Predicting Progression to Septic Shock in the Emergency Department Using an Externally Generalizable Machine-Learning Algorithm

Abstract

Study objective: Machine-learning algorithms allow improved prediction of sepsis syndromes in the emergency department (ED), using data from electronic medical records. Transfer learning, a new subfield of machine learning, allows generalizability of an algorithm across clinical sites. We aim to validate the Artificial Intelligence Sepsis Expert for the prediction of delayed septic shock in a cohort of patients treated in the ED and demonstrate the feasibility of transfer learning to improve external validity at a second site.

Methods: This was an observational cohort study using data from greater than 180,000 patients from 2 academic medical centers between 2014 and 2019, using multiple definitions of sepsis. The Artificial Intelligence Sepsis Expert algorithm was trained with 40 input variables at the development site to predict delayed septic shock (occurring greater than 4 hours after ED triage) at various prediction windows. We then validated the algorithm at a second site, using transfer learning to demonstrate generalizability of the algorithm.

Results: We identified 9,354 patients with severe sepsis, of whom 723 developed septic shock at least 4 hours after triage. The Artificial Intelligence Sepsis Expert algorithm demonstrated excellent area under the receiver operating characteristic curve (>0.8) at 8 and 12 hours for the prediction of delayed septic shock. Transfer learning significantly improved the test characteristics of the Artificial Intelligence Sepsis Expert algorithm and yielded comparable performance at the validation site.

Conclusion: The Artificial Intelligence Sepsis Expert algorithm accurately predicted the development of delayed septic shock. The use of transfer learning allowed significantly improved external validity and generalizability at a second site. Future prospective studies are indicated to evaluate the clinical utility of this model.

Figure 1.

Transfer learning as implemented in this study. In part 1, a prediction model neural network (such as Artificial Intelligence Sepsis Expert) is initialized with random weights and is trained with data from the development site. In part 2, starting with a pretrained model from the development site, the model weights are fine-tuned (or retrained) with a relatively small amount of data from the validation site before application to the validation cohort. This procedure is called transfer learning.

Figure 2.

Inclusion of subjects used in the development and validation cohorts using CMS sepsis definitions.

Figure 3.

Comparison of AUC and specificity (calculated at 85% sensitivity) of models predicting septic shock at different prediction windows at the validation site. Ten-fold cross validation was performed and median and interquartile ranges are presented with lines and shaded areas, respectively.

Figure 4.

AUC ROC and precision-recall curves for predicting t-sepsis 12 hours in advance at the development site using CMS severe sepsis definition. AUCroc, Area under the receiver operating characteristic; AUCpr, AUC precision-recall curve.

Figure 5.

AUC ROC of the ability of the Artificial Intelligence Sepsis Expert algorithm to detect septic shock 12 hours ahead of time in the validation cohort with and without transfer learning (red and black dashed lines, respectively) based on increasing amounts of patient encounters in model development.