A Prediction Model for Assessing Prognosis in Critically Ill Patients with Sepsis-associated Acute Kidney Injury

Machine learning-based prediction of in-hospital mortality for critically ill patients with sepsis-associated acute kidney injury

OBJECTIVES

This study aims to develop and validate a prediction model in-hospital mortality in critically ill patients with sepsis-associated acute kidney injury (SA-AKI) based on machine learning algorithms.

METHODS

Patients who met the criteria for inclusion were identified in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database and divided according to the validation (n = 2440) and development (n = 9756, 80%) queues. Ensemble stepwise feature selection method was used to screen for effective features. The prediction models of short-term mortality were developed by seven machine learning algorithms. Ten-fold cross-validation was used to verify the performance of the algorithm in the development queue. The area under the receiver operating characteristic curve (ROC-AUC) was used to evaluate the differentiation accuracy and performance of the prediction model in the validation queue. The best-performing model was interpreted by Shapley additive explanations (SHAP).

RESULTS

A total of 12,196 patients were enrolled in this study. Eleven variables were finally chosen to develop the prediction model. The AUC of the random forest (RF) model was the highest value both in the Ten-fold cross-validation and evaluation (AUC: 0.798, 95% CI: 0.774-0.821). According to the SHAP plots, old age, low Glasgow Coma Scale (GCS) score, high AKI stage, reduced urine output, high Simplified Acute Physiology Score (SAPS II), high respiratory rate, low temperature, low absolute lymphocyte count, high creatinine level, dysnatremia, and low body mass index (BMI) increased the risk of poor prognosis.

CONCLUSIONS

The RF model developed in this study is a good predictor of in-hospital mortality for patients with SA-AKI in the intensive care unit (ICU), which may have potential applications in mortality prediction.

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.

Predictive models of sepsis-associated acute kidney injury based on machine learning: a scoping review

BACKGROUND

With the development of artificial intelligence, the application of machine learning to develop predictive models for sepsis-associated acute kidney injury has made potential breakthroughs in early identification, grading, diagnosis, and prognosis determination.

METHODS

Here, we conducted a systematic search of the PubMed, Cochrane Library, Embase (Ovid), Web of Science, and Scopus databases on April 28, 2023, and screened relevant literature. Then, we comprehensively extracted relevant data related to machine learning algorithms, predictors, and predicted objectives. We subsequently performed a critical evaluation of research quality, data aggregation, and analyses.

RESULTS

We screened 25 studies on predictive models for sepsis-associated acute kidney injury from a total of originally identified 2898 studies. The most commonly used machine learning algorithm is traditional logistic regression, followed by eXtreme gradient boosting. We categorized these predictive models into early identification models (60%), prognostic prediction models (32%), and subtype identification models (8%) according to their predictive purpose. The five most commonly used predictors were serum creatinine levels, lactate levels, age, blood urea nitrogen concentration, and diabetes mellitus. In addition, a single data source, insufficient assessment of clinical utility, lack of model bias assessment, and hyperparameter adjustment may be the main reasons for the low quality of the current research.

CONCLUSIONS

However, studies on the nondeath prognostic outcomes, the long-term clinical outcomes, and the subtype identification models are insufficient. Additionally, the poor quality of the research and the insufficient practicality of the model are problems that need to be addressed urgently.

Using machine learning to predict the risk of short-term and long-term death in acute kidney injury patients after commencing CRRT

BACKGROUND

The mortality rate and prognosis of short-term and long-term acute kidney injury (AKI) patients who undergo continuous renal replacement therapy (CRRT) are different. Setting up risk stratification tools for both short-term and long-term deaths is highly important for clinicians.

METHOD

A total of 1535 AKI patients receiving CRRT were included in this study, with 1144 from the training set (the Dryad database) and 391 from the validation set (MIMIC IV database). A model for predicting mortality within 10 and 90 days was built using nine different machine learning (ML) algorithms. AUROC, F1-score, accuracy, sensitivity, specificity, precision, and calibration curves were used to assess the predictive performance of various ML models.

RESULTS

A total of 420 (31.1%) deaths occurred within 10 days, and 1080 (68.8%) deaths occurred within 90 days. The random forest (RF) model performed best in both predicting 10-day (AUROC: 0.80, 95% CI: 0.74-0.84; accuracy: 0.72, 95% CI: 0.67-0.76; F1-score: 0.59) and 90-day mortality (AUROC: 0.78, 95% CI: 0.73-0.83; accuracy: 0.73, 95% CI: 0.69-0.78; F1-score: 0.80). The importance of the feature shows that SOFA scores are rated as the most important risk factor for both 10-day and 90-day mortality.

CONCLUSION

Our study, utilizing multiple machine learning models, estimates the risk of short-term and long-term mortality among AKI patients who commence CRRT. The results demonstrated that the prognostic factors for short-term and long-term mortality are different. The RF model has the best prediction performance and has valuable potential for clinical application.

Machine learning for the prediction of 1-year mortality in patients with sepsis-associated acute kidney injury

INTRODUCTION

Sepsis-associated acute kidney injury (SA-AKI) is strongly associated with poor prognosis. We aimed to build a machine learning (ML)-based clinical model to predict 1-year mortality in patients with SA-AKI.

METHODS

Six ML algorithms were included to perform model fitting. Feature selection was based on the feature importance evaluated by the SHapley Additive exPlanations (SHAP) values. Area under the receiver operating characteristic curve (AUROC) was used to evaluate the discriminatory ability of the prediction model. Calibration curve and Brier score were employed to assess the calibrated ability. Our ML-based prediction models were validated both internally and externally.

RESULTS

A total of 12,750 patients with SA-AKI and 55 features were included to build the prediction models. We identified the top 10 predictors including age, ICU stay and GCS score based on the feature importance. Among the six ML algorithms, the CatBoost showed the best prediction performance with an AUROC of 0.813 and Brier score of 0.119. In the external validation set, the predictive value remained favorable (AUROC = 0.784).

CONCLUSION

In this study, we developed and validated a ML-based prediction model based on 10 commonly used clinical features which could accurately and early identify the individuals at high-risk of long-term mortality in patients with SA-AKI.

Artificial intelligence and machine learning's role in sepsis-associated acute kidney injury

Sepsis-associated acute kidney injury (SA-AKI) is a serious complication in critically ill patients, resulting in higher mortality, morbidity, and cost. The intricate pathophysiology of SA-AKI requires vigilant clinical monitoring and appropriate, prompt intervention. While traditional statistical analyses have identified severe risk factors for SA-AKI, the results have been inconsistent across studies. This has led to growing interest in leveraging artificial intelligence (AI) and machine learning (ML) to predict SA-AKI better. ML can uncover complex patterns beyond human discernment by analyzing vast datasets. Supervised learning models like XGBoost and RNN-LSTM have proven remarkably accurate at predicting SA-AKI onset and subsequent mortality, often surpassing traditional risk scores. Meanwhile, unsupervised learning reveals clinically relevant sub-phenotypes among diverse SA-AKI patients, enabling more tailored care. In addition, it potentially optimizes sepsis treatment to prevent SA-AKI through continual refinement based on patient outcomes. However, utilizing AI/ML presents ethical and practical challenges regarding data privacy, algorithmic biases, and regulatory compliance. AI/ML allows early risk detection, personalized management, optimal treatment strategies, and collaborative learning for SA-AKI management. Future directions include real-time patient monitoring, simulated data generation, and predictive algorithms for timely interventions. However, a smooth transition to clinical practice demands continuous model enhancements and rigorous regulatory oversight. In this article, we outlined the conventional methods used to address SA-AKI and explore how AI and ML can be applied to diagnose and manage SA-AKI, highlighting their potential to revolutionize SA-AKI care.

Histone H3K18 and Ezrin Lactylation Promote Renal Dysfunction in Sepsis-Associated Acute Kidney Injury

Histone lactylation is a metabolic stress-related histone modification. However, the role of histone lactylation in the development of sepsis-associated acute kidney injury (SA-AKI) remains unclear. Here, histone H3K18 lactylation (H3K18la) is elevated in SA-AKI, which is reported in this study. Furthermore, this lactate-dependent histone modification is enriched at the promoter of Ras homolog gene family member A (RhoA) and positively correlated with the transcription. Correction of abnormal lactate levels resulted in a reversal of abnormal histone lactylation at the promoter of RhoA. Examination of related mechanism revealed that histone lactylation promoted the RhoA/Rho-associated protein kinase (ROCK) /Ezrin signaling, the activation of nuclear factor-κB (NF-κB), inflammation, cell apoptosis, and aggravated renal dysfunction. In addition, Ezrin can undergo lactylation modification. Multiple lactylation sites are identified in Ezrin and confirmed that lactylation mainly occurred at the K263 site. The role of histone lactylation is revealed in SA-AKI and reportes a novel post-translational modification in Ezrin. Its potential role in regulating inflammatory metabolic adaptation of renal proximal tubule epithelial cells is also elucidated. The results provide novel insights into the epigenetic regulation of the onset of SA-AKI.

Interpretable machine learning model for predicting acute kidney injury in critically ill patients

BACKGROUND

This study aimed to create a method for promptly predicting acute kidney injury (AKI) in intensive care patients by applying interpretable, explainable artificial intelligence techniques.

METHODS

Population data regarding intensive care patients were derived from the Medical Information Mart for Intensive Care IV database from 2008 to 2019. Machine learning (ML) techniques with six methods were created to construct the predicted models for AKI. The performance of each ML model was evaluated by comparing the areas under the curve (AUC). Local Interpretable Model-Agnostic Explanations (LIME) method and Shapley Additive exPlanation values were used to decipher the best model.

RESULTS

According to inclusion and exclusion criteria, 53,150 severely sick individuals were included in the present study, of which 42,520 (80%) were assigned to the training group, and 10,630 (20%) were allocated to the validation group. Compared to the other five ML models, the eXtreme Gradient Boosting (XGBoost) model greatly predicted AKI following ICU admission, with an AUC of 0.816. The top four contributing variables of the XGBoost model were SOFA score, weight, mechanical ventilation, and the Simplified Acute Physiology Score II. An AKI and Non-AKI cases were predicted separately using the LIME algorithm.

CONCLUSION

Overall, the constructed clinical feature-based ML models are excellent in predicting AKI in intensive care patients. It would be constructive for physicians to provide early support and timely intervention measures to intensive care patients at risk of AKI.

Machine learning for prediction of acute kidney injury in patients diagnosed with sepsis in critical care

BACKGROUND AND OBJECTIVE

Acute Kidney Injury (AKI) is a common and severe complication in patients diagnosed with sepsis. It is associated with higher mortality rates, prolonged hospital stays, increased utilization of medical resources, and financial burden on patients' families. This study aimed to establish and validate predictive models using machine learning algorithms to accurately predict the occurrence of AKI in patients diagnosed with sepsis.

METHODS

This retrospective study utilized real observational data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. It included patients aged 18 to 90 years diagnosed with sepsis who were admitted to the ICU for the first time and had hospital stays exceeding 48 hours. Predictive models, employing various machine learning algorithms including Light Gradient Boosting Machine (LightGBM), EXtreme Gradient Boosting (XGBoost), Random Forest (RF), Decision Tree (DT), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Logistic Regression (LR), were developed. The dataset was randomly divided into training and test sets at a ratio of 4:1.

RESULTS

A total of 10,575 sepsis patients were included in the analysis, of whom 8,575 (81.1%) developed AKI during hospitalization. A selection of 47 variables was utilized for model construction. The models derived from LightGBM, XGBoost, RF, DT, ANN, SVM, and LR achieved AUCs of 0.801, 0.773, 0.772, 0.737, 0.720, 0.765, and 0.776, respectively. Among these models, LightGBM demonstrated the most superior predictive performance.

CONCLUSIONS

These machine learning models offer valuable predictive capabilities for identifying AKI in patients diagnosed with sepsis. The LightGBM model, with its superior predictive capability, could aid clinicians in early identification of high-risk patients.

The prediction of in-hospital mortality in elderly patients with sepsis-associated acute kidney injury utilizing machine learning models

Background

Sepsis-associated acute kidney injury (SA-AKI) is a severe complication associated with poorer prognosis and increased mortality, particularly in elderly patients. Currently, there is a lack of accurate mortality risk prediction models for these patients in clinic.

Objectives

This study aimed to develop and validate machine learning models for predicting in-hospital mortality risk in elderly patients with SA-AKI.

Methods

Machine learning models were developed and validated using the public, high-quality Medical Information Mart for Intensive Care (MIMIC)-IV critically ill database. The recursive feature elimination (RFE) algorithm was employed for key feature selection. Eleven predictive models were compared, with the best one selected for further validation. Shapley Additive Explanations (SHAP) values were used for visualization and interpretation, making the machine learning models clinically interpretable.

Results

There were 16,154 patients with SA-AKI in the MIMIC-IV database, and 8426 SA-AKI patients were included in this study (median age: 77.0 years; female: 45%). 7728 patients excluded based on these criteria. They were randomly divided into a training cohort (5,934, 70%) and a validation cohort (2,492, 30%). Nine key features were selected by the RFE algorithm. The CatBoost model achieved the best performance, with an AUC of 0.844 in the training cohort and 0.804 in the validation cohort. SHAP values revealed that AKI stage, PaO2, and lactate were the top three most important features contributing to the CatBoost model.

Conclusion

We developed a model capable of predicting the risk of in-hospital mortality in elderly patients with SA-AKI.

Predictive nomogram for in-hospital mortality among older patients with intra-abdominal sepsis incorporating skeletal muscle mass

BACKGROUND

Studies on prognostic factors for older patients with intra-abdominal sepsis are scarce, and the association between skeletal muscle mass and prognosis among such patients remains unclear.

AIMS

To develop a nomogram to predict in-hospital mortality among older patients with intra-abdominal sepsis.

METHODS

Older patients with intra-abdominal sepsis were prospectively recruited. Their demographics, clinical features, laboratory results, abdominal computed tomography-derived muscle mass, and in-hospital mortality were recorded. The predictors of mortality were selected via least absolute shrinkage and selection operator and multivariable logistic regression analyses, and a nomogram was developed. The nomogram was assessed and compared with Sequential Organ Failure Assessment score, Acute Physiology and Chronic Health Evaluation II score, and Simplified Acute Physiology Score II.

RESULTS

In total, 464 patients were included, of whom 104 (22.4%) died. Six independent risk factors (skeletal muscle index, cognitive impairment, frailty, heart rate, red blood cell distribution width, and blood urea nitrogen) were incorporated into the nomogram. The Hosmer-Lemeshow goodness-of-fit test and calibration plot revealed a good consistency between the predicted and observed probabilities. The area under the receiver operating characteristic curve was 0.875 (95% confidence interval = 0.838-0.912), which was significantly higher than those of commonly used scoring systems. The decision curve analysis indicated the nomogram had good predictive performance.

DISCUSSION

Our nomogram, which is predictive of in-hospital mortality among older patients with intra-abdominal sepsis, incorporates muscle mass, a factor that warrants consideration by clinicians. The model has a high prognostic ability and might be applied in clinical practice after external validation.

Construction and validation of prognostic models in critically Ill patients with sepsis-associated acute kidney injury: interpretable machine learning approach

BACKGROUND

Acute kidney injury (AKI) is a common complication in critically ill patients with sepsis and is often associated with a poor prognosis. We aimed to construct and validate an interpretable prognostic prediction model for patients with sepsis-associated AKI (S-AKI) using machine learning (ML) methods.

METHODS

Data on the training cohort were collected from the Medical Information Mart for Intensive Care IV database version 2.2 to build the model, and data of patients were extracted from Hangzhou First People's Hospital Affiliated to Zhejiang University School of Medicine for external validation of model. Predictors of mortality were identified using Recursive Feature Elimination (RFE). Then, random forest, extreme gradient boosting (XGBoost), multilayer perceptron classifier, support vector classifier, and logistic regression were used to establish a prognosis prediction model for 7, 14, and 28 days after intensive care unit (ICU) admission, respectively. Prediction performance was assessed using the receiver operating characteristic (ROC) curve and decision curve analysis (DCA). SHapley Additive exPlanations (SHAP) were used to interpret the ML models.

RESULTS

In total, 2599 patients with S-AKI were included in the analysis. Forty variables were selected for the model development. According to the areas under the ROC curve (AUC) and DCA results for the training cohort, XGBoost model exhibited excellent performance with F1 Score of 0.847, 0.715, 0.765 and AUC (95% CI) of 0.91 (0.90, 0.92), 0.78 (0.76, 0.80), and 0.83 (0.81, 0.85) in 7 days, 14 days and 28 days group, respectively. It also demonstrated excellent discrimination in the external validation cohort. Its AUC (95% CI) was 0.81 (0.79, 0.83), 0.75 (0.73, 0.77), 0.79 (0.77, 0.81) in 7 days, 14 days and 28 days group, respectively. SHAP-based summary plot and force plot were used to interpret the XGBoost model globally and locally.

CONCLUSIONS

ML is a reliable tool for predicting the prognosis of patients with S-AKI. SHAP methods were used to explain intrinsic information of the XGBoost model, which may prove clinically useful and help clinicians tailor precise management.

Machine learning algorithm to predict mortality in critically ill patients with sepsis-associated acute kidney injury

This study aimed to establish and validate a machine learning (ML) model for predicting in-hospital mortality in patients with sepsis-associated acute kidney injury (SA-AKI). This study collected data on SA-AKI patients from 2008 to 2019 using the Medical Information Mart for Intensive Care IV. After employing Lasso regression for feature selection, six ML approaches were used to build the model. The optimal model was chosen based on precision and area under curve (AUC). In addition, the best model was interpreted using SHapley Additive exPlanations (SHAP) values and Local Interpretable Model-Agnostic Explanations (LIME) algorithms. There were 8129 sepsis patients eligible for participation; the median age was 68.7 (interquartile range: 57.2-79.6) years, and 57.9% (4708/8129) were male. After selection, 24 of the 44 clinical characteristics gathered after intensive care unit admission remained linked with prognosis and were utilized developing ML models. Among the six models developed, the eXtreme Gradient Boosting (XGBoost) model had the highest AUC, at 0.794. According to the SHAP values, the sequential organ failure assessment score, respiration, simplified acute physiology score II, and age were the four most influential variables in the XGBoost model. Individualized forecasts were clarified using the LIME algorithm. We built and verified ML models that excel in early mortality risk prediction in SA-AKI and the XGBoost model performed best.

A predictive model for prognosis in very low birth weight infants with late-onset sepsis

OBJECTIVES

This study aims to develop a predictive model to assess the probability of poor prognosis in very low birth weight infants (VLBWI) with late-onset sepsis (LOS).

METHODS

A total of 309 eligible VLBWI with LOS were included in the study. Logistic regression was used to determine prognostic factors for VLBWI with LOS. A nomogram incorporating these factors was created to predict the probability of poor prognosis. Poor prognosis includes death and survival with severe complications.

RESULTS

In the developmental cohort, the incidence of poor prognosis was 59.5% (147/247). Forward stepwise logistic regression analysis showed that HCO3, albumin (ALB), ionized calcium (iCa), blood urea nitrogen (BUN), gestational age (GA), and birth weight (BW) were independent predictors of poor prognosis in VLBWI with LOS. The predictive model showed good discrimination and calibration. In the developmental cohort, the prediction model had a sensitivity of 83.7%, a specificity of 74.0%, and a C-index of 0.845 (95% confidence interval: 0.795-0.894).

CONCLUSION

Our study identified independent predictors of poor prognosis in VLBWI with LOS and used them to construct a predictive model. This model can help clinicians to identify high-risk groups with poor prognosis early and provide important clinical reference information.

IMPACT

This article highlights the development of a predictive model to assess the probability of poor prognosis in very low birth weight infants with late-onset sepsis (LOS). The model constructed in this manuscript was the first model to predict the poor prognosis of VLBWI with LOS. We mean a poor prognosis that includes death and some severe complications that may lead to long-term disability. Clinicians can use the model's scoring results to assess a patient's condition and accurately identify the occurrence of poor prognosis.

Clinical relevance of timing of assessment of ICU mortality in patients with moderate-to-severe Acute Respiratory Distress Syndrome

Mortality is a frequently reported outcome in clinical studies of acute respiratory distress syndrome (ARDS). However, timing of mortality assessment has not been well characterized. We aimed to identify a crossing-point between cumulative survival and death in the intensive care unit (ICU) of patients with moderate-to-severe ARDS, beyond which the number of survivors would exceed the number of deaths. We hypothesized that this intersection would occur earlier in a successful clinical trial vs. observational studies of moderate/severe ARDS and predict treatment response. We conducted an ancillary study of 1580 patients with moderate-to-severe ARDS managed with lung-protective ventilation to assess the relevance and timing of measuring ICU mortality rates at different time-points during ICU stay. First, we analyzed 1303 patients from four multicenter, observational cohorts enrolling consecutive patients with moderate/severe ARDS. We assessed cumulative ICU survival from the time of moderate/severe ARDS diagnosis to ventilatory support discontinuation within 7-days, 28-days, 60-days, and at ICU discharge. Then, we compared these findings to those of a successful randomized trial of 277 moderate/severe ARDS patients. In the observational cohorts, ICU mortality (487/1303, 37.4%) and 28-day mortality (425/1102, 38.6%) were similar (p = 0.549). Cumulative proportion of ICU survivors and non-survivors crossed at day-7; after day-7, the number of ICU survivors was progressively higher compared to non-survivors. Measures of oxygenation, lung mechanics, and severity scores were different between survivors and non-survivors at each point-in-time (p < 0.001). In the trial cohort, the cumulative proportion of survivors and non-survivors in the treatment group crossed before day-3 after diagnosis of moderate/severe ARDS. In clinical ARDS studies, 28-day mortality closely approximates and may be used as a surrogate for ICU mortality. For patients with moderate-to-severe ARDS, ICU mortality assessment within the first week of a trial might be an early predictor of treatment response.

Machine learning for the prediction of cognitive impairment in older adults

Objective

The purpose of this study was to develop and validate a predictive model of cognitive impairment in older adults based on a novel machine learning (ML) algorithm.

Methods

The complete data of 2,226 participants aged 60-80 years were extracted from the 2011-2014 National Health and Nutrition Examination Survey database. Cognitive abilities were assessed using a composite cognitive functioning score (Z-score) calculated using a correlation test among the Consortium to Establish a Registry for Alzheimer's Disease Word Learning and Delayed Recall tests, Animal Fluency Test, and the Digit Symbol Substitution Test. Thirteen demographic characteristics and risk factors associated with cognitive impairment were considered: age, sex, race, body mass index (BMI), drink, smoke, direct HDL-cholesterol level, stroke history, dietary inflammatory index (DII), glycated hemoglobin (HbA1c), Patient Health Questionnaire-9 (PHQ-9) score, sleep duration, and albumin level. Feature selection is performed using the Boruta algorithm. Model building is performed using ten-fold cross-validation, machine learning (ML) algorithms such as generalized linear model (GLM), random forest (RF), support vector machine (SVM), artificial neural network (ANN), and stochastic gradient boosting (SGB). The performance of these models was evaluated in terms of discriminatory power and clinical application.

Results

The study ultimately included 2,226 older adults for analysis, of whom 384 (17.25%) had cognitive impairment. After random assignment, 1,559 and 667 older adults were included in the training and test sets, respectively. A total of 10 variables such as age, race, BMI, direct HDL-cholesterol level, stroke history, DII, HbA1c, PHQ-9 score, sleep duration, and albumin level were selected to construct the model. GLM, RF, SVM, ANN, and SGB were established to obtain the area under the working characteristic curve of the test set subjects 0.779, 0.754, 0.726, 0.776, and 0.754. Among all models, the GLM model had the best predictive performance in terms of discriminatory power and clinical application.

Conclusions

ML models can be a reliable tool to predict the occurrence of cognitive impairment in older adults. This study used machine learning methods to develop and validate a well performing risk prediction model for the development of cognitive impairment in the elderly.

Early pulmonary artery catheterization is not associated with survival benefits in critically ill patients with cardiac disease: An analysis of the MIMIC-IV database

BACKGROUND

Many studies demonstrated no improved survival in patients with pulmonary artery catheter placement. However, no consistent conclusions have been drawn regarding the impact of pulmonary artery catheter in critically ill patients with heart disease. This study aimed to investigate the association of early pulmonary artery catheter use with 28-day mortality in that population.

METHODS

The Multiparameter Intelligent Monitoring in Intensive Care IV (MIMIC-IV) database, a single-center critical care database, was employed to investigate this issue. This study enrolled a total of 11,887 critically ill patients with cardiac disease with or without pulmonary artery catheter insertion. The primary outcome was 28-day mortality. The multivariate regression was modeled to examine the association between pulmonary artery catheter and outcomes. Additionally, we examined the effect modification by cardiac surgeries. Propensity score matching was conducted to validate our findings.

RESULTS

No improvement in 28-day mortality was observed among the pulmonary artery catheter group compared to the non-pulmonary artery catheter group (odds ratio 95% confidence interval: 1.18 [1.00-1.38], P = .049). When stratified by cardiac surgeries, the results were consistent. The patients in the pulmonary artery catheter group had fewer ventilation-free days and vasopressor-free days than those in the nonpulmonary artery catheter group after surgery stratification. In the surgical patients, pulmonary artery catheter insertion was not associated with the occurrence of acute kidney injury, and it was associated with a higher daily fluid input (mean difference 95% confidence interval: 0.13 [0.05-0.20], P = .001). In nonsurgical patients, the pulmonary artery catheter group had a higher risk of acute kidney injury occurrence (odds ratio 95% confidence interval: 1.94 [1.32-2.84], P = .001).

CONCLUSION

Early pulmonary artery catheter placement is not associated with survival benefits in critically ill patients with cardiac diseases, either in surgical or nonsurgical patients.

No sex differences in the incidence, risk factors and clinical impact of acute kidney injury in critically ill patients with sepsis

Background

Sex-stratified medicine is an important aspect of precision medicine. We aimed to compare the incidence and risk factors of acute kidney injury (AKI) for critically ill men and women with sepsis. Furthermore, the short-term mortality was compared between men and women with sepsis associated acute kidney injury (SA-AKI).

Method

This was a retrospective study based on the Medical Information Mart for Intensive Care IV database. We used the multivariable logistic regression analysis to evaluate the independent effect of sex on the incidence of SA-AKI. We further applied three machine learning methods (decision tree, random forest and extreme gradient boosting) to screen for the risk factors associated with SA-AKI in the total, men and women groups. We finally compared the intensive care unit (ICU) and hospital mortality between men and women with SA-AKI using propensity score matching.

Results

A total of 6463 patients were included in our study, including 3673 men and 2790 women. The incidence of SA-AKI was 83.8% for men and 82.1% for women. After adjustment for confounders, no significant association was observed between sex and the incidence of SA-AKI (odds ratio (OR), 1.137; 95% confidence interval (CI), 0.949-1.361; p=0.163). The machine learning results revealed that body mass index, Oxford Acute Severity of Illness Score, diuretic, Acute Physiology Score III and age were the most important risk factors of SA-AKI, irrespective of sex. After propensity score matching, men had similar ICU and hospital mortality to women.

Conclusions

The incidence and associated risk factors of SA-AKI are similar between men and women, and men and women with SA-AKI experience comparable rates of ICU and hospital mortality. Therefore, sex-related effects may play a minor role in developing SA-AKI. Our study helps to contribute to the knowledge gap between sex and SA-AKI.

Development and Validation of Machine Learning Models for Real-Time Mortality Prediction in Critically Ill Patients With Sepsis-Associated Acute Kidney Injury

Background

Sepsis-associated acute kidney injury (SA-AKI) is common in critically ill patients, which is associated with significantly increased mortality. Existing mortality prediction tools showed insufficient predictive power or failed to reflect patients' dynamic clinical evolution. Therefore, the study aimed to develop and validate machine learning-based models for real-time mortality prediction in critically ill patients with SA-AKI.

Methods

The multi-center retrospective study included patients from two distinct databases. A total of 12,132 SA-AKI patients from the Medical Information Mart for Intensive Care IV (MIMIC-IV) were randomly allocated to the training, validation, and internal test sets. An additional 3,741 patients from the eICU Collaborative Research Database (eICU-CRD) served as an external test set. For every 12 h during the ICU stays, the state-of-the-art eXtreme Gradient Boosting (XGBoost) algorithm was used to predict the risk of in-hospital death in the following 48, 72, and 120 h and in the first 28 days after ICU admission. Area under the receiver operating characteristic curves (AUCs) were calculated to evaluate the models' performance.

Results

The XGBoost models, based on routine clinical variables updated every 12 h, showed better performance in mortality prediction than the SOFA score and SAPS-II. The AUCs of the XGBoost models for mortality over different time periods ranged from 0.848 to 0.804 in the internal test set and from 0.818 to 0.748 in the external test set. The shapley additive explanation method provided interpretability for the XGBoost models, which improved the understanding of the association between the predictor variables and future mortality.

Conclusions

The interpretable machine learning XGBoost models showed promising performance in real-time mortality prediction in critically ill patients with SA-AKI, which are useful tools for early identification of high-risk patients and timely clinical interventions.

Machine learning for the prediction of acute kidney injury in patients with sepsis

BACKGROUND

Acute kidney injury (AKI) is the most common and serious complication of sepsis, accompanied by high mortality and disease burden. The early prediction of AKI is critical for timely intervention and ultimately improves prognosis. This study aims to establish and validate predictive models based on novel machine learning (ML) algorithms for AKI in critically ill patients with sepsis.

METHODS

Data of patients with sepsis were extracted from the Medical Information Mart for Intensive Care III (MIMIC- III) database. Feature selection was performed using a Boruta algorithm. ML algorithms such as logistic regression (LR), k-nearest neighbors (KNN), support vector machine (SVM), decision tree, random forest, Extreme Gradient Boosting (XGBoost), and artificial neural network (ANN) were applied for model construction by utilizing tenfold cross-validation. The performances of these models were assessed in terms of discrimination, calibration, and clinical application. Moreover, the discrimination of ML-based models was compared with those of Sequential Organ Failure Assessment (SOFA) and the customized Simplified Acute Physiology Score (SAPS) II model.

RESULTS

A total of 3176 critically ill patients with sepsis were included for analysis, of which 2397 cases (75.5%) developed AKI during hospitalization. A total of 36 variables were selected for model construction. The models of LR, KNN, SVM, decision tree, random forest, ANN, XGBoost, SOFA and SAPS II score were established and obtained area under the receiver operating characteristic curves of 0.7365, 0.6637, 0.7353, 0.7492, 0.7787, 0.7547, 0.821, 0.6457 and 0.7015, respectively. The XGBoost model had the best predictive performance in terms of discrimination, calibration, and clinical application among all models.

CONCLUSION

The ML models can be reliable tools for predicting AKI in septic patients. The XGBoost model has the best predictive performance, which can be used to assist clinicians in identifying high-risk patients and implementing early interventions to reduce mortality.

A novel prognostic model for predicting the mortality risk of patients with sepsis-related acute respiratory failure: a cohort study using the MIMIC-IV database

OBJECTIVES

Acute respiratory failure increases short-term mortality in sepsis patients. Hence, in this study, we aimed to develop a novel model for predicting the risk of hospital mortality in sepsis patients with acute respiratory failure.

METHODS

From the Medical Information Mart for Intensive Care (MIMIC)-IV database, we developed a matched cohort of adult sepsis patients with acute respiratory failure. After applying a multivariate COX regression analysis, we developed a nomogram based on the identified risk factors of mortality. Further, we evaluated the ability of the nomogram in predicting individual hospital death by the area under a receiver operating characteristic (ROC) curve.

RESULTS

A total of 663 sepsis patients with acute respiratory failure were included in this study. Systolic blood pressure, neutrophil percentage, white blood cells count, mechanical ventilation, partial pressure of oxygen < 60 mmHg, abdominal cavity infection, Klebsiella pneumoniae and Acinetobacter baumannii infection, and immunosuppressive diseases were the independent risk factors of mortality in sepsis patients with acute respiratory failure. The area under the ROC curve of the nomogram was 0.880 (95% CI: 0.851-0.908), which provided significantly higher discrimination compared to that of the simplified acute physiology score II [0.656 (95% CI: 0.612-0.701)].

CONCLUSION

The model shows a good performance in predicting the mortality risk of patients with sepsis-related acute respiratory failure. Hence, this model can be used to evaluate the short-term prognosis of critically ill patients with sepsis and acute respiratory failure.