Modelling the risk of abnormal pregnancy-related outcomes such as stillbirth and preterm birth have been proposed in the past. Commonly they utilize maternal demographic and medical history information as predictors, and they are based on conventional statistical modelling techniques. In this study, we utilize state-of-the-art machine learning methods in the task of predicting early stillbirth, late stillbirth and preterm birth pregnancies. The aim of this experimentation is to discover novel risk models that could be utilized in a clinical setting. A CDC data set of almost sixteen million observations was used conduct feature selection, parameter optimization and verification of proposed models. An additional NYC data set was used for external validation. Algorithms such as logistic regression, artificial neural network and gradient boosting decision tree were used to construct individual classifiers. Ensemble learning strategies of these classifiers were also experimented with. The best performing machine learning models achieved 0.76 AUC for early stillbirth, 0.63 for late stillbirth and 0.64 for preterm birth while using a external NYC test data. The repeatable performance of our models demonstrates robustness that is required in this context. Our proposed novel models provide a solid foundation for risk prediction and could be further improved with the addition of biochemical and/or biophysical markers.
Currently, popular methods for prenatal risk assessment of fetal aneuploidies are based on multivariate probabilistic modelling, that are built on decades of scientific research and large-scale multi-center clinical studies. These static models that are deployed to screening labs are rarely updated or adapted to local population characteristics. In this article, we propose an adaptive risk prediction system or ARPS, which considers these changing characteristics and automatically deploys updated risk models. 8 years of real-life Down syndrome screening data was used to firstly develop a distribution shift detection method that captures significant changes in the patient population and secondly a probabilistic risk modelling system that adapts to new data when these changes are detected. Various candidate systems that utilize transfer -and incremental learning that implement different levels of plasticity were tested. Distribution shift detection using a windowed approach provides a computationally less expensive alternative to fitting models at every data block step while not sacrificing performance. This was possible when utilizing transfer learning. Deploying an ARPS to a lab requires careful consideration of the parameters regarding the distribution shift detection and model updating, as they are affected by lab throughput and the incidence of the screened rare disorder. When this is done, ARPS could be also utilized for other population screening problems. We demonstrate with a large real-life dataset that our best performing novel Incremental-Learning-Population-to-Population-Transfer-Learning design can achieve on par prediction performance without human intervention, when compared to a deployed risk screening algorithm that has been manually updated over several years.
Soluble growth stimulation protein form of interleukin-1 receptor-like 1 (ST2) may signal myocardial stress, and elevated ST2 blood levels are associated with adverse outcomes in adult heart disease. Data on ST2 in children with congenital heart disease (CHD) is limited. This study explored ST2 in newborns and older children with atrial septal defect (ASD), as this represents a common CHD type that remains clinically challenging to recognize in childhood with slowly evolving symptoms. A case–control study was carried out in newborn ASD cases versus controls measuring ST2 on dried blood spot samples and additionally in pediatric ASD cases versus controls on venous blood together with cardiac magnetic resonance before and after treatment. ST2 was higher in newborns with ASD (n = 19) compared to controls (n = 93); (p < 0.01). Receiver operating characteristics to diagnose newborn ASD by ST2 showed an area under the curve of 0.848. Levels of ST2 decreased in pediatric ASD (n = 16) after treatment (p = 0.014). Lower left ventricular ejection fraction correlated with higher ST2 levels before (r = −0.348) and after treatment (r = −0.497). Elevated ST2 in newborns may aid early ASD diagnosis. Levels of ST2 in pediatric ASD decrease after treatment, and higher levels are associated with lower left ventricular ejection fraction, warranting further study.