Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York.
Hasso Plattner Institute of Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York.
Clin J Am Soc Nephrol. 2020 Nov 6;15(11):1557-1565. doi: 10.2215/CJN.09330819. Epub 2020 Oct 8.
Sepsis-associated AKI is a heterogeneous clinical entity. We aimed to agnostically identify sepsis-associated AKI subphenotypes using deep learning on routinely collected data in electronic health records.
DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: We used the Medical Information Mart for Intensive Care III database, which consists of electronic health record data from intensive care units in a tertiary care hospital in the United States. We included patients ≥18 years with sepsis who developed AKI within 48 hours of intensive care unit admission. We then used deep learning to utilize all available vital signs, laboratory measurements, and comorbidities to identify subphenotypes. Outcomes were mortality 28 days after AKI and dialysis requirement.
We identified 4001 patients with sepsis-associated AKI. We utilized 2546 combined features for -means clustering, identifying three subphenotypes. Subphenotype 1 had 1443 patients, and subphenotype 2 had 1898 patients, whereas subphenotype 3 had 660 patients. Subphenotype 1 had the lowest proportion of liver disease and lowest Simplified Acute Physiology Score II scores compared with subphenotypes 2 and 3. The proportions of patients with CKD were similar between subphenotypes 1 and 3 (15%) but highest in subphenotype 2 (21%). Subphenotype 1 had lower median bilirubin levels, aspartate aminotransferase, and alanine aminotransferase compared with subphenotypes 2 and 3. Patients in subphenotype 1 also had lower median lactate, lactate dehydrogenase, and white blood cell count than patients in subphenotypes 2 and 3. Subphenotype 1 also had lower creatinine and BUN than subphenotypes 2 and 3. Dialysis requirement was lowest in subphenotype 1 (4% versus 7% [subphenotype 2] versus 26% [subphenotype 3]). The mortality 28 days after AKI was lowest in subphenotype 1 (23% versus 35% [subphenotype 2] versus 49% [subphenotype 3]). After adjustment, the adjusted odds ratio for mortality for subphenotype 3, with subphenotype 1 as a reference, was 1.9 (95% confidence interval, 1.5 to 2.4).
Utilizing routinely collected laboratory variables, vital signs, and comorbidities, we were able to identify three distinct subphenotypes of sepsis-associated AKI with differing outcomes.
脓毒症相关性急性肾损伤（AKI）是一种异质性的临床实体。我们旨在通过对电子病历中常规收集的数据进行深度学习，来发现脓毒症相关性 AKI 的亚表型。
方法、设置、参与者和测量：我们使用了医疗信息集市重症监护 III 数据库（Medical Information Mart for Intensive Care III database），该数据库由美国一家三级保健医院重症监护病房的电子病历数据组成。我们纳入了年龄≥18 岁、在入住重症监护病房后 48 小时内发生 AKI 的脓毒症患者。然后，我们使用深度学习方法利用所有可用的生命体征、实验室测量值和合并症来识别亚表型。结局为 AKI 后 28 天的死亡率和透析需求。
我们共纳入了 4001 例脓毒症相关性 AKI 患者。我们使用了 2546 个组合特征进行均值聚类，共识别出 3 个亚表型。表型 1 有 1443 例患者，表型 2 有 1898 例，表型 3 有 660 例。与表型 2 和表型 3 相比，表型 1 的肝病比例最低，简化急性生理学评分 II 评分也最低。表型 1 和表型 3 的慢性肾脏病（CKD）患者比例相似（15%），但表型 2 的比例最高（21%）。表型 1 的中位胆红素、天门冬氨酸氨基转移酶和丙氨酸氨基转移酶水平低于表型 2 和表型 3。与表型 2 和表型 3 相比，表型 1 的患者中位乳酸、乳酸脱氢酶和白细胞计数也较低。表型 1 的肌酐和血尿素氮也低于表型 2 和表型 3。表型 1 的透析需求最低（4%，表型 2 为 7%，表型 3 为 26%）。AKI 后 28 天死亡率最低的是表型 1（23%，表型 2 为 35%，表型 3 为 49%）。调整后，表型 3 与表型 1 相比，死亡的调整比值比为 1.9（95%置信区间，1.5 至 2.4）。
通过利用常规收集的实验室变量、生命体征和合并症，我们能够识别出脓毒症相关性 AKI 的三个不同的亚表型，这些亚表型的结局不同。
Zotero 插件