Infectious Diseases Unit, Hospital Universitario HM Montepríncipe, Madrid, Spain.
Research and Innovation Department, Pragmatech AI Solutions, Oviedo, Spain.
Antimicrob Agents Chemother. 2024 Oct 8;68(10):e0077724. doi: 10.1128/aac.00777-24. Epub 2024 Aug 28.
Errors in antibiotic prescriptions are frequent, often resulting from the inadequate coverage of the infection-causative microorganism. The efficacy of iAST, a machine-learning-based software offering empirical and organism-targeted antibiotic recommendations, was assessed. The study was conducted in a 12-hospital Spanish institution. After model fine-tuning with 27,531 historical antibiograms, 325 consecutive patients with acute infections were selected for retrospective validation. The primary endpoint was comparing each of the top three of iAST's antibiotic recommendations' success rates (confirmed by antibiogram results) with the antibiotic prescribed by the physicians. Secondary endpoints included examining the same hypothesis within specific study population subgroups and assessing antibiotic stewardship by comparing the percentage of antibiotics recommended that belonged to different World Health Organization AWaRe groups within each arm of the study. All of iAST first three recommendations were non-inferior to doctor prescription in the primary endpoint analysis population as well as the secondary endpoint. The overall success rate of doctors' empirical treatment was 68.93%, while that of the first three iAST options was 91.06% ( < 0.001), 90.63% ( < 0.001), and 91.06% ( < 001), respectively. For organism-targeted therapy, the doctor's overall success rate was 84.16%, and that of the first three ranked iAST options was 97.83% ( < 0.001), 94.09% ( < 0.001), and 91.30% ( < 0.001), respectively. In empirical therapy, compared to physician prescriptions, iAST demonstrated a greater propensity to recommend access antibiotics, fewer watch antibiotics, and higher reserve antibiotics. In organism-targeted therapy, iAST advised a higher utilization of access antibiotics. The present study demonstrates iAST accuracy in predicting antibiotic susceptibility, showcasing its potential to promote effective antibiotic stewardship.
This study is registered with ClinicalTrials.gov as NCT06174519.
抗生素处方中的错误很常见，通常是由于感染病原体的覆盖范围不足所致。评估了基于机器学习的软件 iAST 提供经验性和针对病原体的抗生素推荐的疗效。这项研究在西班牙的一家 12 家医院进行。在对 27531 份历史抗生素药敏试验数据进行模型微调后，选择了 325 名连续的急性感染患者进行回顾性验证。主要终点是比较 iAST 推荐的前三种抗生素的成功率（根据抗生素药敏试验结果确定）与医生开出的抗生素。次要终点包括在特定研究人群亚组中检验相同假设，并通过比较研究中每个手臂中推荐的抗生素在不同世界卫生组织 AWaRe 组中的百分比来评估抗生素管理。在主要终点分析人群和次要终点中，iAST 的前三种推荐方案均不劣于医生处方。医生经验性治疗的总成功率为 68.93%，而 iAST 的前三种选择的成功率分别为 91.06%（<0.001）、90.63%（<0.001）和 91.06%（<001）。对于靶向病原体治疗，医生的总成功率为 84.16%，而排名前三的 iAST 选择的成功率分别为 97.83%（<0.001）、94.09%（<0.001）和 91.30%（<0.001）。在经验性治疗中，与医生处方相比，iAST 更倾向于推荐使用抗生素，使用观察性抗生素的比例更低，储备抗生素的比例更高。在靶向病原体治疗中，iAST 建议更多地使用抗生素。本研究表明 iAST 在预测抗生素敏感性方面具有较高的准确性，展示了其在促进有效抗生素管理方面的潜力。
本研究在 ClinicalTrials.gov 注册为 NCT06174519。
