Search

Author(s): Haotian Lin 1, Erping Long 1, Xiaohu Ding 1, Hongxing Diao 1, Zicong Chen 2, Runzhong Liu 2, Jialing Huang 2, Jingheng Cai 3, Shuangjuan Xu 3, Xiayin Zhang [...], Background Electronic medical records provide large-scale real-world clinical data for use in developing clinical decision systems. However, sophisticated methodology and analytical skills are required to handle the large-scale datasets necessary for the optimisation of prediction accuracy. Myopia is a common cause of vision loss. Current approaches to control myopia progression are effective but have significant side effects. Therefore, identifying those at greatest risk who should undergo targeted therapy is of great clinical importance. The objective of this study was to apply big data and machine learning technology to develop an algorithm that can predict the onset of high myopia, at specific future time points, among Chinese school-aged children. Methods and findings Real-world clinical refraction data were derived from electronic medical record systems in 8 ophthalmic centres from January 1, 2005, to December 30, 2015. The variables of age, spherical equivalent (SE), and annual progression rate were used to develop an algorithm to predict SE and onset of high myopia (SE [less than or equal to] -6.0 dioptres) up to 10 years in the future. Random forest machine learning was used for algorithm training and validation. Electronic medical records from the Zhongshan Ophthalmic Centre (a major tertiary ophthalmic centre in China) were used as the training set. Ten-fold cross-validation and out-of-bag (OOB) methods were applied for internal validation. The remaining 7 independent datasets were used for external validation. Two population-based datasets, which had no participant overlap with the ophthalmic-centre-based datasets, were used for multi-resource validation testing. The main outcomes and measures were the area under the curve (AUC) values for predicting the onset of high myopia over 10 years and the presence of high myopia at 18 years of age. In total, 687,063 multiple visit records ([greater than or equal to]3 records) of 129,242 individuals in the ophthalmic-centre-based electronic medical record databases and 17,113 follow-up records of 3,215 participants in population-based cohorts were included in the analysis. Our algorithm accurately predicted the presence of high myopia in internal validation (the AUC ranged from 0.903 to 0.986 for 3 years, 0.875 to 0.901 for 5 years, and 0.852 to 0.888 for 8 years), external validation (the AUC ranged from 0.874 to 0.976 for 3 years, 0.847 to 0.921 for 5 years, and 0.802 to 0.886 for 8 years), and multi-resource testing (the AUC ranged from 0.752 to 0.869 for 4 years). With respect to the prediction of high myopia development by 18 years of age, as a surrogate of high myopia in adulthood, the algorithm provided clinically acceptable accuracy over 3 years (the AUC ranged from 0.940 to 0.985), 5 years (the AUC ranged from 0.856 to 0.901), and even 8 years (the AUC ranged from 0.801 to 0.837). Meanwhile, our algorithm achieved clinically acceptable prediction of the actual refraction values at future time points, which is supported by the regressive performance and calibration curves. Although the algorithm achieved balanced and robust performance, concerns about the compromised quality of real-world clinical data and over-fitting issues should be cautiously considered. Conclusions To our knowledge, this study, for the first time, used large-scale data collected from electronic health records to demonstrate the contribution of big data and machine learning approaches to improved prediction of myopia prognosis in Chinese school-aged children. This work provides evidence for transforming clinical practice, health policy-making, and precise individualised interventions regarding the practical control of school-aged myopia.

Background: Different visual acuity chart can be targeted to evaluate the visual function of patients with different eye diseases. We conducted a comparative analysis of the digital logarithm of the minimum angle of resolution (LogMAR) vision chart and the standard logarithmic vision chart for the measurement of visual acuity after retinal detachment surgery., Methods: We used the digital LogMAR vision chart and the standard logarithmic vision chart to measure the visual acuity of 100 patients (100 eyes) who underwent retinal detachment surgery at our hospital using the LogMAR recording method and compared the differences between the mean measurements obtained by both methods for all patients and for different age groups., Results: When all of the patients were analyzed, the mean visual acuity differed between the digital LogMAR vision chart and the standard logarithmic vision chart by -0.07 LogMAR units. No significant difference was observed in the mean visual acuity between the two vision charts in the 10-20 year and 21-40 year age groups (P > 0.05), while a significant difference was observed in post-operative mean visual acuity between the two vision charts for patients aged 41-65 years (P < 0.05)., Conclusions: Both the digital LogMAR vision chart and the standard vision chart were effective and reliable for the measurement of visual acuity. The visual acuity measured by the standard vision chart was higher than that measured by the digital LogMAR vision chart. We recommend using the digital LogMAR vision chart as the preferred chart for measuring visual acuity after retinal detachment surgery.

Purpose: To conduct dynamic detection of refraction changes in adolescents with myopia and analyze the correlation between different reexamination times and factors that included age of onset, initial refractive power, and rate of myopia progression., Methods: A total of 900 adolescents (aged 6-15 years) with myopia admitted to Zhongshan Ophthalmic Center between 2009 and 2013 were randomly selected in this investigation. All participants underwent objective refraction measurement with an autorefractometer (Topcon 8900) or streak retinoscopy and subjective refraction detection with an autorefractor (Nidek) or minus-lens procedures at different time intervals (6 months, 1, and 2 years). Accurate refractive power was obtained. All data were analyzed with SPSS 18.0 statistical software., Results: The mean refractive power was increased by 0.56 ± 0.37 diopters(D) after 6 months, by 0.83 ± 0.45 D after 1 year, and by 1.50 ± 0.70 D after 2 years. Among the 900 adolescents, the most rapid increase in refractive power was observed at the age of 8 years at the 6-month reexamination, at the age of 8 and 9 years at the 1-year reexamination, and at the age of 7-9 years at the 2-year reexamination. The increase in index of refraction tended to diminish with aging. The different cycles of reexamination revealed a slowing of the rate of myopia progression along with the increase in the initial index of refraction. The highest rate of myopia progression was noted in low-myopic adolescents with initial refractive power ranging from -0.25 to 2.75 D., Conclusion: No positive correlation was documented between different cycles of reexamination and the refractive power. The increase in refractive power was associated with factors that included the reexamination cycle, age of onset, and initial refractive power.

Purpose: To compare the education effect of video demonstrations and conventional teaching on the prevention and control of myopia., Methods: Eighty students were randomly divided into an experimental (n = 40) and a control (n = 40) group, and each group was split into two classes of 40 students. The students in the experimental group attended classes mainly based on video demonstration and those in the control group received conventional teaching. All students then undertook a test and the examination scores were statistically compared between the two groups., Results: The educational background, age, and gender did not differ between the two groups (all P > 0.05). The experimental group had a mean test score of 8.25 ± 1.45, which was slightly lower than the mean of 8.58 ± 1.11 in the control group, but the difference was not statistically significant (t = -1.589, P = 0.114)., Conclusion: The educational effect of video demonstrations was almost identical to that of traditional teaching. In addition, video classes reduced the training time and financial costs, indicating that they deserve widespread application.

Purpose: To evaluate the applicability of different visual acuity charts for outpatient pediatric visual tests., Methods: Fifty-three children (53 eyes) aged 4-8 years undergoing visual acuity tests as outpatients were randomly selected for this study. The best corrected visual acuity (BCVA) of the eye with better visual acuity was measured for each child using the digital LogMAR visual chart, the ETDRS visual chart, and a new standard logarithm visual chart; all measurements were repeated twice and the BCVA was recorded. Paired comparisons were made between the LogMAR visual acuity chart and ETDRS chart measurements or between the ETDRS chart and logarithm visual acuity chart measurements for statistical analysis of the differences in measurement of visual acuity. The results of different measurements by the same chart were compared to evaluate the consistency of the measurement results. Bland-Altman analysis was employed to evaluate the most suitable chart for outpatient measurement of visual acuity in children., Results: Bland-Altman analysis revealed that the mean visual acuity measured was (0.447 ± 0.017 LogMAR) by the digital LogMAR chart, (0.301 ± 0.024 LogMAR) by the standard logarithm visual acuity chart, and (0.309 ± 0.018 LogMAR) by the ETDRS visual acuity chart. The BCVA was significantly lower when measured by the LogMAR visual acuity chart than by the ETDRS chart (P < 0.01). The BCVA was slightly higher when measured by the logarithm visual acuity chart than by the ETDRS chart, but the difference was not statistically significant (P > 0.05). The Bland-Altman plot showed that the highest consistency was obtained with the digital LogMAR chart, with a difference between two repeated measurements of 0.068 LogMAR, compared to 0.090 and 0.072 LogMAR for the logarithm and ETDRS visual acuity charts, respectively., Conclusion: All three types of visual acuity charts are applicable for outpatient measurement of pediatric visual acuity. The ETDRS and logarithm visual acuity charts have a higher consistency, but the LogMAR visual acuity chart shows better reproducibility. Consequently, it is difficult to identify and distinguish which acuity chart is most suitable for cooperative children.

Objective: To study the anti-cataract effect of gigantol combined with syringic acid and their action mechanism., Method: H202-induced lens oxidative injury in vitro rat model was establish to observe the impact of gigantol combined with syringic acid on lens transparency under a dissecting microscope. D-galactose-induced cataract rat model was established to observe the impact of gigantol combined with syringic acid on lens transparency under a slit-lamp. UV spectrophotometry was adopted to detect the inhibitory activity of gigantol combined with syringic acid against AR. Molecular docking method was used to detect binding sites, binding types and pharmacophores of gigantol combined with syringic acid in prohibiting aldose reductase., Result: Both in vitro and in vivo experiments showed a good anti-sugar cataract activity in the combination of gigantol and syringic acid and a better collaborative effect than single component-gigantol and syringic acid and positive control drug Catalin. Molecular docking and dynamic simulation showed their collaborative AR-inhibiting amino acid residue was Asn160 and the major acting force was Van der Waals' force, which formed common pharmacophores., Conclusion: Gigantol combined with syringic acid shows good anti-cataract, their action mechanism is reflected in their good collaborative inhibitory effect on AR.