Stoenescu Manuela, Şerbănescu Mircea-Sebastian, Dijmarescu Anda Lorena, Manolea Maria Magdalena, Sandulescu Sidonia, Vrabie Sidonia, Camen Ioana, Tabacu Maria Carmen, Novac Marius Bogdan
PhD, University of Medicine and Pharmacy of Craiova, Romania.
Medical Informatics and Biostatistics Department, University of Medicine and Pharmacy of Craiova, Romania.
Curr Health Sci J. 2021 Apr-Jun;47(2):215-220. doi: 10.12865/CHSJ.47.02.11. Epub 2021 Jun 30.
The study aims to predict mother and fetus outcome based on the mother's lipid profile in the second and third trimester of pregnancy.
Blood and urinary samples were taken from 135 mothers that were prospectively monitored during the hole pregnancy. Total cholesterol (TC), triglycerides (TG), low-density lipoprotein-cholesterol (LDL-C), high-density lipoprotein-cholesterol (HDL-C), together with other parameters, were used as predictors in a multilayer perceptron (MLP) artificial neural network (ANN). Small for gestational age (SGA) was used to assess the fetal outcome, while Gestational diabetes mellitus (GDM) and, Hypertensive disorders in pregnancy (HDP) to assess the mother's outcome.
SGA prediction rate was 0.637±0.022 for the second trimester and 0.632±0.017 for the third trimester. GDM prediction rate was 0.897±0.006 for the second trimester and 0.632±0.017 for the third trimester. HDP prediction rate was 0.620±0.046 for the second trimester and 0.775±0.030 for the third trimester. When used with other parameters (hemoglobin, thrombocytes, uric acid, GOT, GPT, the presence of proteinuria, urea, and creatinine) the prediction rates raised, going over 90% for the GDM.
Though individual lipid parameters do not statistically correlate with the output variables the use of ANN generated prediction rates raging from 60% to 90%. The lipid profile from the third trimesters seems to be a better prediction for both fetus and mother outcome.
本研究旨在根据孕妇妊娠中期和晚期的血脂情况预测母婴结局。
采集了135名孕妇的血液和尿液样本，并在整个孕期进行前瞻性监测。总胆固醇（TC）、甘油三酯（TG）、低密度脂蛋白胆固醇（LDL-C）、高密度脂蛋白胆固醇（HDL-C）以及其他参数被用作多层感知器（MLP）人工神经网络（ANN）的预测指标。小于胎龄儿（SGA）用于评估胎儿结局，而妊娠期糖尿病（GDM）和妊娠高血压疾病（HDP）用于评估母亲的结局。
孕中期SGA预测率为0.637±0.022，孕晚期为0.632±0.017。孕中期GDM预测率为0.897±0.006，孕晚期为0.632±0.017。孕中期HDP预测率为0.620±0.046，孕晚期为0.775±0.030。当与其他参数（血红蛋白、血小板、尿酸、谷草转氨酶、谷丙转氨酶、蛋白尿、尿素和肌酐）一起使用时，预测率提高，GDM的预测率超过90%。
尽管单个血脂参数与输出变量在统计学上无相关性，但使用人工神经网络生成的预测率在60%至90%之间。孕晚期的血脂情况似乎对胎儿和母亲的结局有更好的预测作用。
