No abstract

Objective. This study was aimed at identifying the potential outcome predictors, comparing the efficacy in patients with different tremor characteristics, and summarizing the adverse effect rates (AERs) of deep brain stimulation on the ventral intermediate nucleus (VIM-DBS) for essential tremor (ET). Methods. An extensive search of articles published to date in 2019 was conducted, and two main aspects were analyzed. Improvement was calculated as a percentage of change in any objective tremor rating scale (TRS) and analyzed by subgroup analyses of patients’ tremor characteristics, laterality, and stimulation parameters. Furthermore, the AERs were analyzed as follows: the adverse effects (AEs) were classified as stimulation-related, surgical-related, or device-related effects. A simple regression analysis was used to identify the potential prognostic factors, and a two-sample mean-comparison test was used to verify the statistical significance of the subgroup analyses. Results. Forty-six articles involving 1714 patients were included in the meta-analysis. The pooled improvement in any objective TRS score was 61.3% (95% CI: 0.564-0.660) at the mean follow-up visit (20.0±17.3 months). The midline and extremity symptoms showed consistent improvement (P=0.440), and the results of the comparison of postural and kinetic tremor were the same (P=0.219). In addition, the improvement in rest tremor was similar to that in action tremor (OR=2.759, P=0.120). In the simple regression analysis, the preoperative Fahn-Tolosa-Marin Tremor Rating Scale (FTM-TRS) scores and follow-up time were negatively correlated with the percentage change in any objective TRS score (P<0.05). The most common adverse event was dysarthria (10.5%), which is a stimulation-related AE (23.6%), while the rates of the surgical-related and device-related AEs were 6.4% and 11.5%, respectively. Conclusion. VIM-DBS is an efficient and safe surgical method in ET, and the efficacy was not affected by the body distribution of tremor, age at surgery, and disease duration. Lower preoperative FTM-TRS scores likely indicate greater improvement, and the effect of VIM-DBS declines over time.

No abstract

Artificial intelligence (AI), also known as machine intelligence, is a branch of science that empowers machines using human intelligence. AI refers to the technology of rendering human intelligence through computer programs. From healthcare to the precise prevention, diagnosis, and management of diseases, AI is progressing rapidly in various interdisciplinary fields, including ophthalmology. Ophthalmology is at the forefront of AI in medicine because the diagnosis of ocular diseases heavy reliance on imaging. Recently, deep learning-based AI screening and prediction models have been applied to the most common visual impairment and blindness diseases, including glaucoma, cataract, age-related macular degeneration (ARMD), and diabetic retinopathy (DR). The success of AI in medicine is primarily attributed to the development of deep learning algorithms, which are computational models composed of multiple layers of simulated neurons. These models can learn the representations of data at multiple levels of abstraction. The Inception-v3 algorithm and transfer learning concept have been applied in DR and ARMD to reuse fundus image features learned from natural images (non-medical images) to train an AI system with a fraction of the commonly used training data (&lt;1%). The trained AI system achieved performance comparable to that of human experts in classifying ARMD and diabetic macular edema on optical coherence tomography images. In this study, we highlight the fundamental concepts of AI and its application in these four major ocular diseases and further discuss the current challenges, as well as the prospects in ophthalmology.