Prediction of refractive error and its progression: a machine learning-based algorithm.

OBJECTIVE: Myopia is the refractive error that shows the highest prevalence for younger ages in Southeast Asia and its projection over the next decades indicates that this situation will worsen. Nowadays, several management solutions are being applied to help fight its onset and development, nonetheless, the applications of these techniques depend on a clear and reliable assessment of risk to develop myopia. METHODS AND ANALYSIS: In this study, population-based data of Chinese children were used to develop a machine learning-based algorithm that enables the risk assessment of myopia's onset and development. Cross-sectional data of 12 780 kids together with longitudinal data of 226 kids containing age, gender, biometry and refractive parameters were used for the development of the models. RESULTS: A combination of support vector regression and Gaussian process regression resulted in the best performing algorithm. The Pearson correlation coefficient between prediction and measured data was 0.77, whereas the bias was -0.05 D and the limits of agreement was 0.85 D (95% CI: -0.91 to 0.80D). DISCUSSION: The developed algorithm uses accessible inputs to provide an estimate of refractive development and may serve as guide for the eye care professional to help determine the individual best strategy for management of myopia.

LMS parameters, percentile, and Z-score growth curves for axial length in Chinese schoolchildren in Wuhan.

Understanding the ocular structural changes are fundamental to defining strategies for myopia prevention and management. This study aimed to establish age-gender specific normative LMS parameters for axial length to generate percentile and Z-score growth curves in a population of Chinese schoolchildren. A total of 14,760 individuals aged 6 to 15 years from Wuhan, central China, contributed to this study. The LMS method was used for the calculation of LMS parameters and the generation of percentile and Z-score growth curves for axial length. Growth curves derived from the LMS parameters were compared with those originally calculated. Axial elongation was age- and percentile-dependent. The highest elongation rate occurred at the 98th percentile in the range 6 to 9 years, being up to 1.46 mm in boys and 1.42 mm in girls. The largest differences between original and newly generated growth curves were detected at the 98th percentile at age 15; 0.78 mm (females) and 0.63 mm (males). Multinomial logistic regression and receiver operating characteristic analyses revealed Z-scores as a good predictor for estimating high myopia development. The axial length growth curves presented in this study provide a technically solid instrument that depicts the best description of physiological eye growth for Chinese schoolchildren aged 6 to 15 years.

Genetic variants of cell cycle pathway genes are associated with head and neck squamous cell carcinoma in the Chinese population.

Genetic alterations in the cell cycle pathway are common in head and neck squamous cell carcinoma (HNSCC). We identified four novel HNSCC susceptibility loci (CDKN1C rs452338, CDK4 rs2072052, E2F2 rs3820028 and E2F2 rs2075993) through a two-stage matched case-control study. There was a combined effect among the four single nucleotide polymorphisms (SNPs), as the number of risk genotypes increased, the risk of HNSCC displayed an increasing trend (Ptrend < 0.001). And there were multiplicative interactions between rs452338 and rs2072052, rs2072052 and rs3820028, rs2072052 and rs2075993. Functional bioinformatics analysis and dual-luciferase reporter assay revealed that E2F2 rs2075993 T>C reduced the stability of E2F2 3'-UTR secondary structure and affected the binding of E2F2 to miR-940, which was up-regulated in HNSCC tumor tissues (P = 2.9e-8) and was correlated with poor overall survival of HNSCC (HR = 1.39, 95% CI = 1.02-1.90). In vitro assays, we discovered that the expression of miR-940 was regulated by METTL3, and miR-940 promoted the proliferation, migration and invasion, and inhibited the senescence and autophagy of tumor cells. In terms of mechanism, compared with rs2075993 allele T, we found that the protective variant rs2075993 allele C interfered with the translational inhibition of E2F2 by miR-940, resulting in increased expression of E2F2 protein, which further reduced the proliferation, migration, invasion, and increased the senescence of tumor cells.

A Risk Score System for Myopia Symptom Warning.

Myopia is the leading cause of visual impairments worldwide. Some studies revealed that visual experience in early life affected the final myopia, indicating that environmental factors play an impellent role in the development of myopia. However, risk factors of myopia are still not identified among adolescents in China. A total of 4104 cases of myopia symptom and 3306 emmetropia controls were selected from students in primary and middle schools in Wuhan in 2008. We identified the risk factors associated with myopia symptom by multivariate logistic regression in this cross-sectional study and constructed a risk score system for myopia symptom. The value of the area under the receiver operating characteristic curve (ROC) was 0.735. Furthermore, we followed up 93 students aged 7-9 years for one year and calculated the total points using the score system. We found no significant difference between the final myopia symptom and the results predicted by the total points by pair chi-square test (P>0.05). The score system had a modest ability to estimate the risk factors of myopia symptom. Using this score system, we could identify the students who are at risk of myopia symptom in the future according to their behaviors and environmental factors, and take measures to slow the progress of myopia symptom.

Growth curves of myopia-related parameters to clinically monitor the refractive development in Chinese schoolchildren.

PURPOSE: To produce a clinical model for the prediction of myopia development based on the creation of percentile curves of axial length in school-aged children from Wuhan in central China. METHODS: Data of 12,554 children (6054 girls and 6500 boys) were collected and analyzed for the generation of the axial length growth curves. A second data set with 226 children and three yearly successive measurements was used to verify the predictive power of the axial length growth percentile curves. Percentile curves were calculated for both gender groups and four age groups (6, 9, 12, and 15 years). The second data set was used to verify the efficacy of identifying the refractive error of the children using the axial length curves, based on their spherical refractive error from the third visit. RESULTS: From 6 to 15 years of age, all percentiles showed a growth trend in axial length, except for the percentiles below the first quartile, which appear to stabilize after the age of 12 (- 0.10; 95%CI, - 0.36-0.16; P = 0.23 for girls; - 0.16; 95%CI, - 0.70-0.39; P = 0.34 for boys); however, the growth continued for the remaining 75% of cases. The second data set showed that the likelihood of suffering high myopia (spherical refractive error ≤- 5.00D) during adolescent years increased when axial length values were above the first quartile, for both genders. CONCLUSIONS: The data from the current study provide a tool to observe the annual growth rates of axial length and can be considered as an approach to predict the refractive development at school ages.

Aberrant Methylation of RASSF1A Closely Associated with HNSCC, a Meta-Analysis.

The RAS association domain family protein 1a (RASSF1A), a tumor suppressor gene at 3p21.3, plays a very important role in various cancers, including the head and neck squamous cell carcinoma (HNSCC). Hypermethylation of CpG islands in the RASSF1A promoter region contribute to epigenetic inactivation. However, the association between RASSF1A promoter methylation and HNSCC remains unclear and controversial. Therefore, a meta-analysis was performed in the study to identify the association. We identified the eligible studies through searching PubMed, EMBASE, Web of Science, and China National Knowledge Infrastructure (CNKI) databases with a systematic searching strategy. The information on characteristics of each study and prevalence of RASSF1A methylation were collected. Pooled odds ratios (ORs) with corresponding confidence intervals (CIs) were calculated. Meta-regression was performed to analyze heterogeneity and funnel plots were applied to evaluate publication bias. A total of 550 HNSCC patients and 404 controls from twelve eligible studies were included in the meta-analysis. Overall, a significant association was observed between RASSF1A methylation status and HNSCC risk under a random-effects model (OR = 2.93, 95% CI: 1.58-5.46). There was no significant publication bias observed. The meta-analysis suggested that there was a significant association between aberrant RASSF1A methylation and HNSCC.