Validating a Proteomic Signature of Severe COVID-19.

COVID-19 is a heterogenous disease. Biomarker-based approaches may identify patients at risk for severe disease, who may be more likely to benefit from specific therapies. Our objective was to identify and validate a plasma protein signature for severe COVID-19. DESIGN: Prospective observational cohort study. SETTING: Two hospitals in the United States. PATIENTS: One hundred sixty-seven hospitalized adults with COVID-19. INTERVENTION: None. MEASUREMENTS AND MAIN RESULTS: We measured 713 plasma proteins in 167 hospitalized patients with COVID-19 using a high-throughput platform. We classified patients as nonsevere versus severe COVID-19, defined as the need for high-flow nasal cannula, mechanical ventilation, extracorporeal membrane oxygenation, or death, at study entry and in 7-day intervals thereafter. We compared proteins measured at baseline between these two groups by logistic regression adjusting for age, sex, symptom duration, and comorbidities. We used lead proteins from dysregulated pathways as inputs for elastic net logistic regression to identify a parsimonious signature of severe disease and validated this signature in an external COVID-19 dataset. We tested whether the association between corticosteroid use and mortality varied by protein signature. One hundred ninety-four proteins were associated with severe COVID-19 at the time of hospital admission. Pathway analysis identified multiple pathways associated with inflammatory response and tissue repair programs. Elastic net logistic regression yielded a 14-protein signature that discriminated 90-day mortality in an external cohort with an area under the receiver-operator characteristic curve of 0.92 (95% CI, 0.88-0.95). Classifying patients based on the predicted risk from the signature identified a heterogeneous response to treatment with corticosteroids (p = 0.006). CONCLUSIONS: Inpatients with COVID-19 express heterogeneous patterns of plasma proteins. We propose a 14-protein signature of disease severity that may have value in developing precision medicine approaches for COVID-19 pneumonia.

A Machine Learning Algorithm to Predict Severe Sepsis and Septic Shock: Development, Implementation, and Impact on Clinical Practice.

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.

Clinician Perception of a Machine Learning-Based Early Warning System Designed to Predict Severe Sepsis and Septic Shock.

OBJECTIVE: To assess clinician perceptions of a machine learning-based early warning system to predict severe sepsis and septic shock (Early Warning System 2.0). DESIGN: Prospective observational study. SETTING: Tertiary teaching hospital in Philadelphia, PA. PATIENTS: Non-ICU admissions November-December 2016. INTERVENTIONS: During a 6-week study period conducted 5 months after Early Warning System 2.0 alert implementation, nurses and providers were surveyed twice about their perceptions of the alert's helpfulness and impact on care, first within 6 hours of the alert, and again 48 hours after the alert. MEASUREMENTS AND MAIN RESULTS: For the 362 alerts triggered, 180 nurses (50% response rate) and 107 providers (30% response rate) completed the first survey. Of these, 43 nurses (24% response rate) and 44 providers (41% response rate) completed the second survey. Few (24% nurses, 13% providers) identified new clinical findings after responding to the alert. Perceptions of the presence of sepsis at the time of alert were discrepant between nurses (13%) and providers (40%). The majority of clinicians reported no change in perception of the patient's risk for sepsis (55% nurses, 62% providers). A third of nurses (30%) but few providers (9%) reported the alert changed management. Almost half of nurses (42%) but less than a fifth of providers (16%) found the alert helpful at 6 hours. CONCLUSIONS: In general, clinical perceptions of Early Warning System 2.0 were poor. Nurses and providers differed in their perceptions of sepsis and alert benefits. These findings highlight the challenges of achieving acceptance of predictive and machine learning-based sepsis alerts.