Search for: All records

Introduction:Detecting water contamination in community housing is crucial for protecting public health. Early detection enables timely action to prevent waterborne diseases and ensures equitable access to safe drinking water. Traditional methods recommended by the Environmental Protection Agency (EPA) rely on collecting water samples and conducting lab tests, which can be both time-consuming and costly. Methods:To address these limitations, this study introduces a Graph Attention Network (GAT) to predict lead contamination in drinking water. The GAT model leverages publicly available municipal records and housing information to model interactions between homes and identify contamination patterns. Each house is represented as a node, and relationships between nodes are analyzed to provide a clearer understanding of contamination risks within the community. Results:Using data from Flint, Michigan, the model demonstrated higher performance compared to traditional methods. Specifically, the GAT achieved an accuracy of 0.80, precision of 0.71, and recall of 0.93, outperforming XGBoost, a classical machine learning algorithm, which had an accuracy of 0.70, precision of 0.66, and recall of 0.67. Discussion:In addition to its predictive capabilities, the GAT model identifies key factors contributing to lead contamination, enabling more precise targeting of at-risk areas. This approach offers a practical tool for policymakers and public health officials to assess and mitigate contamination risks, ultimately improving community health and safety. 

Importance Autism detection early in childhood is critical to ensure that autistic children and their families have access to early behavioral support. Early correlates of autism documented in electronic health records (EHRs) during routine care could allow passive, predictive model-based monitoring to improve the accuracy of early detection. Objective To quantify the predictive value of early autism detection models based on EHR data collected before age 1 year. Design, Setting, and Participants This retrospective diagnostic study used EHR data from children seen within the Duke University Health System before age 30 days between January 2006 and December 2020. These data were used to train and evaluate L2-regularized Cox proportional hazards models predicting later autism diagnosis based on data collected from birth up to the time of prediction (ages 30-360 days). Statistical analyses were performed between August 1, 2020, and April 1, 2022. Main Outcomes and Measures Prediction performance was quantified in terms of sensitivity, specificity, and positive predictive value (PPV) at clinically relevant model operating thresholds. Results Data from 45 080 children, including 924 (1.5%) meeting autism criteria, were included in this study. Model-based autism detection at age 30 days achieved 45.5% sensitivity and 23.0% PPV at 90.0% specificity. Detection by age 360 days achieved 59.8% sensitivity and 17.6% PPV at 81.5% specificity and 38.8% sensitivity and 31.0% PPV at 94.3% specificity. Conclusions and Relevance In this diagnostic study of an autism screening test, EHR-based autism detection achieved clinically meaningful accuracy by age 30 days, improving by age 1 year. This automated approach could be integrated with caregiver surveys to improve the accuracy of early autism screening.