There is significant research being performed on quantified algorithms and urinary biomarkers to improve the detection and diagnosis of AKI. However, many of the research excludes urine output as a metric or data input. It is important to recognize all the challenges in obtaining high-fidelity urine output measurements in the different clinical settings. The lack of availability of automatic urine meters are often impeding factors in applying the strict urine output based AKI criteria definition.
Despite these difficulties, the results of recent studies establish the absolute necessity for urine output assessment in patients for diagnosing and staging AKI. Applying these criteria can increase the sensitivity and specificity of the AKIN classification system, as oliguric patients without sCr change have an increased mortality, dialysis requirement and longer length of ICU stay than non-AKI patients. Applying the AKIN classification system without the urine criteria significantly underscores the incidence and grade of AKI and potentially delays the prediction and diagnosis of AKI in any algorithm.
In the near future, Output will aim build an ecosystem to refine existing algorithms with high fidelity urine output measurements, and introduce additional data input into these algorithms by developing immunoassays to detect established, well-researched urinary biomarkers. The goal to develop an improved quantitative analytics model to predict and diagnose acute kidney injury by incorporating high fidelity urine output measurements into existing AKI predictive and diagnostic algorithms.
Implementing predictive and diagnostic algorithms into the management of AKI is a principle point of discussion as per the KDIGO and ADQI initiatives. There have been attempts to incorporate such models into retrospective reviews to attest clinical utility in decision-making. Yet, variables from these patient-specific models are often constrained to the clinical care specific to that population; for example, models for cardiac surgery patients include cardiopulmonary bypass time and number of bypass grafts.
However, a number of variables commonly appear across many of the existing models (i.e., age, baseline renal function, medications, diabetes, hypertension, etc.); these variables may be better suited for a generalized model. Most models had modest predictive success with area under the receiver operating curves (AUC) approximating 0.75; a few models reached AUCs as high as 0.9, although the sample sizes were smaller and there was a pre-selection of high-risk patients.
Many of these predictive models and other similar studies on AKI diagnostic specificity and sensitivity fail to include urine output and trends in urine output as a data input into the model. Urine output is either considered unreliable data or not statistically significant to decision making. Output Medical aims to change that.