ICU开放数据库用于脓毒症人工智能研究:创新与数据质量挑战的平衡
该研究采用描述性比较设计,评估MIMIC-IV(2008-2019)、eICU-CRD(2014-2015)和AmsterdamUMCdb(2003-2016)三个开放ICU数据库用于脓毒症AI研究的适用性,聚焦数据完整性、术语一致性、结构冗余和临床可解释性。结果显示各库均存在显著异质性:MIMIC-IV用药途径缺失49%、剂量缺失58%,微生物数量字段缺失99.9%,诊断字符串达17,557个唯一值并含174个近重复变体;eICU-CRD有1.9%入院无诊断、7,319次住院的ICU与院内死亡率不一致;AmsterdamUMCdb结构不一致较少但人口学信息有限、61.4%入院无诊断且中英荷兰语术语混用。三个数据库均缺乏可靠的脓毒症诊断时间戳,限制早期干预分析。结论提示需严格预处理并推动标准化数据采集,以提高AI驱动脓毒症研究的有效性和泛化性。
要点
- MIMIC-IV用药途径缺失49%、剂量缺失58%,微生物数量字段缺失99.9%,用于脓毒症AI建模前需重点处理这些缺失。
- MIMIC-IV诊断字段存在17,557个唯一字符串和174个近重复变体,诊断编码需先做规范化归并。
- eICU-CRD有1.9%入院无诊断,且7,319次住院的ICU死亡率与院内死亡率不一致,结局定义需核实。
- AmsterdamUMCdb结构不一致较少,但61.4%入院无诊断且英语-荷兰语术语混用,人口学信息有限。
- 三个数据库均缺乏可靠的脓毒症诊断时间戳,无法可靠分析早期干预时机,相关AI研究结论需谨慎解读。
适用人群与场景
- 适用场景为使用MIMIC-IV(2008-2019)、eICU-CRD(2014-2015)或AmsterdamUMCdb(2003-2016)开展脓毒症人工智能研究的ICU数据使用者;原文未提及具体患者纳入或排除人群。
诊断标准与关键阈值
- 原文未提及脓毒症诊断标准、评分界值或启动/停止阈值。
处置流程与药物剂量
- 原文未提及
红旗征与不能漏的情况
- 原文未提及临床红旗征或需立刻处理的情况。
研究设计与关键结果
- 研究类型为描述性比较设计,评估三个开放ICU数据库(MIMIC-IV 2008-2019、eICU-CRD 2014-2015、AmsterdamUMCdb 2003-2016),原文未报告样本量和中心数。
- MIMIC-IV用药途径缺失49%、剂量缺失58%,微生物数量字段缺失99.9%,诊断字段有17,557个唯一字符串和174个近重复变体。
- eICU-CRD有1.9%入院缺乏诊断,7,319次住院的ICU死亡率与院内死亡率不一致。
- AmsterdamUMCdb结构不一致较少但人口学信息有限,61.4%入院无诊断,且存在英语-荷兰语术语混用。
- 三个数据库均缺乏可靠的脓毒症诊断时间戳,限制早期干预分析。
证据类型、等级与局限
- 证据类型为描述性比较研究(非RCT、非系统评价),原文未给出证据等级或推荐强度;局限包括仅评估三个开放数据库、未报告样本量与中心数、为描述性设计无法推断因果。
对床旁实践的改变
- 使用上述数据库开展脓毒症AI研究前,须对用药途径、剂量、微生物数量等高频缺失字段做严格预处理,否则模型有效性存疑。
- 诊断字段需先做字符串归并(如MIMIC-IV的17,557个唯一字符串与174个近重复变体),不能直接以原始诊断编码建模。
- 涉及死亡结局时需核对eICU-CRD中ICU死亡率与院内死亡率不一致的7,319次住院,明确结局定义。
- 因三个数据库均缺乏可靠脓毒症诊断时间戳,不宜用其做早期干预时机相关分析,或需在结论中明确该局限。
- AmsterdamUMCdb因61.4%入院无诊断及英荷术语混用,用于脓毒症研究时需额外术语映射和人群筛选。
指南或共识出处
- 原文未提及指南或共识名称;文献来源为Crit Care Med。
以上提炼依据论文摘要(全文未开放获取,或许可不允许翻译转载);全文请点「阅读原文」。
英文原文(摘要)· 点击展开
OBJECTIVES: To evaluate the suitability of three major open-access ICU databases (Medical Information Mart for Intensive Care IV [MIMIC-IV], eICU Collaborative Research Database [eICU-CRD], and Amsterdam University Medical Center Database [AmsterdamUMCdb]) for artificial intelligence (AI)-based sepsis research, with a focus on data completeness, internal consistency, terminological standardization, and structural redundancy affecting clinical interpretability and reproducibility.
DESIGN: A descriptive comparative design was employed to evaluate data completeness, terminological consistency, structural integrity, and clinical usability, with emphasis on sepsis-related variables such as antimicrobial administration, hemodynamic support, and mortality indicators.
SETTING: Open-access ICU electronic health record databases including MIMIC-IV (2008-2019), eICU-CRD (2014-2015), and AmsterdamUMCdb (2003-2016), accessed under credentialed use agreements. Documentation, schema, and metadata were reviewed in parallel to primary datasets.
INTERVENTIONS: Structured queries and descriptive analyses were performed to quantify missing values, distinct diagnosis strings, medication administration completeness, and redundancy of mortality markers. Manual semantic inspection of terminology, units, and coding ( International Classification of Diseases , 9th revision/10th revision) was applied to evaluate inconsistency and typographical variability. Comparisons were made across key clinical dimensions including diagnosis, mortality, microbiology, and antibiotic administration.
MEASUREMENTS AND MAIN RESULTS: Marked heterogeneity and data quality limitations were identified. MIMIC-IV demonstrated extensive missingness in medication route (49%) and dose (58%), 99.9% missing fields in microbiology quantity, and diagnosis redundancy with 17,557 unique strings and 174 near-duplicate variants. eICU-CRD exhibited 1.9% admissions lacking diagnosis and discordance between ICU and hospital mortality in 7,319 stays. AmsterdamUMCdb showed fewer structural inconsistencies but limited demographics and the highest proportion of admissions without diagnosis (61.4%), complicated by mixed English-Dutch terminology. All three databases lacked reliable sepsis diagnosis timestamps, constraining analysis of early intervention.
CONCLUSIONS: Although widely used and valuable for sepsis research, open-access ICU databases exhibit substantial missingness, redundancy, semantic variability, and demographic imbalance. These limitations require rigorous preprocessing and highlight the need for standardized data collection to improve the validity and generalizability of AI-driven sepsis studies.
参考来源
- Jegou J, Manolescu I, Ruckly S, et al. ICU Open-Access Databases for Artificial Intelligence in Sepsis: Balancing Innovation With Data Quality Challenges. Crit Care Med. 2026. PMID: 42635479. doi:10.1097/CCM.0000000000007319
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。