Abstract:BackgroundAcute kidney injury (AKI) is the most common major complication of cardiac surgery field. The purpose of this study is to investigate the association between acute kidney injury and the prognoses of cardiac surgery patients in the Medical Information Mart for Intensive Care III (MIMIC-III) database.MethodsClinical data were extracted from the MIMIC-III database. Adult (≥18 years) cardiac surgery patients in the database were enrolled. Multivariable logistic regression analyses were employed to assess… Show more
“…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.…”
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.
“…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.…”
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.
“…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].…”
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.