Application of pretrained model based on electronic medical record in recognition of acute respiratory infection.
- Author:
Meng Meng JIA
1
;
Xi Zhao LIU
2
;
Li QI
3
;
Pei Xi DAI
1
;
Qin LI
3
;
Minig Yue JIANG
1
;
Wen Ge TANG
3
;
Ming Wei TAN
2
;
Ting Ting LI
3
;
Bin Shan JIANG
1
;
Yu Hua REN
4
;
Jun Li RAO
2
;
Zhao Yang YAN
4
;
Yan Lin CAO
1
;
Wei Zhong YANG
1
;
Hua RAN
4
;
Luzhao FENG
1
Author Information
- Publication Type:Journal Article
- MeSH: Adult; Male; Female; Humans; Electronic Health Records; Respiratory Tract Infections/diagnosis*; Outpatients
- From: Chinese Journal of Preventive Medicine 2022;56(11):1543-1548
- CountryChina
- Language:Chinese
- Abstract: Objective: To evaluate the recognition of acute respiratory infection (ARI) by a pretrained model based on electronic medical records (EMRs). Methods: 38 581 EMRs were obtained from Chongqing University Three Gorges Hospital in December 2021. Bidirectional encoder representation from transformers (BERT) pretrained model was used to identify ARI in EMRs. The results of medical professionals were considered as the gold standard to calculate the sensitivity, specificity, Kappa value, and area under the curve of the receiver operating characteristic (AUC). Results: There were 3 817 EMRs in the test set, with 1 200 ARIs. A total of 1 205 cases were determined as ARI by the model, with a sensitivity of 92.67% (1 112/1 200) and a specificity of 96.45% (2 524/2 617). The model identified ARI with similar accuracy in males and females (AUCs 0.95 and 0.94, respectively), and was more accurate in identifying ARI cases in those aged less than 18 than in adults 18-59 and adults 60 and older (AUCs 0.94, 0.89 and 0.94, respectively). The current model had a better identification of ARIs in outpatient patients than that in hospitalized patients, with AUCs of 0.74 and 0.95, respectively. Conclusion: The use of the BERT pretrained model based on EMRs has a good performance in the recognition of ARI cases, especially for the outpatients and juveniles. It shows a great potential to be applied to the monitoring of ARI cases in medical institutions.
