Development of a new mortality scoring system for acute kidney injury with continuous renal replacement therapy

Construction and evaluation of a mortality prediction model for patients with acute kidney injury undergoing continuous renal replacement therapy based on machine learning algorithms

BACKGROUND

To construct and evaluate a predictive model for in-hospital mortality among critically ill patients with acute kidney injury (AKI) undergoing continuous renal replacement therapy (CRRT), based on nine machine learning (ML) algorithm.

METHODS

The study retrospectively included patients with AKI who underwent CRRT during their initial hospitalization in the United States using the medical information mart for intensive care (MIMIC) database IV (version 2.0), as well as in the intensive care unit (ICU) of Huzhou Central Hospital. Patients from the MIMIC database were used as the training cohort to construct the models (from 2008 to 2019, n = 1068). Patients from Huzhou Central Hospital were utilized as the external validation cohort to evaluate the models (from June 2019 to December 2022, n = 327). In the training cohort, least absolute shrinkage and selection operator (LASSO) regression with cross-validation was employed to select features for constructing the model and subsequently established nine ML predictive models. The performance of these nine models on the external validation cohort dataset was comprehensively evaluated based on the area under the receiver operating characteristic curve (AUROC) and the optimal model was selected. A static nomogram and a web-based dynamic nomogram were presented, with a comprehensive evaluation from the perspectives of discrimination (AUROC), calibration (calibration curve) and clinical practicability (DCA curves).

RESULTS

Finally, 1395 eligible patients were enrolled, including 1068 patients in the training cohort and 327 patients in the external validation cohort. In the training cohort, LASSO regression with cross-validation was employed to select features and nine models were individually constructed. Compared to the other eight models, the Lasso regularized logistic regression (Lasso-LR) model exhibited the highest AUROC (0.756) and the optimal calibration curve. The DCA curve suggested a certain clinical utility in predicting in-hospital mortality among critically ill patients with AKI undergoing CRRT. Consequently, the Lasso-LR model was the optimal model and it was visualized as a common nomogram (static nomogram) and a web-based dynamic nomogram (https://chsyh2006.shinyapps.io/dynnomapp/). Discrimination, calibration and DCA curves were employed to assess the performance of the nomogram. The AUROC for the training and external validation cohorts in the nomogram model was 0.771 (95%CI: 0.743, 0.799) and 0.756 (95%CI: 0.702, 0.809), respectively. The calibration slope and Brier score for the training cohort were 1.000 and 0.195, while for the external validation cohort, they were 0.849 and 0.197, respectively. The DCA indicated that the model had a certain clinical application value.

CONCLUSIONS

Our study selected the optimal model and visualized it as a static and dynamic nomogram integrating clinical predictors, so that clinicians can personalized predict the in-hospital outcome of critically ill patients with AKI undergoing CRRT upon ICU admission.

Predicting outcomes of continuous renal replacement therapy using body composition monitoring: a deep-learning approach

Fluid balance is a critical prognostic factor for patients with severe acute kidney injury (AKI) requiring continuous renal replacement therapy (CRRT). This study evaluated whether repeated fluid balance monitoring could improve prognosis in this clinical population. This was a multicenter retrospective study that included 784 patients (mean age, 67.8 years; males, 66.4%) with severe AKI requiring CRRT during 2017-2019 who were treated in eight tertiary hospitals in Korea. Sequential changes in total body water were compared between patients who died (event group) and those who survived (control group) using mixed-effects linear regression analyses. The performance of various machine learning methods, including recurrent neural networks, was compared to that of existing prognostic clinical scores. After adjusting for confounding factors, a marginal benefit of fluid balance was identified for the control group compared to that for the event group (p = 0.074). The deep-learning model using a recurrent neural network with an autoencoder and including fluid balance monitoring provided the best differentiation between the groups (area under the curve, 0.793) compared to 0.604 and 0.606 for SOFA and APACHE II scores, respectively. Our prognostic, deep-learning model underlines the importance of fluid balance monitoring for prognosis assessment among patients receiving CRRT.

Development and validation of clinical prediction models for acute kidney injury recovery at hospital discharge in critically ill adults

PURPOSE

Acute kidney injury (AKI) recovery prediction remains challenging. The purpose of the present study is to develop and validate prediction models for AKI recovery at hospital discharge in critically ill patients with ICU-acquired AKI stage 3 (AKI-3).

METHODS

Models were developed and validated in a development cohort (n = 229) and a matched validation cohort (n = 244) from the multicenter EPaNIC database to create prediction models with the least absolute shrinkage and selection operator (Lasso) machine-learning algorithm. We evaluated the discrimination and calibration of the models and compared their performance with plasma neutrophil gelatinase-associated lipocalin (NGAL) measured on first AKI-3 day (NGAL_AKI3) and reference model that only based on age.

RESULTS

Complete recovery and complete or partial recovery occurred in 33.20% and 51.23% of the validation cohort patients respectively. The prediction model for complete recovery based on age, need for renal replacement therapy (RRT), diagnostic group (cardiac/surgical/trauma/others), and sepsis on admission had an area under the receiver operating characteristics curve (AUROC) of 0.53. The prediction model for complete or partial recovery based on age, need for RRT, platelet count, urea, and white blood cell count had an AUROC of 0.61. NGAL_AKI3 showed AUROCs of 0.55 and 0.53 respectively. In cardiac patients, the models had higher AUROCs of 0.60 and 0.71 than NGAL_AKI3's AUROCs of 0.52 and 0.54. The developed models demonstrated a better performance over the reference models (only based on age) for cardiac surgery patients, but not for patients with sepsis and for a general ICU population.

CONCLUSION

Models to predict AKI recovery upon hospital discharge in critically ill patients with AKI-3 showed poor performance in the general ICU population, similar to the biomarker NGAL. In cardiac surgery patients, discrimination was acceptable, and better than NGAL. These findings demonstrate the difficulty of predicting non-reversible AKI early.

Hyperlactatemia is a predictor of mortality in patients undergoing continuous renal replacement therapy for acute kidney injury

BACKGROUND

Hyperlactatemia occurs frequently in critically ill patients, and this pathologic condition leads to worse outcomes in several disease subsets. Herein, we addressed whether hyperlactatemia is associated with the risk of mortality in patients undergoing continuous renal replacement therapy (CRRT) due to acute kidney injury.

METHODS

A total of 1,661 patients who underwent CRRT for severe acute kidney injury were retrospectively reviewed between 2010 and 2020. The patients were categorized according to their serum lactate levels, such as high (≥ 7.6 mmol/l), moderate (2.1-7.5 mmol/l) and low (≤ 2 mmol/l), at the time of CRRT initiation. The hazard ratios (HRs) for the risk of in-hospital mortality were calculated with adjustment of multiple variables. The increase in the area under the receiver operating characteristic curve (AUROC) for the mortality risk was evaluated after adding serum lactate levels to the Sequential Organ Failure Assessment (SOFA) and the Acute Physiology and Chronic Health Evaluation (APACHE) II score-based models.

RESULTS

A total of 802 (48.3%) and 542 (32.6%) patients had moderate and high lactate levels, respectively. The moderate and high lactate groups had a higher risk of mortality than the low lactate group, with HRs of 1.64 (1.22-2.20) and 4.18 (2.99-5.85), respectively. The lactate-enhanced models had higher AUROCs than the models without lactates (0.764 vs. 0.702 for SOFA score; 0.737 vs. 0.678 for APACHE II score).

CONCLUSIONS

Hyperlactatemia is associated with mortality outcomes in patients undergoing CRRT for acute kidney injury. Serum lactate levels may need to be monitored in this patient subset.

Development of New Equations Predicting the Mortality Risk of Patients on Continuous RRT

Background

Predicting the risk of death in patients admitted to the critical care unit facilitates appropriate management. In particular, among patients who are critically ill, patients with continuous RRT (CRRT) have high mortality, and predicting the mortality risk of these patients is difficult. The purpose of this study was to develop models for predicting the mortality risk of patients on CRRT and to validate the models externally.

Methods

A total of 699 adult patients with CRRT who participated in the VolumE maNagement Under body composition monitoring in critically ill patientS on CRRT (VENUS) trial and 1515 adult patients with CRRT in Seoul National University Hospital were selected as the development and validation cohorts, respectively. Using 11 predictor variables selected by the Cox proportional hazards model and clinical importance, equations predicting mortality within 7, 14, and 28 days were developed with development cohort data.

Results

The equation using 11 variables had area under the time-dependent receiver operating characteristic curve (AUROC) values of 0.75, 0.74, and 0.73 for predicting 7-, 14-, and 28-day mortality, respectively. All equations had significantly higher AUROCs than the Sequential Organ Failure Assessment (SOFA) and Acute Physiology and Chronic Health Evaluation II (APACHE II) scores. The 11-variable equation was superior to the SOFA and APACHE II scores in the integrated discrimination index and net reclassification improvement analyses.

Conclusions

The newly developed equations for predicting CRRT patient mortality showed superior performance to the previous scoring systems, and they can help physicians manage patients.

Development and validation of outcome prediction models for acute kidney injury patients undergoing continuous renal replacement therapy

Object

This study aimed to develop and validate a set of practical predictive tools that reliably estimate the 28-day prognosis of acute kidney injury patients undergoing continuous renal replacement therapy.

Methods

The clinical data of acute kidney injury patients undergoing continuous renal replacement therapy were extracted from the Medical Information Mart for Intensive Care IV database with structured query language and used as the development cohort. An all-subset regression was used for the model screening. Predictive models were constructed via a logistic regression, and external validation of the models was performed using independent external data.

Results

Clinical prediction models were developed with clinical data from 1,148 patients and validated with data from 121 patients. The predictive model based on seven predictors (age, vasopressor use, red cell volume distribution width, lactate, white blood cell count, platelet count, and phosphate) exhibited good predictive performance, as indicated by a C-index of 0.812 in the development cohort, 0.811 in the internal validation cohort and 0.768 in the external validation cohort.

Conclusions

The model reliably predicted the 28-day prognosis of acute kidney injury patients undergoing continuous renal replacement therapy. The predictive items are readily available, and the web-based prognostic calculator (https://libo220284.shinyapps.io/DynNomapp/) can be used as an adjunctive tool to support the management of patients.

Explainable Machine Learning-Based Risk Prediction Model for In-Hospital Mortality after Continuous Renal Replacement Therapy Initiation

In this study, we established an explainable and personalized risk prediction model for in-hospital mortality after continuous renal replacement therapy (CRRT) initiation. This retrospective cohort study was conducted at Changhua Christian Hospital (CCH). A total of 2932 consecutive intensive care unit patients receiving CRRT between 1 January 2010, and 30 April 2021, were identified from the CCH Clinical Research Database and were included in this study. The recursive feature elimination method with 10-fold cross-validation was used and repeated five times to select the optimal subset of features for the development of machine learning (ML) models to predict in-hospital mortality after CRRT initiation. An explainable approach based on ML and the SHapley Additive exPlanation (SHAP) and a local explanation method were used to evaluate the risk of in-hospital mortality and help clinicians understand the results of ML models. The extreme gradient boosting and gradient boosting machine models exhibited a higher discrimination ability (area under curve [AUC] = 0.806, 95% CI = 0.770-0.843 and AUC = 0.823, 95% CI = 0.788-0.858, respectively). The SHAP model revealed that the Acute Physiology and Chronic Health Evaluation II score, albumin level, and the timing of CRRT initiation were the most crucial features, followed by age, potassium and creatinine levels, SPO2, mean arterial pressure, international normalized ratio, and vasopressor support use. ML models combined with SHAP and local interpretation can provide the visual interpretation of individual risk predictions, which can help clinicians understand the effect of critical features and make informed decisions for preventing in-hospital deaths.

Predicting mortality in critically ill patients requiring renal replacement therapy for acute kidney injury in a retrospective single-center study of two cohorts

Half of the critically ill patients with renal replacement therapy (RRT) dependent acute kidney injury (AKI) die within one year despite RRT. General intensive care prediction models perform inadequately in AKI. Predictive models for mortality would be an invaluable complementary tool to aid clinical decision making. We aimed to develop and validate new prediction models for intensive care unit (ICU) and hospital mortality customized for patients with RRT dependent AKI in a retrospective single-center study. The models were first developed in a cohort of 471 critically ill patients with continuous RRT (CRRT) and then validated in a cohort of 193 critically ill patients with intermittent hemodialysis (IHD) as the primary modality for RRT. Forty-two risk factors for mortality were examined at ICU admission and CRRT initiation, respectively, in the first univariate models followed by multivariable model development. Receiver operating characteristics curve analyses were conducted to estimate the area under the curve (AUC), to measure discriminative capacity of the models for mortality. AUCs of the respective models ranged between 0.76 and 0.83 in the CRRT model development cohort, thereby showing acceptable to excellent predictive power for the mortality events (ICU mortality and hospital mortality). The models showed acceptable external validity in a validation cohort of IHD patients. In the IHD validation cohort the AUCs of the MALEDICT RRT initiation model were 0.74 and 0.77 for ICU and hospital mortality, respectively. The MALEDICT model shows promise for mortality prediction in critically ill patients with RRT dependent AKI. After further validation, the model might serve as an additional clinical tool for estimating individual mortality risk at the time of RRT initiation.

Development and Validation of a Prognostic Model to Predict the Risk of In-hospital Death in Patients With Acute Kidney Injury Undergoing Continuous Renal Replacement Therapy After Acute Type a Aortic Dissection

Background

This study aimed to construct a model to predict the risk of in-hospital death in patients with acute renal injury (AKI) receiving continuous renal replacement therapy (CRRT) after acute type A aortic dissection (ATAAD) surgery.

Methods

We reviewed the data of patients with AKI undergoing CRRT after ATAAD surgery. The patients were divided into survival and nonsurvival groups based on their vital status at hospital discharge. The data were analyzed using univariate and multivariate logistic regression analyses. Establish a risk prediction model using a nomogram and its discriminative ability was validated using C statistic and the receiver operating characteristic (ROC) curve. Its calibration ability was tested using a calibration curve, 10-fold cross-validation and Hosmer–Lemeshow test.

Results

Among 175 patients, in-hospital death occurred in 61 (34.9%) patients. The following variables were incorporated in predicting in-hospital death: age > 65 years, lactic acid 12 h after CRRT, liver dysfunction, and permanent neurological dysfunction. The risk model revealed good discrimination (C statistic = 0.868, 95% CI: 0.806–0.930; a bootstrap-corrected C statistic of 0.859, the area under the ROC = 0.868). The calibration curve showed good consistency between predicted and actual probabilities (via 1,000 bootstrap samples, mean absolute error = 2.2%; Hosmer–Lemeshow test, P = 0.846). The 10-fold cross validation of the nomogram showed that the average misdiagnosis rate was 16.64%.

Conclusion

The proposed model could be used to predict the probability of in-hospital death in patients undergoing CRRT for AKI after ATAAD surgery. It had the potential to assist doctors to identify the gravity of the situation and make the targeted therapeutic measures.

Outcomes of Continuous Renal Replacement Therapy in a Community Health System

OBJECTIVE

Continuous renal replacement therapy (CRRT) is commonly used in critically ill, hemodynamically unstable patients with acute kidney injury (AKI). This procedure is resource intensive with reported high in-hospital mortality. We evaluated mortality with CRRT in our healthcare system and markers associated with decreased survival.

METHODS

A retrospective cohort study collected data on patients 18 years or older, without prior history of end stage kidney disease (ESKD), who received CRRT in the intensive care units at one of three hospitals in our health system in Columbus, OH from July 1, 2016 to July 1, 2019. Data included demographics, presenting diagnosis, comorbidities, laboratory markers, and patient disposition. In-hospital mortality rates and sequential organ failure assessment (SOFA) scores were calculated. We then compared information between two groups (patients who died during hospitalization and survivors) using univariate comparisons and multivariate logistic regression models.

RESULTS

In-hospital mortality was 56.8% (95%CI: 53.4-60.1) among patients who received CRRT. Mean SOFA scores did not differ between survival and mortality groups. The odds for in-patient mortality were increased for patients age ≥60 (OR = 1.74, 95%CI: 1.23-2.44), first bilirubin >2 mg/dL (OR = 1.73, 95%CI: 1.12-2.69), first creatinine < 2 mg/dL (OR = 1.57, 95%CI: 1.04-2.37), first lactate > 2 mmol/L (OR = 2.08, 95%CI: 1.43-3.04). The odds for in-patient mortality were decreased for patients with cardiogenic shock (OR = .32, 95%CI: .17-.58) and hemorrhagic shock (OR = .29, 95%CI: .13-.63).

CONCLUSIONS

We report in-hospital mortality rates of 56.8% with CRRT. Unlike prior studies, higher mean SOFA scores were not predictive of higher in-hospital mortality in patients utilizing CRRT.

Prognostic Performance of Existing Scoring Systems among Critically Ill Patients Requiring Continuous Renal Replacement Therapy: An Observational Study

BACKGROUND

Among critical patients, few studies have evaluated the discrimination of current illness scoring systems in predicting outcomes after continuous renal replacement therapy (CRRT) initiation.

METHODS

Patients receiving CRRT in the ICU between 2005 and 2018 from the Chang Gung Research Database were extracted. All the components of the Acute Physiology Assessment and Chronic Health Evaluation (APACHE) III, Sequential Organ Failure Assessment (SOFA), qSOFA, and MOSAIC scoring systems on days 1, 3, and 7 of CRRT were recorded. Patients older than 80 years were identified and analyzed separately.

RESULTS

We identified 3370 adult patients for analysis. The discrimination ability of the scoring systems was acceptable at day 7 after CRRT initiation, including SOFA (area under the receiver operating characteristic curve, 74.1% (95% confidence interval, 71.7-76.5%)), APACHEIII (74.7% (72.3-77.1%)), and MOSAIC (71.3% (68.8%-73.9%)). These systems were not ideal on days 1 and 3, and that of qSOFA was poor at any time point. The discrimination performance was slightly better among patients ≥80 years.

CONCLUSIONS

APACHE III, MOSAIC, and SOFA can be intensivists and families' reference to make their decision of withdrawing or withholding CRRT after a short period of treatment, especially in adults ≥80 years old.

Machine learning model to predict hypotension after starting continuous renal replacement therapy

Hypotension after starting continuous renal replacement therapy (CRRT) is associated with worse outcomes compared with normotension, but it is difficult to predict because several factors have interactive and complex effects on the risk. The present study applied machine learning algorithms to develop models to predict hypotension after initiating CRRT. Among 2349 adult patients who started CRRT due to acute kidney injury, 70% and 30% were randomly assigned into the training and testing sets, respectively. Hypotension was defined as a reduction in mean arterial pressure (MAP) ≥ 20 mmHg from the initial value within 6 h. The area under the receiver operating characteristic curves (AUROCs) in machine learning models, such as support vector machine (SVM), deep neural network (DNN), light gradient boosting machine (LGBM), and extreme gradient boosting machine (XGB) were compared with those in disease-severity scores such as the Sequential Organ Failure Assessment and Acute Physiology and Chronic Health Evaluation II. The XGB model showed the highest AUROC (0.828 [0.796-0.861]), and the DNN and LGBM models followed with AUROCs of 0.822 (0.789-0.856) and 0.813 (0.780-0.847), respectively; all machine learning AUROC values were higher than those obtained from disease-severity scores (AUROCs < 0.6). Although other definitions of hypotension were used such as a reduction of MAP ≥ 30 mmHg or a reduction occurring within 1 h, the AUROCs of machine learning models were higher than those of disease-severity scores. Machine learning models successfully predict hypotension after starting CRRT and can serve as the basis of systems to predict hypotension before starting CRRT.

GDF-15 Predicts In-Hospital Mortality of Critically Ill Patients with Acute Kidney Injury Requiring Continuous Renal Replacement Therapy: A Multicenter Prospective Study

Growth differentiation factor-15 (GDF-15) is a stress-responsive cytokine. This study evaluated the association between GDF-15 and in-hospital mortality among patients with severe acute kidney injury (AKI) requiring continuous renal replacement therapy (CRRT). Among the multicenter prospective CRRT cohort between 2017 and 2019, 66 patients whose blood sample was available were analyzed. Patients were divided into three groups according to the GDF-15 concentrations. The median GDF-15 level was 7865.5 pg/mL (496.9 pg/mL in the healthy control patients). Baseline characteristics were not different among tertile groups except the severity scores and serum lactate level, which were higher in the third tertile. After adjusting for confounding factors, the patients with higher GDF-15 had significantly increased risk of mortality (second tertile: adjusted hazards ratio [aHR], 3.67; 95% confidence interval [CI], 1.05-12.76; p = 0.041; third tertile: aHR, 6.81; 95% CI, 1.98-23.44; p = 0.002). Furthermore, GDF-15 predicted in-hospital mortality (area under the curve, 0.710; 95% CI, 0.585-0.815) better than APACHE II and SOFA scores. Serum GDF-15 concentration was elevated in AKI patients requiring CRRT, higher in more severe patients. GDF-15 is a better independent predictor for in-hospital mortality of critically ill AKI patients than the traditional risk scoring system such as APACHE II and SOFA scores.

Balancing the Needs of Acute and Maintenance Dialysis Patients during the COVID-19 Pandemic: A Proposed Ethical Framework for Dialysis Allocation

The COVID-19 pandemic continues to strain health care systems and drive shortages in medical supplies and equipment around the world. Resource allocation in times of scarcity requires transparent, ethical frameworks to optimize decision making and reduce health care worker and patient distress. The complexity of allocating dialysis resources for both patients receiving acute and maintenance dialysis has not previously been addressed. Using a rapid, collaborative, and iterative process, BC Renal, a provincial network in Canada, engaged patients, doctors, ethicists, administrators, and nurses to develop a framework for addressing system capacity, communication challenges, and allocation decisions. The guiding ethical principles that underpin this framework are (1) maximizing benefits, (2) treating people fairly, (3) prioritizing the worst-off individuals, and (4) procedural justice. Algorithms to support resource allocation and triage of patients were tested using simulations, and the final framework was reviewed and endorsed by members of the provincial nephrology community. The unique aspects of this allocation framework are the consideration of two diverse patient groups who require dialysis (acute and maintenance), and the application of two allocation criteria (urgency and prognosis) to each group in a sequential matrix. We acknowledge the context of the Canadian health care system, and a universal payer in which this framework was developed. The intention is to promote fair decision making and to maintain an equitable reallocation of limited resources for a complex problem during a pandemic.

Comparison of Approaches for Prediction of Renal Replacement Therapy-Free Survival in Patients with Acute Kidney Injury

BACKGROUND/AIMS

Acute kidney injury (AKI) in critically ill patients is common, and continuous renal replacement therapy (CRRT) is a preferred mode of renal replacement therapy (RRT) in hemodynamically unstable patients. Prediction of clinical outcomes in patients on CRRT is challenging. We utilized several approaches to predict RRT-free survival (RRTFS) in critically ill patients with AKI requiring CRRT.

METHODS

We used the Medical Information Mart for Intensive Care (MIMIC-III) database to identify patients ≥18 years old with AKI on CRRT, after excluding patients who had ESRD on chronic dialysis, and kidney transplantation. We defined RRTFS as patients who were discharged alive and did not require RRT ≥7 days prior to hospital discharge. We utilized all available biomedical data up to CRRT initiation. We evaluated 7 approaches, including logistic regression (LR), random forest (RF), support vector machine (SVM), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), multilayer perceptron (MLP), and MLP with long short-term memory (MLP + LSTM). We evaluated model performance by using area under the receiver operating characteristic (AUROC) curves.

RESULTS

Out of 684 patients with AKI on CRRT, 205 (30%) patients had RRTFS. The median age of patients was 63 years and their median Simplified Acute Physiology Score (SAPS) II was 67 (interquartile range 52-84). The MLP + LSTM showed the highest AUROC (95% CI) of 0.70 (0.67-0.73), followed by MLP 0.59 (0.54-0.64), LR 0.57 (0.52-0.62), SVM 0.51 (0.46-0.56), AdaBoost 0.51 (0.46-0.55), RF 0.44 (0.39-0.48), and XGBoost 0.43 (CI 0.38-0.47).

CONCLUSIONS

A MLP + LSTM model outperformed other approaches for predicting RRTFS. Performance could be further improved by incorporating other data types.

Target value of mean arterial pressure in patients undergoing continuous renal replacement therapy due to acute kidney injury

Background

Although patients undergoing continuous renal replacement therapy (CRRT) due to acute kidney injury (AKI) frequently have instability in mean arterial pressure (MAP), no consensus exists on the target value of MAP related to high mortality after CRRT.

Methods

A total of 2,292 patients who underwent CRRT due to AKI in three referral hospitals were retrospectively reviewed. The MAPs were divided into tertiles, and the 3^rd tertile group served as a reference in the analyses. The major outcome was all-cause mortality during the intensive care unit period. The odds ratio (OR) of mortality was calculated using logistic regression after adjustment for multiple covariates. The nonlinear relationship regression model was applied to determine the threshold value of MAP related to increasing mortality.

Results

The mean value of MAP was 80.7 ± 17.3 mmHg at the time of CRRT initiation. The median intensive care unit stay was 5 days (interquartile range, 2–12 days), and during this time, 1,227 (55.5%) patients died. The 1^st tertile group of MAP showed an elevated risk of mortality compared with the 3^rd tertile group (adjusted OR, 1.28 [1.03–1.60]; P = 0.029). In the nonlinear regression analysis, the threshold value of MAP was calculated as 82.7 mmHg. Patients with MAP < 82.7 mmHg had a higher mortality rate than those with ≥ 82.7 mmHg (adjusted OR, 1.21 [1.01–1.45]; P = 0.037).

Conclusions

Low MAP at CRRT initiation is associated with a high risk of mortality, particularly when it is < 82.7 mmHg. This value may be used for risk classification and as a potential therapeutic target.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12882-020-02227-4.

Machine learning algorithm to predict mortality in patients undergoing continuous renal replacement therapy

Background

Previous scoring models such as the Acute Physiologic Assessment and Chronic Health Evaluation II (APACHE II) and the Sequential Organ Failure Assessment (SOFA) scoring systems do not adequately predict mortality of patients undergoing continuous renal replacement therapy (CRRT) for severe acute kidney injury. Accordingly, the present study applies machine learning algorithms to improve prediction accuracy for this patient subset.

Methods

We randomly divided a total of 1571 adult patients who started CRRT for acute kidney injury into training (70%, n = 1094) and test (30%, n = 477) sets. The primary output consisted of the probability of mortality during admission to the intensive care unit (ICU) or hospital. We compared the area under the receiver operating characteristic curves (AUCs) of several machine learning algorithms with that of the APACHE II, SOFA, and the new abbreviated mortality scoring system for acute kidney injury with CRRT (MOSAIC model) results.

Results

For the ICU mortality, the random forest model showed the highest AUC (0.784 [0.744–0.825]), and the artificial neural network and extreme gradient boost models demonstrated the next best results (0.776 [0.735–0.818]). The AUC of the random forest model was higher than 0.611 (0.583–0.640), 0.677 (0.651–0.703), and 0.722 (0.677–0.767), as achieved by APACHE II, SOFA, and MOSAIC, respectively. The machine learning models also predicted in-hospital mortality better than APACHE II, SOFA, and MOSAIC.

Conclusion

Machine learning algorithms increase the accuracy of mortality prediction for patients undergoing CRRT for acute kidney injury compared with previous scoring models.