A machine learning and centrifugal microfluidics platform for bedside prediction of sepsis
Lidija Malic, Peter Zhang, Pamela Plant, Liviu Clime, Christina Nassif, Dillon Da Fonte, Evan F. Haney, Byeong‐Ui Moon, Victor Mun-Sing Sit, D. Brassard, Maxence Mounier, Eryn Churcher, Jim Tsoporis, Reza Falsafi, Manjeet Bains, Andrew Baker, Uriel Trahtemberg, Ljuboje Lukic, John C. Marshall, Matthias Geißler, Robert E. W. Hancock, Teodor Veres, Claúdia C. dos Santos
Abstract
Sepsis is a life-threatening organ dysfunction due to a dysfunctional response to infection. Delays in diagnosis have substantial impact on survival. Herein, blood samples from 586 in-house patients with suspected sepsis are used in conjunction with machine learning and cross-validation to define a six-gene expression signature of immune cell reprogramming, termed Sepset, to predict clinical deterioration within the first 24 h (h) of clinical presentation. Prediction accuracy (~90% in early intensive care unit (ICU) and 70% in emergency room patients) is validated in 3178 patients from existing independent cohorts. A RT-PCR-based Sepset detection test shows a 94% sensitivity in 248 patients to predict worsening of the sequential organ failure assessment scores within the first 24 h. A stand-alone centrifugal microfluidic instrument that automates whole-blood Sepset classifier detection is tested, showing a sensitivity of 92%, and specificity of 89% in identifying the risk of clinical deterioration in patients with suspected sepsis. Sepsis may promptly develop into lethal organ failure, so early diagnosis and treatment planning are essential. Here the authors use machine learning to develop a six-gene signature, termed Sepset, for initial diagnosis, and integrate Sepset into a microfluidic-based bench-side platform for predicting the prognosis of suspected sepsis suitable for the clinic.