基于人工智能的成人常见感染抗生素治疗临床决策支持系统：从开发到临床实施的一项系统综述。
完整摘要 · 中文译文
背景：抗菌药物耐药性是全球死亡的主要原因之一，已提出基于人工智能（AI）的临床决策支持系统（CDSS）来指导抗生素处方。已开发并验证了若干用于抗生素决策的AI模型，但其在临床实践中的实际部署及对患者结局的影响尚未得到系统描述。 目的：识别、分类并评价评估基于AI的CDSS用于住院成人常见感染抗生素治疗的研究，并按临床实施水平分层。 方法：检索策略的制定始于2026年6月7日；在提交PROSPERO记录后，于2026年6月28日执行了对PubMed/MEDLINE、Scopus、Web of Science Core Collection和Embase的最终检索。四名评价者独立筛选记录并评估报告。研究被分类为已部署于临床实践（1级）、未部署情况下对照医师决策进行评估（2级），或通过回顾性模拟进行测试（3级）。偏倚风险酌情采用RoB 2、ROBINS-I或PROBAST评估。由于临床和方法学异质性，对研究结果进行叙述性综合，并进行结局特异性GRADE评估。 结果：在识别的1,157条记录中，10项研究符合纳入标准：3项为1级（30%），4项为2级（40%），3项为3级（30%）。三项已部署的研究评估了肺炎，主要为肺部嗜麦芽窄食单胞菌感染，以及金黄色葡萄球菌 ba 菌血症，并报告了在死亡率、医院流程、处方或用药安全方面的有利信号。Kanjilal 等发表的一篇会议摘要被纳入，作为一项对 29,508 例社区起病脓毒症成人进行的 3 级回顾性评估。在采用 PROBAST 评估的 7 项 2/3 级研究中，3 项被归为低偏倚风险，3 项在预先设定的描述性调整下被归为中等偏倚风险，1 项被归为高总体偏倚风险。死亡率/生存率的确定性为低，其余临床相关结局的确定性为极低。 结论：10 项纳入研究中有 3 项达到临床部署，而 7 项仍未部署。已部署系统显示出有利的结局和过程信号，但证据具有异质性，且根据结局不同，确定性为低至极低。在将计算性能解释为临床有效性之前，需要对已部署系统进行前瞻性多中心评价。 系统综述注册：https://www.crd.york.ac.uk/PROSPERO/view/CRD420261435593，标识符 CRD420261435593。
完整摘要 · 英文原文
BACKGROUND: Antimicrobial resistance is among the leading causes of global mortality, and artificial intelligence (AI)-based clinical decision support systems (CDSS) have been proposed to guide antibiotic prescribing. Several AI models for antibiotic decision-making have been developed and validated, but their actual deployment in clinical practice and effect on patient outcomes have not been systematically characterized. OBJECTIVE: To identify, classify, and appraise studies evaluating AI-based CDSS for antibiotic therapy in hospitalized adults with common infections, stratified by level of clinical implementation. METHODS: Search-strategy development began on June 7, 2026; definitive searches of PubMed/MEDLINE, Scopus, Web of Science Core Collection, and Embase were executed on June 28, 2026, after submission of the PROSPERO record. Four reviewers independently screened records and assessed reports. Studies were classified as deployed in clinical practice (Level 1), evaluated against physicians' decisions without deployment (Level 2), or tested through retrospective simulation (Level 3). Risk of bias was assessed with RoB 2, ROBINS-I, or PROBAST, as appropriate. Owing to clinical and methodological heterogeneity, findings were synthesized narratively, with an outcome-specific GRADE assessment. RESULTS: Of 1,157 records identified, 10 studies met the inclusion criteria: three Level 1 (30%), four Level 2 (40%), and three Level 3 (30%). The three deployed studies evaluated pneumonia, predominantly pulmonary Stenotrophomonas maltophilia infection, and Staphylococcus aureus bacteremia and reported favorable signals for mortality, hospital processes, prescribing, or medication safety. Kanjilal et al., a published conference abstract, was included as a Level 3 retrospective evaluation of 29,508 adults with community-onset sepsis. Among the seven Level 2/3 studies assessed with PROBAST, three were classified as low, three as moderate under the prespecified descriptive adaptation, and one as high overall risk of bias. Certainty was low for mortality/survival and very low for the remaining clinically relevant outcomes. CONCLUSIONS: Three of 10 included studies reached clinical deployment, whereas seven remained non-deployed. Deployed systems showed favorable outcome and process signals, but the evidence was heterogeneous and of low to very-low certainty, depending on the outcome. Prospective multicenter evaluations of deployed systems are required before computational performance can be interpreted as clinical effectiveness. SYSTEMATIC REVIEW REGISTRATION: https://www.crd.york.ac.uk/PROSPERO/view/CRD420261435593, identifier CRD420261435593.