Unsupervised clustering identifies sub-phenotypes and reveals novel outcome predictors in patients with dialysis-requiring sepsis-associated acute kidney injury

Abstract

Introduction Heterogeneity exists in sepsis-associated acute kidney injury (SA-AKI). This study aimed to perform unsupervised consensus clustering in critically ill patients with dialysis-requiring SA-AKI. Patients and Methods This prospective observational cohort study included all septic patients, defined by the Sepsis-3 criteria, with dialysis-requiring SA-AKI in surgical intensive care units in Taiwan between 2009 and 2018. We employed unsupervised consensus clustering based on 23 clinical variables upon initializing renal replacement therapy. Multivariate-adjusted Cox regression models and Fine–Gray sub-distribution hazard models were built to test associations between cluster memberships with mortality and being free of dialysis at 90 days after hospital discharge, respectively. Results Consensus clustering among 999 enrolled patients identified three sub-phenotypes characterized with distinct clinical manifestations upon renal replacement therapy initiation ( n = 352, 396 and 251 in cluster 1, 2 and 3, respectively). They were followed for a median of 48 (interquartile range 9.5–128.5) days. Phenotypic cluster 1, featured by younger age, lower Charlson Comorbidity Index, higher baseline estimated glomerular filtration rate but with higher severity of acute illness was associated with an increased risk of death (adjusted hazard ratio of 3.05 [95% CI, 2.35–3.97]) and less probability to become free of dialysis (adjusted sub-distribution hazard ratio of 0.55 [95% CI, 0.38–0.8]) than cluster 3. By examining distinct features of the sub-phenotypes, we discovered that pre-dialysis hyperlactatemia ≥3.3 mmol/L was an independent outcome predictor. A clinical model developed to determine high-risk sub-phenotype 1 in this cohort (C-static 0.99) can identify a sub-phenotype with high in-hospital mortality risk (adjusted hazard ratio of 1.48 [95% CI, 1.25–1.74]) in another independent multi-centre SA-AKI cohort. Conclusions Our data-driven approach suggests sub-phenotypes with clinical relevance in dialysis-requiring SA-AKI and serves an outcome predictor. This strategy represents further development toward precision medicine in the definition of high-risk sub-phenotype in patients with SA-AKI. Key messages Unsupervised consensus clustering can identify sub-phenotypes of patients with SA-AKI and provide a risk prediction. Examining the features of patient heterogeneity contributes to the discovery of serum lactate levels ≥ 3.3 mmol/L upon initializing RRT as an independent outcome predictor. This data-driven approach can be useful for prognostication and lead to a better understanding of therapeutic strategies in heterogeneous clinical syndromes.

Sepsis-Associated Acute Kidney Injury: Where Are We Now?

“…Nevertheless, the choice of which fluids should be administered, for example, 0.9% saline versus colloids, depends upon various parameters. In early SA-AKI, a more aggressive fluid administration to restore hemodynamic stabilization seems mandatory, whereas in late SA-AKI, the main concern for clinicians is fluid overload [ 5 , 67 , 68 , 69 , 70 , 71 , 72 , 73 ]. Apart from this major difference between the needs in early versus late SA-AKI, a more personalized approach, bearing in mind the performance status of each patient as well as comorbidities, should be pursued.…”

“…The use of diuretics may be individualized as well. Regarding the administration of more specified fluids, such as hydroxyethyl starch, a synthetic colloid made of amylopectin, there is consensus that it should be avoided, as it has been related to an increased mortality and increased KRT in patients with sepsis [ 5 , 67 , 68 , 69 , 70 , 71 , 72 , 73 ]. However, in terms of supplementation with albumin, the results are controversial.…”

“…Notably, there is growing interest in the classification of sub-phenotypes among patients with SA-AKI [ 5 , 71 ]. Recently, Lai et al proposed the existence of three different sub-phenotypes in patients with SA-AKI [ 71 ].…”

“…Notably, there is growing interest in the classification of sub-phenotypes among patients with SA-AKI [ 5 , 71 ]. Recently, Lai et al proposed the existence of three different sub-phenotypes in patients with SA-AKI [ 71 ]. They have suggested that sub-phenotype 1 involved younger patients, with higher baseline levels of the estimated glomerular filtration rate (eGFR) and a lower Charlson Comorbidity Index (CCI) [ 71 , 92 ].…”

“…Recently, Lai et al proposed the existence of three different sub-phenotypes in patients with SA-AKI [ 71 ]. They have suggested that sub-phenotype 1 involved younger patients, with higher baseline levels of the estimated glomerular filtration rate (eGFR) and a lower Charlson Comorbidity Index (CCI) [ 71 , 92 ]. In their study, Lai et al used the CCI Calculator, which comprises a series of comorbidities, such as cardiovascular disease, renal disease, diabetes, etc.…”