System and method for blood pressure estimation

A method for estimating a subject's blood pressure comprising:

• receiving a subject's photoplethysmogram signal and anthropometric characteristics;
• determining a plurality of photoplethysmogram signal characteristic points based on the received photoplethysmogram signal;
• calculating a plurality of distances in both time and amplitude between any two of the photoplethysmogram signal characteristic points;
• calculating, based on the calculated distances and the anthropometric characteristics, the subject's systolic and diastolic blood pressure values using a machine-learning regression model;
• and
• calculating, based on the received systolic and diastolic blood pressure values and photoplethysmogram signal, the subject's continuous mean blood pressure values using a Hilbert-Huang transform and an empirical mode decomposition process.

A system comprising:

• a feature extraction module;
• a blood pressure calculation module;
• and
• a controller comprising a memory and at least one processor, wherein the memory is configured to store instructions and wherein the at least one processor is configured to execute the instructions so as to carry out operations, the operations comprising:
• receiving, via the feature extraction module, a subject's photoplethysmogram signal;
• determining a plurality of photoplethysmogram signal characteristic points based on the received photoplethysmogram signal;
• calculating a plurality of distances in both time and amplitude between any two of the detected photoplethysmogram signal characteristic points;
• providing a feature information signal comprising information about the calculated distances;
• receiving, via the blood pressure calculation module, the photoplethysmogram signal, the feature information signal, and anthropometric characteristics of the subject;
• calculating systolic and diastolic blood pressure values of the subject based on the received feature information signal, anthropometric characteristics, and a machine- learning regression model for calculating the systolic and diastolic blood pressure values;
• and
• calculating continuous mean blood pressure values of the subject based on the calculated systolic and diastolic blood pressure values, the photoplethysmogram signal, a Hilbert-Huang transform, and an empirical mode decomposition process for calculating the continuous mean blood pressure values.