Methods and apparatus disclosed herein use a filtering technique to improve the accuracy of the results achieved when processing data provided by a physiological sensor. The disclosed filtering technique corrects many of the accuracy problems associated with physiological sensors, particularly PPG sensors. Broadly, the filtering technique adjusts a current filtered estimate of a physiological metric as a function of a rate limit based on a comparison between an instantaneous estimate of the physiological metric and the current filtered estimate.

The automated determination of an individual function of a DPOAE level map with p.sub.dp,I=f(L.sub.1, L.sub.2) of human or animal hearing. The method may include reading into a main memory a model function with model parameters of a DPOAE level map, based upon a number of N DPOAE measurements of a stimulation frequency pair with respectively different level pairs in a population (p) of a population of normally hearing subjects, automatically presenting n different level pairs of a stimulation frequency pair via tone output means to an individual and detecting the corresponding DPOAE's of the individual via tone recording means, wherein at least the first level pair is predefined, iteratively adapting the model function to the measured n DPOAE's until an individual function is obtained with individual parameters of a DPOAE level map of the individual, outputting the individual function and/or its individual parameters.

A smart glass including photoplethysmography and electrocardiogram sensors to determine a health condition of the user is provided. The smart glass includes a frame for holding two eyepieces, the frame having two nose pads to rest on a user's nose, and two arms to rest on two user's ears, a sensor mounted on at least one of the nose pads or the arms, and configured to collect an optical signal from a user's blood vessel, and a processor configured to obtain a waveform from the optical signal or the electrical signal, and to determine a cardiovascular parameter based on the waveform.

The invention pertains to the establishment, implementation and management of a personalized information system pertinent to a user's general health, wellness and/or sport performance. Disclosed is a system capable of transcutaneous measurement of a subject including at least one light source, at least one light detector, and at least one component for generating or storing at least one value of VC02 or at least one value of V02 from the detected signal. Further, disclosed is a portable device for analyzing the composition of the respired gasses of a subject including at least one air flow conduit through which the subject can inspire or expire air through the body of the device, at least one sampling portal, an oxygen sensor, and at least one flow sensor. A dual-battery system is also provided by which an uninterrupted power supply can be provided for electronic components.

The abnormal data processing system is provided with: a storage unit for holding a multiple-subject DB in which data on multiple subjects are accumulated and individual-subject DB in which data on individual subjects are accumulated; an individual-subject DB divergence-degree calculation unit for calculating an individual-subject DB divergence degree which is the degree of divergence of the new data from the individual-subject DB; a multiple-subject DB divergence degree calculation unit for calculating a multiple-subject DB divergence degree which is the degree of divergence of the new data from the multiple-subject DB; and a composite divergence degree calculation unit for determining a composite divergence by compositing the individual-subject DB divergence degree and the multiple-subject DB divergence degree using the number of data instances in the individual-subject DB. The abnormal data processing system determines whether or not the new data is abnormal on the basis of the composite divergence degree.

A blood pressure measurement apparatus includes circuitry configured to: detect a pulse of a subject, and obtain a photoplethysmography signal; and obtain estimated blood pressure of the subject based on the photoplethysmography signal. The circuitry receives parameter information, generates time information based on the photoplethysmography signal, applies a blood pressure estimation equation to the time information and the parameter information to calculate the estimated blood pressure, receives basic blood pressure information for the subject and the time information, and performs learning processing of applying a learning operational equation to statistical time information, which is obtained by performing statistical processing on the time information, and the basic blood pressure information to update the parameter information.

Techniques are described herein for converting time series data such as electrocardiogram (“ECG”) data into forms suitable for application across machine learning models, and for applying those converted data as input across machine learning models to, for instance, determine health conditions of underlying subjects. In various embodiments, a two-dimensional image may be generated (601) based on vectorcardiography (“VCG”) data, wherein the VCG data is measured directly or is based on electrocardiogram (“ECG”) data measured from a subject. The two-dimensional image may be applied (612) as input across a machine learning model to generate output, wherein the machine learning model is configured for use in processing two-dimensional images. A health condition of the subject may be determined (614) based on the output.

An apparatus and method for non-invasively determining the blood oxygen saturation within a subject's tissue by near-infrared spectroscopy is disclosed. Embodiments of the apparatus and method use the multi-distance method and take into account the attenuation of the light signal due to light absorbers other than hemoglobin and deoxyhemoglobin and the scattering properties of a subject's tissue.

A system and method for evaluating blood flow in a vessel of a patient includes a catheter containing a first pressure sensor and a second pressure sensor and configured to simultaneously measure pressure data within a vessel on either side of a stenosis. Pressure data generated by the catheter includes a first series of pressure measurements from the first pressure sensor a second series of pressure measurements from the second pressure sensor. The system and method further includes a fractional flow reserve (FFR) calculation module executable on one or more processors and configured to calculate a stability index for each of two or more portions of the pressure data, wherein each stability index indicates at least one of heart rate stability and catheter stability for the respective portion of the pressure data. An optimal time window is identified based on the stability indexes for calculation of FFR based on the pressure data. A FFR value is then calculated based on the pressure data in the optimal time window.

Light is irradiated to a finger of a subject and received from the finger of the subject to extract a pulse wave signal, generates an optimized pulse wave signal in a desired type by sampling the extracted pulse wave signal according to a predetermined sampling condition and normalizes the generated pulse wave signal, the entire segment of the normalized pulse signal is divided into a plurality of window segments to detect a pulse wave amplitude value with respect to a pulse wave signal for each window, a first eigenvector for each subject corresponding to a pulse wave amplitude value of the entire window segment is extracted by using a linear discriminant analysis and then the first eigenvector per subject is compared with a threshold, determines distribution of eigenvectors for each subject compared to the threshold and thus a characteristic of the corresponding subject is diagnosed.