Using machine learning and natural language processing in triage for prediction of clinical disposition in the emergency department

Using machine learning and natural language processing in triage for prediction of clinical disposition in the emergency department

Accurate triage is required for efficient allocation of resources and to decrease patients’ length of stay. Triage decisions are often subjective and vary by provider, leading to patients being over-triaged or under-triaged. This study developed machine learning models that incorporated natural language processing (NLP) to predict patient disposition. The models were assessed by comparing their performance with the judgements of emergency physicians (EPs).

A total of 17,2101 and 41,883 patients were enrolled from CMUH and AUH, respectively. EPs achieved F1 core of 0.361 and 0.498 for the primary and secondary outcomes, respectively. All machine learning models achieved higher F1 scores compared to EPs and Logistic Regression derived from triage level. Random Forest was selected for further evaluation and fine-tuning, because of its robust calibration and predictive performance. In internal validation, it achieved Brier scores of 0.072 and 0.089 for the primary and secondary outcomes, respectively, and 0.076 and 0.095 in external validation. Further analysis revealed that incorporating unstructured data significantly enhanced the model’s performance. Threshold adjustments were applied to improve clinical applicability, aiming to balance the trade-off between sensitivity and positive predictive value.

Yu-Hsin Chang, Ying-Chen Lin, Fen-Wei Huang, Dar-Min Chen, Yu-Ting Chung, Wei-Kung Chen & Charles C.N. Wang

https://bmcemergmed.biomedcentral.com/articles/10.1186/s12873-024-01152-1

BMC Emergency Medicine

18 december 2024

Fajar bagus W

PDF

English

Text