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 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 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 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.

scholarly journals A deep-learning model to continuously predict severe acute kidney injury based on urine output changes in critically ill patients

2021 ◽  
Author(s):  
Francesca Alfieri ◽  
Andrea Ancona ◽  
Giovanni Tripepi ◽  
Dario Crosetto ◽  
Vincenzo Randazzo ◽  
...  
Keyword(s):  
At Risk ◽  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Deep Learning ◽  
Logistic Regression Analysis ◽  
Urine Output ◽  
Kidney Injury ◽  
Learning Model ◽  
Deep Learning Model

Abstract Background Acute Kidney Injury (AKI), a frequent complication of pateints in the Intensive Care Unit (ICU), is associated with a high mortality rate. Early prediction of AKI is essential in order to trigger the use of preventive care actions. Methods The aim of this study was to ascertain the accuracy of two mathematical analysis models in obtaining a predictive score for AKI development. A deep learning model based on a urine output trends was compared with a logistic regression analysis for AKI prediction in stages 2 and 3 (defined as the simultaneous increase of serum creatinine and decrease of urine output, according to  the Acute Kidney Injury Network (AKIN) guidelines). Two retrospective datasets including 35,573 ICU patients were analyzed. Urine output data were used to train and test the logistic regression and the deep learning model. Results The deep learning model defined an area under the curve (AUC) of 0.89 (± 0.01), sensitivity = 0.8 and specificity = 0.84, which was higher than the logistic regression analysis. The deep learning model was able to predict 88% of AKI cases more than 12 h before their onset: for every 6 patients identified as being at risk of AKI by the deep learning model, 5 experienced the event. On the contrary, for every 12 patients not considered to be at risk by the model, 2 developed AKI. Conclusion In conclusion, by using urine output trends, deep learning analysis was able to predict AKI episodes more than 12 h in advance, and with a higher accuracy than the classical urine output thresholds. We suggest that this algorithm could be integrated in the ICU setting to better manage, and potentially prevent, AKI episodes. Graphic abstract

scholarly journals Incidence of Contrast Induced Acute Kidney Injury, Its Risk Factors and In-Hospital Outcomes in Patients Undergoing Coronary Angiography and Angioplasty

2020 ◽  
Vol 42 (2) ◽  
pp. 59-63
Author(s):  
Prashun Upadhaya ◽  
Pradeep Thapa ◽  
Ratna M Gajurel ◽  
Mahesh R Sigdel
Keyword(s):  
Risk Factors ◽  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Statistical Analysis ◽  
Coronary Angiography ◽  
Logistic Regression Analysis ◽  
Kidney Injury ◽  
Increased Risk ◽  
Contrast Exposure

Introduction Contrast-induced acute kidney injury (CI-AKI) is a serious complication of angiographic procedures with significant morbidity and mortality. We aimed to find the incidence, risk factors and outcomes of CI-AKI in patients who have undergone coronary angiography/angioplasty in a referral hospital in Nepal. MethodsIt was a descriptive observational study of consenting consecutive patients above 18 years undergoing coronary angiography/angioplasty at Manmohan Cardiothoracic Vascular and Transplant Centre, Nepal from July 2015 to September 2017. CI AKI was defined as an elevation of serum creatinine of >25% or ≥0.5 mg/dl (44 μmol/L) from baseline within 48 hour of exposure to contrast. Statistical analysis was performed using SPSS 18 software. Statistical analysis was completed using Student’s t-test, chi-square test and multivariable logistic regression analysis. ResultsOut of 240 patients, 156 (65%) were male, mean age was 60.36±11.29 years. Eighteen patients (7.5%) developed CI-AKI. Incidence of CI-AKI was 20% in patients with chronic kidney disease (CKD), 5.4% in diabetics, 13.6% in patients >70 years, 12.79 % in patients with anaemia and 12.3% in patients with prior contrast exposure. Multivariate logistic regression analysis found smoking and history of prior contrast exposure to be independent predictors for development of CI-AKI. Among patients with CI-AKI, one (5.88%) required dialysis and one (5.88%) died. ConclusionIncidence of CI-AKI after coronary angiography/angioplasty was 7.5%. Patients with prior contrast exposure and smoking were at significantly increased risk of CI-AKI; higher trend of CI-AKI was seen in patients with CKD, diabetes, elderly and anaemia.

scholarly journals A Risk Prediction Model for Acute Kidney Injury in Pulmonary Tuberculosis Patients during Anti-tuberculosis Treatment

2021 ◽  
Author(s):  
Zhi xiang Du ◽  
Fang Chang ◽  
Zi jian Wang ◽  
Da ming Zhou ◽  
Yang Li ◽  
...  
Keyword(s):  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Pulmonary Tuberculosis ◽  
Prediction Model ◽  
Risk Prediction ◽  
Logistic Regression Analysis ◽  
Predictive Factors ◽  
Kidney Injury ◽  
Ca 125

Abstract Background Acute kidney injury (AKI) is not a rare complication during anti-tuberculosis treatment in some pulmonary tuberculosis (PTB) patients. We aimed to develop a risk prediction model to early recognize PTB patients at high risk of AKI during anti-TB treatment.Methods In this retrospective cohort study, clinical baseline, and laboratory test data of 315 inpatients with active PTB from January 2019 and June 2020 were screened for predictive factors. The factors were analyzed by logistic regression analysis. A nomogram was established by the results of the logistic regression analysis. The prediction model discrimination and calibration were evaluated by the concordance index (C-Index), ROC Curve, and Hosmer-Lemeshow analysis.Results 7 factors (Microalbuminuria, Hematuria, CYS-C, Albumin, eGFR, BMI and CA-125) are acquired to develop the predictive model. According to the logistic regression, Microalbuminuria (OR=3.038, 95% CI 1.168-7.904), Hematuria (OR=3.656, 95% CI 1.325-10.083), CYS-C (OR=4.416, 95% CI 2.296-8.491), CA-125 (OR=3.93, 95% CI 1.436-10.756) were risk parameter and ALB (OR=0.741, 95% CI 0.650-0.844) was protective parameter. The nomogram demonstrated a good prediction in estimating AKI. C-Index= 0.967, AUC=0.967, 95% CI (0.941-0.984) Sensitivity=91.04%, Specificity=93.95%, Hosmer-Lemeshow analysis SD=0.00054, Quantile of absolute error=0.049. Conclusion Microalbuminuria, Hematuria, Albumin reduction, elevated CYS-C, and CA125 are predictive factors for AKI in PTB patients during anti-tuberculosis treatments. The predictive nomogram based on five predictive factors is achieved a good risk prediction of AKI during anti-tuberculosis treatments.

scholarly journals Does Aspartate Aminotransferase to Alanine Aminotransferase Ratio Predict Acute Kidney Injury After Cardiac Surgery?

2021 ◽  
Vol 24 (3) ◽  
pp. E506-E511
Author(s):  
Yildirim Gultekin ◽  
Ali Bolat ◽  
Keles Hatice ◽  
Atike Tekeli Kunt
Keyword(s):  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Cardiac Surgery ◽  
Logistic Regression Analysis ◽  
Aspartate Aminotransferase ◽  
Alanine Aminotransferase ◽  
Kidney Injury ◽  
Diagnosis And Prognosis ◽  
Postoperative Aki

Background: Aspartate aminotransferase (AST) to alanine aminotransferase (ALT) ratio (AST/ALT) frequently is used in the diagnosis and prognosis of liver diseases, however it is also used in the diagnosis and prognosis of many other diseases, such as myocardial infarction, acute ischemic stroke, and peripheral artery disease. Acute kidney injury (AKI) is one of the most important complications after cardiac surgery and is one of the main causes of morbidity and mortality. The purpose of the study was to analyze the relationship between AST to ALT and AKI after isolated coronary artery bypass graft surgery (CABG). Methods: We retrospectively reviewed the prospectively collected data of 253 adult patients, who underwent isolated CABG surgery with normal renal function (baseline serum creatinine value <1.4 mg/dL). Preoperative (T0) and postoperative day 1 and day 3 (T1 and T2) serum AST and ALT levels were analyzed, and AST/ALT was calculated. A preoperative AST/ALT of 1.22 was found to be the best cutoff point for predicting postoperative AKI. Kidney injury was interpreted, according to RIFLE classification. The effect of AST to ALT ratio on AKI after CABG was determined using logistic regression analysis, and the results were expressed as odds ratio (OR) with a 95% confidence interval (CI). A P value < .05 was considered statistically significant. Results: Postoperative AKI occurred in 40 patients (15.8%). On logistic regression analysis, higher AST/ALT both preoperatively and postoperatively were associated with an increased incidence of postoperative AKI (T0: OR, 3.983; 95% CI, 1.940-8.180, P < .001, T1: OR, 2.760; 95% CI, 1.381-5.515, P = .004, T2: OR, 2.515; 95% CI, 1.195-5.294, P = .015). Conclusion: Preoperative and postoperative elevated AST to ALT ratio seems to be associated with an increased incidence of AKI after elective isolated CABG surgery.

scholarly journals Effects of Anesthetic Technique on the Occurrence of Acute Kidney Injury after Spine Surgery: A Retrospective Cohort Study

2021 ◽  
Vol 10 (23) ◽  
pp. 5653
Author(s):  
Jiwon Han ◽  
Ah-Young Oh ◽  
Chang-Hoon Koo ◽  
Yu Kyung Bae ◽  
Yong-Tae Jeon
Keyword(s):  
Risk Factors ◽  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Propensity Score ◽  
Propensity Score Matching ◽  
Spine Surgery ◽  
Logistic Regression Analysis ◽  
Kidney Injury ◽  
Volatile Anesthetics

The effects of anesthetics on acute kidney injury (AKI) after spine surgery have not been evaluated fully. This study compared propofol-based total intravenous anesthesia (TIVA) and volatile anesthetics in the development of AKI after spine surgery. This retrospective study reviewed patients who underwent spine surgery between 2015 and 2019. A logistic regression analysis was performed to identify risk factors for AKI. Additionally, after propensity score matching, the incidence of AKI was compared between TIVA and volatile groups. Of the 4473 patients, 709 were excluded and 3764 were included in the logistic regression. After propensity score matching, 766 patients from each group were compared, and we found that the incidence of AKI was significantly lower in the TIVA group (1% vs. 4.2%, p < 0.001). In the multivariate logistic regression analysis, the risk factors for postoperative AKI were male sex (OR 1.85, 95% CI 1.18–3.06), hypertension (OR 2.48, 95% CI 1.56–3.94), anemia (OR 2.66, 95% CI 1.76–4.04), and volatile anesthetics (OR 4.69, 95% CI 2.24–9.84). Compared with volatile anesthetics, TIVA is associated with a reduced risk of AKI for patients who have undergone spine surgery.

scholarly journals O63: POST-OPERATIVE ACUTE KIDNEY INJURY IN PATIENTS UNDERGOING MAJOR GASTROINTESTINAL SURGERY— AN OBSERVATIONAL COHORT STUDY AND EXTERNAL VALIDATION OF A PROGNOSTIC MODEL

2021 ◽  
Vol 108 (Supplement_1) ◽  
Author(s):  
Keyword(s):  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Logistic Regression Analysis ◽  
Cox Regression ◽  
Gastrointestinal Surgery ◽  
Kidney Injury ◽  
One Year ◽  
Postoperative Aki

Abstract Introduction Acute kidney injury (AKI) is well-recognised as a significant cause of morbidity and mortality. Due to limited evidence on the longer-term implications, this study aimed to explore the association of postoperative AKI one-year survival and renal function in patients undergoing major gastrointestinal and liver surgery. Method Patients undergoing major gastrointestinal surgery in the prospective Outcomes of Kidney Injury after Surgery (OAKS) study across UK and Ireland were followed up at one-year postoperatively. The primary outcome was survival at 1-year and secondary outcomes included the composite “Major Adverse Kidney Events” outcome at day 365 (MAKE-365), with respective multivariable Cox-regression and logistic regression analysis performed. Result Of 62.2% of OAKS patients (n=3,575/5,745) with 1-year follow-up, there were no significant differences compared to those without follow-up. Among the follow-up cohort, 8.0% (n=269) patients died. On univariate analysis, patients experiencing 7-day postoperative AKI had a significantly higher hazard of death between 30 to 365 days postoperatively (HR: 2.10, 95% CI: 1.50-2.94, p&lt;0.001) compared to patients who did not. This persisted on multivariable Cox-regression (HR: 1.67, 95% CI: 1.17-2.40, p=0.005). Furthermore, 9.1% (n=305) patients met the MAKE-365 endpoint. Multilevel logistic regression analysis demonstrated that the MAKE-365 endpoint was independently associated with both stage 1 (OR: 1.78, 95% CI: 1.22-2.61, p=0.003) and stage 2-3 7-day postoperative AKI (OR: 6.13, 95% CI: 3.97-9.45, p&lt;0.001). Conclusion Post-operative AKI is associated with significantly higher rate of 1-year mortality and MAKE-365 endpoints. Improved monitoring of these patients may be warranted to identify and facilitate potential avenues for intervention Take-home message Post-operative AKI is associated with significantly higher rate of 1-year mortality. Hence, early detection and improved monitoring of patients with AKI with improve long-term outcomes of these patients.

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.

Sign in / Sign up

Export Citation Format

Share Document