Development of a prediction model on preeclampsia using machine learning-based method: a retrospective cohort study in China

Liu, Mengyuan; Yang, Xiaofeng; Chen, Guolu; Ding, Yuzhen; Shi, Meiting; Sun, Lu; Huang, Zhengrui; Liu, Jia; Liu, Tong; Yan, Ruiling; Li, Ruiman

doi:10.3389/fphys.2022.896969

Cited by 14 publications

(16 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Four studies were included in this review. Based on the risk of bias assessment, two studies were at low risk of bias [ 5 , 12 ], and two with low to moderate risk of bias [ 13 , 14 ] (Table 1 ).…”

Section: Resultsmentioning

confidence: 99%

“…As a result, novel statistical approaches are urgently needed to develop an early predictive model of preeclampsia. Recently, an ML-based model was proposed as a practical antenatal preeclampsia screening method [ 5 , 12 – 14 ].…”

Section: Discussionmentioning

confidence: 99%

“…The random forest model had the highest accuracy rate compared to other prediction algorithms. The area under the curve was 0.86 (95% CI 0.80–0.92), the precision was 0.82 (95% CI 0.79–0.84), the recall rate was 0.42 (95% CI 0.41–0.44), and the F1 score was 0.56 (95% CI 0.54–0.57) [ 14 ].…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Machine learning models for predicting preeclampsia: a systematic review

Ranjbar,

Montazeri,

Ghamsari

et al. 2024

BMC Pregnancy Childbirth

View full text Add to dashboard Cite

Background This systematic review provides an overview of machine learning (ML) approaches for predicting preeclampsia. Method This review adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyzes (PRISMA) guidelines. We searched the Cochrane Central Register, PubMed, EMBASE, ProQuest, Scopus, and Google Scholar up to February 2023. Search terms were limited to “preeclampsia” AND “artificial intelligence” OR “machine learning” OR “deep learning.” All studies that used ML-based analysis for predicting preeclampsia in pregnant women were considered. Non-English articles and those that are unrelated to the topic were excluded. The PROBAST was used to assess the risk of bias and applicability of each included study. Results The search strategy yielded 128 citations; after duplicates were removed and title and abstract screening was completed, 18 full-text articles were evaluated for eligibility. Four studies were included in this review. Two studies were at low risk of bias, and two had low to moderate risk. All of the study designs included were retrospective cohort studies. Nine distinct models were chosen as ML models from the four studies. Maternal characteristics, medical history, medication intake, obstetrical history, and laboratory and ultrasound findings obtained during prenatal care visits were candidate predictors to train the ML model. Elastic net, stochastic gradient boosting, extreme gradient boosting, and Random forest were among the best models to predict preeclampsia. All four studies used metrics such as the area under the curve, true positive rate, negative positive rate, accuracy, precision, recall, and F1 score. The AUC of ML models varied from 0.860 to 0.973 in four studies. Conclusion The results of studies yielded high prediction performance of ML models for preeclampsia risk from routine early pregnancy information.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning models for predicting preeclampsia: a systematic review

Ranjbar,

Montazeri,

Ghamsari

et al. 2024

BMC Pregnancy Childbirth

View full text Add to dashboard Cite

show abstract

“…The final performance of models is calculated as the average of all the iterations. [24] Statistical description and analysis…”

Section: Predictive Modelsmentioning

confidence: 99%

Effect of variable selection strategy on the predictive models for adverse pregnancy outcomes of pre-eclampsia: A retrospective study

Zheng,

Hao,

Khan

et al. 2024

PRM

View full text Add to dashboard Cite

Objectives: The improvement of prediction for adverse pregnancy outcomes is quite essential to the women suffering from pre-eclampsia, while the collection of predictive indicators is the prerequisite. The traditional knowledge-based strategy for variable selection confronts challenge referring to dataset with high-dimensional or unfamiliar data. In this study, we employed five different automatic variable selection methods to screen out influential indicators, and evaluated the performance of constructed predictive models. Methods: Seven hundreds and thirty-three Han-Chinese women were enrolled and 56 clinical and laboratory variables were recorded. After grouping based on binary pregnancy outcomes, statistical description and analysis were performed. Then, utilizing forward stepwise logistic regression (FSLR) as the reference method, another four variable selection strategies were included for filtering contributing variables as the predictive subsets, respectively. Finally, the logistic regression prediction models were constructed by the five subsets and evaluated by the receiver operator characteristic curve. Results: The variables confirmed statistical significance between the adverse and satisfactory outcomes groups did not overlap with the variables selected by selection strategies. “Platelet” and “Creatinine clearance rate” were the most influential indicator to predict adverse maternal outcome, while “Birth weight of neonates” was the best indicator for predicting adverse neonatal outcome. In average, the predictive models for neonatal outcomes achieved better performance than models for maternal outcomes. “Mutual information” and “Recursive feature elimination” were the best strategy under current dataset and study design. Conclusions: Variable selection strategies may provide an alternative approach besides picking influential indicators by statistical significance. Future work will focus on applying different variable selection methods to the high-dimensional dataset, which includes novel or unfamiliar variables. This aims to identify the most appropriate collection of predictors that can enhance prediction ability and clinical decision-making.

show abstract

“…Our screening method can also be used to calculate the risk of early and late pre-eclampsia (< 34 and < 37 weeks' gestation, respectively) and fetal growth restriction (< 37 weeks' gestation) when calculating the risk of chromosomal aneuploidy 32 .…”

Section: Main Ndings Of the Studymentioning

confidence: 99%

The value of combined detailed first- trimester ultrasound– biochemical analysis for screening fetal aneuploidy in the era of non-invasive prenatal testing

Ye¹,

Duan²,

Liu³

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Purpose This study aimed to investigate the performance, cost-effectiveness and additional findings of combined detailed ultrasound and biochemical screening for risks of major fetal trisomies in the first- trimester. Methods This is a retrospective analysis study, we estimated the risk of trisomies 21, 18 and 13 based on maternal age, fetal nuchal translucency thickness, nasal bone, ductus venosus pulsatility index velocity, tricuspid regurgitation, fetal heart rate, free beta-human chorionic gonadotropin, and pregnancy-associated plasma protein A in singleton pregnant women, and performed non-invasive prenatal testing for women with risks of trisomy 21 between 1:500 and 1:300. Invasive diagnostic testing was performed for women with positive or failed non-invasive prenatal testing result and in the high-risk group of this screening method. The direct costs were compared between this strategy and the non-invasive prenatal testing which alone used as first-line screening for all pregnant women. Results Among 25,155 singleton pregnant women who underwent screening, 24,361 were available for analysis, of these, 194 cases underwent non-invasive prenatal testing. Among the 24,361 women, 39, 19, and 7 had trisomies 21, 18 and 13, respectively. The use of this strategy could potentially detect approximately 94.87% of trisomy 21 cases, 100% of trisomy 18 cases, and 100% of trisomy 13 cases, with false-positive rates of 2.49%, 0.41%, and 0.49%, respectively. The overall detection rate and overall false-positive rates were 96.92% and 2.52%, respectively. The detection rate was 100% in the advanced age group and 94.12% in the general age group. Additionally, structural abnormalities were detected in 137 fetuses, and 44 fetuses had other chromosomal abnormalities. The total cost of this strategy was $3,730,843.30, and the cost per person tested was $153.15. The total cost of using non-invasive prenatal testing as the first-line strategy would be $6,813,387.04 and the cost per person tested was $279.68. Conclusions Our strategy is an efficient and cost-effective approach for detecting major trisomies and identifying more fetuses with a potential abnormality. Therefore, this strategy is a valuable screening method and highly feasible in the clinical setting.

show abstract

Development of a prediction model on preeclampsia using machine learning-based method: a retrospective cohort study in China

Cited by 14 publications

References 45 publications

Machine learning models for predicting preeclampsia: a systematic review

Machine learning models for predicting preeclampsia: a systematic review

Effect of variable selection strategy on the predictive models for adverse pregnancy outcomes of pre-eclampsia: A retrospective study

The value of combined detailed first- trimester ultrasound– biochemical analysis for screening fetal aneuploidy in the era of non-invasive prenatal testing

Contact Info

Product

Resources

About