Prediction of In‐hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data–Driven, Machine Learning Approach
Problem
Existing clinical decision rules for predicting in-hospital mortality in emergency department sepsis patients use few variables, generalize poorly, and cannot be easily updated.
Why it matters
Early, accurate mortality prediction in sepsis could guide life-saving treatment decisions.
What the AI did
A proof-of-concept study built a local big-data machine learning model harnessing many EHR variables to predict in-hospital mortality, compared against existing clinical decision rules and traditional analytic methods.
Results
not stated in source
Impact
Proof-of-concept suggesting ML may improve prediction over CDRs; deployment and measured outcomes not stated.
Record
| Venue | Academic Emergency Medicine |
|---|---|
| Published | 2015 |
| Work type | article |
| Authors | Richard Andrew Taylor, Joseph R. Pare, Arjun K. Venkatesh, Hani O. Mowafi, Edward R. Melnick, William M. Fleischman, Michael Kennedy Hall |
| Citations | 491 (OpenAlex, at import time) |
| References | 60 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1111/acem.12876 |
| Open access | bronze |
| Keywords | sepsis, machine learning, mortality prediction, electronic health records, emergency medicine |
Importance rating
significant — thousands to millions affected
Sepsis in-hospital mortality prediction could guide life-saving treatment; abstract frames it as a use case for better ED predictive analytics but gives no scale.