基于人工智能模型量化视网膜血管特征参数预测子痫前期的可行性研究

周天凡, 邵飞雪, 万盛, 周晨晨, 周思锦, 花晓琳

Feasibility study on quantifying retinal vascular features for predicting preeclampsia based on artificial intelligence models

ZHOU Tianfan, SHAO Feixue, WAN Sheng, ZHOU Chenchen, ZHOU Sijin, HUA Xiaolin

表3 PE发生的影响因素的单因素和多因素Logistic回归分析

Tab 3 Univariate and multivariate Logistic regression analysis of the influencing factors of PE occurrence

Characteristic Univariate Logistic analysis Multivariate Logistic analysis OR 95% CI P value aOR 95% CI P value Second-trimester MAP 1.110 1.076‒1.148 0.000 1.106 1.068‒1.147 0.000 Second-trimester EFW 0.702 0.571‒0.869 0.001 0.700 0.560‒0.870 0.000 CRAE 0.936 0.904‒0.965 0.000 0.940 0.910‒0.970 0.000 CRVE 0.972 0.952‒0.993 0.009 0.970 0.950‒0.990 0.010 AVR 0.010 0.000‒0.288 0.008 0.020 0.000‒0.500 0.020 Retinal artery tortuosity 0.000 0.000‒0.012 0.012 0.000 0.000‒0.050 0.020 Retinal artery fractal dimension 0.046 0.006‒0.393 0.004 0.070 0.010‒0.720 0.020