Helping Emergency Care Physicians Diagnose Sepsis and Bacterial Infections with Machine Learning and Vision
Sepsis, a life-threatening complication of bacterial infection, leads to millions of worldwide deaths requires significant time and resources to diagnose. This disease is associated with very high mortality rates, making early detection crucial for treatment.
Researchers have investigated direct clinical evaluation by using dark field imaging of capillary beds under the tongue of septic and healthy subjects for signatures of microcirculatory dysfunction associated with sepsis. Our published results, in collaboration with Beth Israel Deaconess Medical Center, have shown that machine learning and vision can learn higher-order hierarchical diagnostic and prognostic features for rapid and non-invasive diagnosis of sepsis using these dark field microcirculatory images. A neural network capable of distinguishing between images from non-septic and septic patients with more than 90% accuracy is reported for the first time. This approach can help physicians to rapidly stratify patients, facilitate rational use of antibiotics, and reduce disease burden in hospital emergency rooms.
Why is this work important?
Sepsis is a life-threatening disease where the host’s response to an infection leads to inflammation that may result in multiple organ failure and eventually death of the patient. Sepsis is associated with very high mortality rates that make early detection crucial for treatment. Microcirculation is the flow of blood in the smallest elements of the cardiovascular system, the capillary network, where the exchange of oxygen takes place and is pivotal in the maintenance of homeostasis. Improvements in microcirculation function after early resuscitation have been associated with reduction in subsequent organ failure.
What has been done before?
In previous studies, microcirculation dysfunction was experimentally induced in animal models with drugs and other agents followed by Sidestream Dark Field (SDF) imaging. SDF imaging is a non-invasive imaging modality and has been used to track changes in the microcirculation on mucosal surfaces. SDF uses green polarized light with wavelength of 550 nm which is absorbed by hemoglobin and makes red blood cells visible. The distinguishing parameters and measurements associated to microcirculation include MFI (Microcirculation Flow Index), PVD (Perfused Vessel Density), TVD (Total Vessel Density) and PPV (Portion of Perfused Vessels). These measurements require identification of vessels in microcirculation video frames. Several software systems have been developed to analyze the microcirculation images and videos for these measurements, but often fail to provide desired results. Marking of hand engineered features on each frame of the video is required at some stage of analyses and is time consuming and not accurate.
What are our key contributions?
To our knowledge, this is the first study that successfully classifies human microcirculation image data using a deep neural network. In this work, we implement a CNN to analyze microcirculatory dysfunction captured by dark field imaging in human patients and distinguish between septic and nonseptic images with high accuracies.
Explainability of this work and what does the classifier learn?
We investigated outputs from the last convolutional layer in our architecture, and using a t-SNE embedding show that the representation learned by the classifier successfully differentiates the frames. Additionally, an unsupervised learning approach, independent of clinical labels, was used to investigate the feature space of the microcirculation image validation dataset and showed clustering images from non-septic and septic patients. These were first demonstrations in this field of separation between learnable features in the data.
What are the next steps?
We reason that the salient feature space used by our trained classifier has diagnostic applications for evaluating microcirculation dysfunction in humans. We also hypothesize that our neural network may be learning highly discernible features between images from septic and non-septic patients. The overlap, if any, between diagnostic features used by human experts and our machine learning algorithms is an active area of investigation in our research group. We also continue to investigate the learned feature space and it’s explainability to human physicians.
Microcirculation and capillary network
Dr. Pratik Shah
Dr. Nathan Shapiro. Beth Israel Deaconess Medical Center.
P. Javia, A. Rana, N. Shapiro and P. Shah, “Machine Learning Algorithms for Classification of Microcirculation Images from Septic and Non-septic Patients,” 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, 2018, pp. 607-611, doi: 10.1109/ICMLA.2018.00097.