Prediction of cesarean delivery in class III obese nulliparous women: An externally validated model using machine learning

BACKGROUND

class III obese women, are at a higher risk of cesarean section during labor, and cesarean section is responsible for increased maternal and neonatal morbidity in this population.

OBJECTIVE

the objective of this project was to develop a method with which to quantify cesarean section risk before labor.

METHODS

this is a multicentric retrospective cohort study conducted on 410 nulliparous class III obese pregnant women who attempted vaginal delivery in two French university hospitals. We developed two predictive algorithms (a logistic regression and a random forest models) and assessed performance levels and compared them.

RESULTS

the logistic regression model found that only initial weight and labor induction were significant in the prediction of unplanned cesarean section. The probability forest was able to predict cesarean section probability using only two pre-labor characteristics: initial weight and labor induction. Its performances were higher and were calculated for a cut-point of 49.5% risk and the results were (with 95% confidence intervals): area under the curve 0.70 (0.62,0.78), accuracy 0.66 (0.58, 0.73), specificity 0.87 (0.77, 0.93), and sensitivity 0.44 (0.32, 0.55).

CONCLUSIONS

this is an innovative and effective approach to predicting unplanned CS risk in this population and could play a role in the choice of a trial of labor versus planned cesarean section. Further studies are needed, especially a prospective clinical trial.

FUNDING

French state funds "Plan Investissements d'Avenir" and Agence Nationale de la Recherche.

Daily precipitation performances of regression-based statistical downscaling models in a basin with mountain and semi-arid climates

The impacts of climate change on current and future water resources are important to study local scale. This study aims to investigate the prediction performances of daily precipitation using five regression-based statistical downscaling models (RBSDMs), for the first time, and the ERA-5 reanalysis dataset in the Susurluk Basin with mountain and semi-arid climates for 1979-2018. In addition, comparisons were also performed with an artificial neural network (ANN). Before achieving the aim, the effects of atmospheric variables, grid resolution, and long-distance grid on precipitation prediction were holistically investigated for the first time. Kling-Gupta efficiency was modified and used for holistic evaluation of statistical moments parameters at precipitation prediction comparison. The standard triangular diagram, quite new in the literature, was also modified and used for graphical evaluation. The results of the study revealed that near grids were more effective on precipitation than single or far grids, and 1.50° × 1.50° resolution showed similar performance to 0.25° × 0.25° resolution. When the polynomial multivariate adaptive regression splines model, which performed slightly higher than ANN, tended to capture skewness and standard deviation values of precipitations and to hit wet/dry occurrence than the other models, all models were quite well able to predict the mean value of precipitations. Therefore, RBSDMs can be used in different basins instead of black-box models. RBSDMs can also be established for mean precipitation values without dry/wet classification in the basin. A certain success was observed in the models; however, it was justified that bias correction was required to capture extreme values in the basin.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s00477-022-02345-5.

Directed acyclic graphs and causal thinking in clinical risk prediction modeling

BACKGROUND

In epidemiology, causal inference and prediction modeling methodologies have been historically distinct. Directed Acyclic Graphs (DAGs) are used to model a priori causal assumptions and inform variable selection strategies for causal questions. Although tools originally designed for prediction are finding applications in causal inference, the counterpart has remained largely unexplored. The aim of this theoretical and simulation-based study is to assess the potential benefit of using DAGs in clinical risk prediction modeling.

METHODS

We explore how incorporating knowledge about the underlying causal structure can provide insights about the transportability of diagnostic clinical risk prediction models to different settings. We further probe whether causal knowledge can be used to improve predictor selection in clinical risk prediction models.

RESULTS

A single-predictor model in the causal direction is likely to have better transportability than one in the anticausal direction in some scenarios. We empirically show that the Markov Blanket, the set of variables including the parents, children, and parents of the children of the outcome node in a DAG, is the optimal set of predictors for that outcome.

CONCLUSIONS

Our findings provide a theoretical basis for the intuition that a diagnostic clinical risk prediction model including causes as predictors is likely to be more transportable. Furthermore, using DAGs to identify Markov Blanket variables may be a useful, efficient strategy to select predictors in clinical risk prediction models if strong knowledge of the underlying causal structure exists or can be learned.