD study (NCT01574053). Unsupervised machine learning (k-means; km3d) was used to jointly model clinical and functional disease measures simultaneously over time, based on one-dimensional clustering concordance such that individuals with manifest HD (N = 4,961) were grouped into three clusters: rapid (Cluster A; 25.3%), moderate (Cluster B; 45.5%) and slow (Cluster C; 29.2%) progressors. Features that were considered predictive of disease trajectory were then identified using a supervised machine learning method (XGBoost).ResultsThe cytosine adenine guanine-age product score (a product of age and polyglutamine repeat length) at enrollment was the top predicting feature for cluster assignment, followed by years since symptom onset, medical history of apathy, body mass index at enrollment and age at enrollment.ConclusionsThese results are useful for understanding factors that affect the global rate of decline in HD. Further work is needed to develop prognostic models of HD progression as these could help clinicians with individualized clinical care planning and disease management.

Background: Gait disruption is a common poststroke problem. Robot-assisted gait training (RAGT) might improve motor function, balance, and activities of daily living. Objective: We compared the clinical effectiveness of early integrated RAGT using the Walkbot robotic gym with an intensity-matched enhanced lower limb therapy (ELLT) program and with conventional rehabilitation therapy (CRT) in patients with acute ischemic stroke. Methods: A total of 192 patients with acute ischemic stroke were randomly assigned (1:1:1) to receive RAGT, ELLT, or CRT. All three groups received 45 min of training daily, 3 days a week, for 4 weeks consecutively. Before and after the 4-week treatment, the patients were assessed based on a 6-minute walking test (6MWT), functional ambulation classification (FAC), timed up and go (TUG) test, dual-task walking (DTW) test, Tinetti’s test, Barthel’s index (BI), stroke-specific quality of life (SS-QOL) scale, and gait analysis parameters. Results: After the 4-week intervention, the results of the 6MWT, FAC, TUG, DTW, Tinetti’s test, BI, SS-QOL, and gait in the three groups significantly improved. Compared with ELLT and CRT groups, participants in the RAGT group had a better performance in 6MWT (199.11 ± 60.72 versus 182.47 ± 59.72 versus 173.69 ± 40.58, p = 0.035), FAC (4.10 ± 0.91 versus 3.69 ± 0.88 versus 3.58 ± 0.81, p = 0.044), DTW (10.29 ± 2.38 versus 12.92 ± 2.64 versus 13.89 ± 2.62, p = 0.031), SS-QOL (184.46 ± 20.53 versus 165.39 ± 20.49 versus 150.72 ± 20.59, p = 0.012), velocity (0.66 ± 0.22 versus 0.55 ± 0.23 versus 0.51 ± 0.20, p = 0.008), cycle duration (1.38 ± 0.40 versus 1.50 ± 0.38 versus 1.61 ± 0.30, p = 0.040), and swing phase symmetry ratio (SPSR, 1.10 ± 0.33 versus 1.21 ± 0.22 versus 1.48 ± 0.25, p = 0.021). The TUG, Tinetti’s test, BI, and RMT results were similar, however. Conclusion: In the acute stroke phase, early integrated RAGT showed greater performance in gait rehabilitation than CRT and ELLT. Registration: ChiCTR1900026225

Introduction: Huntington's disease (HD) is a rare neurodegenerative disease characterized by cognitive, behavioral and motor symptoms that progressively worsen with time. Cognitive and behavioral signs of HD are generally present in the years prior to a diagnosis; however, manifest HD is typically assessed by genetic confirmation and/or the presence of unequivocal motor symptoms. Nevertheless, there is a large variation in symptom severity and rate of progression among individuals with HD. Methods: In this retrospective study, longitudinal natural history of disease progression was modeled in individuals with manifest HD from the global, observational Enroll-HD study (NCT01574053). Unsupervised machine learning (k-means; km3d) was used to jointly model clinical and functional disease measures simultaneously over time, based on one-dimensional clustering concordance such that individuals with manifest HD (N = 4,961) were grouped into three clusters: rapid (Cluster A; 25.3%), moderate (Cluster B; 45.5%) and slow (Cluster C; 29.2%) progressors. Features that were considered predictive of disease trajectory were then identified using a supervised machine learning method (XGBoost). Results: The cytosine adenine guanine-age product score (a product of age and polyglutamine repeat length) at enrollment was the top predicting feature for cluster assignment, followed by years since symptom onset, medical history of apathy, body mass index at enrollment and age at enrollment. Conclusions: These results are useful for understanding factors that affect the global rate of decline in HD. Further work is needed to develop prognostic models of HD progression as these could help clinicians with individualized clinical care planning and disease management. [ABSTRACT FROM AUTHOR]