November 13, 2026 · The western journal of emergency medicine · DOI: 10.5811/westjem.63917

Machine Learning Algorithms for Predicting Psychostimulant Intoxication in Emergency Department Patients: A Multicenter Study.

Listen to this summary

This multicenter study asked whether machine learning models could reliably identify psychostimulant intoxication in emergency department patients with suspected substance use, using urine LC-MS confirmation as the reference standard and a chronologically separated validation cohort to test generalizability. The extreme gradient boosting (XGB) model achieved an AUC of 0.836 in the temporal validation cohort and showed specificity (0.910) comparable to senior emergency physicians, though its sensitivity (0.681) was moderate. The authors conclude that these models may serve as a standardized aid for reducing false positives and diagnostic uncertainty, but not as standalone rule-out tools.

Jiun-Hao Yu, Yueh-Peng Chen, Chih-Huang Hsieh, Yu-Jang Su, Hsien-Yi Chen, Chih-Chuan Lin, Te-I Weng, Cheng-Chung Fang, Sung-Wei Liu, Yen-Chia Chen, Yu-Cheng Pei, Kuan-Fu Chen

This is one of 33,000+ journals available on OSLR. Try it free for 14 days.

Free 14-day trial. 33,000+ journals. Cancel anytime.

14-day free trial. No commitment.

“

"Oslr has become part of my weekly routine on my day off. The clinical relevance of the summaries is outstanding — I'd rate it 9/10. Being able to consume research hands-free is a huge advantage for busy physicians."

Dr. Jennifer Thompson

Dr. Jennifer Thompson

Portland, OR

Stay current without falling behind

33,000+ journals. 3-minute audio summaries. Free for 14 days.

Download on the App StoreGet it on Google Play