Can complete blood count parameters that change according to trimester in pregnancy be used to predict severe preeclampsia?

Complete blood count as a biomarker for preeclampsia with severe features diagnosis: a machine learning approach

OBJECTIVE

This study introduces the complete blood count (CBC), a standard prenatal screening test, as a biomarker for diagnosing preeclampsia with severe features (sPE), employing machine learning models.

METHODS

We used a boosting machine learning model fed with synthetic data generated through a new methodology called DAS (Data Augmentation and Smoothing). Using data from a Brazilian study including 132 pregnant women, we generated 3,552 synthetic samples for model training. To improve interpretability, we also provided a ridge regression model.

RESULTS

Our boosting model obtained an AUROC of 0.90±0.10, sensitivity of 0.95, and specificity of 0.79 to differentiate sPE and non-PE pregnant women, using CBC parameters of neutrophils count, mean corpuscular hemoglobin (MCH), and the aggregate index of systemic inflammation (AISI). In addition, we provided a ridge regression equation using the same three CBC parameters, which is fully interpretable and achieved an AUROC of 0.79±0.10 to differentiate the both groups. Moreover, we also showed that a monocyte count lower than 490 / m m 3 yielded a sensitivity of 0.71 and specificity of 0.72.

CONCLUSION

Our study showed that ML-powered CBC could be used as a biomarker for sPE diagnosis support. In addition, we showed that a low monocyte count alone could be an indicator of sPE.

SIGNIFICANCE

Although preeclampsia has been extensively studied, no laboratory biomarker with favorable cost-effectiveness has been proposed. Using artificial intelligence, we proposed to use the CBC, a low-cost, fast, and well-spread blood test, as a biomarker for sPE.

A meta-analysis on first-trimester blood count parameters-is the neutrophil-to-lymphocyte ratio a potentially novel method for first-trimester preeclampsia screening?

Objective

Meta-analysis focusing on the role of first-trimester neutrophil-to-lymphocyte ratio (NLR) in the prediction of preeclampsia.

Data sources

PubMed, Scopus, Web of Science, Cochrane Library, and Embase databases were queried from inception up to December 31, 2022.

Study eligibility criteria

The study included all types of original research that was conducted in humans and values of NLR were measured during the first trimester, among patients who later developed preeclampsia, compared to the values of control groups.

Study appraisal and synthesis methods

Two reviewers independently performed data abstraction and quality appraisal, and disagreements were resolved by consensus and, if necessary, by the opinion of a third reviewer. During the analysis, PRISMA and MOOSE guidelines were followed. All statistical analyses were made with R.

Results

For the research on the predictive role of NLR values in the first trimester for preeclampsia, a total of 6 studies were selected for analysis, covering 2,469 patients. The meta-analysis revealed a 95% confidence interval (CI) for the effect size of 0.641 to 1.523, with a prediction interval of 0.027 to 2.137.

Conclusion

Based on the analysis, NLR is a promising biochemical marker for future pieces of research that try to find new screening methods for first-trimester preeclampsia. We encourage other researchers to examine NLR's predictive value combined with other markers in preeclampsia screening, this way being able to find new and affordable protocols for first-trimester preeclampsia screening.

Systematic review registration

identifier CRD42023392663.

Diagnostic value of platelet to lymphocyte ratio in preeclampsia: a systematic review and meta-analysis

BACKGROUND

Using straightforward and accessible haematological parameters platelet/lymphocyte ratio (PLR) to diagnose preeclampsia (PE) early and precisely remains a challenge. Although several clinical studies suggested that PLR is able to diagnose PE, there has been no systematic evaluation of the diagnostic utility.

OBJECTIVES

To examine the diagnostic accuracy and potential applicability of PLR in the detection of PE.

STUDY DESIGN

Seven databases were searched using a combination of PLR and PE terms, and all potentially pertinent studies were systematically searched up to March 2023. All potentially relevant studies both prospective and retrospective were reviewed. To assess the diagnostic value of PLR for PE, pooled sensitivity (Sen), specificity (Spe), diagnostic odds ratio (DOR) and area under the summary receiver operating characteristic curve (SROC-AUC) were calculated.

RESULTS

Thirteen studies were enrolled in the meta-analysis. In the second and third trimesters, the PLR suggested a diagnostic value for PE with a pooled Sen of 54.7% [95% confidence interval (CI) (51.7, 57.6)], Spe of 77.8% [95% CI (75.5, 80.0)], + LR of 2.457 [95% CI (1.897, 3.182)], -LR of 0.584 [95% CI (0.491, 0.695)], DOR of 4.434 [95% CI (3.071, 6.402)], the SROC-AUC of 0.7296 and the standard error (SE) of 0.0370.

CONCLUSION

For the diagnosis of PE, PLR has a limited sensitivity but an acceptable specificity, and showed moderate accuracy. Further using complete blood count (CBC) indicators such as PLR alone or in combination to diagnose and predict PE could reduce healthcare costs and improve maternal and child prognosis.

Investigations of leukocyte and inflammatory markers in pregnancies complicated by preeclampsia

OBJECTIVES

Preeclampsia is a frequent and potentially fatal pregnancy complication. It can be challenging to make a timely diagnosis. Identifying clinically useful biochemical markers would be a remedying tool to support the diagnosis of preeclampsia. The aim was to investigate differential cell counts and acute phase reactants as diagnostic markers of preeclamptic third-trimester pregnancies and in relation to pregnancy term, gravidity and the severity of hypertension.

METHODS

Based on a cohort of 421 pregnant women, we included 174 participants (case n = 84, control n = 90) during the third trimester. Peripheral blood was sampled to measure differential white blood cell counts and acute phase reactants on the day of inclusion.

RESULTS

The neutrophil-to-lymphocyte ratio and plasma haptoglobin levels were significantly increased in healthy pregnancies compared with preeclamptic pregnancies. Plasma ferritin levels and albumin levels were respectively increased and decreased in cases of preeclampsia compared with controls. Albumin was specific among multigravida. Plasma transferrin and high-sensitivity C-reactive protein (hs-CRP) levels were significantly decreased and increased, respectively, in cases with preterm preeclampsia compared with term preeclampsia.

CONCLUSION

Plasma ferritin and albumin levels reflected higher inflammation in cases with preeclampsia compared with healthy pregnancies; the same did plasma transferrin and hs-CRP levels in preterm versus term preeclampsia. When considering the normal ranges plasma albumin and hs-CRP levels identified preeclamptic from healthy third-trimester pregnancies and preterm from term preeclampsia cases, respectively, with near-acceptable diagnostic performances. Further validation of the diagnostic value will require larger sample-sized studies with paired plasma and serum samples.

The role of first trimester eosinophil count and eosinophil-based complete blood cell indices in the predictiction of preeclampsia: A case-control study

INTRODUCTION

The importance of eosinophils in the pathogenesis of preeclampsia is an question of interest and there are recent studies in the literature indicating significantly lower eosinophil count values in pregnant women with preeclampsia. The present study aims to evaluate the utility of first-trimester eosinophil count and eosinophil-based complete blood cell count indices in the prediction of preeclampsia.

METHODS

Pregnant women diagnosed with preeclampsia (n = 281) were retrospectively compared with a control group (n = 307). The utility of first trimester eosinophil count, neutrophil to eosinophil ratio (NER) (neutrophil/eosinophil), leukocyte to eosinophil ratio (LER) (leukocyte/eosinophil), eosinophil to monocyte ratio (EMR) (eosinophil/monocyte) and, eosinophil to lymphocyte ratio (ELR) (eosinophil/lymphocyte) in the prediction of preeclampsia were evaluated.

RESULTS

Optimal cut-off values for eosinophil count, NER, LER, EMR and, ELR in predicting preeclampsia were 0.07 (AUC: 0.62, 58.7% sensitivity, 56.4% specificity), 90.9 (AUC: 0.65, 61.1% sensitivity, 59.4% specificity), 125.7 (AUC: 0.64, 61.4% sensitivity, 58.4% specificity), 0.15 (AUC: 0.63, 60.1% sensitivity, 59.6% specificity) and, 0.03 (AUC: 0.62, 60.9% sensitivity, 57% specificity), respectively. Mentioned values in predicting early-onset preeclampsia were 0.07 (AUC: 0.64, 60.5% sensitivity, 50.8% specificity), 102.1 (AUC: 0.64, 62.4% sensitivity, 58.8% specificity), 140.2 (AUC: 0.65, 63.5% sensitivity, 59.1% soecificity), 0.14 (AUC: 0.66, 66.3% sensitivity, 59.2% specificity), and, 0.03 (AUC: 0.63, 60.5% sensitivity, 57.4% specificity), respectively. The optimal cut-off value for EMR in the prediction of preeclampsia with severe features was 0.16 (AUC: 0.56, 56.9% sensitivity, 53.2% specificity).

DISCUSSION

Eosinophil-based complete blood count indices may be used to predict early-onset preeclampsia with relatively low sensitivity and specificity.

Platelet count in preeclampsia: a systematic review and meta-analysis

OBJECTIVE

Many studies have reported the association between platelets and preeclampsia. However, sample sizes were small, and their findings were inconsistent. We conducted a systematic review and meta-analysis to evaluate the association in pooled samples and in detail.

DATA SOURCES

A systematic literature search was performed using Medline, Embase, ScienceDirect, Web of Science, Cochrane Library, NICHD-DASH, LILACS, and Scopus from inception to April 22, 2022.

STUDY ELIGIBILITY CRITERIA

Observational studies comparing platelet count between women with preeclampsia and normotensive pregnant women were included.

METHODS

The mean differences with 95% confidence interval in platelet count were calculated. Heterogeneity was assessed using I2 statistics. Sensitivity and subgroup analyses were conducted. Statistical analysis was performed using RevMan 5.3 and ProMeta 3 software.

RESULTS

A total of 56 studies comprising 4892 preeclamptic and 9947 normotensive pregnant women were included. Meta-analysis showed that platelet count was significantly lower in women with preeclampsia than in normotensive controls (overall: mean difference, -32.83; 95% confidence interval, -40.13 to -25.52; P<.00001; I2=92%; mild preeclampsia: mean difference, -18.65; 95% confidence interval, -27.17 to -10.14; P<.00001; I2=84%; severe preeclampsia: mean difference, -42.61; 95% confidence interval, -57.53 to -27.68; P<.00001; I2=94%). Significantly lower platelet count was also observed in the second trimester (mean difference, -28.84; 95% confidence interval, -44.59 to -13.08; P=.0003; I2=93%), third trimester (mean difference, -40.67; 95% confidence interval, -52.14 to -29.20; P<.00001; I2=92%), and before the diagnosis of preeclampsia (mean difference, -18.81; 95% confidence interval, -29.98 to -7.64; P=.009; I2=87%), but not in the first trimester (mean difference, -15.14; 95% confidence interval, -37.71 to 7.43; P=.19; I2=71%). Overall, the pooled sensitivity and specificity of platelet count were 0.71 and 0.77, respectively. The area under the curve was 0.80.

CONCLUSION

This meta-analysis confirmed that platelet count was significantly lower in preeclamptic women, irrespective of severity and presence or absence of associated complications, even before the onset of preeclampsia and in the second trimester of pregnancy. Our findings suggest that platelet count may be a potential marker to identify and predict preeclampsia.

Detecting Preeclampsia Severity Using Maternal-Obstetrical Characteristics and Complete Blood Cell Counts

Purpose

This study aimed to use the combination of maternal-obstetrical characteristics (MOCs) and complete blood cell counts (CBCs) with different red blood cell (RBC) indices as an alternative tool to detect preeclampsia (PE) severity immediately before delivery.

Patients and Methods

This retrospective study included all singleton pregnancies delivered after 24 weeks of gestation from April 2016 to April 2020. Patients were divided into four different groups: non-hypertensive (NH), gestational hypertension (GH), PE, and severe PE (SPE). Univariate and forward stepwise multivariate logistic regression analysis was conducted using MOCs, CBCs, and RBC indices. The calculation was performed between SPE and other non-hypertensive and hypertensive (GH, PE) groups. Moreover, the area under the curve (AUC) for the receiver operating characteristic curve, sensitivity, and specificity were estimated.

Results

The combined variables for differentiating SPE from NH were maternal age >29.5 years, weight >27.24, gestational age <272 days at the time of blood withdrawal, platelet count <217.5×103/μL, Srivastava indices <6.35, and Siradah indices <43.02 (AUC, 0.834; 95% confidence interval [CI], 0.773-0.895). The combined variables for differentiating SPE from GH were maternal age >29.5 years, body mass index >25.28, gestational age <268.5 days at the time of blood withdrawal, mean corpuscular volume <78.85 fL, and platelet count <234.5×103/μL (AUC, 0777; 95% CI, 0.703-0.852). The combined variables for differentiating SPE from PE were maternal age >32.5 years, mean corpuscular hemoglobin concentration >34.55 g/dL, and Siradah indices <40.05 (AUC, 0.745; 95% CI, 0.656-0.833).

Conclusion

The combination of selected variables from MOCs and CBCs with RBC indices before delivery showed satisfactory results for detecting PE severity.

Association between platelet indices and risk of preeclampsia in pregnant women

We aimed to examine the association between the platelet indices and the risk of preeclampsia (PE) at different gestational weeks (GW) to explore the feasibility of early prediction of PE with these indices. About 7314 normotensive pregnant women and 396 PE patients were included and platelet indices, including platelet count (PC), plateletcrit (PCT), platelet distribution width (PDW), mean platelet volume (MPV) at different gestational weeks (1-12, 13-28, 29-32, 33-36 and 37-41 GW) were compared in two statistical methods. Patients with PE tended to have higher means of PC, PCT, PDW and MPV than normal pregnant women at early stage of pregnancy. The odds of PE were significantly increased with the increase of PC, PCT, PDW and MPV both at 13-28 GW and 29-32 GW, which indicated that increased values of PC, PCT, PDW and MPV at 13-32 GW were associated with greater subsequent risk of preeclampsia. Increased PC, PCT, PDW and MPV may have potential to predict preeclampsia before the disease onset.Impact StatementWhat is already known on this subject? Previous studies indicated that preeclampsia patients may have decreased platelet count (PC), plateletcrit (PCT) and increased platelet distribution width (PDW) and mean platelet volume (MPV). Increased PDW and MPV or decreased PC/MPV may have predictive values for PE.What do the results of this study add? The discrepancy with previous studies lay in the increased values of PC and PCT in PE patients at early stage of pregnancy. The study indicated that increased PC, PCT, PDW and MPV may have potential to predict preeclampsia far ahead of the disease onset. The results may reflect the abnormal turnover of platelets in PE patients.What are the implications of these findings for clinical practice and/or further research? These findings may help to guide early interventions before progress to overt preeclampsia by predicting onset of preeclampsia via easily available platelet indices in early weeks of gestation, which is especially valuable in areas lacking medical resources. The inconsistency with previous studies can facilitate researchers to further explore the coagulation mechanism beneath preeclampsia and pay more attention to the dynamic changes of platelet indices and other coagulation indices during pregnancy.