Systematic comparison of routine laboratory measurements with in-hospital mortality: ICU-Labome, a large cohort study of critically ill patients

Alkozai, Edris M.; Mahmoodi, Bakhtawar K.; Decruyenaere, Johan; Porte, Robert J.; Lansink‐Hartgring, Annemieke Oude; Lisman, Ton; Nijsten, Maarten W. N.

doi:10.1515/cclm-2016-1028

Cited by 7 publications

(7 citation statements)

References 34 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we complemented the descriptive statistics of each cluster with SHAP values to establish the directionality of the association between high and low values of a variable and cluster membership. For example, membership of clusters with higher mortality risk was associated with increased ASAT and LDH, which are known biomarkers of myocardial ischemia and have also been shown to be positively correlated with ICU mortality 14 , 26 – 29 . Likewise, patients were more likely to be in the cluster with the lowest mortality risk (cluster 4) when their albumin, hemoglobin, and pO 2 values were higher, as well as when their liver function was better.…”

Section: Discussionmentioning

confidence: 99%

“…variables for which no measurements were registered at any moment during ICU stay) were excluded from the analysis. Missing laboratory data were imputed using a rolling mean based on ICU-specific values 14 . For other variables, iterative imputation with 10 iterations (a method similar to multivariate imputation by chained equations) was used 15 .…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering

Forte

Yeshmagambetova

Grinten

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Critically ill patients constitute a highly heterogeneous population, with seemingly distinct patients having similar outcomes, and patients with the same admission diagnosis having opposite clinical trajectories. We aimed to develop a machine learning methodology that identifies and provides better characterization of patient clusters at high risk of mortality and kidney injury. We analysed prospectively collected data including co-morbidities, clinical examination, and laboratory parameters from a minimally-selected population of 743 patients admitted to the ICU of a Dutch hospital between 2015 and 2017. We compared four clustering methodologies and trained a classifier to predict and validate cluster membership. The contribution of different variables to the predicted cluster membership was assessed using SHapley Additive exPlanations values. We found that deep embedded clustering yielded better results compared to the traditional clustering algorithms. The best cluster configuration was achieved for 6 clusters. All clusters were clinically recognizable, and differed in in-ICU, 30-day, and 90-day mortality, as well as incidence of acute kidney injury. We identified two high mortality risk clusters with at least 60%, 40%, and 30% increased. ICU, 30-day and 90-day mortality, and a low risk cluster with 25–56% lower mortality risk. This machine learning methodology combining deep embedded clustering and variable importance analysis, which we made publicly available, is a possible solution to challenges previously encountered by clustering analyses in heterogeneous patient populations and may help improve the characterization of risk groups in critical care.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering

Forte

Yeshmagambetova

Grinten

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The BAC classification was based on physiological background information: total bilirubin level has been associated with mortality, 13 whereas increases in ALP and γGT levels have been reported to be protective. [16][17][18] We defined "sepsis-related cholestasis" as the occurrence of cholestasis within 7 days after sepsis.…”

Section: Definitionsmentioning

confidence: 99%

Contributing factors and outcomes of burn-associated cholestasis

Tymowski

Dépret

Soussi

et al. 2019

Journal of Hepatology

View full text Add to dashboard Cite

“…variables for which no measurements were registered at any moment during ICU stay) were excluded from the analysis. Remaining missing data were imputed using a rolling mean based on ICU-specific values [13]. Feature extraction (mean and variance concatenated over the whole time-series) was employed to represent time-series data.…”

Section: Co-morbidity Clinical Examination and Laboratory Datamentioning

confidence: 99%

Unraveling Patient Heterogeneity in ICU With Deep Embedded Clustering Using Co-morbidity, Clinical Examination, and Laboratory Data

Jc¹,

Yeshmagambetova²,

Mvd³

et al. 2020

Preprint

View full text Add to dashboard Cite

Introduction Despite extensive research, the goal of unravelling patient heterogeneity in critical care remains largely unattained. Combining clustering analysis of routinely collected high-frequency data with the identification of features driving cluster separation may constitute a step towards improving patient characterization. Methods In this study, we analysed prospectively collected data from 743 patients including co-morbidities, clinical examination, and laboratory parameters. We compared four clustering methodologies – deep embedded clustering (DEC), hierarchical clustering with and without dynamic time warping, and k-means – and trained a classifier to predict and validate cluster membership. The contribution of different variables to the predicted cluster membership was assessed using SHapley Additive exPlanations values.Results DEC yielded better results compared to the traditional clustering algorithms, with the best Jaccard and entropy scores being achieved for 6 clusters. These clusters were characterized as medium to high co-morbidity patients with respiratory pathology and sepsis (cluster 1), patients with primarily acute and chronic cardiac conditions and surgical admission (cluster 2), patients with diverse disease etiology and poor outcomes (cluster 3), low co-morbidity neurological, neurosurgical, and trauma patients (cluster 4), medium co-morbidity patients with cardio-respiratory problems, and neuro-trauma patients with longer length of stay (cluster 5), and patients with sepsis and respiratory infections (cluster 6). All clusters differed in in-ICU, 30-day, and 90-day mortality, as well as incidence of acute kidney injury, and two clusters were categorized as having higher mortality risk, and one cluster as lower mortality risk. Conclusions This machine learning methodology, which we made publicly available, is a possible solution to challenges previously encountered by clustering analyses, and may help unravel patient heterogeneity in critical care.

show abstract

Systematic comparison of routine laboratory measurements with in-hospital mortality: ICU-Labome, a large cohort study of critically ill patients

Cited by 7 publications

References 34 publications

Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering

Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering

Contributing factors and outcomes of burn-associated cholestasis

Unraveling Patient Heterogeneity in ICU With Deep Embedded Clustering Using Co-morbidity, Clinical Examination, and Laboratory Data

Contact Info

Product

Resources

About