Machine Learning Algorithms for Classification of Microcirculation Images from Septic and Non-Septic Patients
This addresses the challenge of diagnosing sepsis, a life-threatening disease, for patients in hospitals, but it is incremental as it applies existing methods to a new medical imaging dataset.
The researchers tackled the problem of automated sepsis diagnosis by developing a machine learning classifier to distinguish between septic and non-septic microcirculation images, achieving an accuracy of 89.45% and an AUC of 0.92.
Sepsis is a life-threatening disease and one of the major causes of death in hospitals. Imaging of microcirculatory dysfunction is a promising approach for automated diagnosis of sepsis. We report a machine learning classifier capable of distinguishing non-septic and septic images from dark field microcirculation videos of patients. The classifier achieves an accuracy of 89.45%. The area under the receiver operating characteristics of the classifier was 0.92, the precision was 0.92 and the recall was 0.84. Codes representing the learned feature space of trained classifier were visualized using t-SNE embedding and were separable and distinguished between images from critically ill and non-septic patients. Using an unsupervised convolutional autoencoder, independent of the clinical diagnosis, we also report clustering of learned features from a compressed representation associated with healthy images and those with microcirculatory dysfunction. The feature space used by our trained classifier to distinguish between images from septic and non-septic patients has potential diagnostic application.