Lopes João, Guimarães Tiago, Duarte Júlio, Santos Manuel
ALGORITMI Research Centre, University of Minho, Rua da Universidade, Braga, 4800-058, Portugal, 351 934373667.
JMIR Med Inform. 2025 Feb 11;13:e57231. doi: 10.2196/57231.
BACKGROUND: Health care is facing many challenges. The recent pandemic has caused a global reflection on how clinical and organizational processes should be organized, which requires the optimization of decision-making among managers and health care professionals to deliver care that is increasingly patient-centered. The efficiency of surgical scheduling is particularly critical, as it affects waiting list management and is susceptible to suboptimal decisions due to its complexity and constraints. OBJECTIVE: In this study, in collaboration with one of the leading hospitals in Portugal, Centro Hospitalar e Universitário de Santo António (CHUdSA), a heuristic approach is proposed to optimize the management of the surgical center. METHODS: CHUdSA's surgical scheduling process was analyzed over a specific period. By testing an optimization approach, the research team was able to prove the potential of artificial intelligence (AI)-based heuristic models in minimizing scheduling penalties-the financial costs incurred by procedures that were not scheduled on time. RESULTS: The application of this approach demonstrated potential for significant improvements in scheduling efficiency. Notably, the implementation of the hill climbing (HC) and simulated annealing (SA) algorithms stood out in this implementation and minimized the scheduling penalty, scheduling 96.7% (415/429) and 84.4% (362/429) of surgeries, respectively. For the HC algorithm, the penalty score was 0 in the urology, obesity, and pediatric plastic surgery medical specialties. For the SA algorithm, the penalty score was 5100 in urology, 1240 in obesity, and 30 in pediatric plastic surgery. Together, this highlighted the ability of AI-heuristics to optimize the efficiency of this process and allowed for the scheduling of surgeries at closer dates compared to the manual method used by hospital professionals. CONCLUSIONS: Integrating these solutions into the surgical scheduling process increases efficiency and reduces costs. The practical implications are significant. By implementing these AI-driven strategies, hospitals can minimize patient wait times, maximize resource use, and enhance surgical outcomes through improved planning. This development highlights how AI algorithms can effectively adapt to changing health care environments, having a transformative impact.
背景:医疗保健面临诸多挑战。近期的疫情引发了全球对于临床和组织流程应如何安排的反思,这需要管理者和医疗保健专业人员优化决策,以提供日益以患者为中心的护理。手术排期的效率尤为关键,因为它影响着候诊名单管理,且由于其复杂性和限制条件,容易出现决策欠佳的情况。 目的:在本研究中,与葡萄牙领先医院之一圣安东尼奥大学中心医院(CHUdSA)合作,提出一种启发式方法来优化手术中心的管理。 方法:在特定时间段内分析了CHUdSA的手术排期流程。通过测试一种优化方法,研究团队能够证明基于人工智能(AI)的启发式模型在最小化排期处罚(即未按时排期的手术所产生的财务成本)方面的潜力。 结果:该方法的应用显示出排期效率有显著提高的潜力。值得注意的是,爬山法(HC)和模拟退火算法(SA)在此次实施中表现突出,将排期处罚降至最低,分别安排了96.7%(415/429)和84.4%(362/429)的手术。对于HC算法,泌尿外科、肥胖症和小儿整形外科专业的处罚分数为0。对于SA算法,泌尿外科的处罚分数为5100,肥胖症为1240,小儿整形外科为30。这共同凸显了人工智能启发式方法优化该流程效率的能力,并且与医院专业人员使用的手动方法相比,能够安排更接近的手术日期。 结论:将这些解决方案整合到手术排期流程中可提高效率并降低成本。实际影响重大。通过实施这些由人工智能驱动的策略,医院可以最大限度地减少患者等待时间,最大化资源利用,并通过改进规划提高手术效果。这一进展凸显了人工智能算法如何能够有效适应不断变化的医疗保健环境,产生变革性影响。
Health Care Manag Sci. 2015-9
J Med Syst. 2025-3-21
BMC Health Serv Res. 2020-7-23
Artif Intell Med. 2015-7
J Med Syst. 2013-6
J Med Internet Res. 2022-10-5
Med J Armed Forces India. 2022-9
J Healthc Inform Res. 2018-5-22
Health Care Manag Sci. 2013-6-20