Association between acute kidney injury and prognoses of cardiac surgery patients: Analysis of the MIMIC-III database

Sun, Chun; Chen, Deqing; Jin, Xin; Xu, Guangtao; Tang, Chenye; X, Guo; Tang, Zhiling; Bao, Yuhai; Wang, Fei; Shen, Ruilin

doi:10.3389/fsurg.2022.1044937

Cited by 4 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although several AKI or CRRT prediction models have been reported recently, notable limitations exist. First, these models have often been derived and validated within specific patient cohorts, such as those undergoing cardiac surgery or catheterization [22][23][24][25] , children 26 , elderly adults 27 , or the critically ill 28 . This specificity may limit their generalizability to broader patient populations.…”

Section: Introductionmentioning

confidence: 99%

Forecasting Acute Kidney Injury and Resource Utilization in ICU patients using longitudinal, multimodal models

Tan,

Dede,

Mohanty

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: Advances in artificial intelligence (AI) have realized the potential of revolutionizing healthcare, such as predicting disease progression via longitudinal inspection of Electronic Health Records (EHRs) and lab tests from patients admitted to Intensive Care Units (ICU). Although substantial literature exists addressing broad subjects, including the prediction of mortality, length-of-stay, and readmission, studies focusing on forecasting Acute Kidney Injury (AKI), specifically dialysis anticipation like Continuous Renal Replacement Therapy (CRRT) are scarce. The technicality of how to implement AI remains elusive. Objective: This study aims to elucidate the important factors and methods that are required to develop effective predictive models of AKI and CRRT for patients admitted to ICU, using EHRs in the Medical Information Mart for Intensive Care (MIMIC) database. Methods: We conducted a comprehensive comparative analysis of established predictive models, considering both time-series measurements and clinical notes from MIMIC-IV databases. Subsequently, we proposed a novel multi-modal model which integrates embeddings of top-performing unimodal models, including Long Short-Term Memory (LSTM) and BioMedBERT, and leverages both unstructured clinical notes and structured time series measurements derived from EHRs to enable the early prediction of AKI and CRRT. Results: Our multimodal model achieved a lead time of at least 12 hours ahead of clinical manifestation, with an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.888 for AKI and 0.997 for CRRT, as well as an Area Under the Precision Recall Curve (AUPRC) of 0.727 for AKI and 0.840 for CRRT, respectively, which significantly outperformed the baseline models. Additionally, we performed a SHapley Additive exPlanation (SHAP) analysis using the expected gradients algorithm, which highlighted important, previously underappreciated predictive features for AKI and CRRT. Conclusion: Our study revealed the importance and the technicality of applying longitudinal, multimodal modeling to improve early prediction of AKI and CRRT, offering insights for timely interventions. The performance and interpretability of our model indicate its potential for further assessment towards clinical applications, to ultimately optimize AKI management and enhance patient outcomes.

show abstract

Section: Introductionmentioning

confidence: 99%

Forecasting Acute Kidney Injury and Resource Utilization in ICU patients using longitudinal, multimodal models

Tan,

Dede,

Mohanty

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Apart from its high incidence, this complication bears severe consequences for the patient's health. It increases postoperative morbidity and mortality [2,5,6], and can result in the development of chronic kidney disease (CKD) [4,7].…”

Section: Introductionmentioning

confidence: 99%

Alterations to Kidney Physiology during Cardiopulmonary Bypass—A Narrative Review of the Literature and Practical Remarks

Udzik,

Pacholewicz,

Biskupski

et al. 2023

JCM

View full text Add to dashboard Cite

Introduction: According to different authors, cardiac surgery-associated acute kidney injury (CSA-AKI) incidence can be as high as 20–50%. This complication increases postoperative morbidity and mortality and impairs long-term kidney function in some patients. This review aims to summarize current knowledge regarding alterations to renal physiology during cardiopulmonary bypass (CPB) and to discuss possible nephroprotective strategies for cardiac surgeries. Relevant sections: Systemic and renal circulation, Vasoactive drugs, Fluid balance and Osmotic regulation and Inflammatory response. Conclusions: Considering the available scientific evidence, it is concluded that adequate kidney perfusion and fluid balance are the most critical factors determining postoperative kidney function. By adequate perfusion, one should understand perfusion with proper oxygen delivery and sufficient perfusion pressure. Maintaining the fluid balance is imperative for a normal kidney filtration process, which is essential for preserving the intra- and postoperative kidney function. Future directions: The review of the available literature regarding kidney function during cardiac surgery revealed a need for a more holistic approach to this subject.

show abstract

Forecasting acute kidney injury and resource utilization in ICU patients using longitudinal, multimodal models

Tan,

Dede,

Mohanty

et al. 2024

Journal of Biomedical Informatics

View full text Add to dashboard Cite

Association between acute kidney injury and prognoses of cardiac surgery patients: Analysis of the MIMIC-III database

Cited by 4 publications

References 22 publications

Forecasting Acute Kidney Injury and Resource Utilization in ICU patients using longitudinal, multimodal models

Forecasting Acute Kidney Injury and Resource Utilization in ICU patients using longitudinal, multimodal models

Alterations to Kidney Physiology during Cardiopulmonary Bypass—A Narrative Review of the Literature and Practical Remarks

Forecasting acute kidney injury and resource utilization in ICU patients using longitudinal, multimodal models

Contact Info

Product

Resources

About