Clinical prediction models for pre-eclampsia: time to take the next step

Machine-learning predictive model of pregnancy-induced hypertension in the first trimester

In the first trimester of pregnancy, accurately predicting the occurrence of pregnancy-induced hypertension (PIH) is important for both identifying high-risk women and adopting early intervention. In this study, we used four machine-learning models (LASSO logistic regression, random forest, backpropagation neural network, and support vector machines) to predict the occurrence of PIH in a prospective cohort. Candidate features for predicting the occurrence of middle and late PIH were acquired using a LASSO algorithm. The performance of predictive models was assessed using receiver operating characteristic analysis. Finally, a nomogram was established with the model scores, age, and nulliparity. Calibration, clinical usefulness, and internal validation were used to assess the performance of the nomogram. In the training set (2258 pregnant women), eleven candidate factors in the first trimester were significantly associated with the occurrence of PIH (P < 0.001 in the training set). Four models showed AUCs from 0.780 to 0.816 in the training set. For the validation set (939 pregnant women), AUCs varied from 0.516 to 0.795. The nomogram showed good discrimination, with an AUC of 0.847 (95% CI: 0.805-0.889) in the training set and 0.753 (95% CI: 0.653-0.853) in the validation set. Decision curve analysis suggested that the model was clinically useful. The model developed using LASSO logistic regression achieved the best performance in predicting the occurrence of PIH. The derived nomogram, which incorporates the model score and maternal risk factors, can be used to predict PIH in clinical practice. We develop a model with good performance for clinical prediction of PIH in the first trimester.

Early prediction of preeclampsia via machine learning

BACKGROUND

Early prediction of preeclampsia is challenging because of poorly understood causes, various risk factors, and likely multiple pathogenic phenotypes of preeclampsia. Statistical learning methods are well-equipped to deal with a large number of variables, such as patients' clinical and laboratory data, and to select the most informative features automatically.

OBJECTIVE

Our objective was to use statistical learning methods to analyze all available clinical and laboratory data that were obtained during routine prenatal visits in early pregnancy and to use them to develop a prediction model for preeclampsia.

STUDY DESIGN

This was a retrospective cohort study that used data from 16,370 births at Lucile Packard Children Hospital at Stanford, CA, from April 2014 to January 2018. Two statistical learning algorithms were used to build a predictive model: (1) elastic net and (2) gradient boosting algorithm. Models for all preeclampsia and early-onset preeclampsia (<34 weeks gestation) were fitted with the use of patient data that were available at <16 weeks gestational age. The 67 variables that were considered in the models included maternal characteristics, medical history, routine prenatal laboratory results, and medication intake. The area under the receiver operator curve, true-positive rate, and false-positive rate were assessed via cross-validation.

RESULTS

Using the elastic net algorithm, we developed a prediction model that contained a subset of the most informative features from all variables. The obtained prediction model for preeclampsia yielded an area under the curve of 0.79 (95% confidence interval, 0.75-0.83), sensitivity of 45.2%, and false-positive rate of 8.1%. The prediction model for early-onset preeclampsia achieved an area under the curve of 0.89 (95% confidence interval, 0.84-0.95), true-positive rate of 72.3%, and false-positive rate of 8.8%.

CONCLUSION

Statistical learning methods in a retrospective cohort study automatically identified a set of significant features for prediction and yielded high prediction performance for preeclampsia risk from routine early pregnancy information.