CC-Cruiser is an artificial intelligence (AI) platform developed for diagnosing childhood cataracts and providing risk stratification and treatment recommendations. The high accuracy of CC-Cruiser was previously validated using specific datasets. The objective of this study was to compare the diagnostic efficacy and treatment decision-making capacity between CC-Cruiser and ophthalmologists in real-world clinical settings. This multicentre randomized controlled trial was performed in five ophthalmic clinics in different areas across China. Pediatric patients (aged ≤ 14 years) without a definitive diagnosis of cataracts or history of previous eye surgery were randomized (1:1) to receive a diagnosis and treatment recommendation from either CC-Cruiser or senior consultants (with over 5 years of clinical experience in pediatric ophthalmology). The experts who provided a gold standard diagnosis, and the investigators who performed slit-lamp photography and data analysis were blinded to the group assignments. The primary outcome was the diagnostic performance for childhood cataracts with reference to cataract experts' standards. The secondary outcomes included the evaluation of disease severity and treatment determination, the time required for the diagnosis, and patient satisfaction, which was determined by the mean rating. This trial is registered with ClinicalTrials.gov (NCT03240848). Between August 9, 2017 and May 25, 2018, 350 participants (700 eyes) were randomly assigned for diagnosis by CC-Cruiser (350 eyes) or senior consultants (350 eyes). The accuracies of cataract diagnosis and treatment determination were 87.4% and 70.8%, respectively, for CC-Cruiser, which were significantly lower than 99.1% and 96.7%, respectively, for senior consultants (p < 0.001, OR = 0.06 [95% CI 0.02 to 0.19]; and p < 0.001, OR = 0.08 [95% CI 0.03 to 0.25], respectively). The mean time for receiving a diagnosis from CC-Cruiser was 2.79 min, which was significantly less than 8.53 min for senior consultants (p < 0.001, mean difference 5.74 [95% CI 5.43 to 6.05]). The patients were satisfied with the overall medical service quality provided by CC-Cruiser, typically with its time-saving feature in cataract diagnosis. CC-Cruiser exhibited less accurate performance comparing to senior consultants in diagnosing childhood cataracts and making treatment decisions. However, the medical service provided by CC-Cruiser was less time-consuming and achieved a high level of patient satisfaction. CC-Cruiser has the capacity to assist human doctors in clinical practice in its current state. National Key R&D Program of China (2018YFC0116500) and the Key Research Plan for the National Natural Science Foundation of China in Cultivation Project (91846109).

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. 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. 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.

Early and precise identification of individuals with prediabetes and type 2 diabetes (T2D) at risk for progressing to chronic kidney disease (CKD) is essential to prevent complications of diabetes. Here, we identify and evaluate prospective metabolite biomarkers and the best set of predictors of CKD in the longitudinal, population-based Cooperative Health Research in the Region of Augsburg (KORA) cohort by targeted metabolomics and machine learning approaches. Out of 125 targeted metabolites, sphingomyelin C18:1 and phosphatidylcholine diacyl C38:0 were identified as candidate metabolite biomarkers of incident CKD specifically in hyperglycemic individuals followed during 6.5 years. Sets of predictors for incident CKD developed from 125 metabolites and 14 clinical variables showed highly stable performances in all three machine learning approaches and outperformed the currently established clinical algorithm for CKD. The two metabolites in combination with five clinical variables were identified as the best set of predictors, and their predictive performance yielded a mean area value under the receiver operating characteristic curve of 0.857. The inclusion of metabolite variables in the clinical prediction of future CKD may thus improve the risk prediction in people with prediabetes and T2D. The metabolite link with hyperglycemia-related early kidney dysfunction warrants further investigation.

Approximately 1 in 33 newborns is affected by congenital anomalies worldwide. We aimed to develop a practical model for identifying infants with a high risk of congenital cataracts (CCs), which is the leading cause of avoidable childhood blindness. This case-control study was performed in the Zhongshan Ophthalmic Center and involved 2005 subjects, including 1274 children with CCs and 731 healthy controls. The CC identification models were established based on birth conditions, family medical history, and family environmental factors using the random forest (RF) and adaptive boosting methods (trained by 1129 CC cases and 609 healthy controls), which were tested by internal 4-fold cross-validation and external validation (145 CC cases and 122 healthy controls). The models were also tested using 4 datasets with gradually reduced proportions of CC patients (bilateral cases) to validate their performance in an approximate simulation of a clinical environment with a relatively low disease prevalence. The CC identification models showed high discrimination in both the 4-fold cross validation (area under the curve (AUC)=0.91 [95% confidence interval: 0.88-0.94] in bilateral cases; 0.82 [0.77-0.89] in unilateral cases) and external validation (AUC=0.93±0.05 in bilateral cases; 0.86±0.01 in unilateral cases), and achieved stable performance in the clinical tests (AUC=0.94-0.96 in the four subgroups by RF). Furthermore, family history of CC, low parental education level, and comorbidity were identified as the top three most relevant factors to both bilateral and unilateral CC diagnosis. Our CC identification models can accurately discriminate CC patients from healthy children and have the potential to serve as a complementary screening procedure, especially in undeveloped and remote areas.

Ageing, one of the largest risk factors for many complex diseases, is highly interconnected to metabolic processes. Investigating the changes in metabolite concentration during ageing among healthy individuals offers us unique insights to healthy ageing. We aim to identify ageing-associated metabolites that are independent from chronological age to deepen our understanding of the long-term changes in metabolites upon ageing. Sex-stratified longitudinal analyses were performed using fasting serum samples of 590 healthy KORA individuals (317 women and 273 men) who participated in both baseline (KORA S4) and seven-year follow-up (KORA F4) studies. Replication was conducted using serum samples of 386 healthy CARLA participants (195 women and 191 men) in both baseline (CARLA-0) and four-year follow-up (CARLA-1) studies. Generalized estimation equation models were performed on each metabolite to identify ageing-associated metabolites after adjusting for baseline chronological age, body mass index, physical activity, smoking status, alcohol intake and systolic blood pressure. Literature researches were conducted to understand their biochemical relevance. Out of 122 metabolites analysed, we identified and replicated five (C18, arginine, ornithine, serine and tyrosine) and four (arginine, ornithine, PC aa C36:3 and PC ae C40:5) significant metabolites in women and men respectively. Arginine decreased, while ornithine increased in both sexes. These metabolites are involved in several ageing processes: apoptosis, mitochondrial dysfunction, inflammation, lipid metabolism, autophagy and oxidative stress resistance. The study reveals several significant ageing-associated metabolite changes with two-time-point measurements on healthy individuals. Larger studies are required to confirm our findings.

In clinical and epidemiological researches, continuous predictors are often discretized into categorical variables for classification of patients. When the relationship between a continuous predictor and log relative hazards is U-shaped in survival data, there is a lack of a satisfying solution to find optimal cut-points to discretize the continuous predictor. In this study, we propose a novel approach named optimal equal-HR method to discretize a continuous variable that has a U-shaped relationship with log relative hazards in survival data. The main idea of the optimal equal-HR method is to find two optimal cut-points that have equal log relative hazard values and result in Cox models with minimum AIC value. An R package ‘CutpointsOEHR’ has been developed for easy implementation of the optimal equal-HR method. A Monte Carlo simulation study was carried out to investigate the performance of the optimal equal-HR method. In the simulation process, different censoring proportions, baseline hazard functions and asymmetry levels of U-shaped relationships were chosen. To compare the optimal equal-HR method with other common approaches, the predictive performance of Cox models with variables discretized by different cut-points was assessed. Simulation results showed that in asymmetric U-shape scenarios the optimal equal-HR method had better performance than the median split method, the upper and lower quantiles method, and the minimum p-value method regarding discrimination ability and overall performance of Cox models. The optimal equal-HR method was applied to a real dataset of small cell lung cancer. The real data example demonstrated that the optimal equal-HR method could provide clinical meaningful cut-points and had good predictive performance in Cox models. In general, the optimal equal-HR method is recommended to discretize a continuous predictor with right-censored outcomes if the predictor has an asymmetric U-shaped relationship with log relative hazards based on Cox regression models.