AI-DRAFTED — PHYSICIAN REVIEW IN PROGRESSThe citation for this entry was checked against Crossref and PubMed, but its summary and interpretation were drafted by an AI model from the published abstract and have not yet been individually read by a physician. Read the linked source before relying on this operationally.
Paper
✓ verified
Comparison of Prediction Models for Use of Medical Resources at Urban Auto-racing Events[1]
Summary
A head-to-head field test of the two dominant prediction models against actual medical utilization at the 2011 and 2012 Baltimore Grand Prix urban IndyCar events (~130,000–131,000 spectators). Actual demand: 19–57 encounters/day and 2–9 transports/day in 2011; 19–44 encounters and 4–9 transports/day in 2012. The Arbon regression over-predicted patient encounters on every day except one, and the Hartman model over-predicted encounters at both events; for hospital transports, Arbon under-predicted while Hartman scattered both above and below actuals by day. The study is the clearest demonstration that literature models transfer poorly to novel event types and that transport prediction is weaker than encounter prediction.
Key findings
- Baltimore Grand Prix 2011/2012 (~130k spectators): 19–57 encounters/day; 2–9 transports/day.
- Arbon over-predicted encounters on all but one day; Hartman over-predicted encounters at both events.
- Transports: Arbon under-predicted; Hartman inconsistent (over and under by day).
- Published PDM 2014;29(6):608-613 — entry year (2016) needs BA reconciliation; candidate DOI 10.1017/s1049023x14001046.
Read the paper
- Publisher (DOI) ↗may be paywalled