Accurate prediction of myopic progression and high myopia by machine learning.

Background: Myopia is a leading cause of visual impairment in Asia and worldwide. However, accurately predicting the progression of myopia and the high risk of myopia remains a challenge. This study aims to develop a predictive model for the development of myopia. Methods: We first retrospectively gathered 612 530 medical records from five independent cohorts, encompassing 227 543 patients ranging from infants to young adults. Subsequently, we developed a multivariate linear regression algorithm model to predict the progression of myopia and the risk of high myopia. Result: The model to predict the progression of myopia achieved an R2 value of 0.964 vs a mean absolute error (MAE) of 0.119D [95% confidence interval (CI): 0.119, 1.146] in the internal validation set. It demonstrated strong generalizability, maintaining consistent performance across external validation sets: R2 = 0.950 vs MAE = 0.119D (95% CI: 0.119, 1.136) in validation study 1, R2 = 0.950 vs MAE = 0.121D (95% CI: 0.121, 1.144) in validation study 2, and R2 = 0.806 vs MAE = -0.066D (95% CI: -0.066, 0.569) in the Shanghai Children Myopia Study. In the Beijing Children Eye Study, the model achieved an R2 of 0.749 vs a MAE of 0.178D (95% CI: 0.178, 1.557). The model to predict the risk of high myopia achieved an area under the curve (AUC) of 0.99 in the internal validation set and consistently high area under the curve values of 0.99, 0.99, 0.96 and 0.99 in the respective external validation sets. Conclusion: Our study demonstrates accurate prediction of myopia progression and risk of high myopia providing valuable insights for tailoring strategies to personalize and optimize the clinical management of myopia in children.

A prediction model for acute respiratory distress syndrome in immunocompetent adults with adenovirus-associated Pneumonia: a multicenter retrospective analysis.

BACKGROUND: In recent years, the number of human adenovirus (HAdV)-related pneumonia cases has increased in immunocompetent adults. Acute respiratory distress syndrome (ARDS) in these patients is the predominant cause of HADV-associated fatality rates. This study aimed to identify early risk factors to predict early HAdV-related ARDS. METHODS: Data from immunocompetent adults with HAdV pneumonia between June 2018 and May 2022 in ten tertiary general hospitals in central China was analyzed retrospectively. Patients were categorized into the ARDS group based on the Berlin definition. The prediction model of HAdV-related ARDS was developed using multivariate stepwise logistic regression and visualized using a nomogram. RESULTS: Of 102 patients with adenovirus pneumonia, 41 (40.2%) developed ARDS. Overall, most patients were male (94.1%), the median age was 38.0 years. Multivariate logistic regression showed that dyspnea, SOFA (Sequential Organ Failure Assessment) score, lactate dehydrogenase (LDH) and mechanical ventilation status were independent risk factors for this development, which has a high mortality rate (41.5%). Incorporating these factors, we established a nomogram with good concordance statistics of 0.904 (95% CI 0.844-0.963) which may help to predict early HAdV-related ARDS. CONCLUSION: A nomogram with good accuracy in the early prediction of ARDS in patients with HAdV-associated pneumonia may could contribute to the early management and effective treatment of severe HAdV infection.

Research on the Corrosion Behavior of Q235 Pipeline Steel in an Atmospheric Environment through Experiment.

Low-carbon steel pipelines are frequently used as transport pipelines for various media. As the pipeline transport industry continues to develop in extreme directions, such as high efficiency, long life, and large pipe diameters, the issue of pipeline reliability is becoming increasingly prominent. This study selected Q235 steel, a typical material for low-carbon steel pipelines, as the research object. In accordance with the pipeline service environment and the accelerated corrosion environment test spectrum, cyclic salt spray accelerated corrosion tests that simulated the effects of the marine atmosphere were designed and implemented. Corrosion properties, such as corrosion weight loss, morphology, and product composition of samples with different cycles, were characterized through appearance inspection, scanning electron microscopy analysis, and energy spectrum analysis. The corrosion behavior and mechanism of Q235 low-carbon steel in the enhanced corrosion environment were studied, and the corrosion weight loss kinetics of Q235 steel was verified to conform to the power function law. During the corrosion process, the passivation film on the surface of the low-carbon steel and the dense and stable α-FeOOH layer formed after the passivation film was peeled off played a role in corrosion resistance. The passivation effect, service life, and service limit of Q235 steel were studied and determined, and an evaluation model for quick evaluation of the corrosion life of Q235 low-carbon steel was established. This work provides technical support to improve the life and reliability of low-carbon steel pipelines. It also offers a theoretical basis for further research on the similitude and relevance of cyclic salt spray accelerated corrosion testing.

Research on High Temperature Stamping Forming Performance and Process Parameters Optimization of 7075 Aluminum Alloy.

The stress strain curve of 7075 aluminum alloy in the temperature range of 310 °C to 410 °C was obtained by Gleeble-3800. By Nakazima test, the isothermal thermoforming limit diagrams of 7075 aluminum alloy at different deformation temperatures and stamping speeds were acquired. Moreover, the parameters of automotive S-rail hot stamping process were optimized by GA-BP neural network. The results show that the forming limit curve of 7075 aluminum alloy increases as the deformation temperature and stamping speed increase. The predicted optimal parameters for hot stamping of automotive S-rails by GA-BP neural network are: stamping speed is 50 mm/s, friction coefficient between die and blank is 0.1, and blank holder force is 5 kN. The maximum thinning rate at this process parameter is 9.37%, which provided a reference for 7075 aluminum alloy automotive S-rail hot stamping.

Transcriptome and expression profile analysis of highly resistant and susceptible banana roots challenged with Fusarium oxysporum f. sp. cubense tropical race 4.

Banana wilt disease, caused by the fungal pathogen Fusarium oxysporum f. sp. cubense 4 (Foc4), is regarded as one of the most devastating diseases worldwide. Cavendish cultivar 'Yueyoukang 1' was shown to have significantly lower disease severity and incidence compared with susceptible cultivar 'Brazilian' in greenhouse and field trials. De novo sequencing technology was previously performed to investigate defense mechanism in middle resistant 'Nongke No 1' banana, but not in highly resistant cultivar 'Yueyoukang 1'. To gain more insights into the resistance mechanism in banana against Foc4, Illumina Solexa sequencing technology was utilized to perform transcriptome sequencing of 'Yueyoukang 1' and 'Brazilian' and characterize gene expression profile changes in the both two cultivars at days 0.5, 1, 3, 5 and 10 after infection with Foc4. The results showed that more massive transcriptional reprogramming occurs due to Foc4 treatment in 'Yueyoukang 1' than 'Brazilian', especially at the first three time points, which suggested that 'Yueyoukang 1' had much faster defense response against Foc4 infection than 'Brazilian'. Expression patterns of genes involved in 'Plant-pathogen interaction' and 'Plant hormone signal transduction' pathways were analyzed and compared between the two cultivars. Defense genes associated with CEBiP, BAK1, NB-LRR proteins, PR proteins, transcription factor and cell wall lignification were expressed stronger in 'Yueyoukang 1' than 'Brazilian', indicating that these genes play important roles in banana against Foc4 infection. However, genes related to hypersensitive reaction (HR) and senescence were up-regulated in 'Brazilian' but down-regulated in 'Yueyoukang 1', which suggested that HR and senescence may contribute to Foc4 infection. In addition, the resistance mechanism in highly resistant 'Yueyoukang 1' was found to differ from that in middle resistant 'Nongke No 1' banana. These results explain the resistance in the highly resistant cultivar and provide more insights in understanding the compatible and incompatible interactions between banana and Foc4.