Machine Learning Models for Predicting Acute Kidney Injury in Patients With Sepsis-Associated Acute Respiratory Distress Syndrome

Zhou, Yang; Feng, Jinhua; Mei, Shuya; Han, Zhongchao; Tang, Ri; Xing, Shunpeng; Gao, Yuan; Xu, Qiaoyi; He, Zhengyu

doi:10.1097/shk.0000000000002065

Cited by 14 publications

(23 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, multiple machine learning techniques are being employed in critical care studies. Specific applications include early detection of acute kidney injury, pulmonary embolism, gene expression in sepsis, and leukocyte phenotyping when trying to understand the pathophysiology of sepsis (45)(46)(47)(48)(49). Reinforcement learning has also been used to formulate ICU electrolyte replacement protocols and determine treatment decisions in sepsis (50,51).…”

Section: Discussionmentioning

confidence: 99%

Man Versus Machine: Provider Directed Versus Precision Automated Critical Care Management in a Porcine Model of Distributive Shock

Sanin,

Cambronero,

Wood

et al. 2024

Shock

View full text Add to dashboard Cite

BACKGROUND Critical care management of shock is a labor-intensive process. Precision automated critical care management (PACC-MAN) is an automated closed-loop system incorporating physiologic and hemodynamic inputs to deliver interventions while avoiding excessive fluid or vasopressor administration. To understand PACC-MAN efficacy, we compared PACC-MAN to provider-directed management (PDM). We hypothesized that PACC-MAN would achieve equivalent resuscitation outcomes to PDM while maintaining normotension with lower fluid and vasopressor requirements. METHODS Twelve swine underwent 30% controlled hemorrhage over 30 minutes, followed by 45 minutes of aortic occlusion to generate a vasoplegic shock state, transfusion to euvolemia, and randomization to PACC-MAN or PDM for 4.25 hours. Primary outcomes were total crystalloid volume, vasopressor administration, total time spent at hypotension (MAP <60 mmHg), and total number of interventions. RESULTS Weight-based fluid volumes were similar between PACC-MAN and PDM, median and IQR are reported (73.1 mL/kg [59.0-78.7] vs. 87.1 mL/kg [79.4-91.8] p = 0.07). There was no statistical difference in cumulative norepinephrine (PACC-MAN: 33.4 mcg/kg [27.1-44.6] vs. PDM: 7.5 [3.3-24.2] mcg/kg, p = 0.09). The median percentage of time spent at hypotension was equivalent (PACC-MAN: 6.2% [3.6-7.4] and PDM: 3.1% [1.3-6.6], p = 0.23). Urine outputs were similar between PACC-MAN and PDM (14.0 mL/kg vs. 21.5 mL/kg, p = 0.13). CONCLUSION Automated resuscitation achieves equivalent resuscitation outcomes to direct human intervention in this shock model. This study provides the first translational experience with the PACC-MAN system versus PDM.

show abstract

Section: Discussionmentioning

confidence: 99%

Man Versus Machine: Provider Directed Versus Precision Automated Critical Care Management in a Porcine Model of Distributive Shock

Sanin,

Cambronero,

Wood

et al. 2024

Shock

View full text Add to dashboard Cite

show abstract

“…These results indicate that ML has good predictive value for in-hospital mortality rate in ARDS patients caused by trauma. In addition, a study constructed a prognostic model for sepsis-induced ARDS patients using ML to predict the occurrence of AKI within 48 hours of admission to the ICU, achieving a high AUC of 0.86 and accuracy of 0.81 [23]. Moreover, several other studies have demonstrated the ability of ML to predict the duration of mechanical ventilation in ARDS, indicating that it can provide early and accurate predictions for MV duration in ARDS [13,24].…”

Section: Discussionmentioning

confidence: 99%

Machine learning-based prediction model of acute kidney injury in patients with acute respiratory distress syndrome

Wei

Zhang

Dong

et al. 2023

Preprint

View full text Add to dashboard Cite

Background Acute kidney injury (AKI) can make cases of acute respiratory distress syndrome (ARDS) more complex, and the combination of the two can significantly worsen the prognosis. Our objective, therefore, is to utilize machine learning techniques to construct models that can promptly identify the risk of AKI in ARDS patients, and provide guidance for early intervention and treatment, ultimately leading to improved prognosis. Method We obtained data regarding ARDS patients from the Medical Information Mart for Intensive Care III (MIMIC-III) database and utilized 11 machine learning (ML) algorithms to construct our predictive models. We selected the best model based on various metrics, and visualized the importance of its features using Shapley additive explanations (SHAP). We then created a more concise model using fewer variables, and optimized it using hyperparameter optimization (HPO). Additionally, we developed a web-based calculator to facilitate clinical usage. Result A total of 928 ARDS patients were included in the analysis, of whom 179 (19.3%) developed AKI during hospitalization. A total of 43 features were used to build the model. Among all models, XGBoost performed the best. We used the top 10 features to build a compact model with an area under the curve (AUC) of 0.838, which improved to an AUC of 0.848 after the HPO. Conclusion Machine learning algorithms, especially XGBoost, are reliable tools for predicting AKI in ARDS patients. The compact model still retains excellent predictive ability, and the web-based calculator makes clinical usage more convenient.

show abstract

“…In recent years, there has been a growing interest in utilizing machine learning (ML) algorithms for diagnostic and prognostic disease studies. These ML models have shown to surpass traditional scoring methods in terms of predictive accuracy ( 15 , 16 ). In our study, we also observed that machine learning models outperformed conventional scoring systems in all 28-day mortality prediction for S-AKI patients.…”

Section: Discussionmentioning

confidence: 99%

“…Zhou et al utilized data from the MIMIC III database to create a machine learning model for predicting AKI within 48 h of sepsis-related ARDS cases. Their model outperformed the discriminatory ability of SOFA ( 16 ). This highlights the potential of machine learning algorithms in accurately predicting the development of S-AKI.…”

Section: Introductionmentioning

confidence: 98%

Explainable ensemble machine learning model for prediction of 28-day mortality risk in patients with sepsis-associated acute kidney injury

et al. 2023

View full text Add to dashboard Cite

BackgroundSepsis-associated acute kidney injury (S-AKI) is a major contributor to mortality in intensive care units (ICU). Early prediction of mortality risk is crucial to enhance prognosis and optimize clinical decisions. This study aims to develop a 28-day mortality risk prediction model for S-AKI utilizing an explainable ensemble machine learning (ML) algorithm.MethodsThis study utilized data from the Medical Information Mart for Intensive Care IV (MIMIC-IV 2.0) database to gather information on patients with S-AKI. Univariate regression, correlation analysis and Boruta were combined for feature selection. To construct the four ML models, hyperparameters were tuned via random search and five-fold cross-validation. To evaluate the performance of all models, ROC, K-S, and LIFT curves were used. The discrimination of ML models and traditional scoring systems was compared using area under the receiver operating characteristic curve (AUC). Additionally, the SHapley Additive exPlanation (SHAP) was utilized to interpret the ML model and identify essential variables. To investigate the relationship between the top nine continuous variables and the risk of 28-day mortality. COX regression-restricted cubic splines were utilized while controlling for age and comorbidities.ResultsThe study analyzed data from 9,158 patients with S-AKI, dividing them into a 28-day mortality group of 1,940 and a survival group of 7,578. The results showed that XGBoost was the best performing model of the four ML models with AUC of 0.873. All models outperformed APS-III 0.713 and SAPS-II 0.681. The K-S and LIFT curves indicated XGBoost as the most effective predictor for 28-day mortality risk. The model’s performance was evaluated using ROCpr curves, calibration curves, accuracy, precision, and F1 scores. SHAP force plots were utilized to interpret and visualize the personalized predictive power of the 28-day mortality risk model. Additionally, COX regression restricted cubic splines revealed an interesting non-linear relationship between the top nine variables and 28-day mortality.ConclusionThe use of ensemble ML models has shown to be more effective than the LR model and conventional scoring systems in predicting 28-day mortality risk in S-AKI patients. By visualizing the XGBoost model with the best predictive performance, clinicians are able to identify high-risk patients early on and improve prognosis.

show abstract

Machine Learning Models for Predicting Acute Kidney Injury in Patients With Sepsis-Associated Acute Respiratory Distress Syndrome

Cited by 14 publications

References 54 publications

Man Versus Machine: Provider Directed Versus Precision Automated Critical Care Management in a Porcine Model of Distributive Shock

Man Versus Machine: Provider Directed Versus Precision Automated Critical Care Management in a Porcine Model of Distributive Shock

Machine learning-based prediction model of acute kidney injury in patients with acute respiratory distress syndrome

Explainable ensemble machine learning model for prediction of 28-day mortality risk in patients with sepsis-associated acute kidney injury

Contact Info

Product

Resources

About