Background: Suicide is a leading cause of death worldwide and results in a large number of person years of life lost. There is an opportunity to evaluate whether administrative health care system data and machine learning can quantify suicide risk in a clinical setting. Methods: The objective was to compare the performance of prediction models that quantify the risk of death by suicide within 90 days of an ED visit for parasuicide with predictors available in administrative health care system data. The modeling dataset was assembled from 5 administrative health care data systems. The data systems contained nearly all of the physician visits, ambulatory care visits, inpatient hospitalizations, and community pharmacy dispenses, of nearly the entire 4.07 million persons in Alberta, Canada. 101 predictors were selected, and these were assembled for each of the 8 quarters (2 years) prior to the quarter of death, resulting in 808 predictors in total for each person. Prediction model performance was validated with 10-fold cross-validation. Findings: The optimal gradient boosted trees prediction model achieved promising discrimination (AUC: 0.88) and calibration that could lead to clinical applications. The 5 most important predictors in the optimal gradient boosted trees model each came from a different administrative health care data system. Interpretation: The combination of predictors from multiple administrative data systems and the combination of personal and ecologic predictors resulted in promising prediction performance. Further research is needed to develop prediction models optimized for implementation in clinical settings. Funding: There was no funding for this study.
Background
Serosurveys are important to ascertain burden of infection. Prior SARS-CoV-2 serosurveys in New York City (NYC) have used nonrandom samples. During June–October 2020, the NYC Health Department conducted a population-based survey to estimate SARS-CoV-2 antibody prevalence in NYC adults.
Methods
Participants were recruited from the NYC 2020 Community Health Survey. We estimated citywide and stratified antibody prevalence using a hybrid design: serum tested at the NYC Health Department using the DiaSorin LIAISON ® SARS-CoV-2 S1/S2 IgG assay and self-reported antibody test results were used together. Prevalence was estimated using univariate frequencies and 95% confidence intervals (CI), accounting for complex survey design. Two-sided P-values ≤0.05 were statistically significant.
Results
There were 1074 respondents overall; 497 provided blood and 577 provided only a self-reported antibody test result. Weighted prevalence was 24.3% overall (95% CI: 20.7–28.3). Latino (30.7%, 95% CI: 24.1–38.2, p<0.01) and Black (30.7%, 95% CI: 21.9–41.2, p=0.02) respondents had a higher weighted prevalence compared with White respondents (17.4%, 95% CI: 12.5–23.7).
Conclusions
By October 2020, nearly 1 in 3 Black and 1 in 3 Latino NYC adults had SARS-CoV-2 antibodies, highlighting unequal impacts of the COVID-19 pandemic on Black and Latino adults in NYC.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.