Your neighborhood matters: A machine-learning approach to the geospatial and social determinants of health in 9-1-1 activated chest pain.
Ziad Faramand, Mohammad Alrawashdeh, Stephanie Helman and 4 others
PMID 34820853WHAT IT FOUND
Residential area, older age, prior revascularization, race, and sex were associated with likelihood of acute coronary syndrome among 2,400 Pittsburgh 9-1-1 chest pain patients.
Key findings
01The likelihood that an EMS chest pain encounter was ACS varied across Pittsburgh residential areas, from 11.7% to 19.1%.
02Older age and prior revascularization were the most important predictors of ACS likelihood, followed by income, distance from hospital, and residential area.
03Sex, race, and residential area were important and significant social and geospatial determinants of ACS likelihood in the model results.
STILL TO COME
How it was doneWhat they foundWhat it means for RNs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The study included only patients transported to University of Pittsburgh Medical Center hospitals, which the authors estimate as 69% of chest pain encounters, so patients transported elsewhere were not represented. Residential area was based on EMS pickup location and zip code, not exact home address, and income was zip code median, not individual income. Race was categorized as a dichotomous variable because Pittsburgh demographics did not include many underrepresented minorities. The study was observational, so it cannot show that neighborhood, race, sex, or distance caused ACS, and residual confounding is possible. The model was tested only in this single city and health system, so its findings may not apply elsewhere. The nursing relevance comes from authors' implications; no nurse-delivered intervention was tested.
Declared interests
The authors reported no conflicts of interest. The article is listed as NIH extramural research support, but no detailed funding statement is provided.
The easy way to misread this
Do not use residential area or this model as a standalone triage tool for ACS. The study was observational, at the chosen cutoff only 25% of flagged cases were true ACS, and it was tested only in one city.