Prediction model development of late-onset preeclampsia using machine learning-based methods

• Published in: PloS one Vol. 14; no. 8; p. e0221202
• Main Authors: Jhee, Jong Hyun, Lee, SungHee, Park, Yejin, Lee, Sang Eun, Kim, Young Ah, Kang, Shin-Wook, Kwon, Ja-Young, Park, Jung Tak
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 23.08.2019; Public Library of Science (PLoS)
• Subjects: Adult; Age; Age of Onset; Algorithms; Artificial intelligence; Bayes Theorem; Bayesian analysis; Biology and Life Sciences; Biomarkers; Blood pressure; Calcium; Calcium (blood); Calcium (urinary); Cholesterol; Classification; Cluster analysis; Collaboration; Computer and Information Sciences; Creatinine; Data mining; Decision trees; Diabetes; Diabetic retinopathy; Diagnosis; Electronic health records; Electronic medical records; Electronic records; Family medical history; Female; Fetuses; Gestation; Gestational Age; Glucose; Gynecology; Health aspects; Hospitals; Humans; Hypertension; Laboratories; Learning algorithms; Leukocytes; Life sciences; Logistic Models; Machine Learning; Mathematical models; Medical records; Medical research; Medicine and Health Sciences; Morbidity; Mortality; Obstetrics; Pattern analysis; Pattern recognition; Physical Sciences; Potassium; Pre-eclampsia; Pre-Eclampsia - diagnosis; Pre-Eclampsia - epidemiology; Pre-Eclampsia - physiopathology; Prediction models; Preeclampsia; Pregnancy; Pregnancy Trimester, Second; Pregnancy Trimester, Third; Pregnant women; Prenatal care; Preventive medicine; Regression analysis; Regression models; Research and Analysis Methods; Statistical analysis; Statistical methods; Stochasticity; Support Vector Machine; Support vector machines; Surveillance; Urea; Urine; Variables; White blood cell count; Womens health
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0221202

Preeclampsia is one of the leading causes of maternal and fetal morbidity and mortality. Due to the lack of effective preventive measures, its prediction is essential to its prompt management. This study aimed to develop models using machine learning to predict late-onset preeclampsia using hospital electronic medical record data. The performance of the machine learning based models and models using conventional statistical methods were also compared. A total of 11,006 pregnant women who received antenatal care at Yonsei University Hospital were included. Maternal data were retrieved from electronic medical records during the early second trimester to 34 weeks. The prediction outcome was late-onset preeclampsia occurrence after 34 weeks' gestation. Pattern recognition and cluster analysis were used to select the parameters included in the prediction models. Logistic regression, decision tree model, naïve Bayes classification, support vector machine, random forest algorithm, and stochastic gradient boosting method were used to construct the prediction models. C-statistics was used to assess the performance of each model. The overall preeclampsia development rate was 4.7% (474 patients). Systolic blood pressure, serum blood urea nitrogen and creatinine levels, platelet counts, serum potassium level, white blood cell count, serum calcium level, and urinary protein were the most influential variables included in the prediction models. C-statistics for the decision tree model, naïve Bayes classification, support vector machine, random forest algorithm, stochastic gradient boosting method, and logistic regression models were 0.857, 0.776, 0.573, 0.894, 0.924, and 0.806, respectively. The stochastic gradient boosting model had the best prediction performance with an accuracy and false positive rate of 0.973 and 0.009, respectively. The combined use of maternal factors and common antenatal laboratory data of the early second trimester through early third trimester could effectively predict late-onset preeclampsia using machine learning algorithms. Future prospective studies are needed to verify the clinical applicability algorithms.