Study Shows Medical Device Software System Developed at U-M Could Provide Bridge to Surpass Limits of Traditional Vital Signs in Identifying Patient Deterioration
Image source: Fiftheye
The Analytic for Hemodynamic Instability (AHI) detected the various gold standard measures of hemodynamic deterioration with high sensitivity and specificity, paving the way for further study into AHI’s potential as a surrogate measure of clinical status in settings where continuous monitoring of vital signs would not be possible.
Contact:
Kate Murphy, Marketing Communications Specialist, Weil Institute
mukately@umich.edu
——
ANN ARBOR, MI – In a new study published in Critical Care Explorations, researchers at Michigan Medicine examined whether the Analytic for Hemodynamic Instability (AHI), an artificial-intelligence driven system that both detects and predicts hemodynamic instability, could not only mitigate the limits associated with standard vital sign measurements but also enable continuous assessment of real-time hemodynamic clinical status in patients who would otherwise have their vital signs monitored intermittently.
Delayed or missed recognition of patient deterioration remains a challenge in hospital care. To identify patients at risk of deteriorating, clinicians rely on abnormal vital signs indicating hemodynamic instability (low vital organ blood flow), such as an elevated heart rate (tachycardia) in combination with low blood pressure (hypotension). Monitoring these vital signs has its limitations, however, including limited accuracy in non-invasive compared to invasive monitoring and the potential for human error to occur when vitals are validated and entered into the electronic medical record. Furthermore, patients who are not at obvious risk of immediate deterioration will only have their vital signs monitored and recorded periodically—often with hours between measurements—which could potentially lead to delayed recognition of hemodynamic instability and deterioration events.
"Most vital signs measurements are static, subject to human error, and require validation and interpretation. AHI is the opposite of all of that."
Ben Bassin, MD
Associate Professor, Emergency Medicine
Director, Emergency Critical Care Center (EC3)
AHI is an FDA-cleared software as a medical device designed to address these limitations. Based on technologies developed and tested at the U-M Max Harry Weil Institute and licensed to Fifth Eye, Inc., AHI continuously detects changes in hemodynamic status in real-time using data from a single electrocardiogram (ECG) lead. It can then automatically and continuously predict the likelihood of future episodes of hemodynamic instability ahead of vital signs. The team’s goal with the study was to validate AHI against the measures clinicians would traditionally use (heart rate and blood pressure) and determine if it could indicate hemodynamic instability in real-time without requiring continuous direct measurement of blood pressure.
To test AHI’s performance, the team captured AHI outputs from a dataset of over 500 consecutive adult patients in Michigan Medicine’s emergency critical care center (EC3) and inpatient intensive care units who were undergoing continuous ECG and invasive arterial blood pressure monitoring. The team evaluated these outputs against a reference standard of hemodynamic instability—defined as tachycardia with hypotension—from the same patient cohort. AHI’s observed sensitivity and specificity in tachycardia with hypotension were 96.9% and 79% respectively, with an area under the curve of .90.
Based on these results, AHI appropriately detected the various gold-standard indications of hemodynamic instability, suggesting it may be able to provide continuous dynamic monitoring capabilities in patients who traditionally have intermittent static vital sign measurements.
“AHI performs extremely well, and it functions in a way that we think may have transformative clinical utility,” said Dr. Ben Bassin, Associate Professor of Emergency Medicine and an author on the study. “Most vital signs measurements are static, subject to human error, and require validation and interpretation. AHI is the opposite of all of that: it’s dynamic, gives a binary output of ‘stable’ or ‘unstable’, and may enable early martialing of resources to patients who may not have been on a clinician’s radar.”
Fellow study author Dr. Kevin Ward, executive director of the Weil Institute and a Professor of Emergency Medicine and Biomedical Engineering, spoke on the potential scalability of the AHI system. “The vision of AHI was born out of our continued inability to identify unstable patients and to predict when patients would become unstable, especially in settings where they cannot be intensively monitored. AHI is ideally suited to be utilized with wearable monitors such as ECG patches, making any hospital bed, waiting room or other setting into a sophisticated monitoring environment. The implication of such a technology is that it has the potential to save lives not only in the hospital but also at home, in the ambulance, and on the battlefield.”
While the team’s findings are promising, further study will be needed to determine if AHI provides clinical and resource allocation benefits in patients undergoing infrequent blood pressure monitoring. The next phase of research will focus on how AHI is being used at Michigan Medicine. The team will engage clinical end users to provide feedback on AHI’s functionality as well as how it is helping them provide increased vigilance in caring for the critically ill and injured.
“AHI is a truly novel analytic,” said Dr. Bassin. “It allows us to do what we couldn’t before.”
-----
The study referenced in this article was supported by Fifth Eye, Inc and the Max Harry Weil Institute for Critical Care Research and Innovation.
Kevin R. Ward, MD, is an inventor of the AHI technology, which is patented through the University of Michigan and licensed to Fifth Eye, Inc.
Paper Cited
“Detection of Hemodynamic Status Using an Analytic Based on an Electrocardiogram Lead Waveform,” Critical Care Explorations:
DOI: 10.1097/CCE.0000000000000693
About the Weil Institute, formerly MCIRCC
The team at the Max Harry Weil Institute for Critical Care Research and Innovation (formerly the Michigan Center for Integrative Research in Critical Care) is dedicated to pushing the leading edge of research to develop new technologies and novel therapies for the most critically ill and injured patients. Through a unique formula of innovation, integration and entrepreneurship that was first imagined by Weil, their multi-disciplinary teams of health providers, basic scientists, engineers, data scientists, commercialization coaches, donors and industry partners are taking a boundless approach to re-imagining every aspect of critical care medicine. For more information, visit weilinstitute.med.umich.edu.
About Fifth Eye Inc.
Fifth Eye Inc. is an Ann Arbor, Michigan-based company that develops intuitive, real-time clinical analytics based on physiologic waveforms to improve outcomes and reduce costs. Fifth Eye's machine-learning technology is licensed from the University of Michigan. The AHI System™ is FDA cleared, clinical decision support software that monitors hospital patients and continuously predicts the risk of hemodynamic instability earlier than is possible with vital signs. The AHI System requires only the information embedded in an ECG signal. For more information, please visit www.fiftheye.com.