-
Current Hypertension Reports Jul 2024Machine learning (ML) approaches are an emerging alternative for healthcare risk prediction. We aimed to synthesise the literature on ML and classical regression studies... (Review)
Review
PURPOSE OF REVIEW
Machine learning (ML) approaches are an emerging alternative for healthcare risk prediction. We aimed to synthesise the literature on ML and classical regression studies exploring potential prognostic factors and to compare prediction performance for pre-eclampsia.
RECENT FINDINGS
From 9382 studies retrieved, 82 were included. Sixty-six publications exclusively reported eighty-four classical regression models to predict variable timing of onset of pre-eclampsia. Another six publications reported purely ML algorithms, whilst another 10 publications reported ML algorithms and classical regression models in the same sample with 8 of 10 findings that ML algorithms outperformed classical regression models. The most frequent prognostic factors were age, pre-pregnancy body mass index, chronic medical conditions, parity, prior history of pre-eclampsia, mean arterial pressure, uterine artery pulsatility index, placental growth factor, and pregnancy-associated plasma protein A. Top performing ML algorithms were random forest (area under the curve (AUC) = 0.94, 95% confidence interval (CI) 0.91-0.96) and extreme gradient boosting (AUC = 0.92, 95% CI 0.90-0.94). The competing risk model had similar performance (AUC = 0.92, 95% CI 0.91-0.92) compared with a neural network. Calibration performance was not reported in the majority of publications. ML algorithms had better performance compared to classical regression models in pre-eclampsia prediction. Random forest and boosting-type algorithms had the best prediction performance. Further research should focus on comparing ML algorithms to classical regression models using the same samples and evaluation metrics to gain insight into their performance. External validation of ML algorithms is warranted to gain insights into their generalisability.
Topics: Humans; Pre-Eclampsia; Pregnancy; Female; Machine Learning; Algorithms; Prognosis; Regression Analysis; Risk Assessment; Risk Factors; Predictive Value of Tests
PubMed: 38806766
DOI: 10.1007/s11906-024-01297-1 -
Medical Ultrasonography Jun 2024Accurate prediction of preeclampsia could improve maternal outcomes. However, the role of uterine artery Doppler ultrasound in predicting preeclampsia remains unclear. (Meta-Analysis)
Meta-Analysis Review
AIMS
Accurate prediction of preeclampsia could improve maternal outcomes. However, the role of uterine artery Doppler ultrasound in predicting preeclampsia remains unclear.
MATERIALS AND METHODS
We comprehensively searched several electronic databases, including PubMed, EMBASE, the Cochrane Library, and Web of Science, covering studies published from the time of database creation to September 23, 2023. Studies on the predictive value of uterine artery Doppler ultrasound for preeclampsia were included. The primary pregnancy outcome was preeclampsia. The risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 scoring scale.
RESULTS
The use of resistance index (RI) for predicting preeclampsia demonstrated the highest sensitivity of 0.73 (95% confidence interval [CI], 0.30-0.94) and specificity of 0.90 (95% CI, 0.72-0.97), with a pooled area under the curve value of 0.91 (95% CI, 0.88-0.93). The use of pulsatility index (PI) for predicting preeclampsia showed a sensitivity of 0.65 (95% CI, 0.45-0.81) and specificity of 0.88 (95% CI, 0.77-0.94). Furthermore, preeclampsia prediction via notching showed a sensitivity of 0.54 (95% CI, 0.38-0.68) and specificity of 0.89 (95% CI, 0.79-0.95).
CONCLUSIONS
These findings highlight the varying predictive performance of different preeclampsia indices. PI and RI demonstrated moderate-to-high sensitivity and specificity, whereas notching exhibited relatively lower sensitivity but comparable specificity. Further research and validation are warranted to consolidate these results and enhance the accuracy of preeclampsia prediction.
Topics: Humans; Pre-Eclampsia; Female; Pregnancy; Uterine Artery; Ultrasonography, Doppler; Sensitivity and Specificity; Predictive Value of Tests; Ultrasonography, Prenatal
PubMed: 38805623
DOI: 10.11152/mu-4355 -
Neurology International May 2024Obstructive sleep apnea (OSA) is a prevalent yet underdiagnosed condition in pregnancy, associated with various maternal and fetal complications. This review synthesizes... (Review)
Review
Obstructive sleep apnea (OSA) is a prevalent yet underdiagnosed condition in pregnancy, associated with various maternal and fetal complications. This review synthesizes the current evidence on the epidemiology, pathophysiology, and neurological consequences of OSA in pregnancy, along with the potential management strategies. Articles were sourced from the PubMed, EMBASE, and Cochrane databases until 2023. Our comprehensive review highlights that the incidence of OSA increases during pregnancy due to physiological changes such as weight gain and hormonal fluctuations. OSA in pregnancy is linked with gestational hypertension, pre-eclampsia, gestational diabetes, and potential adverse fetal outcomes such as intrauterine growth restriction and preterm birth. Continuous positive airway pressure (CPAP) therapy remains the most effective management strategy for pregnant women with OSA. However, adherence to CPAP therapy is often suboptimal. This comprehensive review underscores the importance of the early recognition, timely diagnosis, and effective management of OSA in pregnancy to improve both maternal and fetal outcomes. Future research should focus on enhancing screening strategies and improving adherence to CPAP therapy in this population.
PubMed: 38804478
DOI: 10.3390/neurolint16030039 -
Epidemiologia (Basel, Switzerland) Apr 2024Several adverse maternal outcomes have been linked to the excessive consumption of caffeine during pregnancy. Tea is an important source of caffeine. Hypertensive... (Review)
Review
Several adverse maternal outcomes have been linked to the excessive consumption of caffeine during pregnancy. Tea is an important source of caffeine. Hypertensive disorders of pregnancy (HDP) are common pregnancy complications with unfavorable maternal and fetal complications. This study aimed to investigate the relationship between antenatal tea drinking and HDP using a meta-analysis of available evidence. We systematically retrieved eligible studies before computing the pooled odds ratio (OR) and 95% confidence interval (CI) of HDP for women who reported the highest versus the lowest frequencies of antenatal tea drinking. We used the statistic to measure heterogeneity across studies and the test for funnel plot asymmetry to evaluate publication bias. The results showed that the highest frequencies of antenatal tea drinking were associated with increased odds of HDP (pooled OR = 1.16, 95% CI: 1.01, 1.33). We identified no signs of heterogeneity across studies ( = 0.0% and p-heterogeneity = 0.498) or publication bias (z = 0.791 and p-publication bias = 0.429). When the outcome was limited to (pre-)eclampsia, the association became statistically non-significant (pooled OR = 1.28, 95% CI: 0.86, 1.89, = 0.0%, and p-heterogeneity = 0.751). In conclusion, our results indicated that the highest frequency of antenatal tea drinking was positively associated with HDP. Pregnant women should be advised against excessive tea consumption. Still, future prospective cohort studies, considering the effects of different tea types and caffeine content, are needed to confirm our conclusions.
PubMed: 38804341
DOI: 10.3390/epidemiologia5020014 -
Cureus Apr 2024Objective To compare the rates of pregnancies in high-risk groups for preeclampsia recommended for aspirin prophylactic when screened using various common algorithms....
Objective To compare the rates of pregnancies in high-risk groups for preeclampsia recommended for aspirin prophylactic when screened using various common algorithms. Methods This cross-sectional study was conducted on 1726 pregnant women from 11 to 13 weeks six days of gestation receiving antenatal care at two hospitals: Thai Nguyen National Hospital and a hospital in Thai Nguyen Province from October 2022 to October 2023. All participants provided consent for the study. We collected maternal characteristics, obstetric history, mean arterial pressure (MAP), mean uterine artery-PI (UtA-PI), and placental growth factor serum (PLGF). Screening performance estimates were calculated using the Fetal Medicine Foundation (FMF) and National Institute for Health and Care Excellence (NICE) guidelines. All pregnant women in the study had their preeclampsia risk assessed using all three algorithms with two cut-off points. Our data was collected, entered and analyzed using SPSS software 20.0 (IBM Corp., Armonk, NY). Categorical data was reported as frequency and percentage. McNemar's test was used for analyzing differences in the sizes of individual groups. Results In our study, the most common high-risk factor identified was the history of preeclampsia, 132 cases (7.6%). According to the NICE guideline, BMI ≥ 35 (kg/m²) is considered a moderate risk factor for preeclampsia. Several risk factors, such as BMI ≥ 35 kg/m² and history of diabetes mellitus type 1, were not present in any participants. Only one pregnant woman had chronic kidney disease (0.06%). Out of the 1726 pregnant women surveyed, the rates of high-risk preeclampsia were as follows: 9.9% (171 cases) based on algorithm 1; 10.8% (187 cases) based on algorithm 2 with a cut-off point > 1/100, 11.8% (203 cases) with a cut-off point > 1/150; 10.3 % (178 cases) based on algorithm 3 with a cut-off point > 1/100, and 11.6% (201 cases) with a cut-off point > 1/150. Among these algorithms, pregnant women in the high-risk preeclampsia group were advised to consider taking low-dose aspirin. Conclusion Screening for pre-eclampsia based on NICE recommendations resulted in a lower number of high-risk pregnant women requiring prophylactic aspirin use compared to other algorithms. This means that some pregnant women at risk of developing preeclampsia are not recommended to use aspirin as a preventive measure. Adding PLGF to the screening strategy will help us get closer to pregnant women who are truly at risk of progressing to preterm preeclampsia.
PubMed: 38803780
DOI: 10.7759/cureus.59133 -
Frontiers in Endocrinology 2024Hypertension and hypertensive disorders of pregnancy (HDP) are common diseases in women at different stages, which affect women's physical and mental health, and the...
OBJECTIVES
Hypertension and hypertensive disorders of pregnancy (HDP) are common diseases in women at different stages, which affect women's physical and mental health, and the impact of the latter on the offspring cannot not be ignored. Observational studies have investigated the correlation between uterine leiomyoma (UL) and the above conditions, but the relationship remains unclear. In this study, we employed two-sample Mendelian randomization (MR) analysis to assess the association between UL and hypertension, HDP, as well as blood pressure.
METHODS
We collected genetic association data of UL (35,474 cases), hypertension (129,909 cases), HDP (gestational hypertension with 8,502 cases, pre-eclampsia with 6,663 cases and eclampsia with 452cases), systolic blood pressure (SBP) and diastolic blood pressure (DBP) (both 757,601 participants) from published available genome-wide association studies (GWAS). The single nucleotide polymorphisms (SNPs) associated with UL phenotype were used as instrumental variables, and hypertension, three sub-types of HDP, SBP and DBP were used as outcomes. The inverse-variance weighted (IVW) method was employed as the primary method of causal inference. Heterogeneity was assessed using Cochran's Q test, and sensitivity analyses were conducted using MR-Egger regression and MR pleiotropy residual sum and outlier (MR-PRESSO) tests to evaluate the pleiotropy of instrumental variables. PhenoScanner search was used to remove confounding SNP. Robustness and reliability of the results were assessed using methods such as the weighted median and weighted mode.
RESULTS
The IVW analysis revealed a positive correlation between genetically predicted UL and SBP [odds ratio (OR)= 1.67, 95% confidence interval (CI):1.24~2.25, = 0.0007], and no statistical association was found between UL and hypertension, HDP, or DBP. The MR-Egger regression suggested that the above causal relationships were not affected by horizontal pleiotropy. The weighted median method and weighted model produced similar results to the IVW.
CONCLUSION
Based on large-scale population GWAS data, our MR analysis suggested a causal relationship between UL and SBP. Therefore, women with UL, especially pregnant women, should pay attention to monitoring their blood pressure levels. For patients with hypertension who already have UL, interventions for UL may serve as potential therapeutic methods for managing blood pressure.
Topics: Humans; Female; Mendelian Randomization Analysis; Leiomyoma; Uterine Neoplasms; Blood Pressure; Pregnancy; Genome-Wide Association Study; Polymorphism, Single Nucleotide; Hypertension; Hypertension, Pregnancy-Induced
PubMed: 38800482
DOI: 10.3389/fendo.2024.1373724 -
Cureus Apr 2024White-centered, flame-shaped retinal hemorrhages, also known as Roth spots, occur in several diseases, most often in subacute bacterial endocarditis. Other conditions...
White-centered, flame-shaped retinal hemorrhages, also known as Roth spots, occur in several diseases, most often in subacute bacterial endocarditis. Other conditions such as leukemia, hypertensive retinopathy, and pre-eclampsia are other causes. Here, we present the case of a 32-year-old female with sickle cell anemia (HbSS) who was treated at the hospital after experiencing a sickle cell crisis. Fundus examination was performed to rule out sickle cell retinopathies, suggesting the presence of Roth spots in the retina which are rarely seen in sickle cell disease.
PubMed: 38800292
DOI: 10.7759/cureus.59047 -
Cureus Apr 2024Introduction Obstetric emergencies, like eclampsia, need a quick and accurate response from the treating physician coming into first contact with the patient. Therefore,...
Introduction Obstetric emergencies, like eclampsia, need a quick and accurate response from the treating physician coming into first contact with the patient. Therefore, all doctors, even primary care physicians, interns, and resident doctors, need training to handle such cases proficiently, leaving minimal chances of error. Providing training for the management of these critical conditions on actual patients is not practically feasible. Clinical simulation in obstetrics can be used for the improvement of these skills for undergraduate and postgraduate students. We conducted a non-blinded randomized controlled trial with the primary aim of developing and implementing a module for training undergraduate medical students on the assessment and management of eclampsia and to evaluate and compare it with traditional didactic lectures or case-based learning. Methods The present randomized controlled educational trial was conducted in the Department of Obstetrics and Gynecology, All India Institute of Medical Sciences, Bibinagar, Hyderabad, India. The undergraduate medical students (Phase 3, Part 1) posted in the department during their clinical postings or tutorials were randomized into two groups. A total of 62 students were randomly divided into two groups, Group A and Group B, each consisting of 31 students. However, only 24/31 (77.42%) in Group A and 19/31 (61.3%) in Group B finally agreed to participate in the study. One group (Group A, with 24 participants) was taught the diagnosis and management of antepartum eclampsia through simulation-based training, and the other group (Group B, with 19 participants) was taught the same topic through conventional teaching, which consisted of didactic lectures through PowerPoint presentations and case-based discussion. Learning objectives were kept identical for both groups. Pre- and post-test scores were compared for both groups. Results The mean pre-test score of the simulation group was 6.13 ± 1.39, and that of the conventional teaching group was 6.05 ± 1.54. The post-test score of the simulation group was 9.17 ± 1.34, and that of the conventional teaching group was 7.37 ± 1.70. The simulation group showed an extremely significant (two-tailed p < 0.0001) improvement in their post-test scores when compared to their scores before the module was taught. The difference in the scores of simulated teaching (Group A) and conventional teaching (Group B) was also statistically significant (p = 0.005). Simulation-based learning was found to be more interactive, helpful in providing real-life-like experiences, led to better retention and understanding, and motivated the students for self-directed learning. Conclusion Although both conventional and simulation-based teaching were useful, simulation-based training was more effective in teaching undergraduate medical students regarding the diagnosis and management of eclampsia. Simulation-based learning is more interactive, provides real-life-like experiences, leads to better retention and understanding, and motivates the students for self-directed learning.
PubMed: 38800234
DOI: 10.7759/cureus.58898 -
Frontiers in Medicine 2024Preeclampsia (PE), a pregnancy specific syndrome, is defined as new-onset hypertension (≥140/90 mmHg) and proteinuria diagnosed after gestational week 20 or...
BACKGROUND
Preeclampsia (PE), a pregnancy specific syndrome, is defined as new-onset hypertension (≥140/90 mmHg) and proteinuria diagnosed after gestational week 20 or new-onset pre-eclampsia associated signs in the absence of proteinuria, and it may tend to present as late as 4-6 weeks' postpartum period. It is a leading cause of maternal mortality in both developed and developing countries. In order to prevent PE, the disease must be diagnosed at its earliest stage, however, the triads of high blood pressure, edema and albuminuria is neither specific nor sensitive enough for diagnosing the disease. Lactate dehydrogenase (LDH) is useful biochemical marker reflecting the occurrence of complications associated with preeclampsia. Besides, it has been suggested as potential biomarker to predict the severity of preeclampsia and as indicator of multi-organ involvement. The aim of this study was to investigate the diagnostic accuracy of LDH, which is affordable and easy to test, as a potential clinical biomarker to predict onset of preeclampsia.
METHODS
A hospital based cross-sectional study was conducted as of September 9 to December 24, 2022 at Debre Birhan Comprehensive Specialized Hospital (DBCSH). A total of 132 study subjects (66 preeclamptic and 66 normotensive controls) were enrolled in the study. A receiver operating characteristics (ROC) curve was used to calculate the area under the curve (AUC) and determine diagnostic accuracy of LDH. Youden's index was used to identify an optimal cut-off point for LDH in detecting preeclampsia associated complications.
RESULT
AUC for LDH was found to be 0.963 (95% CI, 0.91, 1.0; = 0.000) from ROC curve analysis. An optimal cut-off point for LDH was 376.5 U/L having a sensitivity and specificity of 87.5 and 90.8%, respectively.
CONCLUSION
Serum LDH had an AUC of greater than 0.8 and showed good diagnostic accuracy in predicting development of preeclampsia. Disease duration, gestational age, systolic and diastolic blood pressure among enormous number of predictor variables had association with serum level of LDH.
PubMed: 38799154
DOI: 10.3389/fmed.2024.1240848 -
The Journal of Maternal-fetal &... Dec 2024To investigate the relationship between preeclampsia and SARS-CoV-2 infection during pregnancy. This was a retrospective cohort study of pregnant women between March...
To investigate the relationship between preeclampsia and SARS-CoV-2 infection during pregnancy. This was a retrospective cohort study of pregnant women between March and October 2020. Pregnant patients admitted to 14 obstetrical centers in Michigan, USA formed the study population. Of the = 1458 participants, 369 had SARS-CoV-2 infection (cases). Controls were uninfected pregnancies that were delivered in the same obstetric unit within 30 days of the index case. Robust Poisson regression was used to estimate relative risk (RR) of preterm and term preeclampsia and preeclampsia involving placental lesions. The analysis included adjustment for relevant clinical and demographic risk factors.: SARS-CoV-2 infection during pregnancy increased the risk of preeclampsia [adjusted aRR = 1.69 (1.26-2.26)], preeclampsia involving placental lesions [aRR = 1.97(1.14-3.4)] and preterm preeclampsia 2.48(1.48-4.17). Although the highest rate of preeclampsia was observed in patients infected with SARS-CoV-2 who were symptomatic (18.4%), there was increased risk even in asymptomatic SARS-CoV-2 infected patients (14.2%) relative to non-infected controls (8.7%) ( < 0.05). This association with symptomatology was also noted with preterm preeclampsia for which the rate doubled from 2.7% in controls to 5.2% in asymptomatic cases and reached 11.8% among symptomatic cases ( < 0.05). The rate of preterm preeclampsia among cases of pregnant people self-identified as Black reached 10.1% and was almost double the rate of the reminder of the group of infected pregnancies (5.3%), although the rate among uninfected was almost the same (2.7%) for both Black and non-Black groups (interaction = 0.05). Infection with SARS-CoV-2 increases the risk of preeclampsia even in the absence of symptoms, although symptomatic persons are at even higher risk. Racial disparities in the development of preterm preeclampsia after SARS-CoV-2 infection may explain discrepancies in prematurity between different populations.
Topics: Humans; Female; Pregnancy; Pre-Eclampsia; COVID-19; Retrospective Studies; Adult; Pregnancy Complications, Infectious; SARS-CoV-2; Michigan; Risk Factors; Young Adult; Case-Control Studies
PubMed: 38797682
DOI: 10.1080/14767058.2024.2345852