Nowcasting Neighborhood Overdose Deaths in LA County

Fabrice Harel-Canada, Arthur Funnell, Panayiotis Petousis, Ruby Romero, Adam Koncsol, Michael Shin, Rebecca Trotzky-Sirr, Alex Bui, Morgan Godvin, David Goodman-Meza, Chelsea L. Shover
Last updated on Sep 15, 2026 public health
Top: average overdose deaths per quarter in 2025 by ZIP code, Service Planning Area, and county. Bottom: nowcast error at each scale.

Overdose death records take 90–120 days to finalize, so public health teams are always looking at the past. As part of Rapid Overdose Surveillance Los Angeles (ROSLA), this project builds nowcasts of overdose mortality across Los Angeles County ZIP codes to close that gap.

  • Models. Gradient-boosted Poisson count models trained in a walk-forward backtest on finalized Medical Examiner records from 2012 to 2025, so every estimate uses only data that would have been available at the time.
  • Signals. Each neighborhood’s own overdose history is combined with public data: treatment-facility access, deprivation indices, homeless counts, drug-checking results, EMS calls, and search trends.
  • Knowing what’s knowable. When a ZIP code averages about one death per quarter, random chance dominates. The project measures the ceiling that counting noise places on any model, and uses it to choose the geography and time period where a real rise becomes detectable.
How well each approach identifies the 20 highest-burden ZIP codes, scored against realized counts (open) and against four-quarter deaths that smooth out counting noise (filled).

Manuscript in preparation.

public health surveillance nowcasting gradient boosting spatial epidemiology overdose

Related