System and methods for real time noninvasive estimation of cardiovascular parameters using machine learning

A system configured to use non-invasively measurable physiologic data to estimate cardiovascular parameters of a patient that are non-invasively unobservable, the system comprising:

• a plurality of pulse sensors configured to be applied to the patient, outputs of which enable computation of pulse wave velocities;
• a cuff configured to measure values of systolic and diastolic blood pressures and heart rate;
• a console including a processor, a display, and non-volatile storage, wherein the non-volatile storage stores instructions that, when executed by the processor:
• receive the measured values of systolic and diastolic blood pressure and heart rate generated by the cuff,
• compute actual pulse wave velocities using the outputs of the plurality of pulse sensors;
• iteratively compute estimated values of systolic and diastolic blood pressure using an arterial tree model trained to simulate hemodynamics of an atrial tree including vascular distensibility characteristics and vascular resistance characteristics and compare the estimated values of systolic and diastolic blood pressure to the measured values of systolic and diastolic blood pressure until a difference between the estimated values of systolic and diastolic blood pressure and the measured values of systolic and diastolic blood pressure are less than a first threshold, the vascular distensibility characteristics and vascular resistance characteristics of the arterial tree model adjusted with each iterative computation of the estimated values of systolic and diastolic blood pressure;
• determine an estimator by iteratively computing estimated pulse wave velocities while adjusting one or more of the vascular distensibility characteristics and the vascular resistance characteristics until the difference between the estimated values of systolic and diastolic blood pressure and the measured values of systolic and diastolic blood pressure are less than the first threshold, and a difference between the estimated pulse wave velocities and the actual pulse wave velocities is less than a second threshold to thereby determine one or more of a vascular distensibility characteristic value and a vascular resistance characteristic value causing the difference between the estimated values of systolic and diastolic blood pressure and the measured values of systolic and diastolic blood pressure to be less than the first threshold and further causing the difference between the estimated pulse wave velocities and the actual pulse wave velocities to be less than the second threshold, the estimator comprising a two-layer optimization algorithm adapted to personalize the arterial tree model for the patient;
• and
• compute estimated values of cardiac output or aortic (central) systolic blood pressure using the estimator calibrated with the one or more of the vascular distensibility characteristic value and the vascular resistance characteristic value, and based on second measured values of systolic and diastolic blood pressure and second actual pulse wave velocities;
• and
• display the estimated values of cardiac output or aortic (central) systolic blood pressure on the console.