Acute kidney injury detection using refined and physiological-feature augmented urine output

Acute kidney injury (AKI) is common in the intensive care unit, where it is associated with increased mortality. AKI is often defined using creatinine and urine output criteria. The creatinine-based definition is more reliable but less expedient, whereas the urine output based definition is rapid but less reliable. Our goal is to examine the urine output criterion and augment it with physiological features for better agreement with creatinine-based definitions of AKI. The objectives are threefold: (1) to characterize the baseline agreement of urine output and creatinine definitions of AKI; (2) to refine the urine output criteria to identify the thresholds that best agree with the creatinine-based definition; and (3) to build generalized estimating equation (GEE) and generalized linear mixed-effects (GLME) models with static and time-varying features to improve the accuracy of a near-real-time marker for AKI. We performed a retrospective observational study using data from two independent critical care databases, MIMIC-III and eICU, for critically ill patients who developed AKI in intensive care units. We found that the conventional urine output criterion (6 hr, 0.5 ml/kg/h) has specificity and sensitivity of 0.49 and 0.54 for MIMIC-III database; and specificity and sensitivity of 0.38 and 0.56 for eICU. Secondly, urine output thresholds of 12 hours and 0.6 ml/kg/h have specificity and sensitivity of 0.58 and 0.48 for MIMIC-III; and urine output thresholds of 10 hours and 0.6 ml/kg/h have specificity and sensitivity of 0.49 and 0.48 for eICU. Thirdly, the GEE model of four hours duration augmented with static and time-varying features can achieve a specificity and sensitivity of 0.66 and 0.61 for MIMIC-III; and specificity and sensitivity of 0.66 and 0.64 for eICU. The GLME model of four hours duration augmented with static and time-varying features can achieve a specificity and sensitivity of 0.71 and 0.55 for MIMIC-III; and specificity and sensitivity of 0.66 and 0.60 for eICU. The GEE model has greater performance than the GLME model, however, the GLME model is more reflective of the variables as fixed effects or random effects. The significant improvement in performance, relative to current definitions, when augmenting with patient features, suggest the need of incorporating these features when detecting disease onset and modeling at window-level rather than patient-level.

The importance of the urinary output criterion for the detection and prognostic meaning of AKI

Most reports on AKI claim to use KDIGO guidelines but fail to include the urinary output (UO) criterion in their definition of AKI. We postulated that ignoring UO alters the incidence of AKI, may delay diagnosis of AKI, and leads to underestimation of the association between AKI and ICU mortality. Using routinely collected data of adult patients admitted to an intensive care unit (ICU), we retrospectively classified patients according to whether and when they would be diagnosed with KDIGO AKI stage ≥ 2 based on baseline serum creatinine (Screa) and/or urinary output (UO) criterion. As outcomes, we assessed incidence of AKI and association with ICU mortality. In 13,403 ICU admissions (62.2% male, 60.8 ± 16.8 years, SOFA 7.0 ± 4.1), incidence of KDIGO AKI stage ≥ 2 was 13.2% when based only the SCrea criterion, 34.3% when based only the UO criterion, and 38.7% when based on both criteria. By ignoring the UO criterion, 66% of AKI cases were missed and 13% had a delayed diagnosis. The cause-specific hazard ratios of ICU mortality associated with KDIGO AKI stage ≥ 2 diagnosis based on only the SCrea criterion, only the UO criterion and based on both criteria were 2.11 (95% CI 1.85–2.42), 3.21 (2.79–3.69) and 2.85 (95% CI 2.43–3.34), respectively. Ignoring UO in the diagnosis of KDIGO AKI stage ≥ 2 decreases sensitivity, may lead to delayed diagnosis and results in underestimation of KDIGO AKI stage ≥ 2 associated mortality.

Urine microscopy as a biomarker of Acute Kidney Injury following cardiac surgery with cardiopulmonary bypass

Introduction: Acute kidney injury (AKI) occurs in about 22% of the patients undergoing cardiac surgery and 2.3% requires renal replacement therapy (RRT). The current diagnostic criteria for AKI by increased serum creatinine levels have limitations and new biomarkers are being tested. Urine sediment may be considered a biomarker and it can help to differentiate pre-renal (functional) from renal (intrinsic) AKI. Aims: To investigate the microscopic urinalysis in the AKI diagnosis in patients undergoing cardiac surgery with cardiopulmonary bypass. Methods: One hundred and fourteen patients, mean age 62.3 years, 67.5 % male, with creatinine 0.91 mg/dL (SD 0.22) had a urine sample examined in the first 24 h after the surgery. We looked for renal tubular epithelial cells (RTEC) and granular casts (GC) and associated the results with AKI development as defined by KDIGO criteria. Results: Twenty three patients (20.17 %) developed AKI according to the serum creatinine criterion and 76 (66.67 %) by the urine output criterion. Four patients required RRT. Mortality was 3.51 %. The use of urine creatinine criterion to predict AKI showed a sensitivity of 34.78 % and specificity of 86.81 %, positive likelihood ratio of 2.64 and negative likelihood ratio of 0.75, AUC-ROC of 0.584 (95%CI: 0.445-0.723). For the urine output criterion sensitivity was 23.68 % and specificity 92.11 %, AUC-ROC was 0.573 (95%CI: 0.465-0.680). Conclusion: RTEC and GC in urine sample detected by microscopy is a highly specific biomarker for early AKI diagnosis after cardiac surgery.

An Input-Output Criterion for Linear Model Deduction

Model order deduction algorithms have been developed in an effort to automate the production of accurate, minimal complexity models of dynamic systems in order to aid in the design of these systems. Previous algorithms, MODA and Extended MODA, deduce models independent of system inputs and outputs. FD-MODA uses frequency response methods to deduce models of a single input-output pair. In this paper, an input-output criterion based on controllability and observability is combined with the frequency based criterion used by MODA. The new model deduction algorithm, IO-MODA, compares the ratio of the adjacent diagonal values of the system gramian to a user specified threshold. The gramian is computed from a balanced realization of the system. IO-MODA generates an accurate multiple-input multiple-output model of minimum order with physically meaningful states. This model is called a proper MIMO model. An example problem is used to demonstrate this new model deduction algorithm. [S0022-0434(00)02103-1]