Use of deep artificial neural networks to identify stroke during triage via subtle changes in circulating cell counts

Grant C O'Connell; Kyle B Walsh; Christine G Smothers; Suebsarn Ruksakulpiwat; Bethany L Armentrout; Chris Winkelman; Truman J Milling; Steven J Warach; Taura L Barr

doi:10.1186/s12883-022-02726-x

Use of deep artificial neural networks to identify stroke during triage via subtle changes in circulating cell counts

BMC Neurol. 2022 Jun 3;22(1):206. doi: 10.1186/s12883-022-02726-x.

Authors

Grant C O'Connell^{1

2}, Kyle B Walsh^{3

4}, Christine G Smothers⁵, Suebsarn Ruksakulpiwat⁵, Bethany L Armentrout⁵, Chris Winkelman⁵, Truman J Milling⁶, Steven J Warach⁶, Taura L Barr^{7

8}

Affiliations

¹ School of Nursing, Case Western Reserve University, 10900 Euclid Avenue, Cleveland, OH, 44106-4904, USA. grant.oconnell@case.edu.
² Molecular Biomarker Core, Case Western Reserve University, Cleveland, OH, USA. grant.oconnell@case.edu.
³ Department of Emergency Medicine, College of Medicine, University of Cincinnati, Cincinnati, OH, USA.
⁴ Gardner Neuroscience Institute, University of Cincinnati, Cincinnati, OH, USA.
⁵ School of Nursing, Case Western Reserve University, 10900 Euclid Avenue, Cleveland, OH, 44106-4904, USA.
⁶ Dell Seton Medical Center, University of Texas, Austin, TX, USA.
⁷ School of Nursing, Ohio State University, Columbus, OH, USA.
⁸ Valtari Bio Incorporated, Morgantown, WV, USA.

Abstract

Background: The development of tools that could help emergency department clinicians recognize stroke during triage could reduce treatment delays and improve patient outcomes. Growing evidence suggests that stroke is associated with several changes in circulating cell counts. The aim of this study was to determine whether machine-learning can be used to identify stroke in the emergency department using data available from a routine complete blood count with differential.

Methods: Red blood cell, platelet, neutrophil, lymphocyte, monocyte, eosinophil, and basophil counts were assessed in admission blood samples collected from 160 stroke patients and 116 stroke mimics recruited from three geographically distinct clinical sites, and an ensemble artificial neural network model was developed and tested for its ability to discriminate between groups.

Results: Several modest but statistically significant differences were observed in cell counts between stroke patients and stroke mimics. The counts of no single cell population alone were adequate to discriminate between groups with high levels of accuracy; however, combined classification using the neural network model resulted in a dramatic and statistically significant improvement in diagnostic performance according to receiver-operating characteristic analysis. Furthermore, the neural network model displayed superior performance as a triage decision making tool compared to symptom-based tools such as the Cincinnati Prehospital Stroke Scale (CPSS) and the National Institutes of Health Stroke Scale (NIHSS) when assessed using decision curve analysis.

Conclusions: Our results suggest that algorithmic analysis of commonly collected hematology data using machine-learning could potentially be used to help emergency department clinicians make better-informed triage decisions in situations where advanced imaging techniques or neurological expertise are not immediately available, or even to electronically flag patients in which stroke should be considered as a diagnosis as part of an automated stroke alert system.

Keywords: Decision support; Digital health; Emergency medicine; Immune system; Machine-learning; NLR; Stroke; Stroke scales; Triage; WBC.

MeSH terms

Cell Count
Emergency Service, Hospital
Humans
Neural Networks, Computer
Stroke* / diagnosis
Triage* / methods