Detection of Hemodynamic Status using an Analytic Based on an ECG Lead Waveform
Download as PPTX, PDF0 likes74 views
The document discusses a newly developed heart-rate variability analytic (AHI) aimed at non-invasive monitoring of hemodynamic instability through ECG lead waveform analysis. It reports high sensitivity (96.9%) and good specificity (79.0%) for detecting hypotension and tachycardia, suggesting its effectiveness as a decision support tool in clinical settings. Limitations include reliance on intermittent vital signs and the potential for alarm fatigue if used as an alert system.
Detection of Hemodynamic Status using an Analytic Based on an ECG Lead Waveform
- 1. Detection of hemodynamic status using an analytic based on an ECG lead waveform Florian F. Schmitzberger, MD, MS; Ashley E. Hall, MD; Morgan E. Hughes, RN BSN; Ashwin Belle, PhD; Bryce Benson, PhD, Kevin R. Ward, MD; Benjamin S. Bassin, MD
- 2. Background
- 3. Patient monitoring Invasive VS non-invasive Hemodynamic instability hard to assess Significant limitations
- 4. • Loss of heart rate variability (HRV) reflects the declining health of the autonomic nervous system and has been used to reflect the state of the cardiovascular system in acute illness and injury • Challenging in regard to: signal acquisition, sampling rates, signal noise and processing of EKG data • We studied a newly developed heart-rate variability analytic to assess if continuous HRV monitoring can accurately detect the combination of hypotension and tachycardia as a proxy for hemodynamic instability without the need for invasive arterial BP measurement Clinical decision support systems
- 5. Methods
- 6. • FDA approved • Produced by FifthEye, Inc. • Continuous measurement of EKG lead II • Automated analytical steps extract patterns from the continuous ECG data • Includes signal quality assessment and processing the extracted patterns through a pre-trained classification model • Updated every two minutes AHI - Analytic for Hemodynamic Instability
- 8. Two standards of hemodynamic instability 1) Hypotension (MAP < 70 or SBP < 90) + tachycardia (HR > 100) 2) Shock index > 1.0 EC3 and ICU patients with EKG data were included from November 2019 to February 2020 Compare AHI output to 5 minute intervals of EKG data to continuously measured BP and HR. Evaluation
- 9. • Also: subgroups of patients with or without vasopressors/inotropes and patients with or without beta blockers using only the vital signs based reference standard
- 10. Results
- 12. AHI’s observed sensitivity was 96.9% and the observed specificity was 79.0% with an AUC of 0.90. For the shock index analysis, AHI’s observed sensitivity was 72.0% and the observed specificity was 80.3% with an AUC of 0.81. Subgroup analysis for patients receiving beta blockers and vasopressors/inotropes showed very similar performance of sensitivity, specificity etc. Results
- 13. Discussion
- 14. Systems in use: Modified Early Warning Score (MEWS), National Early Warning Score (NEWS), electronic Cardiac Arrest Risk Triage (eCART), Predicting Intensive Care Transfers and Other Unforeseen Events (PICTURE) and other scores that utilize intermittent vital signs and other data to assess risks for cardiac arrest, ICU transfer, or death Limitations: intermittent data measurements (vitals signs) Early warning systems
- 15. Ideal use: detect clinical deterioration early, take appropriate action AHI is meant as adjunct data, not as an alarm system, good specificity but use as an alarm system would likely increase alarm fatigue (15.1% type I errors). Usage scenarios
- 16. • Retrospective analysis at a single academic healthcare center • Hard cutoffs for vital signs were used As a noninvasive monitoring technology, the system may over advantages in the continuous surveillance of patients and their hemodynamic status Limitations and Conclusion
- 17. Thank you Florian F. Schmitzberger, MD, MS; Ashley E. Hall, MD; Morgan E. Hughes, RN BSN; Ashwin Belle, PhD; Bryce Benson, PhD, Kevin R. Ward, MD; Benjamin S. Bassin, MD fschmitz@med.umich.edu