scholarly journals Machine learning for early discrimination between transient and persistent acute kidney injury in critically ill patients with sepsis

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Xiao-Qin Luo ◽  
Ping Yan ◽  
Ning-Ya Zhang ◽  
Bei Luo ◽  
Mei Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Prediction Model ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Kidney Injury ◽  
Artificial Neural

AbstractAcute kidney injury (AKI) is commonly present in critically ill patients with sepsis. Early prediction of short-term reversibility of AKI is beneficial to risk stratification and clinical treatment decision. The study sought to use machine learning methods to discriminate between transient and persistent sepsis-associated AKI. Septic patients who developed AKI within the first 48 h after ICU admission were identified from the Medical Information Mart for Intensive Care III database. AKI was classified as transient or persistent according to the Acute Disease Quality Initiative workgroup consensus. Five prediction models using logistic regression, random forest, support vector machine, artificial neural network and extreme gradient boosting were constructed, and their performance was evaluated by out-of-sample testing. A simplified risk prediction model was also derived based on logistic regression and features selected by machine learning algorithms. A total of 5984 septic patients with AKI were included, 3805 (63.6%) of whom developed persistent AKI. The artificial neural network and logistic regression models achieved the highest area under the receiver operating characteristic curve (AUC) among the five machine learning models (0.76, 95% confidence interval [CI] 0.74–0.78). The simplified 14-variable model showed adequate discrimination, with the AUC being 0.76 (95% CI 0.73–0.78). At the optimal cutoff of 0.63, the sensitivity and specificity of the simplified model were 63% and 76% respectively. In conclusion, a machine learning-based simplified prediction model including routine clinical variables could be used to differentiate between transient and persistent AKI in critically ill septic patients. An easy-to-use risk calculator can promote its widespread application in daily clinical practice.

scholarly journals Association Between Serum Osmolality and Acute Kidney Injury in Critically Ill Patients: A Retrospective Cohort Study

2021 ◽  
Vol 8 ◽  
Author(s):  
Jie Yang ◽  
Yisong Cheng ◽  
Ruoran Wang ◽  
Bo Wang
Keyword(s):  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Retrospective Cohort ◽  
Kidney Injury ◽  
High Serum ◽  
Serum Osmolality ◽  
Multivariate Logistic Regression ◽  
Low Serum

Purposes: Acute kidney injury (AKI) is a common complication in critically ill patients and is usually associated with poor outcomes. Serum osmolality has been validated in predicting critically ill patient mortality. However, data about the association between serum osmolality and AKI is still lacking in ICU. Therefore, the purpose of the present study was to investigate the association between early serum osmolality and the development of AKI in critically ill patients.Methods: The present study was a retrospective cohort analysis based on the medical information mart for intensive care III (MIMIC-III) database. 20,160 patients were involved in this study and divided into six subgroups according to causes for ICU admission. The primary outcome was the incidence of AKI after ICU admission. The association between early serum osmolality and AKI was explored using univariate and multivariate logistic regression analyses.Results: The normal range of serum osmolality was 285–300 mmol/L. High serum osmolality was defined as serum osmolality >300 mmol/L and low serum osmolality was defined as serum osmolality <285 mmol/L. Multivariate logistic regression indicated that high serum osmolality was independently associated with increased development of AKI with OR = 1.198 (95% CL = 1.199–1.479, P < 0.001) and low serum osmolality was also independently associated with increased development of AKI with OR = 1.332 (95% CL = 1.199–1.479, P < 0.001), compared with normal serum osmolality, respectively.Conclusions: In critically ill patients, early high serum osmolality and low serum osmolality were both independently associated with an increased risk of development of AKI.

A Nonlinear Autoregressive With Exogenous Inputs Artificial Neural Network Model for Building Thermal Load Prediction

2019 ◽  
Vol 142 (5) ◽  
Author(s):  
Byeongho Yu ◽  
Dongsu Kim ◽  
Heejin Cho ◽  
Pedro Mago
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Nonlinear System ◽  
Prediction Model ◽  
Thermal Load ◽  
Ann Model ◽  
Load Prediction ◽  
Artificial Neural ◽  
Nonlinear Autoregressive

Abstract Thermal load prediction is a key part of energy system management and control in buildings, and its accuracy plays a critical role to improve building energy performance and efficiency. Regarding thermal load prediction, various types of prediction model have been considered and studied, such as physics-based, statistical, and machine learning models. Physical models can be accurate but require extended lead time for model development. Statistical models are relatively simple to develop and require less computation time, but they may not provide accurate results for complex energy systems with intricate nonlinear dynamic behaviors. This study proposes an artificial neural network (ANN) model, one of the prevalent machine learning methods to predict building thermal load, combining with the concept of nonlinear autoregressive with exogenous inputs (NARX). NARX-ANN prediction model is distinguished from typical ANN models because the NARX concept can address nonlinear system behaviors effectively based on its recurrent architectures and time indexing features. To examine the suitability and validity of NARX-ANN model for building thermal load prediction, a case study is carried out using the field data of an academic campus building at Mississippi State University (MSU). Results show that the proposed NARX-ANN model can provide an accurate and robust prediction performance and effectively address nonlinear system behaviors in the prediction.

scholarly journals Acute Kidney Injury Associated with Combination Antimicrobial Therapy in the Medical Information Mart for Intensive Care (MIMIC) III Database

2017 ◽  
Vol 4 (suppl_1) ◽  
pp. S344-S344
Author(s):  
W Cliff Rutter ◽  
David S Burgess
Keyword(s):  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Intensive Care ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Hepatorenal Syndrome ◽  
Medical Information ◽  
Kidney Injury ◽  
Rifle Criteria ◽  
Multivariable Logistic Regression

Abstract Background Increased acute kidney injury (AKI) incidence is linked with coadministration of vancomycin (VAN) and piperacillin-tazobactam (TZP) in the general hospital population when compared with VAN and cefepime (FEP); however, this phenomenon was not found in critically ill patients. Methods Patients receiving VAN in combination with FEP or TZP for at least 48 hours during an intensive care unit stay were included in this retrospective review. AKI was defined with the Risk, Injury, Failure, Loss, and End-stage (RIFLE) criteria. Exposure to common nephrotoxins was captured within 24 hours of combination therapy initiation through the entire treatment window. Basic descriptive statistics were performed, along with bivariable and multivariable logistic regression models of AKI odds. Results In total, 2230 patients were included, with 773 receiving FEP+VAN and 1457 receiving TZP+VAN. The groups were well balanced at baseline in most covariates, with the exception of hepatorenal syndrome diagnosis (TZP+VAN 1.4% vs. FEP+VAN 0.3%, P = 0.02) and vasopressor exposure (TZP+VAN 26.2% vs 21.5%, P = 0.01) being more common in the TZP+VAN group. Patients in the FEP+VAN group had a higher underlying severity of disease (Charlson comorbidity index [CCI] 2.7 vs. 2.3, P =0.0002). AKI incidence was higher in the TZP+VAN cohort (35.1% vs. 26.5%, P = 0.00004), with each stratification of the RIFLE criteria being higher. The time until onset of AKI was similar between groups (TZP+VAN median 1 [0–3] days vs. FEP+VAN 1 [0–4] days, P =0.2). After multivariable logistic regression, TZP+VAN therapy was associated with an adjust odds ratio (aOR) of AKI of 1.54 (95% confidence interval [CI] 1.25–1.89) compared with FEP+VAN. Other variables associated with increased odds of AKI included: age >= 65, duration of antibiotic therapy, higher baseline renal function, sepsis, endocarditis, hepatorenal syndrome, thiazide diuretic exposure, and increased CCI. Conclusion Treatment with TZP+VAN is associated with significant increases in AKI incidence among critically ill patients, independent of other risks for AKI. Disclosures All authors: No reported disclosures.

A Prediction Model for Assessing Prognosis in Critically Ill Patients With Sepsis-Associated Acute Kidney Injury

Shock ◽  
2021 ◽  
Vol Publish Ahead of Print ◽  
Author(s):  
Hongbin Hu ◽  
Lulan Li ◽  
Yuan Zhang ◽  
Tong Sha ◽  
Qiaobing Huang ◽  
...  
Keyword(s):  
Acute Kidney Injury ◽  
Prediction Model ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Kidney Injury

scholarly journals Perbandingan Model Logistic Regression dan Artificial Neural Network pada Prediksi Pembatalan Hotel

2021 ◽  
Vol 6 (1) ◽  
pp. 29
Author(s):  
Moch Shandy Tsalasa Putra ◽  
Yufis Azhar
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Logistic Regression ◽  
Management Systems ◽  
Complex Data ◽  
Hotel Performance ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Modern Era

Prediction for canceled booking hotels is an important part of hotel revenue management systems in the modern era. Because the predicted result can be used for the optimization of hotel performance. The application of machine learning will be very helpful for predicting canceled booking hotels because machine learning can process complex data. In this research, the proposed methods are Artificial Neural Network (ANN) and Logistic Regression. Later it will be done five times experiments with hyperparameter tuning to see which method is the most optimal to do prediction canceled booking hotel. From five times experiments, experiments number five (logistic regression with GridSearchCV) is the most optimal for predicting canceled booking hotels, with 79.77% accuracy, 85.86% precision, and 55.07% recall.

Sign in / Sign up

Export Citation Format

Share Document