Objective:To investigate the correlation between hyperreflective dots (HRD) and lipid levels and systemic inflammatory factors in patients with branch retinal vein occlusion (BRVO) or central retinal vein occlusion (CRVO).Methods:A cross-sectional clinical study. From December 2016 to June 2020, 118 eyes of 118 patients with retinal vein occlusion diagnosed in the Department of Ophthalmology, Central Theater Command Hospital of People's Liberation Army were included in the study. Among them, 67 cases of BRVO and 51 cases of CRVO were divided into CRVO group and BRVO group accordingly. Peripheral venous blood was drawn from the patients within 3 days after the eye examination to detect the percentage of neutrophils, monocytes, hypersensitive C-reactive protein (CRP), total cholesterol, triglyceride, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, and lipoprotein(a). The ratio of monocytes to high-density lipoprotein (MHR) was also calculated. The 3D OCT-2000 instrument from Topcon (Japan) was used to measure the central retinal thickness (CRT) and the numbers of HRD. According to the different distribution position, HRD is divided into inner retina HRD, outer retina HRD, and total retina HRD.The independent sample t test was used to compare the continuous variables of the two groups, and the χ2 test was used to compare the rates. The correlation between HRD counts and blood lipid levels and peripheral blood inflammation indicators in patients with different types of RVO was analyzed by Spearman correlation analysis. Results:The average age of patients in the BRVO group and CRVO group were 60.1±9.5 and 53.6±15.7 years, respectively; the prevalence of hypertension was 53.7% (36/67) and 24.5% (12/51), respectively. Comparison of age ( t=2.634) and prevalence of hypertension ( χ2=11.298) between the two groups showed statistically significant differences ( P<0.05). Gender ( χ2=2.000), course of disease ( t=-1.101), prevalence of diabetes ( χ2=1.315), eye category ( χ2=1.742), baseline visual acuity ( t=1.792), intraocular pressure ( t=0.708), CRT ( t=1.318), and peripheral blood include the percentage of neutrophils, the absolute number of monocytes, CRP, total cholesterol, triglycerides, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, lipoprotein(a), MHR ( t=-0.559, 1.126, 0.579, 1.299, -0.134, 0.556, 1.230, -0.267, 0.483), the difference was not statistically significant. Correlation analysis showed that the HRD counts in the outer retina of BRVO patients were positively correlated with total cholesterol ( r=0.289, P=0.036); the HRD in the inner retina and total HRD counts of CRVO patients were positively correlated with CRP ( r=0.406, 0.343; P=0.004, 0.014). There was no correlation between HRD counts and percentage of neutrophils, absolute number of monocytes, triglycerides, high-density lipoprotein, low-density lipoprotein, lipoprotein(a), and MHR ( P>0.05). Conclusion:The number of HRD is related to the blood lipid level in BRVO patients and CRP (an inflammatory index) in CRVO patients.

OBJECTIVES: Firefighters are prone to suffer from psychological trauma and post-traumatic stress disorder (PTSD) in the workplace, and have a poor prognosis after PTSD. Reliable models for predicting PTSD allow for effective identification and intervention for patients with early PTSD. By collecting the psychological traits, psychological states and work situations of firefighters, this study aims to develop a machine learning algorithm with the aim of effectively and accurately identifying the onset of PTSD in firefighters, as well as detecting some important predictors of PTSD onset. METHODS: This study conducted a cross-sectional survey through convenient sampling of firefighters from 20 fire brigades in Changsha, which were evenly distributed across 6 districts and Changsha County, with a total of 628 firefighters. We used the synthetic minority oversampling technique (SMOTE) to process data sets and used grid search to finish the parameter tuning. The predictive capability of several commonly used machine learning models was compared by 5-fold cross-validation and using the area under the receiver operating characteristic curve (ROC-AUC), accuracy, precision, recall, and F1 score. RESULTS: The random forest model achieved good performance in predicting PTSD with an average AUC score at 0.790. The mean accuracy of the model was 90.1%, with an F1 score of 0.945. The three most important predictors were perseverance, forced thinking, and reflective deep thinking, with weights of 0.165, 0.158, and 0.152, respectively. The next most important predictors were employment time, psychological power, and optimism. CONCLUSIONS PTSD onset prediction model for Changsha firefighters constructed by random forest has strong predictive ability, and both psychological characteristics and work situation can be used as predictors of PTSD onset risk for firefighters. In the next step of the study, validation using other large datasets is needed to ensure that the predictive models can be used in clinical setting.
Humans ; Stress Disorders, Post-Traumatic/diagnosis* ; Firefighters/psychology* ; Cross-Sectional Studies ; Algorithms ; Machine Learning