Journal of Systems & Management ›› 2025, Vol. 34 ›› Issue (5): 1327-1341.DOI: 10.3969/j.issn.2097-4558.2025.05.011

Previous Articles     Next Articles

Application Research of AI-Assisted Detection Based on Queuing Theory in Medical Detection

ZHAN Wentao1, YUAN Xuchuan2, BAI Xue1, ZHENG Siyi3,LI Weifeng1, JIANG Minghui1, LIU Jida1#br#   

  1. 1. School of Management, Harbin Institute of Technology, Harbin 150006, China; 2. School of Business, University of Social Sciences, Singapore 599494, Singapore; 3. Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, China
  • Received:2024-01-10 Revised:2024-11-20 Online:2025-09-28 Published:2025-10-16

医疗检测中基于排队理论的AI辅助检测应用

詹文韬1,袁绪川2,白雪1,郑思怡3,李蔚峰1,姜明辉1,刘纪达1
  

  1. 1.哈尔滨工业大学 经济与管理学院,哈尔滨 150001;2.新加坡社科大学 商学院,新加坡 599494;
    3.华中科技大学 同济医学院,武汉 430030
  • 基金资助:
    国家社会科学基金重大项目(17ZDA030);国家自然科学基金重点项目(71831005);国家自然科学基金青年基金资助项目(71502044)

Abstract: With the rapid development of artificial intelligence (AI) technology, AI-assisted detection has shown great potential in the medical field. Medical testing focuses on patient queue congestion, as well as the efficiency and accuracy of detection. Therefore, this paper develops a medical detection model under AI-assisted detection based on the queuing theory, considering the heterogeneity between traditional doctors and AI specialist doctors. Traditional doctors use conventional methods for detection, while AI specialist doctors conduct detection based on information from AI-assisted detection. The findings indicate that AI-assisted detection does not necessarily improve the detection capacity of the medical system. It only enhances the overall detection capacity when the throughput of the detection systems of traditional doctors and AI specialist doctors does not differ significantly. Furthermore, the heterogeneity of patients can lead to a decrease in system throughput, hindering the application of AI-assisted detection. Additionally, when AI-assisted detection can improve system throughput, public hospitals are more inclined to adopt AI-assisted detection compared to private hospitals, and vice versa. This paper provides substantial theoretical support for strategies and management decisions in using AI in medical testing, and offers valuable guidance for the optimization of future medical testing.

Key words: intelligent medical treatment, queuing theory, decision making, artificial intelligence (AI)-assisted detection, physician heterogeneity

摘要: 随着人工智能(AI)技术的迅速发展,AI辅助检测在医疗领域中的应用潜力日益显著。医疗检测系统通常关注患者队列的拥挤程度以及检测的效率与准确性。本研究基于排队理论构建了AI辅助检测模型,并考虑了传统医生与AI专科医生之间的异质性影响。在该模型中,传统医生采用常规检测方法,而AI专科医生则依托AI辅助检测技术进行诊断。研究结果表明:AI辅助检测并非总能提升医疗系统的检测能力,仅当传统医生与AI专科医生的检测系统吞吐量差异较小时,AI技术才能显著提高系统整体的检测能力;患者异质性会降低检测系统吞吐量,从而制约AI辅助检测的实际效果。此外,研究还发现:当AI辅助检测能够提升系统检测吞吐量时,公立医疗机构比私立医疗机构更倾向于采用该技术;反之,则私立医疗机构采纳意愿更高。本研究为医疗机构采用AI辅助检测时的战略决策提供了理论支持,并为未来医疗检测系统的优化方向提供了参考。

关键词: 智能医疗, 排队论, 决策制定, AI辅助检测, 医生异质性

CLC Number: