Machine learning-based prediction of preeclampsia using first-trimester inflammatory markers and red blood cell indices

Qiao et al. BMC Pregnancy and Childbirth (2025) 25:1083 https://doi.org/10.1186/s12884-025-08147-1 BMC Pregnancy and Childbirth Open Access RESEARCH Machine learning-based prediction of preeclampsia using first-trimester inflammatory markers and red blood cell indices Longwei Qiao1,2,3†, Yanqiu Zhang4†, Juan Wang5†, Xiaojuan Wu1, Chunhua Zhang1, Ying Xue1, Jun Cao6, Jieyu Jin6, Ting Wang1*, Jia Li7* and Yuting Liang3,6* Abstract Background Preeclampsia (PE) affects 2–4% of pregnancies, and early detection and intervention can reduce its incidence. Dysregulation of the maternal immune response and red blood cells (RBCs) are key to its development, although early alterations remain unclear. Methods This study analyzed data from 17,955 pregnant women across two centers to explore the relationships among inflammatory markers, RBC indices, and PE via multivariate logistic regression and restricted cubic splines (RCSs). Machine learning integrated inflammatory markers, RBC indices, and maternal risk factors to predict PE risk at 14 weeks, as validated by receiver operating characteristic (ROC) curve analysis. Results After adjusting for confounders, the lymphocyte (LYMPH) count (OR = 1.27, 95% CI: 1.05–1.53, P = 0.013), monocyte (MONO) count (OR = 2.57, 95% CI: 1.31–5.03, P = 0.006), systemic inflammatory response index (SIRI) (OR = 1.11, 95% CI: 1.01–1.21, P = 0.032), and systemic immune inflammatory index (SII) (OR = 1.01, 95% CI: 1.01–1.01, P = 0.002) were identified as significant risk factors for PE. Nonlinear associations between white blood cell (WBC) count, neutrophil (NEUT) count, platelet (PLT) count, RBC count, and hemoglobin (HGB) and PE were observed via RCS (nonlinear P < 0.05). Further analysis revealed threshold effects for WBC (P = 0.034), with an inflection point at 8.44. Below 8.44, no significant association was found (OR = 0.92, P = 0.307), but above 8.44, each unit increase was linked to a 0.14-fold rise in PE risk (OR = 1.14, P < 0.001). Similar threshold effects were found for the PLT, RBC, and HGB † Longwei Qiao, Yanqiu Zhang and Juan Wang contributed these authors contributed equally to this work. *Correspondence: Ting Wang Jia Li Yuting Liang Full list of author information is available at the end of the article © The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creati vecommons.org/licenses/by-nc-nd/4.0/. Qiao et al. BMC Pregnancy and Childbirth (2025) 25:1083 Page 2 of 23 (P < 0.001). A prediction model based on inflammatory markers, RBC indices, and maternal risk factors achieved high performance (ROC = 0.82). Conclusions LYMPH, MONO, SIRI, and SII were linearly associated with PE, whereas WBC, NEUT, PLT, RBC, and HGB showed nonlinear associations with threshold effects. Early prediction using these indicators is a cost-effective strategy for PE prevention. Keywords Preeclampsia, Blood routine, Machine learning, Restricted cubic splines Background Preeclampsia (PE), which occurs after 20 weeks of gestation, is characterized primarily by hypertension and proteinuria. With a global prevalence of 2–4%, it is considered a significant contributor to severe maternal complications and mortality [1]. At present, the only treatment available for PE is the termination of pregnancy, which is a leading cause of preterm labor, neonatal morbidity, and perinatal mortality [2]. Furthermore, a history of PE is associated with a significantly elevated risk of developing type 2 diabetes (T2D) and cardiovascular disease (CVD) later in life [3, 4]. Early and accurate prediction of PE allows timely diagnosis and intervention [5]. Screening high-risk pregnancies with low-dose aspirin before 16 weeks can reduce the incidence of preterm PE [6, 7]. Similarly, late-pregnancy screening mitigates the risk of late-onset pre-eclampsia by facilitating enhanced surveillance and prompt clinical decision-making. Existing screening algorithms for early pregnancy incorporate maternal risk factors, mean arterial pressure, uterine artery resistance, and maternal serum placental growth factor (PlGF) levels to effectively predict preterm pre-eclampsia [8, 9]. However, these methods are both costly and not widely accessible. Therefore, a critical need remains for a predictive parameter that is not only costefficient but also easy to measure. Dysregulation of the maternal systemic immune response is widely regarded as a primary cause of PE. Systemic immune-related disorders, such as systemic lupus erythematosus (SLE) [10], type 1 and type 2 diabetes mellitus (T1D, T2D) [3], and rheumatoid arthritis (RA) [11], have been implicated in increasing the risk of PE. During PE progression, various immune cells play critical roles in modulating maternal immune tolerance, trophoblast invasion, and uterine spiral artery remodeling [12]. Systemic immune-inflammatory biomarkers, including the neutrophil-to-lymphocyte ratio (NLR), derived neutrophil-to-lymphocyte ratio (dNLR), monocyte-tolymphocyte ratio (MLR), neutrophil and monocyteto-lymphocyte ratio (NMLR), platelet-to-lymphocyte ratio (PLR), lymphocyte-to-monocyte ratio (LMR), systemic inflammatory response index (SIRI), and systemic immune inflammatory index (SII), reflect the balance of immune responses and the overall inflammatory status. However, clinicians tend to focus primarily on markedly abnormal parameters, often overlooking the emerging immune-derived markers that may have significant pathogenic roles in disease progression. Recent studies have revealed strong associations between these accessible immune-inflammatory markers and conditions such as cancer [13], cardiovascular diseases [14], diabetes, and adverse pregnancy outcomes, including preterm labor [15]. Similarly, the red blood cell (RBC) index is associated with PE. Notably, the RBC count and hemoglobin (HGB) level slightly increase during disease onset in PE patients [16]. These findings suggest that peripheral blood cell counts may have potential predictive value for PE. The integration of these markers with machine learning te (...truncated)