Prediction of myopia development among Chinese school-aged children using refraction data from electronic medical records: A retrospective, multicentre machine learning study.

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 ≤ -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 (≥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.

Construction and implications of structural equation modeling network for pediatric cataract: a data mining research of rare diseases.

BACKGROUND: The majority of rare diseases are complex diseases caused by a combination of multiple morbigenous factors. However, uncovering the complex etiology and pathogenesis of rare diseases is difficult due to limited clinical resources and conventional statistical methods. This study aims to investigate the interrelationship and the effectiveness of potential factors of pediatric cataract, for the exploration of data mining strategy in the scenarios of rare diseases. METHODS: We established a pilot rare disease specialized care center to systematically record all information and the entire treatment process of pediatric cataract patients. These clinical records contain the medical history, multiple structural indices, and comprehensive functional metrics. A two-layer structural equation model network was applied, and eight potential factors were filtered and included in the final modeling. RESULTS: Four risk factors (area, density, location, and abnormal pregnancy experience) and four beneficial factors (axis length, uncorrected visual acuity, intraocular pressure, and age at diagnosis) were identified. Quantifiable results suggested that abnormal pregnancy history may be the principle risk factor among medical history for pediatric cataracts. Moreover, axis length, density, uncorrected visual acuity and age at diagnosis served as the dominant factors and should be emphasized in regular clinical practice. CONCLUSIONS: This study proposes a generalized evidence-based pattern for rare and complex disease data mining, provides new insights and clinical implications on pediatric cataract, and promotes rare-disease research and prevention to benefit patients.

Statin prevents cancer development in chronic inflammation by blocking interleukin 33 expression.

Chronic inflammation is a major cause of cancer worldwide. Interleukin 33 (IL-33) is a critical initiator of cancer-prone chronic inflammation; however, its induction mechanism by environmental causes of chronic inflammation is unknown. Herein, we demonstrate that Toll-like receptor (TLR)3/4-TBK1-IRF3 pathway activation links environmental insults to IL-33 induction in the skin and pancreas inflammation. An FDA-approved drug library screen identifies pitavastatin to effectively suppress IL-33 expression by blocking TBK1 membrane recruitment/activation through the mevalonate pathway inhibition. Accordingly, pitavastatin prevents chronic pancreatitis and its cancer sequela in an IL-33-dependent manner. The IRF3-IL-33 axis is highly active in chronic pancreatitis and its associated pancreatic cancer in humans. Interestingly, pitavastatin use correlates with a significantly reduced risk of chronic pancreatitis and pancreatic cancer in patients. Our findings demonstrate that blocking the TBK1-IRF3-IL-33 signaling axis suppresses cancer-prone chronic inflammation. Statins present a safe and effective prophylactic strategy to prevent chronic inflammation and its cancer sequela.

Real-world big data demonstrates prevalence trends and developmental patterns of myopia in China: a retrospective, multicenter study.

BACKGROUND: Myopia is a complex disease caused by a combination of multiple pathogenic factors. Prevalence trends and developmental patterns of myopia exhibit substantial variability that cannot be clearly assessed using limited sample sizes. This study aims to determine the myopia prevalence over the past 60 years and trace the myopia development in a school-aged population using medical big data. METHODS: The refraction data from electronic medical records in eight hospitals in South China were collected from January 2005 to October 2018; including patients' year of birth, refraction status, and age at the exam. All optometry tests were performed in accordance with standard procedures by qualified senior optometrists. The cross-sectional datasets (individuals with a single examination) and longitudinal datasets (individuals with multiple examinations) were analyzed respectively. SAS statistical software was used to extract and statistically analyse all target data and to identify prevalence trends and developmental patterns related to myopia. RESULTS: In total, 1,112,054 cross-sectional individual refraction records and 774,645 longitudinal records of 273,006 individuals were collected. The myopia prevalence significantly increased among individuals who were born after the 1960s and showed a steep rise until reaching a peak of 80% at the 1980s. Regarding developmental patterns, the cross-sectional data demonstrated that the myopia prevalence increased dramatically from 23.13% to 82.83% aging from 5 to 11, and the prevalence stabilized at the age of 20. The longitudinal data confirmed the results that the age of myopic onset was 7.47±1.67 years, the age of myopia stabilized at 17.14±2.61 years, and the degree of myopia stabilized at -4.35±3.81 D. CONCLUSIONS: The medical big data used in this study demonstrated prevalence trends of myopia over the past 60 years and revealed developmental patterns in the onset, progression and stability of myopia in China.

Dynamic profile of ocular refraction in pediatric cataract patients after lens surgeries.

AIM: To study the change in ocular refraction in patients with pediatric cataracts (PCs) after lens extraction. METHODS: A total of 1258 patients who were undergoing cataract extraction with/without intraocular lens (IOL) implantation were recruited during preoperative examinations between Jan 2010 and Oct 2013. Patient ages ranged from 1.5mo to 14y. Follow-ups were conducted at 1wk, 1, and 3mo postoperatively and every 3mo in the first year, then 6mo thereafter. Ocular refraction [evaluated as spherical equivalent (SE)] and yearly myopic shift (YMS) were recorded and statistically analyzed among patients with age at surgery, baseline ocular refraction, gender, postoperative time and laterality (bilateral vs unilateral). RESULTS: By Dec 31st 2015, 1172 participants had been followed for more than 2y. The median follow-up period was 3y. The critical factors affecting the ocular refraction of PC patients were baseline ocular refraction, postoperative time for both aphakic and pseudophakic eyes. YMS grew most rapidly in young childhood and early adolescence. CONCLUSION: After lens surgeries, ocular refraction in PC patients shows an individual difference of change. Further concerns should be raising to monitor the rapid myopic shift at early adolescence of these patients.

Clinical characteristics of young adult cataract patients: a 10-year retrospective study of the Zhongshan Ophthalmic Center.

AIM: To investigate the characteristics of young adult cataract (YAC) patients over a 10-year period. METHODS: This observational study included YAC patients aged 18-49 years who were treated surgically for the first time at the Zhongshan Ophthalmic Center in China. YAC patients were analysed and compared with patients with childhood cataract (CC) in January 2005 to December 2014. RESULTS: During the 10-year period, 515 YAC patients and 2421 inpatients with CC were enrolled. Among the YAC patients, 76.76% (109/142) of unilateral patients had a corrected distance visual acuity (CDVA) better than 20/40 in the healthy eye, whereas only 20.38% (76/373) of bilateral patients had a CDVA better than 20/40 in the eye with better visual acuity. Compared with the CC group, the YAC group had a higher proportion of rural patients (40.40% vs 31.60%, p=0.001). Furthermore, the prevalence of other ocular abnormalities in YAC patients was higher than that in patients with CC (29.71% vs 17.47%, p<0.001). CONCLUSIONS: A large proportion coming from rural areas and a high prevalence of complicated ocular abnormalities may be the most salient characteristics of YAC patients. Strengthening the counselling and screening strategy for cataract and health education for young adults are required especially for those in rural areas.