AI Triage System for Outpatient Care
Author Information
Author(s): de Azevedo Cardoso Taiane, Ćirković Aleksandar, Chen Ken, Zhang Yijue, Yang Lingrui, Pang Jiali, Zuo Song, Xu Jian, Jin Wei, Zuo Feng, Xue Kui, Xiao Zhongzhou, Peng Xinwei, Xu Jie, Zhang Xiaofan, Chen Ruiyao, Luo Shuqing, Zhang Shaoting, Sun Xin
Primary Institution: Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine
Hypothesis
Can an AI-based triage system improve outpatient department recommendations in Chinese tertiary hospitals?
Conclusion
The triage system demonstrates high accuracy in recommending outpatient departments and reduces cancellation rates and time consumption.
Supporting Evidence
- The triage system reduced the cancellation rate from 3.83% to 3.53%.
- The system achieved an accuracy of 91.53% in recommending departments.
- Users of the triage system increased from 3590 in January 2023 to 6953 in April 2023.
- The triage system outperformed nurses in recall@3 and time consumption.
- Children made up 54.85% of the training data set.
Takeaway
This study created a smart system that helps patients find the right doctor faster, making it easier for them to get care.
Methodology
The study used electronic medical records and medical dialogue groups to develop and validate an AI-based triage system.
Potential Biases
Potential bias in comparing the triage system's performance with that of triage nurses due to differences in patient interaction.
Limitations
The study was limited to data from a single hospital, which may not represent other settings.
Participant Demographics
The sample included 149 adults and 157 children.
Statistical Information
P-Value
p<0.001
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website