Predicting Laboratory Test Ordering in Emergency Departments Using Integrated Structured and Unstructured Electronic Health Records: Machine Learning Study
Xingyu Zhang, Haipeng Ling, Xin Zhang, Anao Zhang · 2026
Read Predicting Laboratory Test Ordering in Emergency Departments Using Integrated Structured and Unstructured Electronic Health Records: Machine Learning Study by Xingyu Zhang, Haipeng Ling, Xin Zhang, Anao Zhang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13268631.txt.
Description
Xingyu Zhang and colleagues present a 2026 machine learning study predicting lab test orders in emergency departments. Lab testing guides emergency care, but overuse wastes money and time. The team analyzed 13,115 adult emergency visits from a 2021 national US survey. They built models from structured record data, from free-text complaint notes converted by a language model, from both together, and from an averaged ensemble.
The combined model predicted test ordering best, clearly beating either data type alone. The ensemble also did well but did not top the combined model. Older age, ambulance arrival, abnormal vital signs, and chronic illness predicted testing; injury visits predicted less testing. The authors say joining structured and text data could power decision support that trims unnecessary tests without missing needed ones.
Catalog record
| CREATOR | Xingyu Zhang, Haipeng Ling, Xin Zhang, Anao Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49403 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |