Rapid trauma classification under data scarcity: an emergency on-scene decision model combining natural language processing and machine learning.
Uloženo v:
| Název: | Rapid trauma classification under data scarcity: an emergency on-scene decision model combining natural language processing and machine learning. |
|---|---|
| Autoři: | Tang J; Department of Information, Daping Hospital, Army Medical University, Chongqing, 400042, China., Li T; Department of Shock and Transfusion, State Key Laboratory of Trauma, Burns and Combined Injury, Daping Hospital, Army Medical University, Chongqing, 400042, China., Liu L; Department of Shock and Transfusion, State Key Laboratory of Trauma, Burns and Combined Injury, Daping Hospital, Army Medical University, Chongqing, 400042, China. lmliu62@tmmu.edu.cn., Wu D; Department of Information, Daping Hospital, Army Medical University, Chongqing, 400042, China. 604269346@qq.com. |
| Zdroj: | Medical & biological engineering & computing [Med Biol Eng Comput] 2025 Dec; Vol. 63 (12), pp. 3521-3530. Date of Electronic Publication: 2025 Jul 11. |
| Způsob vydávání: | Journal Article |
| Jazyk: | English |
| Informace o časopise: | Publisher: Springer Country of Publication: United States NLM ID: 7704869 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1741-0444 (Electronic) Linking ISSN: 01400118 NLM ISO Abbreviation: Med Biol Eng Comput Subsets: MEDLINE |
| Imprint Name(s): | Publication: New York, NY : Springer Original Publication: Stevenage, Eng., Peregrinus. |
| Výrazy ze slovníku MeSH: | Machine Learning* , Natural Language Processing* , Wounds and Injuries*/classification, Humans ; Algorithms ; Female ; Emergency Medical Services ; Male |
| Abstrakt: | Trauma has become a major cause of increased morbidity and mortality worldwide. In emergency response, the classification of injuries is crucial as it helps to quickly determine the criticality of the injured, allocate rescue resources rationally, and decide the priority order of treatment. However, emergency scenes are often chaotic environments, making it difficult for rescue personnel to collect complete and accurate information about the injured in a short period. The combination of artificial intelligence and emergency rescue is gradually changing the rescue model, improving the efficiency of rescue operations. We selected data from 26,810 trauma patients admitted to Chongqing Daping Hospital between 2013 and 2024. We propose a fast tiered medical treatment method with a two-layer structure under emergency limited data conditions, which integrates natural language processing (NLP) and machine learning (ML) techniques. The tiered medical treatment model utilizes NLP to capture semantic features of unstructured text data, while utilizing four ML algorithms to process structured numerical data. Additionally, we conducted external validation using 245 data entries from the Chongqing Emergency Center. The experimental results show that gradient boosting and logistic regression have the best performance in the two-layer ML algorithms. Based on these two algorithms, our model outperformed the multilayer perceptron (MLP) model on the test dataset, achieving an accuracy of 91.17%, which is 4.33% higher than that of the MLP model. The specificity, F1-score, and AUC of our model were 97.06%, 86.85%, and 0.949, respectively. For the external dataset, the model achieved accuracy, specificity, F1-score, and AUC of 87.35%, 95.78%, 80.37%, and 0.848, respectively. These results demonstrate the model's high generalizability and prediction accuracy. A model integrating NLP and ML techniques enables rapid tiered medical treatment based on limited data from the emergency scene, with significant advantages in terms of prediction accuracy. (© 2025. The Author(s).) |
| References: | Ann Emerg Med. 2024 Aug;84(2):154-156. (PMID: 38795082) IEEE Rev Biomed Eng. 2021;14:156-180. (PMID: 32746371) Zhongguo Xiu Fu Chong Jian Wai Ke Za Zhi. 2023 Nov 15;37(11):1431-1437. (PMID: 37987056) BMC Emerg Med. 2024 Nov 18;24(1):219. (PMID: 39558255) JAMA. 1971 Jan 11;215(2):277-80. (PMID: 5107365) ACS Sens. 2023 Nov 24;8(11):4391-4401. (PMID: 37939316) J Trauma. 1974 Mar;14(3):187-96. (PMID: 4814394) JMIR Form Res. 2025 May 29;9:e67311. (PMID: 40440586) iScience. 2023 Jul 17;26(8):107407. (PMID: 37609632) Crit Care Med. 1999 May;27(5):985-8. (PMID: 10362424) Ann Transl Med. 2022 Oct;10(19):1060. (PMID: 36330417) Beijing Da Xue Xue Bao Yi Xue Ban. 2024 Feb 18;56(1):157-160. (PMID: 38318911) J Med Internet Res. 2023 May 23;25:e40031. (PMID: 36972306) Anesth Analg. 2024 Jun 1;138(6):1260-1266. (PMID: 38091502) |
| Contributed Indexing: | Keywords: Injury severity score; Machine learning; Natural language processing; Tiered medical treatment; Trauma |
| Entry Date(s): | Date Created: 20250711 Date Completed: 20251203 Latest Revision: 20251206 |
| Update Code: | 20251206 |
| PubMed Central ID: | PMC12675745 |
| DOI: | 10.1007/s11517-025-03414-x |
| PMID: | 40643792 |
| Databáze: | MEDLINE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | Trauma has become a major cause of increased morbidity and mortality worldwide. In emergency response, the classification of injuries is crucial as it helps to quickly determine the criticality of the injured, allocate rescue resources rationally, and decide the priority order of treatment. However, emergency scenes are often chaotic environments, making it difficult for rescue personnel to collect complete and accurate information about the injured in a short period. The combination of artificial intelligence and emergency rescue is gradually changing the rescue model, improving the efficiency of rescue operations. We selected data from 26,810 trauma patients admitted to Chongqing Daping Hospital between 2013 and 2024. We propose a fast tiered medical treatment method with a two-layer structure under emergency limited data conditions, which integrates natural language processing (NLP) and machine learning (ML) techniques. The tiered medical treatment model utilizes NLP to capture semantic features of unstructured text data, while utilizing four ML algorithms to process structured numerical data. Additionally, we conducted external validation using 245 data entries from the Chongqing Emergency Center. The experimental results show that gradient boosting and logistic regression have the best performance in the two-layer ML algorithms. Based on these two algorithms, our model outperformed the multilayer perceptron (MLP) model on the test dataset, achieving an accuracy of 91.17%, which is 4.33% higher than that of the MLP model. The specificity, F1-score, and AUC of our model were 97.06%, 86.85%, and 0.949, respectively. For the external dataset, the model achieved accuracy, specificity, F1-score, and AUC of 87.35%, 95.78%, 80.37%, and 0.848, respectively. These results demonstrate the model's high generalizability and prediction accuracy. A model integrating NLP and ML techniques enables rapid tiered medical treatment based on limited data from the emergency scene, with significant advantages in terms of prediction accuracy.<br /> (© 2025. The Author(s).) |
|---|---|
| ISSN: | 1741-0444 |
| DOI: | 10.1007/s11517-025-03414-x |