0.6) were obtained in the orthostatic position. Bland-Altman plots revealed that most values were inside the agreement limits, indicating concordance between measures. Only SDNN and NNv in the supine position were not reproducible. Our results showed reproducibility of HRV parameters when recorded in the same individual with a short time between two exams. The increased sympathetic activity occurring in the orthostatic position probably facilitates reproducibility of the HRV indexes.]]>

Introduction: Instantaneous, non-invasive detection of an elevated left ventricular end-diastolic pressure (LVEDP) offers a significant benefit in diagnosis and treatment of heart failure. We recently proposed a systems approach, called cardiac triangle mapping (CTM), that uses intrinsic frequencies (IFs) of the arterial waveform and pre-ejection period (PEP) to map the global ventricular function (Pahlevan et al. Fluids 4.1 (2019): 16). Here, we tested the hypothesis that an elevated LVEDP can be detected using ECG and arterial pressure waveform by applying an artificial neural network (ANN) combined with CTM approach. Methods: This study included 46 patients (12 females, age 39-90 (66.4±9.9), BMI 20.2-36.8 (27.6±4.1)) who were scheduled for a clinical left heart catheterization or coronary angiogram at the Keck Medical Center of USC. Exclusion criteria were valvular heart disease, atrial fibrillation, or left bundle branch block. Invasive LVEDP and aortic pressure waveforms were measured using a 3F Millar transducer tipped catheter with simultaneous 3 channel ECG. The IFs were computed from pressure waveforms. PEPs were calculated as the time difference between the beginning of QRS and the uprising of the pressure waveform. A 3-layer network consisted of 6 input, 6 hidden and one output nodes was developed. LVEDP=18 mmHg was used as the cut-off for a binary outcome. Data from 34 patients were used to design the ANN (27 for training, 7 for validation). The model was tested on 12 additional patients. Results: Our results showed a specificity of 87% and a sensitivity of 96% in detecting an elevated LVEDP (Fig.1). Conclusions: Here, we demonstrated the proof-of-concept that an AI model based on reduced-order parameters (extracted from arterial waveform and ECG) can instantaneously detect an elevated LVEDP. Although our hemodynamic measurements were done invasively, all variables that are required for this AI-LVEDP calculation can be collected noninvasively.

Introduction: Non-invasive and instantaneous evaluation of left ventricular end-diastolic pressure (LVEDP) is of high significance in diagnosis and treatment of heart failure patients. We recently proposed the cardiac triangle mapping (CTM), a systems approach that uses information from arterial pressure waveforms and pre-ejection periods to map the global ventricular function (Pahlevan et al. Fluids 4.1 (2019): 16). Here, we propose a hybrid machine learning (ML) method based on CTM theory that uses pressure waveforms at the iliac bifurcation level and ECG to instantaneously classify the level of LVEDP. Methods: We studied 46 patients (Age: 39-90 (66.4±9.9), BMI: 20.2-36.8 (27.6±4.1), 12 females) who were scheduled for clinical left heart catheterization or coronary angiogram at the Keck Medical Center of USC. Exclusion criteria were valvular heart disease, left bundle branch block, or atrial fibrillation. Invasive LVEDP and pressure waveforms at iliac bifurcation were measured using a 3F Millar transducer tipped catheter, with simultaneous 3 channel ECG. The range of patients’ LVEDP was from 9.3 to 40.5 mmHg. LVEDP=18 mmHg was used as the ML classification cut-off. A random forest classifier (of n=30 grown decision trees, ensemble learning method: bootstrap aggregation, 6 inputs) was trained using data from 36 patients. The model was blindly tested on 10 additional patients. Results: Our ML model showed accuracies of 100.0% and 80.0% for predicting the true class of LVEDP on blind test data (i.e., elevated or normal, respectively) (Fig1). The accuracy on all data was higher than 93.4% for all classes. Conclusions: We demonstrated the proof-of-concept that a physics-based ML model can instantaneously classify the LV filling pressure using information extracted from femoral waveform and ECG. Our study is invasive validation; however, all required ML input parameters can be obtained noninvasively and remotely (i.e., using wearable devices or a smartphone).