Machine learning-based protein signatures for differentiating hypertensive disorders of pregnancy

Hypertensive disorders of pregnancy (HDP) result in major maternal and fetal complications. Our study aimed to find a panel of protein markers to identify HDP by applying machine-learning models. The study was conducted on a total of 133 samples, divided into four groups, healthy pregnancy (HP, n = 42), gestational hypertension (GH, n = 67), preeclampsia (PE, n = 9), and ante-partum eclampsia (APE, n = 15). Thirty circulatory protein markers were measured using Luminex multiplex immunoassay and ELISA. Significant markers were screened for potential predictive markers by both statistical and machine-learning approaches. Statistical analysis found seven markers such as sFlt-1, PlGF, endothelin-1(ET-1), basic-FGF, IL-4, eotaxin and RANTES to be altered significantly in disease groups compared to healthy pregnant. Support vector machine (SVM) learning model classified GH and HP with 11 markers (eotaxin, GM-CSF, IL-4, IL-6, IL-13, MCP-1, MIP1a, MIP-1 beta, RANTES, ET-1, sFlt-1) and HDP with 13 markers (eotaxin, G-CSF, GM-CSF, IFN-gamma, IL-4, IL-5, IL-6, IL-13, MCP-1, MIP-1 beta, RANTES, ET-1, sFlt-1). While logistic regression (LR) model classified PE with 13 markers (basic FGF, IL-1 beta, IL-1ra, IL-7, IL-9, MIP-1 beta, RANTES, TNF-alpha, nitric oxide, superoxide dismutase, ET-1, PlGF, sFlt-1) and APE by 12 markers (eotaxin, basic-FGF, G-CSF, GM-CSF, IL-1 beta, IL-5, IL-8, IL-13, IL-17, PDGF-BB, RANTES, PlGF). These markers may be used to diagnose the progression of healthy pregnant to a hypertensive state. Future longitudinal studies with large number of samples are needed to validate these findings.

Automated summary

This study aimed to identify a panel of protein markers for the diagnosis of hypertensive disorders of pregnancy (HDP) using machine learning models. Thirty circulatory protein markers were measured, and seven markers were found to be significantly altered in disease groups compared to healthy pregnant women. Support vector machine (SVM) and logistic regression (LR) models were able to classify different hypertensive conditions based on these markers. These findings suggest the potential of using these markers to diagnose the progression of healthy pregnancy to hypertension.