Developing an ensemble machine learning model for early prediction of sepsis-associated acute kidney injury

Zhang, Luming; Wang, Zichen; Zhou, Zhenyu; Li, Shaojin; Yin, Haiyan; Lyu, Jun

doi:10.1016/j.isci.2022.104932

Cited by 20 publications

(24 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this study used a larger sample of around 21 thousand samples, ie, it was more representative of the sepsis patient population. 18 In some of the above studies, the criteria for AKI patients were obtained from observations for 12 to 48 hours, and retrospective data was used. In contrast, the AKI criteria were obtained in our study after observing sepsis patients for seven days according to the KDIGO criteria.…”

Section: Discussionmentioning

confidence: 99%

Acute Kidney Injury Prediction Model Using Cystatin-C, Beta-2 Microglobulin, and Neutrophil Gelatinase-Associated Lipocalin Biomarker in Sepsis Patients

Susianti,

Asmoro,

Sujarwoto

et al. 2024

IJNRD

View full text Add to dashboard Cite

Introduction AKI is a frequent complication in sepsis patients and is estimated to occur in almost half of patients with severe sepsis. However, there is currently no effective therapy for AKI in sepsis. Therefore, the therapeutic approach is focused on prevention. Based on this, there is an opportunity to examine a panel of biomarker models for predicting AKI. Material and Methods This prospective cohort study analysed the differences in Cystatin C, Beta-2 Microglobulin, and NGAL levels in sepsis patients with AKI and sepsis patients without AKI. The biomarker modelling of AKI prediction was done using machine learning, namely Orange Data Mining. In this study, 130 samples were analysed by machine learning. The parameters used to obtain the biomarker panel were 23 laboratory examination parameters. Results This study used SVM and the Naïve Bayes model of machine learning. The SVM model’s sensitivity, specificity, NPV, and PPV were 50%, 94.4%, 71.4%, and 87.5%, respectively. For the Naïve Bayes model, the sensitivity, specificity, NPV, and PPV were 83.3%, 77.8%, 87.5%, and 71.4%, respectively. Discussion This study’s SVM machine learning model has higher AUC and specificity but lower sensitivity. The Naïve Bayes model had better sensitivity; it can be used to predict AKI in sepsis patients. Conclusion The Naïve Bayes machine learning model in this study is useful for predicting AKI in sepsis patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Acute Kidney Injury Prediction Model Using Cystatin-C, Beta-2 Microglobulin, and Neutrophil Gelatinase-Associated Lipocalin Biomarker in Sepsis Patients

Susianti,

Asmoro,

Sujarwoto

et al. 2024

IJNRD

View full text Add to dashboard Cite

show abstract

“…The extent of necrosis has been correlated with organ failure and mortality, this may be associated with further complications of the pancreas and extrapancreatic necrosis, which could predispose the patient to infections, pseudoaneurysms, and intestinal fistulas. Sepsis is also an independent risk factor for acute kidney injury [ 34 ]. In addition, unsaturated fatty acids could worsen systemic inflammation and organ failure.…”

Section: Discussionmentioning

confidence: 99%

Development and validation of a prediction model for the early occurrence of acute kidney injury in patients with acute pancreatitis

Zhou

Cai

et al. 2023

Renal Failure

View full text Add to dashboard Cite

Background Acute pancreatitis (AP) is associated with a high incidence of acute kidney injury (AKI). This study aimed to develop a nomogram for predicting the early onset of AKI in AP patients admitted to the intensive care unit. Method Clinical data for 799 patients diagnosed with AP were extracted from the Medical Information Mart for Intensive Care IV database. Eligible AP patients were randomly divided into training and validation cohorts. The independent prognostic factors for the early development of AKI in AP patients were determined using the all-subsets regression method and multivariate logistic regression. A nomogram was constructed for predicting the early occurrence of AKI in AP patients. The performance of the nomogram was evaluated based on the area under the receiver operating characteristic curve (AUC), calibration curves and decision curve analysis (DCA). Results Seven independent prognostic factors were identified as predictive factors for early onset AKI in AP patients. The AUC of the nomogram in the training and validation cohorts were 0.795 (95% CI, 0.758–0.832) and 0.772 (95% CI, 0.711–0.832), respectively. The AUC of the nomogram was higher compared with that of the BISAP, Ranson, APACHE II scores. Further, the calibration curve revealed that the predicted outcome was in agreement with the actual observations. Finally, the DCA curves showed that the nomogram had a good clinical applicability value. Conclusion The constructed nomogram showed a good predictive ability for the early occurrence of AKI in AP patients.

show abstract

“…After constructing the model, we assessed its performance on the test dataset using metrics including accuracy, sensitivity, specificity, and AUC (area under the receiver operating characteristic curve). Additionally, to optimize our predictive model's efficacy, we employed ensemble machine learning strategies, notably stacking 34 and voting techniques. The model with the highest AUC value was considered the best model and selected for developing a practical prediction system.…”

Section: Methodsmentioning

confidence: 99%

Machine learning approaches for practical predicting outpatient near-future AECOPD based on nationwide electronic medical records

Liao,

Cheng,

Sung

et al. 2024

iScience

View full text Add to dashboard Cite

Developing an ensemble machine learning model for early prediction of sepsis-associated acute kidney injury

Cited by 20 publications

References 29 publications

Acute Kidney Injury Prediction Model Using Cystatin-C, Beta-2 Microglobulin, and Neutrophil Gelatinase-Associated Lipocalin Biomarker in Sepsis Patients

Acute Kidney Injury Prediction Model Using Cystatin-C, Beta-2 Microglobulin, and Neutrophil Gelatinase-Associated Lipocalin Biomarker in Sepsis Patients

Development and validation of a prediction model for the early occurrence of acute kidney injury in patients with acute pancreatitis

Machine learning approaches for practical predicting outpatient near-future AECOPD based on nationwide electronic medical records

Contact Info

Product

Resources

About