A hierarchical procedure to select intrauterine and extrauterine factors for methodological validation of preterm birth risk estimation

Rosa, Pasquale Anthony Della; Miglioli, Cesare; Caglioni, Martina; Tiberio, F.; Mosser, Kelsey H.H.; Vignotto, Edoardo; Canini, Matteo; Baldoli, Cristina; Falini, Andrea; Candiani, Massimo; Cavoretto, Paolo

doi:10.1186/s12884-021-03654-3

Cited by 36 publications

(43 citation statements)

References 122 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This drives the impetus for dimensionality reduction and/or feature selection, which can reduce the risk of overfitting, reduce computational resources required for analysis and, in the case of supervised feature selection, can identify the most important features for prediction. A recent study identified intra- and extra-uterine factors most informative of sPTB to estimate risk of sPTB using a random forest classifier with high predictive performance (AUC 0.81) [ 99 ]. The etiology of sPTB is multi-factorial, and is likely driven by more complex, subtle interactions which machine learning approaches, along with feature selection for identifying informative features, is well suited to detect.…”

Section: Discussionmentioning

confidence: 99%

Is there a maternal blood biomarker that can predict spontaneous preterm birth prior to labour onset? A systematic review

2022

View full text Add to dashboard Cite

Introduction The ability to predict spontaneous preterm birth (sPTB) prior to labour onset is a challenge, and it is currently unclear which biomarker(s), may be potentially predictive of sPTB, and whether their predictive power has any utility. A systematic review was conducted to identify maternal blood biomarkers of sPTB. Methods This study was conducted according to PRISMA protocol for systematic reviews. Four databases (MEDLINE, EMBASE, CINAHL, Scopus) were searched up to September 2021 using search terms: “preterm labor”, “biomarker” and “blood OR serum OR plasma”. Studies assessing blood biomarkers prior to labour onset against the outcome sPTB were eligible for inclusion. Risk of bias was assessed based on the Newcastle Ottawa scale. Increased odds of sPTB associated with maternal blood biomarkers, as reported by odds ratios (OR), or predictive scores were synthesized. This review was not prospectively registered. Results Seventy-seven primary research articles met the inclusion criteria, reporting 278 unique markers significantly associated with and/or predictive of sPTB in at least one study. The most frequently investigated biomarkers were those measured during maternal serum screen tests for aneuploidy, or inflammatory cytokines, though no single biomarker was clearly predictive of sPTB based on the synthesized evidence. Immune and signaling pathways were enriched within the set of biomarkers and both at the level of protein and gene expression. Conclusion There is currently no known predictive biomarker for sPTB. Inflammatory and immune biomarkers show promise, but positive reporting bias limits the utility of results. The biomarkers identified may be more predictive in multi-marker models instead of as single predictors. Omics-style studies provide promising avenues for the identification of novel (and multiple) biomarkers. This will require larger studies with adequate power, with consideration of gestational age and the heterogeneity of sPTB to identify a set of biomarkers predictive of sPTB.

show abstract

Section: Discussionmentioning

confidence: 99%

Is there a maternal blood biomarker that can predict spontaneous preterm birth prior to labour onset? A systematic review

2022

View full text Add to dashboard Cite

show abstract

“…The measurement of fundal height is susceptible to measurement personnel, which may limit its clinical use. Della Rosa et al used 9 most informative predictors to build a preterm birth prediction model, and the AUC of the model reached 0.812 [ 35 ]. Our results show that using only 15 predictions can achieve better model predictions.…”

Section: Discussionmentioning

confidence: 99%

Machine Learning-Based Prediction Model of Preterm Birth Using Electronic Health Record

Sun

Zou

Yan

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Objective. Preterm birth (PTB) was one of the leading causes of neonatal death. Predicting PTB in the first trimester and second trimester will help improve pregnancy outcomes. The aim of this study is to propose a prediction model based on machine learning algorithms for PTB. Method. Data for this study were reviewed from 2008 to 2018, and all the participants included were selected from a hospital in China. Six algorisms, including Naive Bayesian (NBM), support vector machine (SVM), random forest tree (RF), artificial neural networks (ANN), K-means, and logistic regression, were used to predict PTB. The receiver operating characteristic curve (ROC), accuracy, sensitivity, and specificity were used to assess the performance of the model. Results. A total of 9550 pregnant women were included in the study, of which 4775 women had PTB. A total of 4775 people were randomly selected as controls. Based on 27 weeks of gestation, the area under the curve (AUC) and the accuracy of the RF model were the highest compared with other algorithms (accuracy: 0.816; AUC = 0.885, 95% confidence interval (CI): 0.873–0.897). Meanwhile, there was positive association between the accuracy and AUC of the RF model and gestational age. Age, magnesium, fundal height, serum inorganic phosphorus, mean platelet volume, waist size, total cholesterol, triglycerides, globulins, and total bilirubin were the main influence factors of PTB. Conclusion. The results indicated that the prediction model based on the RF algorithm had a potential value to predict preterm birth in the early stage of pregnancy. The important analysis of the RF model suggested that intervention for main factors of PTB in the early stages of pregnancy would reduce the risk of PTB.

show abstract

“…Risk in the individual after treatment might depend on if other risk factors for PTD also are present. Spontaneous PTD is a multifactorial condition, and only a comprehensive model including major risk factors may present adequate risk estimation for a specific patient [ 43 ]. We suggest that future models for individual prediction of spontaneous PTD include cone-length in the excised specimen, together with other risk factors for PTD.…”

Section: Discussionmentioning

confidence: 99%

Associations between cervical intraepithelial neoplasia during pregnancy, previous excisional treatment, cone-length and preterm delivery: a register-based study from western Sweden

Wiik

Kärrberg

Nilsson

et al. 2022

BMC Med

View full text Add to dashboard Cite

Background Excisional treatment of cervical intraepithelial neoplasia (CIN) has been associated with increased risk of preterm delivery (PTD), although the underlying mechanism is as yet unclear. Studies on formalin-fixed excised tissue indicate that the risk increases with cone-length, but the magnitude of increase is uncertain, especially in case of minor excisions (≤10 mm), as well compared to women with untreated CIN during pregnancy. This study assesses the impact of cone-length at previous treatment for CIN as well as diagnosis of CIN during pregnancy on the risk of PTD. Methods A register-based cohort study in western Sweden linking cervical cytology, histology, and treatment data from the Swedish National Cervical Screening Registry to data on obstetric outcomes in singleton pregnancies 2008–2016 from the Swedish Medical Birth Registry. These groups were compared for PTD and other obstetric outcomes: (1) women with one excisional treatment (n=3250, including a subgroup (n=2408) with cone-length measured before fixation; (2) women with untreated CIN diagnosed during pregnancy (n=1380); and (3) women with normal cytology (n=42,398). Logistic regression analyses were adjusted for socioeconomic and health-related confounders. Results Treated women had increased risk of PTD (adjusted odds ratio (aOR) 1.60, 95% confidence interval (CI) 1.21–2.12), spontaneous PTD (aOR 1.95, 95% CI 1.40–2.72) and preterm prelabor rupture of membranes (pPROM) (aOR 2.74, 95% CI 1.66–4.51) compared to the CIN during pregnancy group. ORs were similar when compared to the normal cytology group. Risks of these outcomes increased with cone-length. Mean cone-length was 9.1 mm. Cone-length ≤10 mm was associated with increased risk of PTD (aOR 1.41, 95% CI 1.02–1.94), spontaneous PTD (aOR 1.73, 95% CI 1.18–2.54), and pPROM (aOR 2.44, 95% CI 1.40–4.28), compared to the CIN during pregnancy group. The PTD risk was similar for cone-lengths 3–10 mm, thereafter increasing by 15% with each additional millimeter. Conclusions This study suggests that all excisional treatment, including small cones, are associated with increased risk of PTD and pPROM. Risks increase further with cone-length. In women of reproductive age, clinicians should aim to remove all CIN but minimal healthy cervical tissue. Cone-length should be recorded at treatment, for future prenatal risk estimation.

show abstract

A hierarchical procedure to select intrauterine and extrauterine factors for methodological validation of preterm birth risk estimation

Cited by 36 publications

References 122 publications

Is there a maternal blood biomarker that can predict spontaneous preterm birth prior to labour onset? A systematic review

Is there a maternal blood biomarker that can predict spontaneous preterm birth prior to labour onset? A systematic review

Machine Learning-Based Prediction Model of Preterm Birth Using Electronic Health Record

Associations between cervical intraepithelial neoplasia during pregnancy, previous excisional treatment, cone-length and preterm delivery: a register-based study from western Sweden

Contact Info

Product

Resources

About