Electrocardiography (ECG) remains the primary clinical tool for evaluating heart function, but it has significant limitations when assessing heart failure. Ballistocardiography (BCG), which detects the slight physical movements the body experiences with each heart beat, has the potential to provide some of the information that ECG misses. The problem is that BCG is severely attenuated by each person’s unique mix of fat and muscle tissues. Although it has been studied for over a century, only now is technology getting to the point that we may be able to interpret BCG signals with confidence.
Researchers at Georgia Tech, University of California, San Francisco, and Northwestern University have joined together to develop a system that combines ECG and BCG together to better study the state of heart failure patients.
The team recorded and successfully processed signal data from 43 heart failure patients using a novel BCG scale, made by Tanita, along with a hand-held ECG from Omron. The patients took the devices home where they simply stood on the scale while holding the ECG, and in a matter of minutes the exam was complete. The data were analyzed remotely by the researchers.
Because the technology is fairly inexpensive and can be used within the patient’s own home, it has the potential to provide a way for cardiologists to monitor heart failure patients remotely. This should help reduce the frequency of dangerous events while reducing the stress and costs associated with frequent visits to the doctor.
“The ECG has characteristic waves that clinicians have understood for 100 years, and now, computers read it a lot of the time,” said Omer Inan, the study’s principal investigator. “Elements of the BCG signal aren’t really known well yet, and they haven’t been measured in patients with heart failure very much at all.”
From the study abstract in IEEE Transactions on Biomedical Engineering:
1) High quality BCG signals were collected at home from HF patients after discharge. 2) The BCG recordings were preprocessed to exclude outliers and artifacts. 3) Parameters of the BCG that contain information about the cardiovascular system were extracted. These features were used for the task of classification of the BCG recording based on the status of HF. Results: The best AUC score for the task of classification obtained was 0.78 using slight variant of the leave one subject out validation method. Conclusion: This work demonstrates that high quality BCG signals can be collected in a home environment and used to detect the clinical state of HF patients. Significance: In future work, a clinician/caregiver can be introduced to the system so that appropriate interventions can be performed based on the clinical state monitored at home.
Study in IEEE Transactions on Biomedical Engineering: Classification of Decompensated Heart Failure from Clinical and Home Ballistocardiography
Via: Georgia Tech