Alessio Tamborini

BACKGROUND: Left ventricular (LV) pressure measurement is the clinical gold standard for assessing cardiac function; however, its reliance on invasive catheterization limits accessibility and widespread use. OBJECTIVES: This study aimed to develop a cuff-based machine learning (cuff-ML) approach for reconstructing LV pressure from noninvasive brachial waveforms as a bedside assessment of cardiac function. METHODS: Subjects referred for nonemergent left heart catheterization were recruited for LV pressure and brachial cuff waveform measurement. The cuff-ML method was trained using brachial waveforms to predict LV pressure and was evaluated for morphology and parameters accuracy against invasive catheter measurements. Cardiac function was assessed based on the reduced LV peak pressure derivative ([+]dP/dt <1,200 mm Hg/s). RESULTS: A total of 104 subjects, comprising 3,572 simultaneous LV and cuff-based brachial waveform pairs, were analyzed using a 70:30 train-test split (test cohort: 32 subjects, 1,023 cardiac cycles). The cuff-ML approach demonstrated high accuracy in reconstructing LV waveform shape compared to catheter measurements (median normalized root mean squared error = 8.2%). Pressure-based parameters, including maximum pressure (r = 0.92, P < 0.001), mean blood pressure (r = 0.94, P < 0.001), and developed pressure (r = 0.85, P < 0.001), showed strong correlations with invasive measurements. Cuff-ML-reconstructed waveforms identified abnormal systolic contractility (72% sensitivity, 73% specificity) on a beat-to-beat basis. CONCLUSIONS: Cuff-ML accurately reconstructs LV pressure from brachial cuff measurements. This noninvasive approach may be helpful for assessment of cardiac function and requires further study.

Tactile sensing is central to how robotic systems interact with the real world, yet current solutions face a tradeoff between sensing area and system complexity. This work investigates metallic ultrasound waveguides as distributed tactile sensors fully interrogated from a single proximal transducer. Using cylindrical indenters, we characterized the acoustic response to single and multi-point contacts with varying forces and contact materials. For single point indentation, the applied force was well captured by a linear relationship with the ratio of the reflection to transmission coefficients (F = a * R/T) across all nine tested materials (R2 >= 0.95). The calibration slope, a, correlated strongly with the material’s effective contact modulus (log–log Pearson r=-0.98). The reflected energy partition was found to be a load-independent parameter related to the contacting material’s properties, enabling material classification independent of force. For the two-indenter experiment, both contact forces were recovered from the waveguide signal and were in close agreement with reference load cell measurements (contact 1, R2 = 0.97; contact 2, R2=0.95). The approach was extended to two-dimensional metallic sheets, confirming both contact localization and material-dependent effects. Overall, these results validate metallic waveguides as a robust platform for distributed tactile sensing, providing contact localization, force estimation, and material-class discrimination for the contacting body.

Arterial stiffness is a fundamental characteristic of circulatory physiology and a well-established predictor of cardiovascular risk and mortality. However, routine clinical assessment remains limited by the need for dual-site measurements. To address this challenge, we developed a machine learning algorithm – PulseAI – for automated fiducial point detection on brachial cuff waveforms for single-site assessment of arterial stiffness. PulseAI was trained and evaluated using a clinical dataset comprising 5,215 waveforms from 145 heterogeneous subjects. Performance was assessed on fiducial point predictions accuracy (inflection point, ti, and dicrotic notch, tn) and downstream pulse waveform analysis (PWA) metrics. Our multi-channel convolutional neural network (PulseAI) reported a median [IQR] on mean absolute error for fiducial point detection of 5 [3, 10] ms. PulseAI demonstrated high accuracy in predicting ti (r = 0.913, p < 0.0001) and tn (r = 0.939, p < 0.0001), with an average prediction error of 12.6 ms and 6.2 ms for ti and tn, respectively. While the tn results are comparable to other academic models reporting ∼10 ms errors, our approach provides both fiducial point indices from a single model. PWA features derived from PulseAI closely matched those derived from human-annotated labels, including systolic pressure–time integral (r = 0.988, p < 0.0001), augmentation index (AIx) (r = 0.990, p < 0.0001), and end systolic pressure (r = 0.998, p < 0.0001). AIx tertiles showed statistically significant association with height-adjusted pulse transit time (p < 0.05), used as a surrogate of arterial stiffness, demonstrating the model’s sensitivity to stiffness-related changes. These findings demonstrate that PulseAI enables accurate fiducial point detection and represents a clinically viable tool for automated, single-site monitoring of arterial stiffness.