In a recent study posted to the medRxiv* preprint server, researchers developed a machine-learning-based model using the Medical Record Longitudinal Information AI System (MERLIN) platform for longitudinal preeclampsia risk estimation.
Study: An Interpretable Longitudinal Preeclampsia Risk Prediction Using Machine Learning. Image Credit: Yuriy K/Shutterstock.com
*Vital notice: medRxiv publishes preliminary scientific reports that should not peer-reviewed and, subsequently, shouldn’t be thought to be conclusive, guide clinical practice/health-related behavior, or treated as established information.
Background
Preeclampsia is a selected condition that causes hypertension and proteinuria after 20.0 gestational weeks, complicating pregnancies and contributing to maternal fatalities.
Proteinuria, increased liver enzymes, lung edema, convulsions, and death can all occur on account of increasing end-organ damage.
Preeclampsia is the most important reason for iatrogenic premature deliveries with accompanying infant morbidity and death since there isn’t any definite cure.
Despite substantial clinical research, existing prediction methods fail to detect preeclampsia-risk individuals. Moreover, nothing is thought concerning the risk trajectory or the pace of change in risk while pregnant.
In regards to the study
In the current study, researchers devised and validated the MERLIN machine learning tool to estimate preeclampsia risk throughout pregnancy.
The study included a big group of ladies who gave birth at two hospitals for tertiary care and 6 centers for community care in Latest England between February 2015 and June 2023.
Sociodemographics, family history, clinical diagnoses, vital signs, and laboratory reports were analyzed. The team included only deliveries with ≥1.0 visits with recorded data before 14.0 weeks of pregnancy. Eight datasets were developed at weeks 14.0, 20.0, 24.0, 28.0, 32.0, 36.0, and 39.0 of gestation and hospitalization for childbirth.
The team developed a mixture of blood pressure measurements, ICD codes, and laboratory results to find out the preeclampsia phenotype within the datasets. Linear regression, xgboost random forest classifiers, deep neural networks (DNN), and elastic net models were used to develop the tool and evaluate its performance.
The world under the curve (AUC) metric was used to estimate the predictive power of the tool. The model was validated using the electronic health records of 400.0 preeclampsia patients, reviewed by two clinical experts.
The training and testing datasets comprised 80% and 20% of cases, respectively. The team performed a 5.0-fold cross-validation over the training set to determine hyperparameters, following which probably the most appropriate combination was used to find out the testing metrics.
Shapley values were used to clarify model outputs. As well as, databases reminiscent of the Web of Science, MEDLINE, and PubMed were searched from the study’s inception through 1 May 2023.
Results
Amongst 120,757 individuals, the preeclampsia incidence was 5.7% (6,920 individuals). The AUC values for the model ranged between 0.7 and 0.9, which was validated externally. The associations between a couple of variables were non-linear and complicated; moreover, the relative statistical significance of risk estimators varied in the course of the pregnancy period.
As compared to the usual for predicting preeclampsia risk in the primary trimester, the machine learning-based tool detected 49% more patients with preeclampsia risk.
As well as, using the xgboost model predictions at 14.0 weeks on the testing dataset, 25% (n=5,624) individuals can be eligible for aspirin prophylaxis, whereas 15% (n=3,295) can be eligible using the American College of Obstetricians and Gynecologists (ACOG) criteria.
Using the novel model, an extra 2,329 individuals would have been eligible. If aspirin prophylaxis could prevent 62.0% of preeclampsia amongst high-risk individuals, an extra 28 cases (a complete of 66 cases) of early-onset preeclampsia amongst every 10,000 pregnant women would have the potential to be prevented with updated risk prediction.
Testing different predictive model types involving deep and machine learning showed high estimation power.
In comparison with normotensive individuals, those with a preeclampsia diagnosis included a significantly higher percentage of Blacks (17.0% versus 9.0%) and Hispanics (19.0% versus 15.0%), respectively.
Moreover, preeclampsia patients had an increased likelihood of familial hypertension, higher maximal diastolic and systolic blood pressures, and better weight gain while pregnant than non-preeclampsia individuals.
At 14.0 weeks, probably the most estimative features were long inter-pregnancy intervals and chronic hypertension. With increased gestational age, diastolic and systolic blood pressure, laboratory reports, and vital signs were major contributors.
Further, proteinuria was unlikely to be related to preeclampsia diagnosis if the maximal systolic blood pressure while pregnant was below 140.0 mm of Hg; nonetheless, above the edge, proteinuria became highly predictive.
Individuals under 20 and above 35 years were at increased risk of preeclampsia. The next erythrocyte count within the second trimester was related to higher preeclampsia risks.
In total, 13 studies were identified that incorporated machine learning to predict preeclampsia risk using clinical parameters, amongst which six included biological markers reminiscent of the uterine artery pulsatility index, serological placental growth factor (PIGF), and pregnancy-related serum protein A; two studies included diverse groups of >100,000 individuals; and two relevant studies conducted longitudinal estimations using electronic health records.
Nevertheless, most studies had limited depth, raised data leakage concerns, were overfitted, and lacked generalizability.
Based on the study findings, the chance prediction model for preeclampsia can aid within the early identification of high-risk individuals, enabling longitudinal risk assessments while pregnant. Accurate risk prediction can profit clinical treatment, aspirin prophylaxis, surveillance, and care escalation. Artificial intelligence can enhance perinatal care and reduce iatrogenic preterm births.
*Vital notice: medRxiv publishes preliminary scientific reports that should not peer-reviewed and, subsequently, shouldn’t be thought to be conclusive, guide clinical practice/health-related behavior, or treated as established information.