Prevalence of p.G87V and p.Gln298=Variations in LIPA Gene Within Middle Eastern Population Living Around Los Angeles.

Background: The LIPA gene encodes for lysosomal acid lipase (LAL), which catalyzes the hydrolysis of cholesterol esters and triglycerides. Variations in the LIPA gene impair LAL activity, predisposing patients to a rare metabolic disorder called LAL deficiency (LAL-D). The lack of functioning LAL promotes lipid accumulation and subsequent dyslipidemia, which can increase the likelihood of complications in both infants and adults. Although the worldwide prevalence is 1:500,000 births, the frequency in Mizrahi Jewish populations is projected to be as high as 1 in every 4200 births (Valles-Ayoub et al.) based on the LIPA p.G87V variant frequency among 162 individuals. Materials and Methods: This study was conducted to validate the previously reported prevalence of LAL-D in the Mizrahi Jewish population based on the pathogenic LIPA missense variants in exon 4 (c.260G>T; p.G87V) and exon 8 (c.894G>A; p.Gln298=) using a larger cohort of those with Middle Eastern ancestry living around Los Angeles. Among the 1184 individual samples sequenced, 660 self-reported as Mizrahi Jewish, while the remaining 524 came from other Middle Eastern groups labeled as "non-Jewish." Results: Of the 1184 samples, 22 alleles of the exon 4 variant were identified (1.85%), and 2 alleles of the exon 8 variant were identified (0.16%). For the exon 4 variant, 20 of 22 (90.9%) heterozygotes were Mizrahi Jewish, while 2 of 22 (9.09%) heterozygotes were "non-Jewish." For the exon 8 variant, 2 of 2 (100%) heterozygotes were Mizrahi Jewish. This suggests that the prevalence of LAL-D in this population is 1 in 900, which suggests that LAL-D may be 4.6% higher in the Mizrahi Jewish population in previous reports. Conclusion: These findings show increased prevalence of LIPA gene exon 4 variation p.G87V in the Middle East population when compared to the general population, indicating the need for prenatal screening in those of Mizrahi Jewish ancestry.

Ensemble neural network model for detecting thyroid eye disease using external photographs.

PURPOSE: To describe an artificial intelligence platform that detects thyroid eye disease (TED). DESIGN: Development of a deep learning model. METHODS: 1944 photographs from a clinical database were used to train a deep learning model. 344 additional images ('test set') were used to calculate performance metrics. Receiver operating characteristic, precision-recall curves and heatmaps were generated. From the test set, 50 images were randomly selected ('survey set') and used to compare model performance with ophthalmologist performance. 222 images obtained from a separate clinical database were used to assess model recall and to quantitate model performance with respect to disease stage and grade. RESULTS: The model achieved test set accuracy of 89.2%, specificity 86.9%, recall 93.4%, precision 79.7% and an F1 score of 86.0%. Heatmaps demonstrated that the model identified pixels corresponding to clinical features of TED. On the survey set, the ensemble model achieved accuracy, specificity, recall, precision and F1 score of 86%, 84%, 89%, 77% and 82%, respectively. 27 ophthalmologists achieved mean performance of 75%, 82%, 63%, 72% and 66%, respectively. On the second test set, the model achieved recall of 91.9%, with higher recall for moderate to severe (98.2%, n=55) and active disease (98.3%, n=60), as compared with mild (86.8%, n=68) or stable disease (85.7%, n=63). CONCLUSIONS: The deep learning classifier is a novel approach to identify TED and is a first step in the development of tools to improve diagnostic accuracy and lower barriers to specialist evaluation.

The Effect of Zero Gravity on Eyelid and Brow Position.

PURPOSE: To describe the effect of spaceflight on upper eyelid and brow position. MATERIALS AND METHODS: Images of astronauts on earth and in space were collected from a National Aeronautics and Space Administration image library. For each astronaut, front facing portraits captured within a 5-year period were obtained. At least 6 photos were collected per astronaut, 3 taken on earth, and 3 in zero gravity. Measurements from the center of the pupil to the upper eyelid margin (MRD1) and center of the pupil to the inferior eyebrow margin [pupil-to-brow (PTB)] were performed digitally for each image and averaged for each condition and each individual. Differences in mean MRD1 and PTB were assessed to illustrate the effects of zero gravity on eyelid and eyebrow position respectively. Linear-mixed effects modeling, analysis of variance and post hoc power analysis were performed. RESULTS: One hundred and twelve photographs (55 earth, 57 space) from 18 astronauts (4 women, 14 men; mean age 45.9 years) were retrieved. Zero gravity resulted in a mean PTB increase of 3.7 mm (p < 0.01) but did not result in significant change in MRD1 (p = 0.21). Post hoc power analysis of the measured MRD1 difference was performed by simulation. At an MRD1 difference of 0.5 mm, the probability of a type II error is 2.6%, equivalent to a beta power of 97.4%. Thus, we can be 97.4% confident that a difference in MRD of 0.5 mm or greater would be detected. CONCLUSIONS: While spaceflight led to significant elevation of PTB, it did not consistently alter MRD1. As such, the brow and eyelid appear to be independently regulated with respect to gravitational changes.