Ophthalmological and Neurologic Manifestations in Pre-clinical and Clinical Phases of Spinocerebellar Ataxia Type 7.

Spinocerebellar ataxia type 7 (SCA7) is a polyglutamine disease that progressively affects the cerebellum, brainstem, and retina. SCA7 is quite rare, and insights into biomarkers and pre-clinical phases are still missing. We aimed to describe neurologic and ophthalmological findings observed in symptomatic and pre-symptomatic SCA7 subjects. Several neurologic scales, visual acuity, visual fields obtained by computer perimetry, and macular thickness in optical coherence tomography (mOCT) were measured in symptomatic carriers and at risk relatives. Molecular analysis of the ATXN7 was done blindly in individuals at risk. Thirteen symptomatic carriers, 3 pre-symptomatic subjects, and 5 related controls were enrolled. Symptomatic carriers presented scores significantly different from those of controls in most neurologic and ophthalmological scores. Gradual changes from controls to pre-symptomatic and then to symptomatic carriers were seen in mean (SD) of visual fields - 1.34 (1.15), - 2.81 (1.66). and - 9.56 (7.26); mOCT - 1.11 (2.6), - 3.48 (3.54), and - 7.73 (2.56) Z scores; and "Spinocerebellar Ataxia Functional Index (SCAFI)" - 1.16 (0.28), 0.65 (0.56), and - 0.61 (0.44), respectively. Visual fields and SCAFI were significantly correlated with time to disease onset (pre-symptomatic)/disease duration (symptomatic carriers). Visual fields, mOCT, and SCAFI stood out as candidates for state biomarkers for SCA7 since pre-symptomatic stages of disease.

Advancing healthcare with artificial intelligence: diagnostic accuracy of machine learning algorithm in diagnosis of diabetic retinopathy in the Brazilian population.

BACKGROUND: In healthcare systems in general, access to diabetic retinopathy (DR) screening is limited. Artificial intelligence has the potential to increase care delivery. Therefore, we trained and evaluated the diagnostic accuracy of a machine learning algorithm for automated detection of DR. METHODS: We included color fundus photographs from individuals from 4 databases (primary and specialized care settings), excluding uninterpretable images. The datasets consist of images from Brazilian patients, which differs from previous work. This modification allows for a more tailored application of the model to Brazilian patients, ensuring that the nuances and characteristics of this specific population are adequately captured. The sample was fractionated in training (70%) and testing (30%) samples. A convolutional neural network was trained for image classification. The reference test was the combined decision from three ophthalmologists. The sensitivity, specificity, and area under the ROC curve of the algorithm for detecting referable DR (moderate non-proliferative DR; severe non-proliferative DR; proliferative DR and/or clinically significant macular edema) were estimated. RESULTS: A total of 15,816 images (4590 patients) were included. The overall prevalence of any degree of DR was 26.5%. Compared with human evaluators (manual method of diagnosing DR performed by an ophthalmologist), the deep learning algorithm achieved an area under the ROC curve of 0.98 (95% CI 0.97-0.98), with a specificity of 94.6% (95% CI 93.8-95.3) and a sensitivity of 93.5% (95% CI 92.2-94.9) at the point of greatest efficiency to detect referable DR. CONCLUSIONS: A large database showed that this deep learning algorithm was accurate in detecting referable DR. This finding aids to universal healthcare systems like Brazil, optimizing screening processes and can serve as a tool for improving DR screening, making it more agile and expanding care access.