Predicting state level suicide fatalities in the united states with realtime data and machine learning.

Digital trace data and machine learning techniques are increasingly being adopted to predict suicide-related outcomes at the individual level; however, there is also considerable public health need for timely data about suicide trends at the population level. Although significant geographic variation in suicide rates exist by state within the United States, national systems for reporting state suicide trends typically lag by one or more years. We developed and validated a deep learning based approach to utilize real-time, state-level online (Mental Health America web-based depression screenings; Google and YouTube Search Trends), social media (Twitter), and health administrative data (National Syndromic Surveillance Program emergency department visits) to estimate weekly suicide counts in four participating states. Specifically, per state, we built a long short-term memory (LSTM) neural network model to combine signals from the real-time data sources and compared predicted values of suicide deaths from our model to observed values in the same state. Our LSTM model produced accurate estimates of state-specific suicide rates in all four states (percentage error in suicide rate of -2.768% for Utah, -2.823% for Louisiana, -3.449% for New York, and -5.323% for Colorado). Furthermore, our deep learning based approach outperformed current gold-standard baseline autoregressive models that use historical death data alone. We demonstrate an approach to incorporate signals from multiple proxy real-time data sources that can potentially provide more timely estimates of suicide trends at the state level. Timely suicide data at the state level has the potential to improve suicide prevention planning and response tailored to the needs of specific geographic communities.

Risk of pediatric back-over injuries in residential driveways by vehicle type.

OBJECTIVE: Research suggests that children experience driveway back-over injuries at a significant rate and the severity of the resulting injuries differ by type of vehicle. Yet, no US study attempted to quantify "back-over risk" for classes of vehicles because of the difficulties with determining exposure. Using vehicle registration information, we set out to estimate the relative risk of driveway back-over injuries to children by type of vehicle. METHODS: Driveway back-over events were identified from state police reports and medical records from the state level 1 pediatric trauma center and compared with vehicle registration information to estimate injury incidence for 4 classes of vehicles (passenger cars, trucks, sport utility vehicles, and minivans) over 6 years in the state of Utah. RESULTS: Reported driveway back-over injuries represent an incidence of 7.09 per 100,000 children (<10 years old) per year. Overall, passenger cars account for 1.62 injuries per 100,000 registered vehicles. Compared with passenger cars, children were 53% more likely to be injured by a truck (P = 0.01) and 2.4 times more likely to be injured by a minivan (P < 0.001). Among children transported to a trauma center, admission (P = 0.01) and need for surgery (P = 0.03) were greater among children backed over by trucks, sport utility vehicles, and minivans compared with passenger cars. CONCLUSIONS: Findings suggest that when assessing driveway back-over injuries, larger high-profile vehicles are associated with a higher incidence and severity of injuries when compared with injuries resulting from passenger cars.