Clinical Decision Support Tools

Upcoming Deployment

WounDx

Blast injuries and other combat-associated wounds present unique challenges to healthcare enterprises. We found that a comprehensive biological assessment, coupled with advanced mathematical techniques, can be used to generate a predictive model that may help surgeons improve outcomes by minimizing wound-related complications. This translates to shorter hospital stays, quicker rehabilitation, and lower costs. We then distilled the prognostic information into a Clinical Decision Support tool called WOUNDx™, which uses common inflammatory markers coupled with clinical observations to estimate the likelihood of wound failure in complex wounds. This highly predictive algorithm can help surgeons identify when to close or otherwise cover wounds in high-risk military and civilian populations.

TripleDx

Critically ill patients are at a heightened risk of developing complications due to the physiological stress induced by trauma or major surgeries. Pneumonia (nosocomial or ventilator- associated pneumonia), acute kidney injury (AKI), and venous thromboembolism (VTE) are among the most prevalent complications in this patient population, leading to increased morbidity, prolonged hospital stays, escalated medical costs, and, in worst cases, mortality. TripleDx, an integrated in-vitro diagnostic (IVD) test combined with a machine learning (ML) algorithm is designed to predict the development of these complications in critically ill patients admitted to surgical Intensive Care Units (ICUs) following trauma or major surgeries.

AIDEx / AISE

SC2i is currently working to develop a sepsis prediction tool, referred to as AIDEx (Artificial Intelligence Decompensation Expert). This tool is the data delivery pipeline / infrastructure which will be utilized in conjunction with our sepsis prediction algorithm, AISE (Artificial Intelligence Sepsis Expert), to improve sepsis management amongst adult ICU patients through rapid identification (4-6 hours prior to onset) and treatment of sepsis. The interface will allow clinicians to monitor large patient populations or individual patients in near-real-time, while also sending alerts to the clinician when specific patients reach specific sepsis risk thresholds. This tool and algorithm combination lay the groundwork for cutting edge artificial intelligence and data-based Clinical Decision Support Tool deployments in the Military Health System.

In-Deployment

IFI

Invasive fungal infections are devastating and threaten both life and limb. Typically, rare in immunocompetent individuals, IFI have developed with remarkable frequency in severely combat-injured patients, particularly those sustaining multi-system blast trauma with associated abdomino-pelvic injuries, multiple amputations, and/or requiring massive early life saving transfusions.  Despite the high survival rate of our wounded warriors from the current conflicts, some such patients have succumbed to these aggressive infections after reaching military medical centers. Surviving patients have complex, morbid clinical courses frequently requiring multiple additional procedures and proximal migration of amputations, with high associated complication rates. Using a large database of combat-injured personnel, we have developed Clinical Decision Support Tools to allow early IFI risk stratification at either the in-theater or medical center echelons of care; these tools were subsequently externally validated utilizing a separate, similar database. These tools can facilitate the early diagnosis and aggressive prophylactic local and systemic treatment of patients at high risk for IFI, which we believe is critical to mitigate IFI-associated morbidity and mortality.

MTP

The decision to activate a massive transfusion protocol is both complex and time sensitive. It requires not only an urgent assessment of a critically injured patient's physiology but also must take into account issues of resource availability and utilization. Oftentimes, little empiric data is available rapidly enough to assist the bedside clinician and therefore this key decision is often left to the instincts of the treating team. Several published tools use manual calculations that are either too complex, making them of little use in real-time, or too simple, making them not accurate enough to be truly useful. Fortunately, technology allows us to bring sophisticated computers in the form of smart phones to the bedside to assist in these complex decisions. A mobile application designed to take simple physiologic data available to the clinician within minutes of patient arrival and create an extremely accurate prediction of the need for urgent massive transfusion has been designed using data from over 10 years of patient care in a busy urban trauma center. This application is currently being studied prospectively to understand if it will be a useful Clinical Decision Support tool.

CDST Development Overview