scholarly journals Derivation and Validation of Machine Learning Approaches to Predict Acute Kidney Injury after Cardiac Surgery

2018 ◽  
Vol 7 (10) ◽  
pp. 322 ◽  
Author(s):  
Hyung-Chul Lee ◽  
Hyun-Kyu Yoon ◽  
Karam Nam ◽  
Youn Cho ◽  
Tae Kim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Logistic Regression Analysis ◽  
Kidney Injury ◽  
Gradient Boosting ◽  
Support Vector ◽  
Learning Approaches

Machine learning approaches were introduced for better or comparable predictive ability than statistical analysis to predict postoperative outcomes. We sought to compare the performance of machine learning approaches with that of logistic regression analysis to predict acute kidney injury after cardiac surgery. We retrospectively reviewed 2010 patients who underwent open heart surgery and thoracic aortic surgery. Baseline medical condition, intraoperative anesthesia, and surgery-related data were obtained. The primary outcome was postoperative acute kidney injury (AKI) defined according to the Kidney Disease Improving Global Outcomes criteria. The following machine learning techniques were used: decision tree, random forest, extreme gradient boosting, support vector machine, neural network classifier, and deep learning. The performance of these techniques was compared with that of logistic regression analysis regarding the area under the receiver-operating characteristic curve (AUC). During the first postoperative week, AKI occurred in 770 patients (38.3%). The best performance regarding AUC was achieved by the gradient boosting machine to predict the AKI of all stages (0.78, 95% confidence interval (CI) 0.75–0.80) or stage 2 or 3 AKI. The AUC of logistic regression analysis was 0.69 (95% CI 0.66–0.72). Decision tree, random forest, and support vector machine showed similar performance to logistic regression. In our comprehensive comparison of machine learning approaches with logistic regression analysis, gradient boosting technique showed the best performance with the highest AUC and lower error rate. We developed an Internet–based risk estimator which could be used for real-time processing of patient data to estimate the risk of AKI at the end of surgery.

scholarly journals Prediction of Acute Kidney Injury after Liver Transplantation: Machine Learning Approaches vs. Logistic Regression Model

2018 ◽  
Vol 7 (11) ◽  
pp. 428 ◽  
Author(s):  
Hyung-Chul Lee ◽  
Soo Yoon ◽  
Seong-Mi Yang ◽  
Won Kim ◽  
Ho-Geol Ryu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Liver Transplantation ◽  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Logistic Regression Analysis ◽  
Kidney Injury ◽  
Gradient Boosting ◽  
Learning Approaches ◽  
Gradient Boosting Machine

Acute kidney injury (AKI) after liver transplantation has been reported to be associated with increased mortality. Recently, machine learning approaches were reported to have better predictive ability than the classic statistical analysis. We compared the performance of machine learning approaches with that of logistic regression analysis to predict AKI after liver transplantation. We reviewed 1211 patients and preoperative and intraoperative anesthesia and surgery-related variables were obtained. The primary outcome was postoperative AKI defined by acute kidney injury network criteria. The following machine learning techniques were used: decision tree, random forest, gradient boosting machine, support vector machine, naïve Bayes, multilayer perceptron, and deep belief networks. These techniques were compared with logistic regression analysis regarding the area under the receiver-operating characteristic curve (AUROC). AKI developed in 365 patients (30.1%). The performance in terms of AUROC was best in gradient boosting machine among all analyses to predict AKI of all stages (0.90, 95% confidence interval [CI] 0.86–0.93) or stage 2 or 3 AKI. The AUROC of logistic regression analysis was 0.61 (95% CI 0.56–0.66). Decision tree and random forest techniques showed moderate performance (AUROC 0.86 and 0.85, respectively). The AUROC of support the vector machine, naïve Bayes, neural network, and deep belief network was smaller than that of the other models. In our comparison of seven machine learning approaches with logistic regression analysis, the gradient boosting machine showed the best performance with the highest AUROC. An internet-based risk estimator was developed based on our model of gradient boosting. However, prospective studies are required to validate our results.

scholarly journals Machine Learning Models of Acute Kidney Injury Prediction in Acute Pancreatitis Patients

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Cheng Qu ◽  
Lin Gao ◽  
Xian-qiang Yu ◽  
Mei Wei ◽  
Guo-quan Fang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
Acute Pancreatitis ◽  
Logistic Regression ◽  
Kidney Injury ◽  
Gradient Boosting ◽  
Support Vector ◽  
Learning Models ◽  
Extreme Gradient Boosting ◽  
Machine Learning Models

Background. Acute kidney injury (AKI) has long been recognized as a common and important complication of acute pancreatitis (AP). In the study, machine learning (ML) techniques were used to establish predictive models for AKI in AP patients during hospitalization. This is a retrospective review of prospectively collected data of AP patients admitted within one week after the onset of abdominal pain to our department from January 2014 to January 2019. Eighty patients developed AKI after admission (AKI group) and 254 patients did not (non-AKI group) in the hospital. With the provision of additional information such as demographic characteristics or laboratory data, support vector machine (SVM), random forest (RF), classification and regression tree (CART), and extreme gradient boosting (XGBoost) were used to build models of AKI prediction and compared to the predictive performance of the classic model using logistic regression (LR). XGBoost performed best in predicting AKI with an AUC of 91.93% among the machine learning models. The AUC of logistic regression analysis was 87.28%. Present findings suggest that compared to the classical logistic regression model, machine learning models using features that can be easily obtained at admission had a better performance in predicting AKI in the AP patients.

How Reliable Is Automated Urinalysis in Acute Kidney Injury?

2020 ◽  
Author(s):  
Vani Chandrashekar ◽  
Anil Tarigopula ◽  
Vikram Prabhakar
Keyword(s):  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Epithelial Cells ◽  
Logistic Regression Analysis ◽  
Blood Cells ◽  
White Blood Cells ◽  
Kidney Injury ◽  
Tubular Epithelial Cells ◽  
Spearman Test

Abstract Objective Examination of urine sediment is crucial in acute kidney injury (AKI). In such renal injury, tubular epithelial cells, epithelial cell casts, and dysmorphic red cells may provide clues to etiology. The aim of this study was to compare automated urinalysis findings with manual microscopic analysis in AKI. Methods Samples from patients diagnosed with AKI and control patients were included in the study. Red blood cells, white blood cells, renal tubular epithelial cells/small round cells, casts, and pathologic (path) cast counts obtained microscopically and by a UF1000i cytometer were compared by Spearman test. Logistic regression analysis was used to assess the ability to predict AKI from parameters obtained from the UF1000i. Results There was poor correlation between manual and automated analysis in AKI. None of the parameters could predict AKI using logistic regression analysis. However, the increment in the automated path cast count increased the odds of AKI 93 times. Conclusion Automated urinalysis parameters are poor predictors of AKI, and there is no agreement with manual microscopy.

scholarly journals Impaired T Lymphocyte Subsets Early Predict Acute Kidney Injury in Sepsis Patients

2021 ◽  
Author(s):  
Guanglan Li ◽  
Yu Zhang ◽  
Ganyuan He ◽  
Wenke Hao ◽  
Wenxue Hu
Keyword(s):  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Regression Analysis ◽  
T Lymphocyte ◽  
Logistic Regression Analysis ◽  
Lymphocyte Subsets ◽  
Kidney Injury ◽  
High Morbidity ◽  
T Helper ◽  
T Lymphocyte Subsets

Abstract Objective: Acute kidney injury (AKI) is a frequent complication of sepsis patients and is associated with high morbidity and mortality. Early recognition of sepsis-associated AKI (SA-AKI) is crucial to provide supportive treatment and improve prognosis. Thus, the objective is to analyze the early discriminative predictive information regarding T lymphocyte subsets of SA-AKI.Methods: We evaluated the relationships of T lymphocyte subsets and clinical parameters of sepsis patients, and assessed their potential roles in SA-AKI diagnosis. The following T lymphocyte subsets were studied: total T lymphocyte (CD3+), helper T lymphocyte (T helper, CD3+CD4+), cytotoxic T lymphocyte (CTL, CD3+CD8+), totally activated T lymphocyte (CD3+HLADR+), early activated T lymphocyte (CD4+CD69+, CD8+CD69+), regulatory T lymphocyte (Treg, CD4+CD25+, CD8+CD25+).Results: A total of 171 patients with sepsis were enrolled. The incidence of AKI was 80.1%. The percentages of total T lymphocyte, CTL, and totally activated T lymphocyte of SA-AKI patients were lower than those of sepsis patients without AKI (61.95±19.65 % vs 68.80±18.57 %, 19.95±17.22 % vs 26.48±18.31 %, 19.00±14.21 % vs 30.88±28.86 %, respectively, P<0.05). There were no significant differences in the percentages of T helper, early activated T lymphocyte, and Tregs between SA-AKI group and non-SA-AKI group. Univariate logistic regression analysis showed that percentages of total T lymphocyte, CTL, and totally activated T lymphocyte were protective factors for SA-AKI. Multivariate logistic regression analysis revealed that percentage of totally activated T lymphocyte had a negative association with SA-AKI independently (OR: 0.952, 95% CI: 0.926-0.978, P=0.000). Moreover, ROC analysis showed that total T lymphocyte, CTL, and totally activated T lymphocyte had discriminatory abilities, with areas under the curve (AUC) value of 0.638, 0.615, and 0.661, respectively (P<0.05). Conclusions: Impaired total T lymphocyte, CTL, and totally activated T lymphocyte could contribute to early diagnosis for SA-AKI.

scholarly journals Machine Learning for the Prediction of Progression in Patients with Acute Kidney Injury in Critical Care

2021 ◽  
Author(s):  
Lifan Zhang ◽  
Canzheng Wei ◽  
Yunxia Feng ◽  
Aijia Ma ◽  
Yan Kang
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Critical Care ◽  
Intensive Care ◽  
Logistic Regression Model ◽  
Kidney Injury ◽  
Gradient Boosting ◽  
Extreme Gradient Boosting ◽  
Stage 1

Abstract Background: Acute kidney injury (AKI) is a serve and harmful syndrome in the intensive care unit. The purpose of this study is to develop a prediction model that predict whether patients with AKI stage 1/2 will progress to AKI stage 3. Methods: Patients with AKI stage 1/2, when they were first diagnosed with AKI in the Medical Information Mart for Intensive Care (MIMIC-III), were included. We excluded patients who had underwent RRT or progressed to AKI stage 3 within 72 hours of the first AKI diagnosis. We also excluded patients with chronic kidney disease (CKD). We used the Logistic regression and machine learning extreme gradient boosting (XGBoost) to build two models which can predict patients who will progress to AKI stage 3. Established models were evaluated by cross-validation, receiver operating characteristic curve (ROC), and precision-recall curves (PRC). Results: We included 25711 patients, of whom 2130 (8.3%) progressed to AKI stage 3. Creatinine, multiple organ failure syndromes (MODS), blood urea nitrogen (BUN), sepsis, and respiratory failure were the most important in AKI progression prediction. The XGBoost model has a better performance than the Logistic regression model on predicting AKI stage 3 progression (AU-ROC, 0.926; 95%CI, 0.917 to 0.931 vs. 0.784; 95%CI, 0.771 to 0.796, respectively). Conclusions: The XGboost model can better identify patients with AKI progression than Logistic regression model. Machine learning techniques may improve predictive modeling in medical research. Keywords: Acute kidney injury; Critical care; Logistic Models; Extreme gradient boosting

scholarly journals An explainable supervised machine learning predictor of acute kidney injury after adult deceased donor liver transplantation

2021 ◽  
Vol 19 (1) ◽  
Author(s):  
Yihan Zhang ◽  
Dong Yang ◽  
Zifeng Liu ◽  
Chaojin Chen ◽  
Mian Ge ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Liver Transplantation ◽  
Acute Kidney Injury ◽  
Kidney Injury ◽  
Supervised Machine Learning ◽  
Gradient Boosting ◽  
Support Vector ◽  
Adaptive Boosting ◽  
Validation Set

Abstract Background Early prediction of acute kidney injury (AKI) after liver transplantation (LT) facilitates timely recognition and intervention. We aimed to build a risk predictor of post-LT AKI via supervised machine learning and visualize the mechanism driving within to assist clinical decision-making. Methods Data of 894 cases that underwent liver transplantation from January 2015 to September 2019 were collected, covering demographics, donor characteristics, etiology, peri-operative laboratory results, co-morbidities and medications. The primary outcome was new-onset AKI after LT according to Kidney Disease Improving Global Outcomes guidelines. Predicting performance of five classifiers including logistic regression, support vector machine, random forest, gradient boosting machine (GBM) and adaptive boosting were respectively evaluated by the area under the receiver-operating characteristic curve (AUC), accuracy, F1-score, sensitivity and specificity. Model with the best performance was validated in an independent dataset involving 195 adult LT cases from October 2019 to March 2021. SHapley Additive exPlanations (SHAP) method was applied to evaluate feature importance and explain the predictions made by ML algorithms. Results 430 AKI cases (55.1%) were diagnosed out of 780 included cases. The GBM model achieved the highest AUC (0.76, CI 0.70 to 0.82), F1-score (0.73, CI 0.66 to 0.79) and sensitivity (0.74, CI 0.66 to 0.8) in the internal validation set, and a comparable AUC (0.75, CI 0.67 to 0.81) in the external validation set. High preoperative indirect bilirubin, low intraoperative urine output, long anesthesia time, low preoperative platelets, and graft steatosis graded NASH CRN 1 and above were revealed by SHAP method the top 5 important variables contributing to the diagnosis of post-LT AKI made by GBM model. Conclusions Our GBM-based predictor of post-LT AKI provides a highly interoperable tool across institutions to assist decision-making after LT. Graphic abstract

scholarly journals An explainable supervised machine learning predictor of acute kidney injury after adult deceased donor liver transplantation

2021 ◽  
Author(s):  
Yihan Zhang ◽  
Dong Yang ◽  
Zifeng Liu ◽  
Chaojin Chen ◽  
Mian Ge ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Liver Transplantation ◽  
Acute Kidney Injury ◽  
Clinical Decision Making ◽  
Kidney Injury ◽  
Supervised Machine Learning ◽  
Gradient Boosting ◽  
Support Vector ◽  
Adaptive Boosting

Abstract Background: Early prediction of acute kidney injury (AKI) after liver transplantation (LT) facilitates timely recognition and intervention. We aimed to build a risk predictor of post-LT AKI via supervised machine learning and visualize the mechanism driving within to assist clinical decision-making.Methods: Data of 894 cases that underwent liver transplantation from January 2015 to September 2019 were collected, covering demographics, donor characteristics, etiology, peri-operative laboratory results, co-morbidities and medications. The primary outcome was new-onset AKI after LT according to Kidney Disease Improving Global Outcomes guidelines. Predicting performance of five classifiers including logistic regression, support vector machine, random forest, gradient boosting machine (GBM) and adaptive boosting were respectively evaluated by the area under the receiver-operating characteristic curve (AUC), accuracy, F1-score, sensitivity and specificity. SHapley Additive exPlanations (SHAP) method was applied to evaluate feature importance and explain the predictions made by ML algorithms.Results: 430 AKI cases (55.1%) were diagnosed out of 780 included cases. The GBM model achieved the highest AUC (0.76, CI 0.70 to 0.82), F1-score (0.73, CI 0.66to 0.79) and sensitivity (0.74, CI 0.66 to 0.8). High preoperative indirect bilirubin, low intraoperative urine output, long anesthesia time, low preoperative platelets, and graft steatosis graded NASH CRN 1 and above were revealed by SHAP method the top 5 important variables contributing to the diagnosis of post-LT AKI made by GBM model.Conclusions: Our GBM-based predictor of post-LT AKI provides a highly interoperable tool across institutions to assist decision-making after LT.

scholarly journals Novel Method of Classification in Knee Osteoarthritis: Machine Learning Application Versus Logistic Regression Model

2020 ◽  
Vol 44 (6) ◽  
pp. 415-427
Author(s):  
Jung Ho Yang ◽  
Jae Hyeon Park ◽  
Seong-Ho Jang ◽  
Jaesung Cho
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Knee Osteoarthritis ◽  
Logistic Regression Analysis ◽  
Support Vector ◽  
Svm Classifier ◽  
Machine Learning Method ◽  
Learning Method

Objective To present new classification methods of knee osteoarthritis (KOA) using machine learning and compare its performance with conventional statistical methods as classification techniques using machine learning have recently been developed.Methods A total of 84 KOA patients and 97 normal participants were recruited. KOA patients were clustered into three groups according to the Kellgren-Lawrence (K-L) grading system. All subjects completed gait trials under the same experimental conditions. Machine learning-based classification using the support vector machine (SVM) classifier was performed to classify KOA patients and the severity of KOA. Logistic regression analysis was also performed to compare the results in classifying KOA patients with machine learning method.Results In the classification between KOA patients and normal subjects, the accuracy of classification was higher in machine learning method than in logistic regression analysis. In the classification of KOA severity, accuracy was enhanced through the feature selection process in the machine learning method. The most significant gait feature for classification was flexion and extension of the knee in the swing phase in the machine learning method.Conclusion The machine learning method is thought to be a new approach to complement conventional logistic regression analysis in the classification of KOA patients. It can be clinically used for diagnosis and gait correction of KOA patients.

scholarly journals Elevated De Ritis Ratio as a Predictor for Acute Kidney Injury after Radical Retropubic Prostatectomy

2021 ◽  
Vol 11 (9) ◽  
pp. 836
Author(s):  
Jun-Young Park ◽  
Jihion Yu ◽  
Jun Hyuk Hong ◽  
Bumjin Lim ◽  
Youngdo Kim ◽  
...  
Keyword(s):  
Risk Factors ◽  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Logistic Regression Analysis ◽  
Roc Curve ◽  
Kidney Injury ◽  
Radical Retropubic Prostatectomy ◽  
Multivariable Logistic Regression Analysis ◽  
Retropubic Prostatectomy

Acute kidney injury (AKI) is related to mortality and morbidity. The De Ritis ratio, calculated by dividing the aspartate aminotransferase by the alanine aminotransferase, is used as a prognostic indicator. We evaluated risk factors for AKI after radical retropubic prostatectomy (RRP). This retrospective study included patients who performed RRP. Multivariable logistic regression analysis and a receiver operating characteristic (ROC) curve analysis were conducted. Other postoperative outcomes were also evaluated. Among the 1415 patients, 77 (5.4%) had AKI postoperatively. The multivariable logistic regression analysis showed that estimated glomerular filtration rate, albumin level, and the De Ritis ratio at postoperative day 1 were risk factors for AKI. The area under the ROC curve of the De Ritis ratio at postoperative day 1 was 0.801 (cutoff = 1.2). Multivariable-adjusted analysis revealed that the De Ritis ratio at ≥1.2 was significantly related to AKI (odds ratio = 8.637, p < 0.001). Postoperative AKI was associated with longer hospitalization duration (11 ± 5 days vs. 10 ± 4 days, p = 0.002). These results collectively show that an elevated De Ritis ratio at postoperative day 1 is associated with AKI after RRP in patients with prostate cancer.

Differential Diagnosis of Malignant Thyroid Calcification Nodule Based on Computed Tomography Image Texture

2021 ◽  
Vol 11 (3) ◽  
pp. 767-772
Author(s):  
Wenxian Peng ◽  
Yijia Qian ◽  
Yingying Shi ◽  
Shuyun Chen ◽  
Kexin Chen ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Support Vector Machine ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Ensemble Learning ◽  
Logistic Regression Analysis ◽  
Texture Features ◽  
Support Vector ◽  
Classification Algorithms ◽  
Feature Optimization

Purpose: Calcification nodules in thyroid can be found in thyroid disease. Current clinical computed tomography systems can be used to detect calcification nodules. Our aim is to identify the nature of thyroid calcification nodule based on plain CT images. Method: Sixty-three patients (36 benign and 27 malignant nodules) found thyroid calcification nodules were retrospectively analyzed, together with computed tomography images and pathology finding. The regions of interest (ROI) of 6464 pixels containing calcification nodules were manually delineated by radiologists in CT plain images. We extracted thirty-one texture features from each ROI. And nineteen texture features were picked up after feature optimization by logistic regression analysis. All the texture features were normalized to [0, 1]. Four classification algorithms, including ensemble learning, support vector machine, K-nearest neighbor, decision tree, were used as classification algorithms to identity the benign and malignant nodule. Accuracy, PPV, NPV, SEN, and AUC were calculated to evaluate the performance of different classifiers. Results: Nineteen texture features were selected after feature optimization by logistic regression analysis (P <0.05). Both Ensemble Learning and Support Vector Machine achieved the highest accuracy of 97.1%. The PPV, NPV, SEN, and SPC are 96.9%, 97.4%, 98.4%, and 95.0%, respectively. The AUC was 1. Conclusion: Texture features extracted from calcification nodules could be used as biomarkers to identify benign or malignant thyroid calcification.

Sign in / Sign up

Export Citation Format

Share Document