Using Social Vulnerability Indices to Predict Priority Areas for Prevention of Sudden Unexpected Infant Death in Cook County, IL: Cross-Sectional Study
Bibliographic record
Abstract
Background: The incidence of sudden unexpected infant death (SUID) in the United States has persisted at roughly the same level since the mid-2000s, despite intensive prevention efforts around safe sleep. Disparities in outcomes across racial and socioeconomic lines also persist. These disparities are reflected in the spatial distribution of cases across neighborhoods. Strategies for prevention should be targeted precisely in space and time to further reduce SUID and correct disparities. Objective: We sought to aid neighborhood-level prevention efforts by characterizing communities where SUID occurred in Cook County, IL, from 2015 to 2019 and predicting where it would occur in 2021-2025 using a semiautomated, reproducible workflow based on open-source software and data. Methods: This cross-sectional retrospective study queried geocoded medical examiner data from 2015-2019 to identify SUID cases in Cook County, IL, and aggregated them to "communities" as the unit of analysis. We compared demographic factors in communities affected by SUID versus those unaffected using Wilcoxon rank sum statistical testing. We used social vulnerability indicators from 2014 to train a negative binomial prediction model for SUID case counts in each given community for 2015-2019. We applied indicators from 2020 to the trained model to make predictions for 2021-2025. Results: Validation of our query of medical examiner data produced 325 finalized cases with a sensitivity of 95% (95% CI 93%-97%) and a specificity of 98% (95% CI 94%-100%). Case counts at the community level ranged from a minimum of 0 to a maximum of 17. A map of SUID case counts showed clusters of communities in the south and west regions of the county. All communities with the highest case counts were located within Chicago city limits. Communities affected by SUID exhibited lower median proportions of non-Hispanic White residents at 17% versus 60% (P<.001) and higher median proportions of non-Hispanic Black residents at 32% versus 3% (P<.001). Our predictive model showed moderate accuracy when assessed on the training data (Nagelkerke R2=70.2% and RMSE=17.49). It predicted Austin (17 cases), Englewood (14 cases), Auburn Gresham (12 cases), Chicago Lawn (12 cases), and South Shore (11 cases) would have the largest case counts between 2021 and 2025. Conclusions: Sharp racial and socioeconomic disparities in SUID incidence persisted within Cook County from 2015 to 2019. Our predictive model and maps identify precise regions within the county for local health departments to target for intervention. Other jurisdictions can adapt our coding workflows and data sources to predict which of their own communities will be most affected by SUID.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".