Ramesh Karthik, Boussina Aaron, Shashikumar Supreeth P, Malhotra Atul, Longhurst Christopher A, Josef Christopher S, Quintero Kimberly, Del Rosso Jake, Nemati Shamim, Wardi Gabriel
School of Medicine, University of California San Diego, San Diego, CA.
Department of Medicine, University of California San Diego, San Diego, CA.
Crit Care Explor. 2025 Jun 4;7(6):e1276. doi: 10.1097/CCE.0000000000001276. eCollection 2025 Jun 1.
Sepsis is a major cause of morbidity and mortality, with early intervention shown to improve outcomes. Predictive modeling and artificial intelligence (AI) can aid in early sepsis recognition, but there remains a gap between algorithm development and clinical use. Despite the importance of user experience in adopting clinical predictive models, few studies have focused on provider acceptance and feedback.
To evaluate healthcare worker perception and acceptance of a deep learning sepsis prediction model in the emergency department (ED).
DESIGN, SETTING, AND PARTICIPANTS: COnformal Multidimensional Prediction Of SEpsis Risk (COMPOSER), a deep learning algorithm, is used at two EDs of a large academic medical center to predict sepsis before clear clinical presentation. An internally developed survey following the Checklist for Reporting Results of Internet E-Surveys was distributed to team members who received a COMPOSER alert.
Mann-Whitney U testing was performed on results stratified by provider experience.
A total of 114 responses were received: 76 from doctors of medicine/doctors of osteopathic medicine, 34 from registered nurses, and four from nurse practicioners/physician assistants. Of these, 53% were from providers with fewer than 5 years of experience. Seventy-seven percent of respondents had a positive or neutral perception of the alert's usefulness. Providers with 0-5 years of experience were more likely to expect sepsis after the alert (p = 0.021) and found the alert more useful (p = 0.016) compared with those with 6+ years of experience. Additionally, physicians with 0-5 years of experience were more likely to say the alert changed their patient management (p = 0.048).
Less experienced providers were more likely to perceive benefit from the alert, which was overall received favorably. Future AI implementations might consider tailored alert patterns and education to enhance reception and reduce fatigue.
脓毒症是发病和死亡的主要原因，早期干预可改善预后。预测建模和人工智能（AI）有助于早期识别脓毒症，但算法开发与临床应用之间仍存在差距。尽管用户体验在采用临床预测模型方面很重要，但很少有研究关注医疗服务提供者的接受度和反馈。
评估急诊科医护人员对深度学习脓毒症预测模型的认知和接受度。
设计、设置和参与者：在一家大型学术医疗中心的两个急诊科使用一种深度学习算法——脓毒症风险的共形多维预测（COMPOSER），在明确的临床表现出现之前预测脓毒症。根据互联网电子调查结果报告清单，向收到COMPOSER警报的团队成员分发了一份内部开发的调查问卷。
对按医疗服务提供者经验分层的结果进行曼-惠特尼U检验。
共收到114份回复：76份来自医学博士/整骨医学博士，34份来自注册护士，4份来自执业护士/医师助理。其中，53%来自经验少于5年的医疗服务提供者。77%的受访者对警报的有用性持积极或中性看法。与经验超过6年的医疗服务提供者相比，经验在0至5年的医疗服务提供者在收到警报后更有可能预期患者患有脓毒症（p = 0.021），并且认为警报更有用（p = 0.016）。此外，经验在0至5年的医生更有可能表示警报改变了他们对患者的管理方式（p = 0.048）。
经验较少的医疗服务提供者更有可能从警报中感知到益处，总体上对警报的接受度良好。未来人工智能的应用可能需要考虑定制警报模式和开展相关教育，以提高接受度并减少疲劳感。
