Gross Ben J, Donahue Allison, Ford James S, Lu Xiaolei, Boussina Aaron, Malhotra Atul, Zheng Kai, Nemati Shamim, Wardi Gabriel
Res Sq. 2025 Apr 1:rs.3.rs-6123541. doi: 10.21203/rs.3.rs-6123541/v1.
The current Surviving Sepsis Campaign (SSC) guidelines provide recommendations on timing of administering antibiotics in sepsis patients based on probability of sepsis and presence of shock. However, there have been minimal efforts to stratify patients objectively into these groups and describe patient outcomes as a function of antibiotic timing recommendations based on risk stratification using this approach. We conducted an observational cohort study using prospectively applied patient data from two large health systems using patient encounters between 2016 and 2024. At the time of clinical suspicion of sepsis, two deep learning (DL) models were used to stratify patients objectively into groups analogous to the SSC risk groups, based on a patient's likelihood of having sepsis and likelihood of developing shock. These risk groups were: 1) shock likely to develop and sepsis probable, 2) shock likely to develop and sepsis possible, 3) shock unlikely to develop and sepsis probable, and 4) shock unlikely to develop and sepsis possible. The primary outcome was short-term mortality, a composite of in-hospital mortality and transition to hospice care, across each risk group. We identified 34,163 adult patients with potential sepsis. At the development site, risk group mortality rates (%) and median time to antibiotics [IQR] were as follows: 1) 23.1%, 1.7 [1.0 - 3.1] hours; 17.7%, 3.0 [1.7 - 6.2] hours; 5.0%, 2.8 [1.5 - 5.1] hours; and 1.9%, 4.6 [2.7 - 8.0] hours. Results from the validation site were similar. Mortality rates were similar for patients with probable sepsis unlikely to develop shock regardless of antibiotic administration within 1 or 3 hours from triage. : Our results suggest that patients who are at low risk of developing shock, regardless of their likelihood of having sepsis, had similar rates of mortality in the 1-hour vs 3-hour time to antibiotic administration groups. Thus, a more lenient time to antibiotic administration could allow for more detailed evaluations and judicious administration of antibiotics, without impacting patient mortality, although we did not assess for causation. Additional prospective studies are required to validate these findings.
当前的拯救脓毒症运动（SSC）指南基于脓毒症的可能性和休克的存在，就脓毒症患者使用抗生素的时机提供了建议。然而，在将患者客观地分层到这些组中，并根据使用这种方法的风险分层，将患者结局描述为抗生素时机建议的函数方面，所做的努力微乎其微。我们进行了一项观察性队列研究，使用了来自两个大型医疗系统的前瞻性应用患者数据，这些数据来自2016年至2024年期间的患者就诊情况。在临床怀疑脓毒症时，使用两个深度学习（DL）模型根据患者患脓毒症的可能性和发生休克的可能性，将患者客观地分层到与SSC风险组类似的组中。这些风险组为：1）可能发生休克且可能患脓毒症，2）可能发生休克且可能患脓毒症，3）不太可能发生休克且可能患脓毒症，4）不太可能发生休克且可能患脓毒症。主要结局是每个风险组的短期死亡率，即住院死亡率和转至临终关怀的综合情况。我们确定了34163例有潜在脓毒症的成年患者。在开发地点，风险组的死亡率（%）和使用抗生素的中位时间[四分位间距]如下：1）23.1%，1.7[1.0 - 3.1]小时；17.7%，3.0[1.7 - 6.2]小时；5.0%，2.8[1.5 - 5.1]小时；1.9%，4.6[2.7 - 8.0]小时。验证地点的结果相似。对于不太可能发生休克的可能患脓毒症的患者，无论从分诊开始1小时内还是3小时内使用抗生素，死亡率相似。我们的结果表明，无论患脓毒症的可能性如何，发生休克风险低的患者在抗生素给药1小时组和3小时组中的死亡率相似。因此，更宽松的抗生素给药时间可以允许进行更详细的评估和明智地使用抗生素，而不会影响患者死亡率，尽管我们没有评估因果关系。需要更多的前瞻性研究来验证这些发现。
