Using machine learning and centrifugal microfluidics at the point-of-need to predict clinical deterioration of patients with suspected sepsis within the first 24 h.

Sepsis is the bodys dysfunctional response to infection associated with organ failure. Delays in diagnosis have a substantial impact on survival. Herein, samples from 586 in-house patients were used in conjunction with machine learning and cross-validation to narrow a gene expression signature of immune cell reprogramming to predict clinical deterioration in patients with suspected sepsis within the first 24 hours (h) of clinical presentation using just six genes (Sepset). The accuracy of the test (~90% in early intensive care unit (ICU) and 70% in emergency room patients) was validated in 3,178 patients from existing independent cohorts. A real-time reverse transcriptase polymerase chain reaction (RT-PCR)-based test was shown to have a 98% sensitivity in >230 patients to predict worsening of the sequential organ failure scores or admission to the ICU within the first 24 h following Sepset detection. A stand-alone centrifugal microfluidic instrument that integrates the entire automated workflow for detection of the Sepset classifier in whole blood using digital droplet PCR was developed and tested. This PREcision meDIcine for CriTical care (PREDICT) system had a high sensitivity of 92%, specificity of 89%, and an overall accuracy of 88% in identifying the risk of imminent clinical deterioration in patients with suspected sepsis.