Abstract 14086: A Hybrid Machine Learning Method for Instantaneous Classification of Left Ventricular Filling Pressure Using Femoral Waveforms

Alavi, Rashid; Liu, Jing; Ramos, Melissa; Hindoyan, Antreas; Matthews, Ray V.; Pahlevan, Niema M.

doi:10.1161/circ.144.suppl_1.14086

Cited by 4 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The non-dimensional ratio R s / R d of the two envelope constants is known as the envelope ratio ( ER ) [ 21 , 37 ]. The systolic IF parameters (ω 1 , φ 1 , R s ) are dominated by the dynamics of the coupled LV-arterial system, whereas the diastolic IF parameters (ω 2 , φ 2 , R d ) are dominated by the dynamics of just the arterial network [ 23 , 24 , 28 , 30 , 32 , 38 – 41 ]. Fig 1B illustrates details about the above-mentioned mathematical reformulation through a visualization of ω 1 , ω 2 , φ 1 , φ 2 , R s and R d during the systolic and diastolic phases.…”

Section: Methodsmentioning

confidence: 99%

Section: Plos Onementioning

confidence: 99%

See 1 more Smart Citation

A machine learning approach for computation of cardiovascular intrinsic frequencies

Alavi,

Wang,

Gorji

et al. 2023

PLoS ONE

Self Cite

View full text Add to dashboard Cite

Analysis of cardiovascular waveforms provides valuable clinical information about the state of health and disease. The intrinsic frequency (IF) method is a recently introduced framework that uses a single arterial pressure waveform to extract physiologically relevant information about the cardiovascular system. The clinical usefulness and physiological accuracy of the IF method have been well-established via several preclinical and clinical studies. However, the computational complexity of the current L2 optimization solver for IF calculations remains a bottleneck for practical deployment of the IF method in real-time settings. In this paper, we propose a machine learning (ML)-based methodology for determination of IF parameters from a single carotid waveform. We use a sequentially-reduced Feedforward Neural Network (FNN) model for mapping carotid waveforms to the output parameters of the IF method, thereby avoiding the non-convex L2 minimization problem arising from the conventional IF approach. Our methodology also includes procedures for data pre-processing, model training, and model evaluation. In our model development, we used both clinical and synthetic waveforms. Our clinical database is composed of carotid waveforms from two different sources: the Huntington Medical Research Institutes (HMRI) iPhone Heart Study and the Framingham Heart Study (FHS). In the HMRI and FHS clinical studies, various device platforms such as piezoelectric tonometry, optical tonometry (Vivio), and an iPhone camera were used to measure arterial waveforms. Our blind clinical test shows very strong correlations between IF parameters computed from the FNN-based method and those computed from the standard L2 optimization-based method (i.e., R≥0.93 and P-value ≤0.005 for each IF parameter). Our results also demonstrate that the performance of the FNN-based IF model introduced in this work is independent of measurement apparatus and of device sampling rate.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Plos Onementioning

confidence: 99%

A machine learning approach for computation of cardiovascular intrinsic frequencies

Alavi,

Wang,

Gorji

et al. 2023

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

Instantaneous detection of acute myocardial infarction and ischaemia from a single carotid pressure waveform in rats

Alavi,

Dai,

Matthews

et al. 2023

European Heart Journal Open

Self Cite

View full text Add to dashboard Cite

Background Myocardial infarction (MI) is one of the leading causes of death worldwide. It is well-accepted that early diagnosis followed by early reperfusion therapy significantly increases the MI survival. Diagnosis of acute MI is traditionally based on the presence of chest pain and ECG criteria. However, around 50% of the MIs are without chest pain, and ECG is neither completely specific nor definitive. Therefore, there is an unmet need for methods that allow detection of acute MI or ischemia without using ECG. Our hypothesis is that a hybrid physics-based machine learning (ML) method can detect occurrence of acute MI or ischemia from a single carotid pressure waveform. Methods We used a standard occlusion/reperfusion rat model. Physics-based ML classifiers were developed using intrinsic frequency (IF) parameters extracted from carotid pressure waveforms. ML models were trained, validated, and generalized using data from 32 rats. The final ML models were tested on an external stratified blind dataset from additional 13 rats. Results When tested on blind data, the best ML model showed specificity = 0.92 and sensitivity = 0.92 for detecting acute MI. The best model’s specificity and sensitivity for ischemia detection were 0.85 and 0.92, respectively. Conclusions We demonstrated that a hybrid physics-based machine learning approach can detect occurrence of acute myocardial infarction and ischemia from carotid pressure waveform in rats. Since carotid pressure waveforms can be measured noninvasively, this proof-of-concept preclinical study can potentially be expanded in future studies for noninvasive detection of MI or myocardial ischemia.

show abstract

Adverse Cardiovascular Effects of Nicotine Delivered by Chronic Electronic Cigarettes or Standard Cigarettes Captured by Cardiovascular Intrinsic Frequencies

Alavi,

Dai,

Mazandarani

et al. 2024

JAHA

View full text Add to dashboard Cite

Background Electronic cigarettes have gained popularity as a nicotine delivery system, which has been recommended by some as an aid to help people quit traditional smoking. The potential long‐term effects of vaping on the cardiovascular system, as well as how their effects compare with those from standard cigarettes, are not well understood. The intrinsic frequency (IF) method is a systems approach for analysis of left ventricle and arterial function. Recent clinical studies have demonstrated the diagnostic and prognostic value of IF. Here, we aim to determine whether the novel IF metrics derived from carotid pressure waveforms can detect effects of nicotine (delivered by chronic exposure to electronic cigarette vapor or traditional cigarette smoke) on the cardiovascular system. Methods and Results One hundred seventeen healthy adult male and female rats were exposed to purified air (control), electronic cigarette vapor without nicotine, electronic cigarette vapor with nicotine, and traditional nicotine‐rich cigarette smoke, after which hemodynamics were comprehensively evaluated. IF metrics were computed from invasive carotid pressure waveforms. Standard cigarettes significantly increased the first IF (indicating left ventricle contractile dysfunction). Electronic cigarettes with nicotine significantly reduced the second IF (indicating adverse effects on vascular function). No significant difference was seen in the IF metrics between controls and electronic cigarettes without nicotine. Exposure to electronic cigarettes with nicotine significantly increased the total IF variation (suggesting adverse effects on left ventricle‐arterial coupling and its optimal state), when compared with electronic cigarettes without nicotine. Conclusions Our IF results suggest that nicotine‐containing electronic cigarettes adversely affect vascular function and left ventricle‐arterial coupling, whereas standard cigarettes have an adverse effect on left ventricle function.

show abstract

Abstract 14086: A Hybrid Machine Learning Method for Instantaneous Classification of Left Ventricular Filling Pressure Using Femoral Waveforms

Cited by 4 publications

References 0 publications

A machine learning approach for computation of cardiovascular intrinsic frequencies

A machine learning approach for computation of cardiovascular intrinsic frequencies

Instantaneous detection of acute myocardial infarction and ischaemia from a single carotid pressure waveform in rats

Adverse Cardiovascular Effects of Nicotine Delivered by Chronic Electronic Cigarettes or Standard Cigarettes Captured by Cardiovascular Intrinsic Frequencies

Contact Info

Product

Resources

About