Blood Pressure Measurement for Accurate Assessment of Patient Status in Emergency Medical Settings
Convertino VA. Blood pressure measurement for accurate assessment of patient status in emergency medical settings. Aviat Space Environ Med 2012; 83:614–9.
Obtaining blood pressure measurements with traditional sphygomanometry that are insensitive and nonspecific can fail to provide an accurate assessment of patient status, particularly in specific clinical scenarios of acute reduction in central blood volume such as hemorrhage or orthostatic testing. This paper provides a review of newly emerging monitoring technologies that are being developed and integrated to improve patient diagnosis by using collection and feature extraction in real time of arterial waveforms by machine-learning algorithms. With assessment of continuous, noninvasively measured arterial waveforms, machine-learning algorithms have been developed with the capability to predict cardiovascular collapse with >96% accuracy and a correlation of 0.89 between the time of predicted and actual cardiovascular collapse (e.g., shock, syncope) using a human model of progressive central hypovolemia. The resulting capability to obtain earlier predictions of imminent hemodynamic instability has significant implications for effective countermeasure applications by the aeromedical community. The ability to obtain real-time, continuous information about changes in features and patterns of arterial waveforms in addition to standard blood pressure provides for the first time the capability to assess the status of circulatory blood volume of the patient and can be used to diagnose progression toward development of syncope or overt shock, or guide fluid resuscitation.
Obtaining blood pressure measurements with traditional sphygomanometry that are insensitive and nonspecific can fail to provide an accurate assessment of patient status, particularly in specific clinical scenarios of acute reduction in central blood volume such as hemorrhage or orthostatic testing. This paper provides a review of newly emerging monitoring technologies that are being developed and integrated to improve patient diagnosis by using collection and feature extraction in real time of arterial waveforms by machine-learning algorithms. With assessment of continuous, noninvasively measured arterial waveforms, machine-learning algorithms have been developed with the capability to predict cardiovascular collapse with >96% accuracy and a correlation of 0.89 between the time of predicted and actual cardiovascular collapse (e.g., shock, syncope) using a human model of progressive central hypovolemia. The resulting capability to obtain earlier predictions of imminent hemodynamic instability has significant implications for effective countermeasure applications by the aeromedical community. The ability to obtain real-time, continuous information about changes in features and patterns of arterial waveforms in addition to standard blood pressure provides for the first time the capability to assess the status of circulatory blood volume of the patient and can be used to diagnose progression toward development of syncope or overt shock, or guide fluid resuscitation.
Keywords: central hypovolemia; lower body negative pressure; medical monitoring; shock monitor
Document Type: Technical Note
Publication date: 01 June 2012
- The peer-reviewed monthly journal, Aviation, Space, and Environmental Medicine (ASEM) provides contact with physicians, life scientists, bioengineers, and medical specialists working in both basic medical research and in its clinical applications. It is the most used and cited journal in its field. ASEM is distributed to more than 80 nations.
To access volumes 86 to present, please click here. - Information for Authors
- Submit a Paper
- Subscribe to this Title
- Membership Information
- Information for Advertisers
- Submit Articles
- Ingenta Connect is not responsible for the content or availability of external websites
- Access Key
- Free content
- Partial Free content
- New content
- Open access content
- Partial Open access content
- Subscribed content
- Partial Subscribed content
- Free trial content