Aim: The aim was to validate the Systolic Time Intervals (STI) measured by Ballistocardiography (BCG) with STI derived from simultaneously performed Transthoracic Echocardiogram (TTE) and attempt to create an AI algorithm that automatically calculates Tei Index from BCG tracings.
Study design: Cross-sectional study.
Place and Duration of Study: Department of Cardiology and Department of Electrophysiology of Sri Jayadeva Institute of Cardiovascular Sciences & Research, Bangalore, India, between January 2020 and January 2021.
Methodology: Two hundred seventy-four patients with clinically indicated TTE were enrolled in the study, average age was 52. Simultaneous recordings on BCG and TTE were done. 150 patients had clinically usable TTE images for accurate calculations. STI was calculated independently by operators experienced in TTE and BCG. Results were compared using Pearson’s R. A proprietary AI algorithm for automatically calculating the MPI, was trained over a subset of patients. Its accuracy in detecting STI was compared to that of TTE and manually calculated STI from BCG.
Results: There was a strong positive correlation (r=0.766, P<0.00, 99%CI [0.691,0.824]) between the TTE and BCG derived MPI values. The result was validated over predetermined subgroups of subjects with reduced EF (EF<50) and subjects with normal EF (EF>=50). The AI algorithm had correlation of 0.54(p<0.01) with the MPI calculated by TTE and 0.34(P<0.10) with the manually calculated MPI on the BCG.
Conclusion: BCG derived manual and automated MPI correlates well with TTE derived MPI in a variety of EF fraction subgroups. Automated calculation algorithms for MPI derived from BCG remain a work under progress.
Heart failure is a major cause of morbidity and mortality. Studies have shown that patients with heart failure may have gone through a phase of asymptomatic left ventricular (LV) dysfunction, where objective LV measurements reveal abnormalities in cardiac contractility, but signs and symptoms of overt heart failure are not present.  Also, serial assessment of LV function is important post-myocardial infarction, in individuals receiving chemotherapy with cardiotoxic drugs, dilated cardiomyopathy and infiltrative cardiomyopathies like amyloidosis, sarcoidosis. The most commonly used modalities currently for assessment of LV function include echocardiography and cardiac magnetic resonance imaging (CMR). However, the utility of these modalities in the frequent serial assessment of LV function and large-scale screening to assess asymptomatic individuals with LV dysfunction is limited due to the technical requirements and costs involved.
Myocardial Performance Index (MPI or Tei Index) reflects combined measures of left ventricular systolic and diastolic functions. It is defined as the sum of isovolumic contraction and isovolumic relaxation time divided by ejection time. [2–6] MPI has been used for the overall estimation of the LV function under a variety of diseased conditions, such as dilated cardiomyopathy, amyloidosis, coronary artery disease, heart transplantation, heart failure, as well as in prospective studies of the general population [7-16]. However, a number of studies have cast doubt on its value because of multiple reasons like poor clinical agreement with other metrics, normal values in cases of heart failure with preserved ejection fraction, low diagnostic accuracy in subjects with heart failure and left-ventricular diastolic dysfunction and that a single value of the index fails to diagnose the actual cause.[17–19]
Currently, MPI is measured as an instantaneous value during a TTE whilst the patient is at rest. Continuous MPI values have not been reported owing to technological challenges such as unavailability of an ambulatory device to conduct cardiovascular ultrasound, the high cost of the present systems and the complexity involved in operating them that limit the measurement of MPI within hospital settings. BCG is a technique that captures the body’s vibrations and recoil arising due to the cardiac expulsion of blood into the arteries and respiratory effort. [20–22] Waveforms obtained by BCG signal coincide with the specific events during the cardiac cycle. [23,24] BCG can therefore be used to calculate serial MPI values over a period of time and allow for its evaluation of these values in clinical scenarios.
We propose to validate the calculation of MPI derived from one such novel non-contact, non-invasive BCG recording device with the MPI calculated from a TTE simultaneously and attempt to create an algorithm that will automate the calculation of the MPI from the BCG tracings.