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

Cronin, Robert M.; VanHouten, Jacob P.; Siew, Edward D.; Eden, Svetlana; Fihn, T. Stephan D.; Nielson, Christopher; Peterson, Josh F.; Baker, Clifton R.; İkizler, T. Alp; Speroff, Theodore; Matheny, Michael E.

doi:10.1093/jamia/ocv051

Cited by 38 publications

(44 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In AKI predictive modeling, logistic regression with backward or forward selection (wrapper method) is often used to select a subset of features for model building 7 ; chi-squared test (filter) 8 , random forest (embedded) 9 , and gradient boosting machine (embedded) 10 have also been applied to illustrate the feature importance and ranking in AKI prediction. With the increasing variety of feature selection methods and their frequent utilization in the health informatics research community, new questions arise, namely there is no systematic way to choose the most appropriate feature selection method for a given domain and problem, which often depends on two aspects 11 : (a) the stability of FS ranking with respect to different samples, and (b) the prediction accuracy of FS subset effectively representing the entire data.…”

Section: Introductionmentioning

confidence: 99%

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

Liu

et al. 2018

Sci Rep

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Liu

et al. 2018

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Time of Prediction Most of the past work had chosen a particular time for making predictions, say 24 hours from admission [14,15], or 48 hours from admission [16,17], or even at the time of admission [33], while some of the past work were not clear about it [34,35]. In the rest of the paper, we call a prediction model built to make predictions at 24 hours from admission as one-time-at-24-hour prediction model.…”

Section: 31mentioning

confidence: 99%

A continual prediction model for inpatient acute kidney injury

Kate

Pearce

Mazumdar

et al. 2020

Computers in Biology and Medicine

View full text Add to dashboard Cite

“…Note that every positive laboratory coefficient contains a maximum and every negative a minimum. Comparison with features from Cronin et al [16] We can compare our features to those in Cronin et al [16], where a random forest was used to predict AKI stage 1+ (KDIGO stages 1, 2, or 3). In Cronin et al, we see strong dependence on renal indicators (e.g., GFR, UN), labs indirectly associated with renal function (Hemoglobin), heart failure, diuretics (loop, thiazides), and anti-hypertensives such as angiotensin-converting enzyme inhibitors (ACEi), which is also reflected in our findings.…”

Section: Hplr1mentioning

confidence: 99%

“…Conversely, prior hospitalizations might be renal stressors, diminishing renal reserve. Most previous studies on AKI posit data models, although some more recent work [16,27] explores predictive algorithms, distinct from data models [32], as done here. Penalized regression and ensemble methods were employed to mitigate overfitting.…”

mentioning

confidence: 99%

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

et al. 2018

View full text Add to dashboard Cite

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.

show abstract

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

Cited by 38 publications

References 66 publications

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

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

A continual prediction model for inpatient acute kidney injury

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

Contact Info

Product

Resources

About