Introduction

The Motivation

DAECOS’s motivation is to support physicians to manage critically ill patients by applying the right treatment to the right patient at the right time. Multi organ failure and acute kidney injury (AKI) requiring dialysis (AKI-D) is a devastating, costly complication of critical illness that is associated with mortality rates > 50%, annual costs of > $10 billion, > 40% rehospitalization rates and long-term disabilities.

Over 600,000 AKI cases are seen yearly in the US and over a nine-year span, 1.09 million hospitalizations involved (AKI-D). Recent trials have shown application of AKI-D based on current criteria results in over 40% of patients not needing dialysis while those who receive it late have a 25% higher mortality. Underlying patient heterogeneity, lack of standardization and practice variations in the application of dialysis, contributes to these adverse outcomes.

DAECOS has developed and validated a proprietary patent pending, real-time, scalable clinical decision support system (CDSS) to accurately predict risk of organ failure and outcomes in critically ill patients and empower clinicians to achieve timely decisions and implement appropriate organ support at the right time.

Innovation

Existing scoring systems such as APACHE 3 and SOFA, although correlating with patient outcomes, have not been useful in predicting the need for, timing of and prognosis of dialysis for individual patients (REF). DAECOS utilizes a novel approach to dynamically quantify the need for organ support by assessing the mismatch of the demand (D) placed on any organ and the available organ capacity (C) expressed as a demand-capacity mismatch score (DCM).

The DCM algorithms have been derived from over 20,000 ICU patients from 4 international centers, externally validated in retrospective data from over 80,000 ICU patients from another USA center and prospectively validated in 500 patients across 5 international centers with excellent performance predicting the need for dialysis within 96 hours at any time in the ICU. Our approach to combine real-time predictive risk assessment with prescriptive analytics is unique as it provides timely, standardized, and optimized clinical decision support through the continuum of a patient’s course of disease. The algorithm is transparent as it is based on easily understood pathophysiology thereby making it actionable and more likely to be accepted by physicians and potentially be exempt from the FDA regulations of Software as a Medical Device.