Applying Automated Machine Learning to Predict Mode of Delivery Using Ongoing Intrapartum Data in Laboring Patients.

OBJECTIVE: This study aimed to develop and validate a machine learning (ML) model to predict the probability of a vaginal delivery (Partometer) using data iteratively obtained during labor from the electronic health record. STUDY DESIGN: A retrospective cohort study of deliveries at an academic, tertiary care hospital was conducted from 2013 to 2019 who had at least two cervical examinations. The population was divided into those delivered by physicians with nulliparous term singleton vertex (NTSV) cesarean delivery rates <23.9% (Partometer cohort) and the remainder (control cohort). The cesarean rate among this population of lower risk patients is a standard metric by which to compare provider rates; <23.9% was the Healthy People 2020 goal. A supervised automated ML approach was applied to generate a model for each population. The primary outcome was accuracy of the model developed on the Partometer cohort at 4 hours from admission to labor and delivery. Secondary outcomes included discrimination ability (receiver operating characteristics-area under the curve [ROC-AUC]), precision-recall AUC, and calibration of the Partometer. To assess generalizability, we compared the performance and clinical predictors identified by the Partometer to the control model. RESULTS: There were 37,932 deliveries during the study period; after exclusions, 9,385 deliveries were included in the Partometer cohort and 19,683 in the control cohort. Accuracy of predicting vaginal delivery at 4 hours was 87.1% for the Partometer (ROC-AUC: 0.82). Clinical predictors of greatest importance in the stacked Intrapartum Partometer Model included the Admission Model prediction and ongoing measures of dilatation and station which mirrored those found in the control population. CONCLUSION: Using automated ML and intrapartum factors improved the accuracy of prediction of probability of a vaginal delivery over both previously published models based on logistic regression. Harnessing real-time data and ML could represent the bridge to generating a truly prescriptive tool to augment clinical decision-making, predict labor outcomes, and reduce maternal and neonatal morbidity. KEY POINTS: · Our ML-based model yielded accurate predictions of mode of delivery early in labor.. · Predictors for models created on populations with high and low cesarean rates were the same.. · A ML-based model may provide meaningful guidance to clinicians managing labor..

Data-driven prediction of continuous renal replacement therapy survival.

Continuous renal replacement therapy (CRRT) is a form of dialysis prescribed to severely ill patients who cannot tolerate regular hemodialysis. However, as the patients are typically very ill to begin with, there is always uncertainty whether they will survive during or after CRRT treatment. Because of outcome uncertainty, a large percentage of patients treated with CRRT do not survive, utilizing scarce resources and raising false hope in patients and their families. To address these issues, we present a machine learning-based algorithm to predict short-term survival in patients being initiated on CRRT. We use information extracted from electronic health records from patients who were placed on CRRT at multiple institutions to train a model that predicts CRRT survival outcome; on a held-out test set, the model achieves an area under the receiver operating curve of 0.848 (CI = 0.822-0.870). Feature importance, error, and subgroup analyses provide insight into bias and relevant features for model prediction. Overall, we demonstrate the potential for predictive machine learning models to assist clinicians in alleviating the uncertainty of CRRT patient survival outcomes, with opportunities for future improvement through further data collection and advanced modeling.

Data-driven prediction of continuous renal replacement therapy survival.

Continuous renal replacement therapy (CRRT) is a form of dialysis prescribed to severely ill patients who cannot tolerate regular hemodialysis. However, as the patients are typically very ill to begin with, there is always uncertainty as to whether they will survive during or after CRRT treatment. Because of outcome uncertainty, a large percentage of patients treated with CRRT do not survive, utilizing scarce resources and raising false hope in patients and their families. To address these issues, we present a machine-learning-based algorithm to predict if patients will survive after being treated with CRRT. We use information extracted from electronic health records from patients who were placed on CRRT at multiple institutions to train a model that predicts CRRT survival outcome; on a held-out test set, the model achieved an area under the receiver operating curve of 0.929 (CI=0.917-0.942). Feature importance, error, and subgroup analyses identified consistently, mean corpuscular volume as a driving feature for model predictions. Overall, we demonstrate the potential for predictive machine-learning models to assist clinicians in alleviating the uncertainty of CRRT patient survival outcomes, with opportunities for future improvement through further data collection and advanced modeling.

TSI-GNN: Extending Graph Neural Networks to Handle Missing Data in Temporal Settings.

We present a novel approach for imputing missing data that incorporates temporal information into bipartite graphs through an extension of graph representation learning. Missing data is abundant in several domains, particularly when observations are made over time. Most imputation methods make strong assumptions about the distribution of the data. While novel methods may relax some assumptions, they may not consider temporality. Moreover, when such methods are extended to handle time, they may not generalize without retraining. We propose using a joint bipartite graph approach to incorporate temporal sequence information. Specifically, the observation nodes and edges with temporal information are used in message passing to learn node and edge embeddings and to inform the imputation task. Our proposed method, temporal setting imputation using graph neural networks (TSI-GNN), captures sequence information that can then be used within an aggregation function of a graph neural network. To the best of our knowledge, this is the first effort to use a joint bipartite graph approach that captures sequence information to handle missing data. We use several benchmark datasets to test the performance of our method against a variety of conditions, comparing to both classic and contemporary methods. We further provide insight to manage the size of the generated TSI-GNN model. Through our analysis we show that incorporating temporal information into a bipartite graph improves the representation at the 30% and 60% missing rate, specifically when using a nonlinear model for downstream prediction tasks in regularly sampled datasets and is competitive with existing temporal methods under different scenarios.

Autopopulus: A Novel Framework for Autoencoder Imputation on Large Clinical Datasets.

The adoption of electronic health records (EHRs) has made patient data increasingly accessible, precipitating the development of various clinical decision support systems and data-driven models to help physicians. However, missing data are common in EHR-derived datasets, which can introduce significant uncertainty, if not invalidating the use of a predictive model. Machine learning (ML)-based imputation methods have shown promise in various domains for the task of estimating values and reducing uncertainty to the point that a predictive model can be employed. We introduce Autopopulus, a novel framework that enables the design and evaluation of various autoencoder architectures for efficient imputation on large datasets. Autopopulus implements existing autoencoder methods as well as a new technique that outputs a range of estimated values (rather than point estimates), and demonstrates a workflow that helps users make an informed decision on an appropriate imputation method. To further illustrate Autopopulus' utility, we use it to identify not only which imputation methods can most accurately impute on a large clinical dataset, but to also identify the imputation methods that enable downstream predictive models to achieve the best performance for prediction of chronic kidney disease (CKD) progression.

Adequacy of Existing Surveillance Systems to Monitor Racism, Social Stigma and COVID Inequities: A Detailed Assessment and Recommendations.

The populations impacted most by COVID are also impacted by racism and related social stigma; however, traditional surveillance tools may not capture the intersectionality of these relationships. We conducted a detailed assessment of diverse surveillance systems and databases to identify characteristics, constraints and best practices that might inform the development of a novel COVID surveillance system that achieves these aims. We used subject area expertise, an expert panel and CDC guidance to generate an initial list of N > 50 existing surveillance systems as of 29 October 2020, and systematically excluded those not advancing the project aims. This yielded a final reduced group (n = 10) of COVID surveillance systems (n = 3), other public health systems (4) and systems tracking racism and/or social stigma (n = 3, which we evaluated by using CDC evaluation criteria and Critical Race Theory. Overall, the most important contribution of COVID-19 surveillance systems is their real-time (e.g., daily) or near-real-time (e.g., weekly) reporting; however, they are severely constrained by the lack of complete data on race/ethnicity, making it difficult to monitor racial/ethnic inequities. Other public health systems have validated measures of psychosocial and behavioral factors and some racism or stigma-related factors but lack the timeliness needed in a pandemic. Systems that monitor racism report historical data on, for instance, hate crimes, but do not capture current patterns, and it is unclear how representativeness the findings are. Though existing surveillance systems offer important strengths for monitoring health conditions or racism and related stigma, new surveillance strategies are needed to monitor their intersecting relationships more rigorously.

Domain Adaptation in Children Activity Recognition.

Among the major challenges in training predictive models in wireless health, is adapting them to new individuals or groups of people. This is not trivial largely due to possible differences in the distribution of data between a new individual in a real-world deployment and the training data used for building the model. In this study, we aim to tackle this problem by employing recent advancements in deep Domain Adaptation which tries to transfer a model trained on a labeled dataset to a new unlabeled one that follows a different distribution as well. To show the benefits of our approach, we transfer an activity recognition model, trained on a popular adult dataset to children. We show that direct use of the adult model on children loses 25.2% in F1-score against a supervised baseline, while our proposed transfer approach reduces this to 9%.