National Veterans Health Administration inpatient risk stratification models for hospital-acquired acute kidney injury

Sex, Acute Kidney Injury, and Age: A Prospective Cohort Study

RATIONALE & OBJECTIVE

Animal models of kidney disease suggest a protective role for female sex hormones, but some authorities assert that female sex in humans is a risk factor for acute kidney injury (AKI). To better understand the risk of AKI, we studied the strength of association between sex and AKI incidence in hormonally distinct age groups across the life span.

STUDY DESIGN

Prospective cohort study.

SETTING & PARTICIPANTS

All patients hospitalized in the Montefiore Health System between October 15, 2015, and January 1, 2019, excluding those with kidney failure or obstetrics diagnoses.

EXPOSURE

Male versus female sex.

OUTCOME

AKI occurring during hospitalization based on KDIGO definitions.

ANALYTICAL APPROACH

Generalized estimating equation logistic regression adjusted for comorbidities, sociodemographic factors, and severity of illness. Analyses were stratified into 3 age categories: 6 months to≤16 years,>16 years to<55 years, and≥55 years.

RESULTS

A total of 132,667 individuals were hospitalized a total of 235,629 times. The mean age was 55.2±23.8 (SD) years. The count of hospitalizations for women was 129,912 (55%). Hospitalization count among Black and Hispanic patients was 71,834 (30.5%) and 24,199 (10.3%), respectively. AKI occurred in 53,926 (22.9%) hospitalizations. In adjusted models, there was a significant interaction between age and sex (P<0.001). Boys and men had a higher risk of AKI across all age groups, an association more pronounced in the age group>16 years to<55 years in which the odds ratio for men was 1.7 (95% CI, 1.6-1.8). This age-based pattern remained consistent across prespecified types of hospitalizations. In a sensitivity analysis, women older than 55 years who received prescriptions for estrogen had lower odds of AKI than those without prescriptions.

LIMITATIONS

Residual confounding.

CONCLUSIONS

The greatest relative risk of AKI for males occurred during ages>16 to<55 years. The lower risk among postmenopausal women receiving supplemental estrogen supports a protective role for female sex hormones.

PLAIN-LANGUAGE SUMMARY

Male sex is a risk factor for acute kidney injury (AKI) in animals, but in human studies this association is not as robust. We studied hospitalizations at a single center to examine the association of hospital-acquired AKI and sex. After controlling for various sources of potential bias and stratifying by age categories through the life course, we observed that men have a higher risk of AKI throughout life. This risk was especially high compared with women of fertile age and older women prescribed estrogen. This pattern was consistent in prespecified subgroups of hospitalizations. These results support a protective role for female sex hormones in the occurrence of hospitalized AKI.

An algorithm to assess importance of predictors in systematic reviews of prediction models: a case study with simulations

BACKGROUND

How to assess the importance of predictors in systematic reviews (SR) of prediction models remains largely unknown. The commonly used indicators of importance for predictors in individual models include parameter estimates, information entropy, etc., but they cannot be quantitatively synthesized through meta-analysis.

METHODS

We explored the synthesis method of the importance indicators in a simulation study, which mainly solved the following four methodological issues: (1) whether to synthesize the original values of the importance indicators or the importance ranks; (2) whether to normalize the importance ranks to a same dimension; (3) whether and how to impute the missing values in importance ranks; and (4) whether to weight the importance indicators according to the sample size of the model during synthesis. Then we used an empirical SR to illustrate the feasibility and validity of the synthesis method.

RESULTS

According to the simulation experiments, we found that ranking or normalizing the values of the importance indicators had little impact on the synthesis results, while imputation of missing values in the importance ranks had a great impact on the synthesis results due to the incorporation of variable frequency. Moreover, the results of means and weighted means of the importance indicators were similar. In consideration of accuracy and interpretability, synthesis of the normalized importance ranks by weighted mean was recommended. The synthesis method was used in the SR of prediction models for acute kidney injury. The importance assessment results were approved by experienced nephrologists, which further verified the reliability of the synthesis method.

CONCLUSIONS

An importance assessment of predictors should be included in SR of prediction models, using the weighted mean of importance ranks normalized to a same dimension in different models.

A two-tier feature selection method for predicting mortality risk in ICU patients with acute kidney injury

Acute kidney injury (AKI) is one of the most important lethal factors for patients admitted to intensive care units (ICUs), and timely high-risk prognostic assessment and intervention are essential to improving patient prognosis. In this study, a stacking model using the MIMIC-III dataset with a two-tier feature selection approach was developed to predict the risk of in-hospital mortality in ICU patients admitted for AKI. External validation was performed using separate MIMIC-IV and eICU-CRD. The area under the curve (AUC) was calculated using the stacking model, and features were selected using the Boruta and XGBoost feature selection methods. This study compares the performance of a stacking model using two-tier feature selection with a model using single-tier feature selection (XGBoost: 85; Boruta: 83; two-tier: 0.91). The predictive effectiveness of the stacking model was further validated by using different datasets (Validation 1: 0.83; Validation 2: 0.85) and comparing it with a simpler model and traditional clinical scores (SOFA: 0.65; APACH IV: 0.61). In addition, this study combined interpretable techniques and causal inference to analyze the causal relationship between features and predicted outcomes.

When to start renal replacement therapy in acute kidney injury: What are we waiting for?

Acute kidney injury remains a serious condition with a high mortality risk. In the absence of any new drugs, renal replacement therapy (RRT) is the most important treatment option. Randomized controlled trials have concluded that in critically ill patients without an emergency indication for RRT, a watchful waiting strategy is safe; however, further delays in RRT did not seem to confer any benefit, rather was associated with potential harm. During this process, balancing the risks of complications due to an unnecessary intervention with the risk of not correcting a potentially life-threatening complication remains a challenge. Dynamic renal function assessment, especially dynamic assessment of renal demand-capacity matching, combined with renal biomarkers such as neutrophil gelatinase-associated lipocalin and furosemide stress test, is helpful to identify which patients and when the patients may benefit from RRT.

Sex bias in prediction and diagnosis of cardiac surgery associated acute kidney injury

BACKGROUND

Female sex has been recognized as a risk factor for cardiac surgery associated acute kidney injury (CS-AKI). The current study sought to evaluate whether female sex is a risk factor for CS-AKI, or modifies the association of peri-operative change in serum creatinine with CS-AKI.

METHODS

Observational study of adult patients undergoing cardiac surgery between 2000 and 2019 in a single U.S. center. The main variable of interest was registered patient sex, identified from electronic medical records. The main outcome was CS-AKI within 2 weeks of surgery.

RESULTS

Of 58526 patients, 19353 (33%) were female; 12934 (22%) incurred AKI based on ≥ 0.3 mg/dL or ≥ 50% rise in serum creatinine (any AKI), 3320 (5.7%) had moderate to severe AKI, and 1018 (1.7%) required dialysis within 2 weeks of surgery. Female sex was associated with higher risk for AKI in models that were based on preoperative serum creatinine (OR, 1.35; 95% CI, 1.29-1.42), and lower risk with the use of estimated glomerular filtration, (OR, 0.90; 95% CI, 0.86-0.95). The risk for moderate to severe CS-AKI for a given immediate peri-operative change in serum creatinine was higher in female compared to male patients (p < .0001 and p < .0001 for non-linearity), and the association was modified by pre-operative kidney function (p < .0001 for interaction).

CONCLUSIONS

The association of patient sex with CS-AKI and its direction was dependent on the operational definition of pre-operative kidney function, and differential outcome misclassification due to AKI defined by absolute change in serum creatinine.

Sex Bias in Prediction and Diagnosis of Cardiac Surgery Associated Acute Kidney Injury

Background

Female sex has been recognized as a risk factor for cardiac surgery associated acute kidney injury (CS-AKI). The current study sought to evaluate whether female sex is a risk factor for CS-AKI, or modifies the association of peri-operative change in serum creatinine with CS-AKI.

Methods

Observational study of adult patients undergoing cardiac surgery between 2000 and 2019 in a single U.S. center. The main variable of interest was registered patient sex, identified from electronic medical records. The main outcome was CS-AKI within 2 weeks of surgery.

Results

Of 58526 patients, 19353 (33%) were female; 12934 (22%) incurred AKI based on ≥ 0.3 mg/dL or ≥ 50% rise in serum creatinine (any AKI), 3320 (5.7%) had moderate to severe AKI, and 1018 (1.7%) required dialysis within 2 weeks of surgery. Female sex was associated with higher risk for AKI in models that were based on preoperative serum creatinine (OR, 1.35; 95% CI, 1.29-1.42), and lower risk with the use of estimated glomerular filtration, (OR, 0.90; 95% CI, 0.86-0.95). The risk for moderate to severe CS-AKI for a given immediate peri-operative change in serum creatinine was higher in female compared to male patients (p < .0001 and p < .0001 for non-linearity), and the association was modified by pre-operative kidney function (p < .0001 for interaction).

Conclusions

The association of patient sex with CS-AKI and its direction was dependent on the operational definition of pre-operative kidney function, and differential outcome misclassification due to AKI defined by absolute change in serum creatinine.

Endothelium-related biomarkers enhanced prediction of kidney support therapy in critically ill patients with non-oliguric acute kidney injury

Acute kidney injury (AKI) is a common condition in hospitalized patients who often requires kidney support therapy (KST). However, predicting the need for KST in critically ill patients remains challenging. This study aimed to analyze endothelium-related biomarkers as predictors of KST need in critically ill patients with stage 2 AKI. A prospective observational study was conducted on 127 adult ICU patients with stage 2 AKI by serum creatinine only. Endothelium-related biomarkers, including vascular cell adhesion protein-1 (VCAM-1), angiopoietin (AGPT) 1 and 2, and syndecan-1, were measured. Clinical parameters and outcomes were recorded. Logistic regression models, receiver operating characteristic (ROC) curves, continuous net reclassification improvement (NRI) and integrated discrimination improvement (IDI) were used for analysis. Among the patients, 22 (17.2%) required KST within 72 h. AGPT2 and syndecan-1 levels were significantly greater in patients who progressed to the KST. Multivariate analysis revealed that AGPT2 and syndecan-1 were independently associated with the need for KST. The area under the ROC curve (AUC-ROC) for AGPT2 and syndecan-1 performed better than did the constructed clinical model in predicting KST. The combination of AGPT2 and syndecan-1 improved the discrimination capacity of predicting KST beyond that of the clinical model alone. Additionally, this combination improved the classification accuracy of the NRI and IDI. AGPT2 and syndecan-1 demonstrated predictive value for the need for KST in critically ill patients with stage 2 AKI. The combination of AGPT2 and syndecan-1 alone enhanced the predictive capacity of predicting KST beyond clinical variables alone. These findings may contribute to the early identification of patients who will benefit from KST and aid in the management of AKI in critically ill patients.

Predicting in-hospital outcomes of patients with acute kidney injury

Acute kidney injury (AKI) is prevalent and a leading cause of in-hospital death worldwide. Early prediction of AKI-related clinical events and timely intervention for high-risk patients could improve outcomes. We develop a deep learning model based on a nationwide multicenter cooperative network across China that includes 7,084,339 hospitalized patients, to dynamically predict the risk of in-hospital death (primary outcome) and dialysis (secondary outcome) for patients who developed AKI during hospitalization. A total of 137,084 eligible patients with AKI constitute the analysis set. In the derivation cohort, the area under the receiver operator curve (AUROC) for 24-h, 48-h, 72-h, and 7-day death are 95·05%, 94·23%, 93·53%, and 93·09%, respectively. For dialysis outcome, the AUROC of each time span are 88·32%, 83·31%, 83·20%, and 77·99%, respectively. The predictive performance is consistent in both internal and external validation cohorts. The model can predict important outcomes of patients with AKI, which could be helpful for the early management of AKI.

Characterization of Risk Prediction Models for Acute Kidney Injury: A Systematic Review and Meta-analysis

Importance

Despite the expansion of published prediction models for acute kidney injury (AKI), there is little evidence of uptake of these models beyond their local derivation nor data on their association with patient outcomes.

Objective

To systematically review published AKI prediction models across all clinical subsettings.

Data Sources

MEDLINE via PubMed (January 1946 to April 2021) and Embase (January 1947 to April 2021) were searched using medical subject headings and text words related to AKI and prediction models.

Study Selection

All studies that developed a prediction model for AKI, defined as a statistical model with at least 2 predictive variables to estimate future occurrence of AKI, were eligible for inclusion. There was no limitation on study populations or methodological designs.

Data Extraction and Synthesis

Two authors independently searched the literature, screened the studies, and extracted and analyzed the data following the Preferred Reporting Items for Systematic Review and Meta-analyses guideline. The data were pooled using a random-effects model, with subgroups defined by 4 clinical settings. Between-study heterogeneity was explored using multiple methods, and funnel plot analysis was used to identify publication bias.

Main Outcomes and Measures

C statistic was used to measure the discrimination of prediction models.

Results

Of the 6955 studies initially identified through literature searching, 150 studies, with 14.4 million participants, met the inclusion criteria. The study characteristics differed widely in design, population, AKI definition, and model performance assessments. The overall pooled C statistic was 0.80 (95% CI, 0.79-0.81), with pooled C statistics in different clinical subsettings ranging from 0.78 (95% CI, 0.75-0.80) to 0.82 (95% CI, 0.78-0.86). Between-study heterogeneity was high overall and in the different clinical settings (eg, contrast medium-associated AKI: I2 = 99.9%; P < .001), and multiple methods did not identify any clear sources. A high proportion of models had a high risk of bias (126 [84.4%]) according to the Prediction Model Risk Of Bias Assessment Tool.

Conclusions and Relevance

In this study, the discrimination of the published AKI prediction models was good, reflected by high C statistics; however, the wide variation in the clinical settings, populations, and predictive variables likely drives the highly heterogenous findings that limit clinical utility. Standardized procedures for development and validation of prediction models are urgently needed.

Machine learning for acute kidney injury: Changing the traditional disease prediction mode

Acute kidney injury (AKI) is a serious clinical comorbidity with clear short-term and long-term prognostic implications for inpatients. The diversity of risk factors for AKI has been recognized in previous studies, and a series of predictive models have been developed using traditional statistical methods in conjunction with its preventability, but they have failed to meet the expectations in limited clinical applications, the rapid spread of electronic health records and artificial intelligence machine learning technology has brought new hope for the construction of AKI prediction models. In this article, we systematically review the definition and classification of machine learning methods, modeling ideas and evaluation methods, and the characteristics and current status of modeling studies. According to the modeling objectives, we subdivided them into critical care medical setting models, all medical environment models, special surgery models, special disease models, and special nephrotoxin exposure models. As the first review article to comprehensively summarize and analyze machine learning prediction models for AKI, we aim to objectively describe the advantages and disadvantages of machine learning approaches to modeling, and help other researchers more quickly and intuitively understand the current status of modeling research, inspire ideas and learn from experience, so as to guide and stimulate more research and more in-depth exploration in the future, which will ultimately provide greater help to improve the overall status of AKI diagnosis and treatment.

Machine learning models for predicting acute kidney injury: a systematic review and critical appraisal

BACKGROUND

The number of studies applying machine learning (ML) to predict acute kidney injury (AKI) has grown steadily over the past decade. We assess and critically appraise the state of the art in ML models for AKI prediction, considering performance, methodological soundness, and applicability.

METHODS

We searched PubMed and ArXiv, extracted data, and critically appraised studies based on the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD), Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS), and Prediction Model Risk of Bias Assessment Tool (PROBAST) guidelines.

RESULTS

Forty-six studies from 3166 titles were included. Thirty-eight studies developed a model, five developed and externally validated one, and three studies externally validated one. Flexible ML methods were used more often than deep learning, although the latter was common with temporal variables and text as predictors. Predictive performance showed an area under receiver operating curves ranging from 0.49 to 0.99. Our critical appraisal identified a high risk of bias in 39 studies. Some studies lacked internal validation, whereas external validation and interpretability of results were rarely considered. Fifteen studies focused on AKI prediction in the intensive care setting, and the US-derived Medical Information Mart for Intensive Care (MIMIC) data set was commonly used. Reproducibility was limited as data and code were usually unavailable.

CONCLUSIONS

Flexible ML methods are popular for the prediction of AKI, although more complex models based on deep learning are emerging. Our critical appraisal identified a high risk of bias in most models: Studies should use calibration measures and external validation more often, improve model interpretability, and share data and code to improve reproducibility.

Artificial Intelligence in Acute Kidney Injury Prediction

The use of artificial intelligence (AI) in nephrology and its associated clinical research is growing. Recent years have seen increased interest in utilizing AI to predict the development of hospital-based acute kidney injury (AKI). Several AI techniques have been employed to improve the ability to detect AKI across a variety of hospitalized settings. This review discusses the evolutions of AKI risk prediction discussing the static risk assessment models of yesteryear as well as the more recent trend toward AI and advanced learning techniques. We discuss the relative improvement in AKI detection as well as the relative dearth of data around the clinical implementation and patient outcomes using these models. The use of AI for AKI detection and clinical care is in its infancy, and this review describes how we arrived at our current position and hints at the promise of the future.

Artificial intelligence-enabled decision support in nephrology

Kidney pathophysiology is often complex, nonlinear and heterogeneous, which limits the utility of hypothetical-deductive reasoning and linear, statistical approaches to diagnosis and treatment. Emerging evidence suggests that artificial intelligence (AI)-enabled decision support systems - which use algorithms based on learned examples - may have an important role in nephrology. Contemporary AI applications can accurately predict the onset of acute kidney injury before notable biochemical changes occur; can identify modifiable risk factors for chronic kidney disease onset and progression; can match or exceed human accuracy in recognizing renal tumours on imaging studies; and may augment prognostication and decision-making following renal transplantation. Future AI applications have the potential to make real-time, continuous recommendations for discrete actions and yield the greatest probability of achieving optimal kidney health outcomes. Realizing the clinical integration of AI applications will require cooperative, multidisciplinary commitment to ensure algorithm fairness, overcome barriers to clinical implementation, and build an AI-competent workforce. AI-enabled decision support should preserve the pre-eminence of wisdom and augment rather than replace human decision-making. By anchoring intuition with objective predictions and classifications, this approach should favour clinician intuition when it is honed by experience.

Sex Differences in Acute Kidney Injury

Female sex confers renoprotection in chronic progressive kidney disease. It is less well recognized that sexual dimorphism also is evident in the development of ischemic and nephrotoxic acute kidney injury (AKI). Animal studies consistently have shown that female sex protects against the development of renal injury in experimental models of ischemic AKI. However, the consensus opinion is that in human beings, female sex is an independent risk factor for AKI. Based on a systematic review of experimental and clinical literature, we present data to support the conclusion that, contrary to consensus opinion, it is male sex, not female sex, that is associated with the development of AKI.

Comparison of Adverse Kidney Outcomes With Empagliflozin and Linagliptin Use in Patients With Type 2 Diabetic Patients in a Real-World Setting

Background: To compare the effects of empagliflozin and linagliptin use on kidney outcomes of type 2 diabetes mellitus (T2DM) patients in a real-world setting. Methods: The study involved a propensity score-matched cohort comprising new users of empagliflozin or linagliptin with T2DM between January 1, 2013 and December 31, 2018 from a large healthcare delivery system in Taiwan. Clinical outcomes assessed: acute kidney injury (AKI), post-AKI dialysis, and mortality. Cox proportional hazard model was used to estimate the relative risk of empagliflozin or linagliptin use; a linear mixed model was used to compare the average change in estimated glomerular filtration rate (eGFR) over time. Results: Of the 7,042 individuals, 67 of 3,521 (1.9%) in the empagliflozin group and 144 of 3,521 (4.1%) in the linagliptin group developed AKI during the 2 years follow-up. Patients in the empagliflozin group were at a 40% lower risk of developing AKI compared to those in the linagliptin group (adjusted hazard ratio [aHR], 0.60; 95% confidence interval [CI], 0.45-0.82, p = 0.001). Stratified analysis showed that empagliflozin users ≥65 years of age (aHR, 0.70; 95% CI, 0.43-1.13, p = 0.148), or with a baseline eGFR <60 ml/min/1.73 m² (aHR, 0.97; 95% CI, 0.57-1.65, p = 0.899), or with a baseline glycohemoglobin ≦7% (aHR, 1.01; 95% CI, 0.51-2.00, p =0.973) experienced attenuated benefits with respect to AKI risk. A smaller decline in eGFR was observed in empagliflozin users compared to linagliptin users regardless of AKI occurrence (adjusted β = 1.51; 95% CI, 0.30-2.72 ml/min/1.73 m², p = 0.014). Conclusion: Empagliflozin users were at a lower risk of developing AKI and exhibited a smaller eGFR decline than linagliptin users. Thus, empagliflozin may be a safer alternative to linagliptin for T2DM patients.

Timing of Kidney Support Therapy in Acute Kidney Injury: What Are We Waiting For?

The optimal timing of kidney support therapy in critically ill patients with acute kidney injury (AKI) without life-threatening complications related to AKI is controversial. Recent multicenter, randomized, controlled studies have questioned the need for earlier initiation of therapy, despite one study showing a benefit in survival and others with no differences in mortality based on the timing of kidney support therapy initiation. These findings reflect the uncertainties in decisions to initiate kidney support therapy, which should ideally be individualized according to the patient's comorbidities, severity of illness, trajectory of kidney function, and urine output as well as requirements for fluid balance and solute removal. A delayed approach could translate into a potentially reduced burden of dialysis dependence in addition to saving health resources. However, we must ascertain what constitutes the waiting period and the benefits and risks associated with this approach. This article reviews the concept of timing of dialysis in AKI, performs a critical assessment of the most important clinical trials in this topic, discusses ongoing research and knowledge gaps, and defines key research issues to address in the future.

Comparison of machine learning and logistic regression models in predicting acute kidney injury: A systematic review and meta-analysis

INTRODUCTION

We aimed to assess whether machine learning models are superior at predicting acute kidney injury (AKI) compared to logistic regression (LR), a conventional prediction model.

METHODS

Eligible studies were identified using PubMed and Embase. A total of 24 studies consisting of 84 prediction models met inclusion criteria. Independent samples t-test was performed to detect mean differences in area under the curve (AUC) between ML and LR models. One-way ANOVA and post-hoc t-tests were performed to assess mean differences in AUC between ML methods.

RESULTS

AUC data were similar between ML (0.736 ± 0.116) and LR (0.748 ± 0.057) models (p = 0.538). However, specific ML models, such as gradient boosting (0.838 ± 0.077), exhibited superior performance at predicting AKI as compared to other ML models in the literature (p < 0.05). Creatinine and urine output, standard variables assessed for AKI staging, were classified as significant predictors across multiple ML models, although the majority of significant predictors were unique and study specific.

CONCLUSIONS

These data suggest that ML models perform equally to that of LR, however ML models exhibit variable performance with some ML models displaying exceptional performance. The variability in ML prediction of AKI can be attributed, in part, to the specific ML model utilized, variable selection and processing, study and subject characteristics, and the steps associated with model training, validation, testing, and calibration.

Acute kidney injury is more common in men than women after accounting for socioeconomic status, ethnicity, alcohol intake and smoking history

BACKGROUND

The association of several comorbidities, including diabetes mellitus, hypertension, cardiovascular disease, heart failure and chronic kidney or liver disease, with acute kidney injury (AKI) is well established. Evidence on the effect of sex and socioeconomic factors are scarce. This study was designed to examine the association of sex and socioeconomic factors with AKI and AKI-related mortality and further to evaluate the additional relationship with other possible risk factors for AKI occurrence.

METHODS

We included 3534 patients (1878 males with mean age 61.1 ± 17.7 and 1656 females 1656 with mean age 60.3 ± 20.0 years) admitted to Queen Elizabeth or Heartlands Hospitals, Birmingham, between October 2013 and January 2016. Patients were prospectively followed-up for a median 47.70 [IQR, 18.20] months. Study-endpoints were incidence of AKI, based on KDIGO-AKI Guidelines, and all-cause mortality. Data acquisition was automated, and information on mortality was collected from the Hospital Episode Statistics and Office of National Statistics. Socioeconomic status was evaluated with the Index of Multiple Deprivation (IMD).

RESULTS

Incidence of AKI was higher in men compared to women (11.3% vs 7.1%; P < 0.001). Model regression analysis revealed significant association of male sex with higher AKI risk (OR, 1.659; 95% CI, 1.311-2.099; P < 0.001); this association remained significant after adjustment for age, eGFR, IMD, smoking, alcohol consumption, ethnicity, existing comorbidities and treatment (OR, 1.599; 95% CI, 1.215-2.103; P = 0.001). All-cause mortality was higher in patients with compared to those without AKI. Males with AKI had higher mortality rates in the first 6-month and 1-year periods after the index AKI event. The association of male sex with mortality was independent of socioeconomic factors but was not statistically significant after adjustment for existing comorbidities.

CONCLUSIONS

Men are at higher risk of AKI and this association is independent from existing risk factors for AKI. The association between male sex and AKI-related mortality was not independent from existing comorbidities. A better understanding of factors associated with AKI may help accurately identify high-risk patients.

Artificial intelligence to guide management of acute kidney injury in the ICU: a narrative review

PURPOSE OF REVIEW

Acute kidney injury (AKI) frequently complicates hospital admission, especially in the ICU or after major surgery, and is associated with high morbidity and mortality. The risk of developing AKI depends on the presence of preexisting comorbidities and the cause of the current disease. Besides, many other parameters affect the kidney function, such as the state of other vital organs, the host response, and the initiated treatment. Advancements in the field of informatics have led to the opportunity to store and utilize the patient-related data to train and validate models to detect specific patterns and, as such, predict disease states or outcomes.

RECENT FINDINGS

Machine-learning techniques have also been applied to predict AKI, as well as the patients' outcomes related to their AKI, such as mortality or the need for kidney replacement therapy. Several models have recently been developed, but only a few of them have been validated in external cohorts.

SUMMARY

In this article, we provide an overview of the machine-learning prediction models for AKI and its outcomes in critically ill patients and individuals undergoing major surgery. We also discuss the pitfalls and the opportunities related to the implementation of these models in clinical practices.

Risk of acute kidney injury and Clostridioides difficile infection with piperacillin/tazobactam, cefepime and meropenem with or without vancomycin

BACKGROUND

Empiric antimicrobial therapy for healthcare-acquired infections often includes vancomycin plus an antipseudomonal beta-lactam (AP-BL). These agents vary in risk for adverse events, including acute kidney injury (AKI) and Clostridium difficile infection (CDI). Studies have only examined these risks separately; thus, our objective was to simultaneously evaluate AKI and CDI risks with AP-BL in the same patient cohort.

METHODS

This retrospective cohort study included 789,200 Veterans Health Administration medical admissions from July 1, 2010 through June 30, 2016. The antimicrobials examined were vancomycin, cefepime, piperacillin/tazobactam, and meropenem. Cox proportional hazards regression was used to contrast risks for AKI and CDI across individual target antimicrobials and vancomycin combination therapies, including adjustment for known confounders.

RESULTS

With respect to the base rate of AKI among patients who did not receive a target antibiotic (4.6%), the adjusted hazards ratios for piperacillin/tazobactam, cefepime, and meropenem were 1.50 (95% CI: 1.43-1.54), 1.00 (0.95-1.05), 0.92 (0.83-1.01), respectively. Co-administration of vancomycin increased AKI rates (data not shown). Similarly, against the base rate of CDI (0.7%), these ratios were 1.21 (1.07-1.36), 1.89 (1.62-2.20), and 1.99 (1.55-2.56), respectively. Addition of vancomycin had minimal impact on CDI rates (data not shown).

CONCLUSIONS

Piperacillin/tazobactam increased AKI risk, which was exacerbated by concurrent vancomycin. Cefepime and meropenem increased CDI risk relative to piperacillin/tazobactam. Clinicians should consider the risks and benefits of AP-BL when selecting empiric regimens. Further well-designed studies evaluating the global risks of AP-BL and patient specific characteristics that can guide empiric selection are needed.

Detection of calibration drift in clinical prediction models to inform model updating

Model calibration, critical to the success and safety of clinical prediction models, deteriorates over time in response to the dynamic nature of clinical environments. To support informed, data-driven model updating strategies, we present and evaluate a calibration drift detection system. Methods are developed for maintaining dynamic calibration curves with optimized online stochastic gradient descent and for detecting increasing miscalibration with adaptive sliding windows. These methods are generalizable to support diverse prediction models developed using a variety of learning algorithms and customizable to address the unique needs of clinical use cases. In both simulation and case studies, our system accurately detected calibration drift. When drift is detected, our system further provides actionable alerts by including information on a window of recent data that may be appropriate for model updating. Simulations showed these windows were primarily composed of data accruing after drift onset, supporting the potential utility of the windows for model updating. By promoting model updating as calibration deteriorates rather than on pre-determined schedules, implementations of our drift detection system may minimize interim periods of insufficient model accuracy and focus analytic resources on those models most in need of attention.

Which risk predictors are more likely to indicate severe AKI in hospitalized patients?

OBJECTIVES

Acute kidney injury (AKI) is a sudden episode of kidney failure or damage and the risk of AKI is determined by the complex interactions of patient factors. In this study, we aimed to find out which risk factors in hospitalized patients are more likely to indicate severe AKI.

METHODS

We constructed a retrospective cohort of adult patients from all inpatient units of a tertiary care academic hospital between November 2007 and December 2016. AKI predictors included demographic information, admission and discharge dates, medications, laboratory values, past medical diagnoses and admission diagnosis. We developed a machine learning-based knowledge mining model and a screening framework to analyze which risk predictors are more likely to imply severe AKI in hospitalized populations.

RESULTS

Among the final analysis cohort of 76,957 hospital admissions, AKI occurred in 7,259 (9.43 %) with 6,396 (8.31 %) at stage 1, 678 (0.88 %) at stage 2, and 185 (0.24 %) at stage 3. We compared the non-AKI (without AKI) vs any AKI (stages 1-3), and mild AKI (stage 1) vs severe AKI (stages 2 and 3), where the best cross-validated area under the receiver operator characteristic curve (AUC) were 0.81 (95 % CI, 0.79-0.82) and 0.66 (95 % CI, 0.62-0.71), respectively. Using the developed knowledge mining model and screening framework, we identified 33 risk predictors indicating that severe AKI may occur.

CONCLUSIONS

This study screened out 33 risk predictors that are more likely to indicate severe AKI in hospitalized patients, which would help strengthen the early care and prevention of patients.

Changing relative risk of clinical factors for hospital-acquired acute kidney injury across age groups: a retrospective cohort study

Background

Likelihood of developing acute kidney injury (AKI) increases with age. We aimed to explore whether the predictability of AKI varies between age groups and assess the volatility of risk factors using electronic medical records (EMR).

Methods

We constructed a retrospective cohort of adult patients from all inpatient units of a tertiary care academic hospital and stratified it into four age groups: 18–35, 36–55, 56–65, and > 65. Potential risk factors collected from EMR for the study cohort included demographics, vital signs, medications, laboratory values, past medical diagnoses, and admission diagnoses. AKI was defined based on the Kidney Disease Improving Global Outcomes (KDIGO) serum creatinine criteria. We analyzed relative importance of the risk factors in predicting AKI using Gradient Boosting Machine algorithm and explored the predictability of AKI across age groups using multiple machine learning models.

Results

In our cohort, older patients showed a significantly higher incidence of AKI than younger adults: 18–35 (7.29%), 36–55 (8.82%), 56–65 (10.53%), and > 65 (10.55%) (p < 0.001). However, the predictability of AKI decreased with age, where the best cross-validated area under the receiver operating characteristic curve (AUROC) achieved for age groups 18–35, 36–55, 56–65, and > 65 were 0.784 (95% CI, 0.769–0.800), 0.766 (95% CI, 0.754–0.777), 0.754 (95% CI, 0.741–0.768), and 0.725 (95% CI, 0.709–0.737), respectively. We also observed that the relative risk of AKI predictors fluctuated between age groups.

Conclusions

As complexity of the cases increases with age, it is more difficult to quantify AKI risk for older adults in inpatient population.

Development and validation of an automated algorithm for identifying patients at higher risk for drug-induced acute kidney injury

PURPOSE

Using information from institutional electronic health records, we aimed to develop dynamic predictive models to identify patients at high risk of acute kidney injury (AKI) among those who received a nephrotoxic medication during their hospital stay.

METHODS

Candidate predictors were measured for each of the first 5 hospital days where a patient received a nephrotoxic medication (risk model days) to predict an AKI, using logistic regression with reduced backward variables elimination in 100 bootstrap samples. An AKI event was defined as an increase of serum creatinine ≥ 200% of a baseline SCr within 5 days after a risk model day. Final models were internally validated by replication in 100 bootstrap samples and a risk score for each patient was calculated from the validated model. As performance measures, the area under the receiver operation characteristic curves (AUC) and the number of AKI events among patients who had high risk scores were estimated.

RESULTS

The study population included 62,561 admissions followed by 1,212 AKI events (1.9 events/100 admissions). We constructed 5 risk models corresponding to the first 5 hospital days where patients were exposed to at least one nephrotoxic medication. Validated AUCs of the 5 models ranged from 0.78 to 0.81. Depending on risk model day, admissions ranked in the 90th percentile of the risk score captured between 43% to 49% of all AKI events.

CONCLUSION

A dynamic prediction model was built successfully for inpatient AKI with excellent discriminative validity and good calibration, allowing clinicians to focus on a select high-risk population that captures the majority of AKI events.

Feature Ranking in Predictive Models for Hospital-Acquired Acute Kidney Injury

Acute Kidney Injury (AKI) is a common complication encountered among hospitalized patients, imposing significantly increased cost, morbidity, and mortality. Early prediction of AKI has profound clinical implications because currently no treatment exists for AKI once it develops. Feature selection (FS) is an essential process for building accurate and interpretable prediction models, but to our best knowledge no study has investigated the robustness and applicability of such selection process for AKI. In this study, we compared eight widely-applied FS methods for AKI prediction using nine-years of electronic medical records (EMR) and examined heterogeneity in feature rankings produced by the methods. FS methods were compared in terms of stability with respect to data sampling variation, similarity between selection results, and AKI prediction performance. Prediction accuracy did not intrinsically guarantee the feature ranking stability. Across different FS methods, the prediction performance did not change significantly, while the importance rankings of features were quite different. A positive correlation was observed between the complexity of suitable FS method and sample size. This study provides several practical implications, including recognizing the importance of feature stability as it is desirable for model reproducibility, identifying important AKI risk factors for further investigation, and facilitating early prediction of AKI.

Predicting acute kidney injury at hospital re-entry using high-dimensional electronic health record data

Acute Kidney Injury (AKI), a sudden decline in kidney function, is associated with increased mortality, morbidity, length of stay, and hospital cost. Since AKI is sometimes preventable, there is great interest in prediction. Most existing studies consider all patients and therefore restrict to features available in the first hours of hospitalization. Here, the focus is instead on rehospitalized patients, a cohort in which rich longitudinal features from prior hospitalizations can be analyzed. Our objective is to provide a risk score directly at hospital re-entry. Gradient boosting, penalized logistic regression (with and without stability selection), and a recurrent neural network are trained on two years of adult inpatient EHR data (3,387 attributes for 34,505 patients who generated 90,013 training samples with 5,618 cases and 84,395 controls). Predictions are internally evaluated with 50 iterations of 5-fold grouped cross-validation with special emphasis on calibration, an analysis of which is performed at the patient as well as hospitalization level. Error is assessed with respect to diagnosis, race, age, gender, AKI identification method, and hospital utilization. In an additional experiment, the regularization penalty is severely increased to induce parsimony and interpretability. Predictors identified for rehospitalized patients are also reported with a special analysis of medications that might be modifiable risk factors. Insights from this study might be used to construct a predictive tool for AKI in rehospitalized patients. An accurate estimate of AKI risk at hospital entry might serve as a prior for an admitting provider or another predictive algorithm.

Multi-perspective predictive modeling for acute kidney injury in general hospital populations using electronic medical records

Objectives

Acute kidney injury (AKI) in hospitalized patients puts them at much higher risk for developing future health problems such as chronic kidney disease, stroke, and heart disease. Accurate AKI prediction would allow timely prevention and intervention. However, current AKI prediction researches pay less attention to model building strategies that meet complex clinical application scenario. This study aims to build and evaluate AKI prediction models from multiple perspectives that reflect different clinical applications.

Materials and Methods

A retrospective cohort of 76 957 encounters and relevant clinical variables were extracted from a tertiary care, academic hospital electronic medical record (EMR) system between November 2007 and December 2016. Five machine learning methods were used to build prediction models. Prediction tasks from 4 clinical perspectives with different modeling and evaluation strategies were designed to build and evaluate the models.

Results

Experimental analysis of the AKI prediction models built from 4 different clinical perspectives suggest a realistic prediction performance in cross-validated area under the curve ranging from 0.720 to 0.764.

Discussion

Results show that models built at admission is effective for predicting AKI events in the next day; models built using data with a fixed lead time to AKI onset is still effective in the dynamic clinical application scenario in which each patient's lead time to AKI onset is different.

Conclusion

To our best knowledge, this is the first systematic study to explore multiple clinical perspectives in building predictive models for AKI in the general inpatient population to reflect real performance in clinical application.

Female sex reduces the risk of hospital-associated acute kidney injury: a meta-analysis

Background

Female sex has been included as a risk factor in models developed to predict the development of AKI. In addition, the commentary to the Kidney Disease Improving Global Outcomes Clinical Practice Guideline for AKI concludes that female sex is a risk factor for hospital-acquired AKI. In contrast, a protective effect of female sex has been demonstrated in animal models of ischemic AKI.

Methods

To further explore this issue, we performed a meta-analysis of AKI studies published between January, 1978 and April, 2018 and identified 83 studies reporting sex-stratified data on the incidence of hospital-associated AKI among nearly 240,000,000 patients.

Results

Twenty-eight studies (6,758,124 patients) utilized multivariate analysis to assess risk factors for hospital-associated AKI and provided sex-stratified ORs. Meta-analysis of this cohort showed that the risk of developing hospital-associated AKI was significantly greater in men than in women (OR 1.23 (1.11,1.36). Since AKI is not a single disease but instead represents a heterogeneous group of disorders characterized by an acute reduction in renal function, we performed subgroup meta-analyses. The association of male sex with AKI was strongest among studies of patients who underwent non-cardiac surgery. Male sex was also associated with AKI in studies which included unselected hospitalized patients and in studies of critically ill patients who received care in an intensive care unit. In contrast, cardiac surgery-associated AKI and radiocontrast-induced AKI showed no sexual dimorphism.

Conclusions

Our meta-analysis contradicts the established belief that female sex confers a greater risk of AKI and instead suggests a protective role.

Sex differences in acute kidney injury requiring dialysis

Background

Female sex has been included as a risk factor in models developed to predict the risk of acute kidney injury (AKI) associated with cardiac surgery, aminoglycoside nephrotoxicity and contrast-induced nephropathy. The commentary acompanying the Kidney Disease Improving Global Outcomes Clinical Practice Guideline for Acute Kidney Injury concludes that female sex is a shared susceptibility factor for acute kidney injury based on observations that female sex is associated with the development of hospital-acquired acute kidney injury. In contrast, female sex is reno-protective in animal models. In this context, we sought to examine the role of sex in hospital-associated acute kidney injury in greater detail.

Methods

We utilized the Hospital Episode Statistics database to calculate the sex-stratified incidence of AKI requiring renal replacement therapy (AKI-D) among 194,157,726 hospital discharges reported for the years 1998–2013. In addition, we conducted a systematic review of the English literature to evaluate dialysis practices among men versus women with AKI.

Results

Hospitalized men were more likely to develop AKI-D than hospitalized women (OR 2.19 (2.15, 2.22) p < 0.0001). We found no evidence in the published literature that dialysis practices differ between men and women with AKI.

Conclusions

Based on a population of hospitalized patients which is more than 3 times larger than all previously published cohorts reporting sex-stratified AKI data combined, we conclude that male sex is associated with an increased incidence of hospital-associated AKI-D. Our study is among the first reports to highlight the protective role of female gender in AKI.

Development of an automated phenotyping algorithm for hepatorenal syndrome

OBJECTIVE

Hepatorenal Syndrome (HRS) is a devastating form of acute kidney injury (AKI) in advanced liver disease patients with high morbidity and mortality, but phenotyping algorithms have not yet been developed using large electronic health record (EHR) databases. We evaluated and compared multiple phenotyping methods to achieve an accurate algorithm for HRS identification.

MATERIALS AND METHODS

A national retrospective cohort of patients with cirrhosis and AKI admitted to 124 Veterans Affairs hospitals was assembled from electronic health record data collected from 2005 to 2013. AKI was defined by the Kidney Disease: Improving Global Outcomes criteria. Five hundred and four hospitalizations were selected for manual chart review and served as the gold standard. Electronic Health Record based predictors were identified using structured and free text clinical data, subjected through NLP from the clinical Text Analysis Knowledge Extraction System. We explored several dimension reduction techniques for the NLP data, including newer high-throughput phenotyping and word embedding methods, and ascertained their effectiveness in identifying the phenotype without structured predictor variables. With the combined structured and NLP variables, we analyzed five phenotyping algorithms: penalized logistic regression, naïve Bayes, support vector machines, random forest, and gradient boosting. Calibration and discrimination metrics were calculated using 100 bootstrap iterations. In the final model, we report odds ratios and 95% confidence intervals.

RESULTS

The area under the receiver operating characteristic curve (AUC) for the different models ranged from 0.73 to 0.93; with penalized logistic regression having the best discriminatory performance. Calibration for logistic regression was modest, but gradient boosting and support vector machines were superior. NLP identified 6985 variables; a priori variable selection performed similarly to dimensionality reduction using high-throughput phenotyping and semantic similarity informed clustering (AUC of 0.81 - 0.82).

CONCLUSION

This study demonstrated improved phenotyping of a challenging AKI etiology, HRS, over ICD-9 coding. We also compared performance among multiple approaches to EHR-derived phenotyping, and found similar results between methods. Lastly, we showed that automated NLP dimension reduction is viable for acute illness.

Calibration drift in regression and machine learning models for acute kidney injury

Objective

Predictive analytics create opportunities to incorporate personalized risk estimates into clinical decision support. Models must be well calibrated to support decision-making, yet calibration deteriorates over time. This study explored the influence of modeling methods on performance drift and connected observed drift with data shifts in the patient population.

Materials and Methods

Using 2003 admissions to Department of Veterans Affairs hospitals nationwide, we developed 7 parallel models for hospital-acquired acute kidney injury using common regression and machine learning methods, validating each over 9 subsequent years.

Results

Discrimination was maintained for all models. Calibration declined as all models increasingly overpredicted risk. However, the random forest and neural network models maintained calibration across ranges of probability, capturing more admissions than did the regression models. The magnitude of overprediction increased over time for the regression models while remaining stable and small for the machine learning models. Changes in the rate of acute kidney injury were strongly linked to increasing overprediction, while changes in predictor-outcome associations corresponded with diverging patterns of calibration drift across methods.

Conclusions

Efficient and effective updating protocols will be essential for maintaining accuracy of, user confidence in, and safety of personalized risk predictions to support decision-making. Model updating protocols should be tailored to account for variations in calibration drift across methods and respond to periods of rapid performance drift rather than be limited to regularly scheduled annual or biannual intervals.

Improving acute kidney injury diagnostics using predictive analytics

PURPOSE OF REVIEW

Acute kidney injury (AKI) is a multifactorial syndrome affecting an alarming proportion of hospitalized patients. Although early recognition may expedite management, the ability to identify patients at-risk and those suffering real-time injury is inconsistent. The review will summarize the recent reports describing advancements in the area of AKI epidemiology, specifically focusing on risk scoring and predictive analytics.

RECENT FINDINGS

In the critical care population, the primary underlying factors limiting prediction models include an inability to properly account for patient heterogeneity and underperforming metrics used to assess kidney function. Severity of illness scores demonstrate limited AKI predictive performance. Recent evidence suggests traditional methods for detecting AKI may be leveraged and ultimately replaced by newer, more sophisticated analytical tools capable of prediction and identification: risk stratification, novel AKI biomarkers, and clinical information systems. Additionally, the utility of novel biomarkers may be optimized through targeting using patient context, and may provide more granular information about the injury phenotype. Finally, manipulation of the electronic health record allows for real-time recognition of injury.

SUMMARY

Integrating a high-functioning clinical information system with risk stratification methodology and novel biomarker yields a predictive analytic model for AKI diagnostics.