Prediction Of Preeclampsia Research Articles

Novel maternal risk factors for preeclampsia prediction using machine learning algorithms

<div align="center"><table width="590" border="1" cellspacing="0" cellpadding="0"><tbody><tr><td valign="top" width="387"><p>Preeclampsia and eclampsia are the most common obstetric disorders associated with poor outcomes for women, fetuses, and newborns throughout the perinatal period. The study’s primary objective was to assess the accuracy of novel high-risk factors using MLA in predicting preeclampsia. The study included 400 pregnant women and used 27 novel high-risk factors to predict preeclampsia. The target variables for predicting preeclampsia are systolic and diastolic blood pressures. Various algorithms, including DT, RF, Gradient Boosting, SVM, K-Neighbors, LGBM, MLP, Ada Boost Classifier, and Extra Trees Classifier are used in the analysis. The accuracy and precision of the LGBM Classifier (0.85 and 0.9583 with F1 0.7188), Support Vector Classifier (0.8417 and 0.92 with F1 0.7077), Decision Tree (0.825 and 0.913 with F1 0.6667), and Extra Trees (0.8167 and 0.9091 with F1 0.6452) are found to be better algorithms for prediction of preeclampsia than those of the other models used in the study. According to the novel high-risk factors score, 17.5% of pregnant women were identified as being at high risk for preeclampsia during the first trimester, which increased to 18.7% in 3rd trimester; in addition, 16% of pregnant women had a BP of 140/90 mmHg and the above. Novel, high-risk scores and MLA can effectively predict preeclampsia at an early period.</p></td></tr></tbody></table></div>

A Review on Machine Learning Deployment Patterns and Key Features in the Prediction of Preeclampsia

Previous reviews have investigated machine learning (ML) models used to predict the risk of developing preeclampsia. However, they have not addressed the intended deployment of these models throughout pregnancy, nor have they detailed feature performance. This study aims to provide an overview of existing ML models and their intended deployment patterns and performance, along with identified features of high importance. This review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines. The search was performed in January and February 2024. It included all papers published before March 2024 obtained from the scientific databases: PubMed, Engineering Village, the Association for Computing Machinery, Scopus, and Web of Science. Of a total of 198 identified studies, 18 met the inclusion criteria. Among these, 11 showed the intent to use the ML model as a single-use tool, two intended a dual-use, and two intended multiple-use. Ten studies listed the features of the highest importance, with systolic and diastolic blood pressure, mean arterial pressure, and hypertension frequently mentioned as critical predictors. Notably, three of the four studies proposing dual or multiple-use models were conducted in 2023 and 2024, while the remaining study is from 2009. No single ML model emerged as superior across the subgroups of PE. Incorporating body mass index alongside hypertension and either mean arterial pressure, diastolic blood pressure, or systolic blood pressure as features may enhance performance. The deployment patterns mainly focused on single use during gestational weeks 11+0 to 14+1.

The role of pentraxin 3 and cathepsin B levels in pregnancies complicated by preeclampsia

Objective The objective of this study was to compare the levels of cathepsin B and pentraxin 3 in maternal serum of pregnant women with preeclampsia in the second trimester, to ascertain the impact of these levels on maternal and fetal outcomes, and to present a comprehensive analysis of the combined effects of cathepsin B and pentraxin 3 levels. Methods This prospective case-control study was conducted at Bursa Yuksek Ihtisas Training and Research Hospital between 1 January 2022 and 31 December 2022. The study included 78 pregnant women diagnosed with preeclampsia and 78 healthy pregnant women in the second trimester, between the ages of 18 and 45. Once a diagnosis of preeclampsia was established, maternal serum samples were obtained from the pregnant women prior to the initiation of any therapeutic intervention. Once all samples had been collected, the values for cathepsin B and pentraxin 3 were determined using the ELISA method. Results The results demonstrated a statistically significant elevation in the levels of pentraxin 3 (p = 0.008) and cathepsin B (p = 0.005) in pregnancies affected by preeclampsia when compared to those deemed healthy. Moreover, pentraxin-3 (p = 0.007) and cathepsin B (p = 0.002) were found to be significantly elevated in severe preeclampsia compared to mild preeclampsia. A comparison of the groups with and without HELLP syndrome revealed no statistically significant difference between the two groups. The ROC analysis revealed that the Cathepsin B 7.04 cut-off value was statistically significantly associated with the prediction of preeclampsia in all cases, with a sensitivity of 78.2% and a specificity of 47.4% (p = 0.005, AUC = 0.631). Conclusion The levels of CB and PTX3 may be employed as biomarkers to facilitate the early diagnosis of PE during the second trimester. Furthermore, these biomarkers may prove to be promising for the prediction of PE severity.

OUCH: Oversampling and Undersampling Cannot Help Improve Accuracy in Our Bayesian Classifiers That Predict Preeclampsia

Unbalanced data can have an impact on the machine learning (ML) algorithms that build predictive models. This manuscript studies the influence of oversampling and undersampling strategies on the learning of the Bayesian classification models that predict the risk of suffering preeclampsia. Given the properties of our dataset, only the oversampling and undersampling methods that operate with numerical and categorical attributes will be taken into consideration. In particular, synthetic minority oversampling techniques for nominal and continuous data (SMOTE-NC), SMOTE—Encoded Nominal and Continuous (SMOTE-ENC), random oversampling examples (ROSE), random undersampling examples (UNDER), and random oversampling techniques (OVER) are considered. According to the results, when balancing the class in the training dataset, the accuracy percentages do not improve. However, in the test dataset, both positive and negative cases of preeclampsia were accurately classified by the models, which were built on a balanced training dataset. In contrast, models built on the imbalanced training dataset were not good at detecting positive cases of preeclampsia. We can conclude that while imbalanced training datasets can be addressed by using oversampling and undersampling techniques before building prediction models, an improvement in model accuracy is not always guaranteed. Despite this, the sensitivity and specificity percentages improve in binary classification problems in most cases, such as the one we are dealing with in this manuscript.

Maternal serum Numb in the first trimester of pregnancy as a biomarker for early prediction of pre-eclampsia: A prospective cohort study.

Early identification of women at risk of developing pre-eclampsia is beneficial as it allows for timely intervention strategies. This study aimed to evaluate the potential of serum Numb in the first trimester as a biomarker for early prediction of pre-eclampsia. This prospective observational cohort study was carried out at a tertiary teaching hospital between January 2021 and December 2022. A total of 1024 women were recruited during their 8-13 weeks of pregnancy and were followed up until delivery. Serum Numb levels were measured during 8-13 weeks of gestation for all participants. At the same time, the participants' anthropometric, clinical, and laboratory data were collected. A logistic regression model was used to investigate the potential association between serum Numb levels and the risk of pre-eclampsia. Receiver operating characteristic curves (ROCs) and area under the curves (AUCs) were utilized to evaluate the predictive efficacy of serum Numb levels for pre-eclampsia in the first trimester. Serum Numb levels were found to be significantly higher in pregnant women who developed pre-eclampsia compared to those who did not develop pre-eclampsia. Increased serum Numb levels were identified as an independent risk factor for pre-eclampsia, with an odds ratio (OR) of 3.27 (95% CI: 2.05-4.53) for the risk of pre-eclampsia. Numb levels showed a significant positive correlation with the risk of pre-eclampsia. Furthermore, Numb levels demonstrated a strong predictive efficacy for pre-eclampsia in the first trimester of pregnancy, with an AUC value of 0.86, a cutoff value of 48.73 ng/mL, a sensitivity of 79.24%, and a specificity of 75.73%. Serum Numb in the first trimester of pregnancy can serve as a biomarker for the early prediction of pre-eclampsia. This provides a valuable approach in clinical practice to identify pregnant women in the first trimester of pregnancy, who are at a higher risk of developing pre-eclampsia.

Arterial stiffness as a novel tool for the early prediction of preeclampsia: a perspective.

Preeclampsia is a leading complication of pregnancy that lacks accurate tools for its early prediction. Improved risk stratification tools early in pregnancy would enable more efficient allocation of limited healthcare resources while ensuring that pregnant women destined to develop preeclampsia receive appropriate care. This brief perspective highlights the current state of first-trimester preeclampsia prediction. We focus on arterial stiffness, an important hemodynamic indicator of vascular health that has shown promising results for improved early prediction of preeclampsia by our and independent research groups. Further, we outline the promise, applicability, and feasibility of integrating arterial stiffness assessments into clinical practice.

Prediction of pre-eclampsia with machine learning approaches: Leveraging important information from routinely collected data

BackgroundGlobally, pre-eclampsia (PE) is a leading cause of maternal and perinatal morbidity and mortality. PE prediction using routinely collected data has the advantage of being widely applicable, particularly in low-resource settings. Early intervention for high-risk women might reduce PE incidence and related complications. We aimed to replicate our machine learning (ML) published work predicting another maternal condition (gestational diabetes) to (1) predict PE using routine health data, (2) identify the optimal ML model, and (3) compare it with logistic regression approach. MethodsData were from a large health service network with 48,250 singleton pregnancies between January 2016 and June 2021. Supervised ML models were employed. Maternal clinical and medical characteristics were the feature variables (predictors), and a 70/30 data split was used for training and testing the model. Predictive performance was assessed using area under the curve (AUC) and calibration plots. Shapley value analysis assessed the contribution of feature variables. ResultsThe random forest approach provided excellent discrimination with an AUC of 0.84 (95% CI: 0.82–0.86) and highest prediction accuracy (0.79); however, the calibration curve (slope of 1.21, 95% CI 1.13–1.30) was acceptable only for a threshold of 0.3 or less. The next best approach was extreme gradient boosting, which provided an AUC of 0.77 (95% CI: 0.76–0.79) and well-calibrated (slope of 0.93, 95% CI 0.85–1.01). Logistic regression provided good discrimination performance with an AUC of 0.75 (95% CI: 0.74–0.76) and perfect calibration. Nulliparous, pre-pregnancy body mass index, previous pregnancy with prior PE, maternal age, family history of hypertension, and pre-existing hypertension and diabetes were the top-ranked features in Shapley value analysis. ConclusionTwo ML models created the highest-performing prediction using routinely collected data to identify women at high risk of PE, with acceptable discrimination. However, to confirm this result and also examine model generalisability, external validation studies are needed in other settings, utilising standardised prognostic factors.

A Prospective Study on Risk Prediction of Preeclampsia Using Bi-Platform Calibration and Machine Learning.

Preeclampsia is a pregnancy syndrome characterized by complex symptoms which cause maternal and fetal problems and deaths. The aim of this study is to achieve preeclampsia risk prediction and early risk prediction in Xinjiang, China, based on the placental growth factor measured using the SiMoA or Elecsys platform. A novel reliable calibration modeling method and missing data imputing method are proposed, in which different strategies are used to adapt to small samples, training data, test data, independent features, and dependent feature pairs. Multiple machine learning algorithms were applied to train models using various datasets, such as single-platform versus bi-platform data, early pregnancy versus early plus non-early pregnancy data, and real versus real plus augmented data. It was found that a combination of two types of mono-platform data could improve risk prediction performance, and non-early pregnancy data could enhance early risk prediction performance when limited early pregnancy data were available. Additionally, the inclusion of augmented data resulted in achieving a high but unstable performance. The models in this study significantly reduced the incidence of preeclampsia in the region from 7.2% to 2.0%, and the mortality rate was reduced to 0%.

First-trimester uterine artery Doppler and PAPP-A levels as predictors of pre-eclampsia in a South Asian population; Mardan city, Pakistan

One of the most common causes of maternity and neonatal fatalities and mortality is Pre-eclampsia (PE) which is responsible for 14% of global maternal deaths. The condition is primarily attributed to impaired trophoblastic invasion, which increases uterine artery pulsatility index (PI). A predictive analysis was done at Swat Medical College and Women's Hospital in Mardan, Pakistan from June 2022 to June 2023, including 218 pregnant women aged 11-13+6 weeks. Females with multifetal pregnancies, congenital fetal anomalies, and pre-existing medical conditions were excluded from this research. Uterine artery the Doppler and the PAPP-A testing were done to screen the conditions. Of 624 screened women, 218 were included in the final analysis using SPSS. The study population's mean age was 28 years, with 59% primiparous and 41% multiparous women. The incidence of PE was 35.5%, and gestational hypertension was 22.5%. Women developing hypertensive disorders had significantly higher mean uterine artery PI (2.11) compared to normotensive women (1.21, p=0.01), and significantly lower mean PAPP-A MoM levels (0.78 vs. 1.42, p<0.001). Coupled aberrant uterine blood vessels PI and PAPP-A predicted PE with high significance (p<0.001). Uterine artery in the first trimester Doppler and PAPP-A levels are effective in predicting pre-eclampsia in a South Asian population. Implementing these screenings could enhance early detection and management of PE, potentially reducing associated morbidity and mortality.

Serum macrophage stimulating protein α-chain and uterine artery Doppler ultrasound in the first trimester for the prediction of preeclampsia

To assess how effective macrophage stimulating protein α-chain (MSP-α) combined with uterine artery Doppler is in predicting preeclampsia in singleton pregnancies during 11–13+6 weeks of gestation. This prospective observational study included singleton pregnant women who attended antenatal care at King Chulalongkorn Memorial Hospital, Department of Obstetrics and Gynecology, Faculty of Medicine, Chulalongkorn University between December 2021 and April 2023, during 11–13+6 weeks of gestation. Serum MSP-α levels were collected and uterine artery Doppler ultrasound was performed. Pregnancy outcomes were recorded, and the predictive values of these tests were determined to predict preeclampsia. A total of 365 patients, with 21 cases of preeclampsia (5.8%), were analyzed. Serum MSP-α levels were higher in pregnant women who developed preeclampsia than those who did not (899.7 ± 550.1 ng/ml vs 642.5 ± 466.1 ng/ml, p = 0.016). The mean pulsatility index of the uterine artery and the presence of diastolic notching were not significantly different between the groups. As a cut-off value for predicting preeclampsia, using serum MSP-α levels higher than 1.0 multiple of median for gestational age, the sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) were 71.4%, 50.3%, 8.1%, and 96.7%, respectively. Additionally, when abnormal serum MSP-α levels were combined with a uterine artery Doppler pulsatility index above the 95th percentile and bilateral notching as predictive values for preeclampsia, the sensitivity was 85.7%, specificity was 18.3%, PPV was 6.0%, and NPV was 95.5%. Serum MSP-α alone at 11–13+6 weeks of gestation was effective in predicting preeclampsia. However, the use of serum MSP-α in combination with uterine artery Doppler increased sensitivity but reduced specificity for the prediction of preeclampsia.

Assessing Placental Shear Wave Elastography as a Tool for Evaluating Preeclampsia.

Background Hypertensive disorders of pregnancy, especially its dreaded complication preeclampsia, remain a major cause of morbidity and mortality for both the mother and the fetus. Existing tools for the prediction of preeclampsia remain inadequate in their sensitivity and specificity. Hence, there is an urgent need for a reliable, economically feasible, and objective marker for its diagnosis/early prediction. In this regard, shear wave elastography has shown great promise. Shear wave elastography is a novel method to quantify tissue stiffness, which is objective and has significantly lower inter-observer variability. Objectives We aim to quantify the tissue elasticity using point shear wave elastography (pSWE) in the placentas of diagnosed cases of preeclampsia and to compare them with the placentas of healthy controls in order to evaluate if there is a significant statistical difference between the two. Materials and methods This comparative study was conducted at the Department of Radiodiagnosis, Dr. D. Y. Patil Medical College, Hospital and Research Centre, Pune, India, from August 2022 to July 2024. The study included 60 participants, divided into two groups: 30 patients with preeclampsia and 30 healthy pregnancies. Placental stiffness was measured using a Samsung HS70A ultrasound machine (Samsung Electronics Pvt. Ltd., Seoul, South Korea), and pSWE was performed with a curvilinear probe. Data was analyzed using IBM SPSS Statistics for Windows, Version 21 (Released 2012; IBM Corp., Armonk, New York, United States), and the significance of differences between the two groups was assessed using an independent t-test with a p-value of <0.05, considered statistically significant. Results The mean placental stiffness, measured in kilopascals (kPa), was significantly higher in the preeclampsia group (11.71 ± 1.52 kPa) in comparison to the healthy group (3.36 ± 0.66 kPa) (p = 0.001). Patients suffering from preeclampsia were found to have significantly higher levels of placental stiffness. Conclusion Early diagnosis remains key to managing preeclampsia so that adequate monitoring and treatment could be provided to the patients. Our study showed that there is a significant statistical difference in the placental stiffness in patients with preeclampsia in comparison to a healthy placenta. Hence, shear wave elastography can be used as a supplementary tool to aid in the diagnosis/prediction of preeclampsia.

Fibronectin as a predictor of preeclampsia

Since preeclampsia first emerged a few centuries ago, a substantial portion of humanity has been tormented by this disease, which has jeopardized and disrupted mankind. Numerous biological markers, including ENDOGLIN, PIGF (placental growth factor), SFLT 1(soluble fms like-tyrosine kinase 1), and PAPP-A (pregnancy associated plasma protein-A), suggest preeclampsia. It was beneficial for detecting preeclampsia, even if there was frequent mortality and morbidity among mothers because of the anticipated latency. Then another marker, fibronectin, was added to the picture. A better preeclampsia prognosis leads substantially to an overall decrease in maternal morbidity and mortality. The primary organ that manufactures circulating fibronectin, occasionally referred to as serum fibronectin, is the liver. To enable the extracellular and intracellular matrix to communicate and regulate cell behavior, fibronectin, an extracellular matrix element, primarily interacts with integrin receptors. Fibronectin is a diagnostic marker for a variety of ailments, such as muscular dystrophy, ovarian and stomach cancers, and gestational diabetes. Inflammatory changes result in the release of fibronectin into the bloodstream, and the main triggering factor of preeclampsia is the infiltration of various trophoblasts that injures endothelial tissues and induces inflammation. Therefore, the primary goal of our study was to establish that fibronectin is a biomarker of preeclampsia. To elucidate our perspective and evaluate whether fibronectin is relevant in preeclampsia prediction, we will conduct a qualitative evaluation of prior research and juxtapose it with the findings of the present study. Thus, early detection of preeclampsia could decrease the rate of maternal mortality and morbidity.

Demographic Factors, Biochemical Markers, and Obstetric History Associated with the Risk of Preeclampsia in a Sudanese Population Sample

Background: Preeclampsia significantly contributes to maternal and perinatal illness and death, particularly in low and middle-income countries like Sudan. It is classified by onset timing (early vs. late) and severity (mild vs. severe) and is one of the four hypertensive disorders in pregnancy, including chronic hypertension, gestational hypertension, and chronic hypertension with superimposed preeclampsia. This study aimed to evaluate the demographic, clinical, and biochemical predictors of preeclampsia among Sudanese women. Methods: This case-control study involved 100 women diagnosed with preeclampsia and 100 healthy pregnant women who acted as the control group at Omdurman Maternity Hospital in Khartoum State, Sudan, from 2019 to 2021. Data on sociodemographic characteristics, obstetric history, and biochemical markers, including platelet counts, were collected using a comprehensive questionnaire and blood sample analysis. Results: Women with preeclampsia were more frequently over the age of 40 (OR=9.33, 95% CI: 4.54-19.19, p &lt; 0.001) and had a longer median duration of marriage (OR=2.9, 95% CI: 1.51-5.58, p=0.001). Lower educational levels (p=0.008) and being housewives (p=0.024) were also more prevalent in the preeclampsia group. Clinically, headache (OR=18.98, 95% CI: 2.44-147.5, p=0.005) and blurring of vision (OR=25.83, 95% CI: 1.17-572.6, p=0.04) were more prevalent in women with preeclampsia. Biochemical markers showed lower platelet counts (p=0.002), higher levels of alanine aminotransferase (ALT) (OR=2.23, 95% CI: 1.51-3.28, p &lt; 0.001) and creatinine (OR=16.76, 95% CI: 2.31-121.5, p=0.005), while aspartate aminotransferase (AST) was not significantly associated with preeclampsia. Conclusion: Family history of preeclampsia was the most significant predictor. Other important risk factors included older age, longer duration of marriage, lower education levels, headache, blurring of vision, and higher levels of alanine aminotransferase (ALT) and creatinine.

Routine ante-natal screening using maternal risk factors and biomarkers for preeclampsia in 11-13+6 weeks of gestation.

Prediction of preeclampsia in first trimester can lead to early initiation of preventative measures, as well as timely therapeutic intervention, that will prevent the maternal and perinatal morbidity and mortality. This study, prediction of preeclampsia at 11-13+6 weeks of gestation, was conducted by using serum placental growth factor (PlGF), serum pregnancy associated plasma protein - A (PAPP-A), uterine artery Doppler indices, and mean arterial pressure (MAP), in low-risk pregnant women. It is an observational longitudinal prospective study. Pregnant women with singleton pregnancies of gestational age 11-13+6 weeks were recruited. MAP, bilateral uterine artery Doppler indices, serum PAPP-A, and PlGF were measured. The follow-up of the patients was regularly done till termination of pregnancy and incidence of preeclampsia were noted. Qualitative variables were compared using Chi-square/Fisher exact test, and sensitivity and specificity of each test were analyzed. Among 139 women, 27 (19%) developed preeclampsia, out of which 10 had early preeclampsia and 17 developed late preeclampsia. By combining all the parameters, the sensitivity in detecting early preeclampsia was found to be 70% and for late preeclampsia cases, 64.7%. The sensitivity of all the parameters in predicting cases of preeclampsia in general is 66.7%, specificity is 74.1%, PPV is 38.3%, and NPV is 72%. The maternal biomarkers serum PAPP-A, serum PlGF, uterine artery PI, MAP have sensitivity of 70% in detecting early preeclampsia cases and for late preeclampsia cases, 64.71%, in first trimester and it will help in early initiation of preventative measures as well as timely therapeutic intervention.

Maternal angiogenic factor disruptions prior to clinical diagnosis of preeclampsia: insights from the REVAMP study.

Preeclampsia is characterized by impaired angiogenesis and assessment of angiogenic factors can play a crucial role in the early diagnosis of preeclampsia. The current study reports the levels of angiogenic factors longitudinally from early pregnancy in women with preeclampsia and in the subtypes of preeclampsia, to identify their role in early prediction of preeclampsia. A total of 1154 women with singleton pregnancies were recruited in early pregnancy from 2 hospitals. Blood samples were collected, plasma samples were separated and stored at four time points across gestation: V1 = 11-14 weeks, V2 = 18-22 weeks, V3 = 26-28 weeks, and V4 = at delivery. The current study includes a total of 108 women developed preeclampsia (PE), and 216 matched controls. Angiogenic factors were estimated using commercially available ELISA kits. Receiver operating characteristic (ROC) curves were used to evaluate the potential diagnostic value in the prediction of PE. Lower levels of VEGF, PlGF, and higher levels of sEng and sEng/PlGF ratio (p < 0.05 for all) predate clinical diagnosis in women with preeclampsia. sEng levels and sEng/PlGF ratio showed significant correlation with odds of preeclampsia at all the timepoints. This study identifies a cut off of 33.5 for sFlt-1/PlGF and 25.9 for sEng/PlGF for prediction of early onset preeclampsia. This study reports various angiogenic factors serially across gestation in a general population to identify women at risk of developing preeclampsia and its subtypes. The study also reports a potential biomarker and a pragmatic window for estimation of angiogenic markers to identify women at risk.

O21 PLATELET COUNT-TO-PLATELET DISTRIBUTION WIDTH RATIO AND OTHER PLATELET INDICES AS COST-EFFECTIVE MARKERS OF PREECLAMPSIA: A CASE CONTROL STUDY

Background and objective: Platelet indices, like platelet count (PC), plateletcrit, mean platelet volume (MPV) and platelet distribution width (PDW), and their ratios have shown to be cost-effective and better predictors of preeclampsia (PE). However, PC/PDW ratio was not studied. Thus, this study aimed to compare platelet indices and their ratios between pregnant women with and without PE. Methods: An analytical, comparative, case-control study. Two groups were compared; pregnant women with PE (case, n=24) and without PE (control, n=72). The differences between cases and controls were compared using Student's t-test and Mann–Whitney U-test for continuous variables and chi-square tests and Fisher's exact test for categorical. Multivariable linear regression analysis for hematological parameters was performed to assess the effect of gestational age. Logistic regression was performed to calculate the odds ratio. Receiver operating characteristic curve was used to determine sensitivity, specificity and cutoff values. P &lt; 0.05 was considered significant. Results: There was significant reduction in values of PC (p=0.004), plateletcrit (p=0.012), PC/MPV ratio (p=0.002), and PC/PDW (p= &lt;0.001) among the pregnant women with PE compared to the control study group, while a significant increase was noticed in the values of PDW (p= &lt;0.001) and MPV (p=0.021). PC/PDW had the highest area under the curve (AUC) of 0.767, followed by PDW (AUC=0.752). At the cutoff value of 15.1 (p&lt;0.001) for PC/PDW, sensitivity was 70.8%, and specificity was 81.9%. The odds of diagnosing true positive cases of PE was 11.02 (95% CI =3.79-31.99, p=&lt;0.001) times higher compared to values below it at this cutoff point. Conclusions: Present study suggests that platelet indices are economical tests that can act as indicators of risk of PE. Among all the parameters, PC/PDW has the highest sensitivity and specificity in the detection of PE at the cutoff of 15.1 and has emerged as a better predictor of PE.

Second Trimester Serum Calprotectin in prediction of early onset Preeclampsia

Second Trimester Serum Calprotectin in prediction of early onset Preeclampsia

First-Trimester Prediction of Preterm Pre-eclampsia and Prophylaxis by Aspirin: Effect on Spontaneous and Iatrogenic Preterm Birth

First-Trimester Prediction of Preterm Pre-eclampsia and Prophylaxis by Aspirin: Effect on Spontaneous and Iatrogenic Preterm Birth

Real-time pre-eclampsia prediction model based on IoT and machine learning

Pre-eclampsia (PET) is a hypertensive disease that occurs during pregnancy or in the postpartum period. It complicates 2% to 8% of all pregnancies and is one of the causes of more than 50,000 maternal deaths and over 500,000 fetal deaths worldwide annually. Adverse birth outcomes due to pregnancy complications have been associated with three delays: delay in recognizing the complication, delay in reaching an appropriate facility, and delay in receiving adequate care when the facility is reached. Thus prevention, timely detection, and care of pregnancy complications can prevent maternal deaths and morbidity. The Internet of Things (IoT) and machine learning (ML) technologies have become the new revolution of research in the field of healthcare. These technologies can be utilized to interconnect various sensors, monitor the health status of a patient, and predict the occurrence of an ailment. This study has designed and prototyped a pre-eclampsia monitoring model based on IoT and machine learning for remotely monitoring the health status of an expectant woman and her unborn child, to enhance early diagnosis of pre-eclampsia and improve birth outcomes. The study involved researching the on most appropriate biosensors and then designing and prototyping the pre-eclampsia watch. To build the pre-eclampsia prediction model the best ML algorithm was empirically analysed. A Naïve Bayes pre-eclampsia prediction model was found to perform better in identifying pregnant women who are at risk of pre-eclampsia after evaluation of various pre-eclampsia models built using decision trees, Naïve Bayes, K Nearest Neighbor (KNN), logistic regression, support vector machines (SVM) and Artificial neural networks (ANN). Lastly, the predictive model was integrated with the pre-eclampsia model to assist in early diagnosis of pre-eclampsia. The prototype generates alerts when the expectant woman is at risk of Pre-eclampsia. The pre-eclampsia watch model can securely capture and transmit expectant women's vital to the cloud for processing and provide timely alerts when the woman is at risk. Further research on the performance and efficacy of the model in a real environment will be done by experimenting with it in a purposively selected sample.

Angiogenic factors for early prediction of preeclampsia.

.