A Machine Learning Algorithm to Predict Severe Sepsis and Septic Shock: Development, Implementation, and Impact on Clinical Practice*. Issue 11 (November 2019)

• Record Type: Journal Article
• Authors: Giannini, Heather M.; Ginestra, Jennifer C.; Chivers, Corey; Draugelis, Michael; Hanish, Asaf; Schweickert, William D.; Fuchs, Barry D.; Meadows, Laurie; Lynch, Michael; Donnelly, Patrick J.; Pavan, Kimberly; Fishman, Neil O.; Hanson, C. William; Umscheid, Craig A.
• Is Part Of: Critical care medicine. Volume 47:Issue 11(2019)
• Publication Date: 2019-11
• Subjects: early warning system -- electronic medical record -- machine learning -- predictive medicine -- septic shock -- severe sepsis; Critical care medicine -- Periodicals; Soins intensifs -- Périodiques; 616.028
• DOI: 10.1097/CCM.0000000000003891
• Languages: English
• ISSNs: 0090-3493

Abstract

Abstract : Objectives: Develop and implement a machine learning algorithm to predict severe sepsis and septic shock and evaluate the impact on clinical practice and patient outcomes. Design: Retrospective cohort for algorithm derivation and validation, pre-post impact evaluation. Setting: Tertiary teaching hospital system in Philadelphia, PA. Patients: All non-ICU admissions; algorithm derivation July 2011 to June 2014 ( n = 162, 212); algorithm validation October to December 2015 ( n = 10, 448); silent versus alert comparison January 2016 to February 2017 (silent n = 22, 280; alert n = 32, 184). Interventions: A random-forest classifier, derived and validated using electronic health record data, was deployed both silently and later with an alert to notify clinical teams of sepsis prediction. Measurement and Main Result: Patients identified for training the algorithm were required to have International Classification of Diseases, 9th Edition codes for severe sepsis or septic shock and a positive blood culture during their hospital encounter with either a lactate greater than 2.2 mmol/L or a systolic blood pressure less than 90 mm Hg. The algorithm demonstrated a sensitivity of 26% and specificity of 98%, with a positive predictive value of 29% and positive likelihood ratio of 13. The alert resulted in a small statistically significant increase in lactate testing and IV fluid administration. There was no significant difference in mortality, discharge disposition, or transfer to ICU, although there was a reduction in time-to-ICU transfer. Conclusions: Our machine learning algorithm can predict, with low sensitivity but high specificity, the impending occurrence of severe sepsis and septic shock. Algorithm-generated predictive alerts modestly impacted clinical measures. Next steps include describing clinical perception of this tool and optimizing algorithm design and delivery. Abstract : Supplemental Digital Content is available in the text.