Predicting ICU Transfers

Saving Lives by Catching Patients Before the Crash with Data Analytics and AI

Goal

Strategic Advantage –> Better/Personalized Treatments –> Customer Satisfaction –> Increased Revenue and ROI

Challenges

Studies show that patients who undergo an unplanned transfer to the ICU experience worse outcomes than patients admitted directly. These patients typically stay in the hospital 8 to 12 days longer and have significantly higher mortality rates – these patients account for only 5% of patients but represent one-fifth of all hospital deaths. The challenge is to find patients before they “crash” and need to be moved to the ICU, but these patients often lack recognizable symptoms that clinicians can access as ones leading to a serious change in condition.

Opportunities

AI models can be used to find patients who are likely to crash. The machine learning models use patient medical records, laboratory results, and vital signs from patients to find early warning signals of deteriorating condition. These models can be used with existing patients in real-time to determine their risk of a crash and as part of an early warning system for clinicians so they can intervene before the ICU transfer is needed. The AI system can also provide reason codes for a specific patient, which can be a helpful tool to clinicians to understand where they should begin their treatment.

Skip to content