Spectroscopic monitoring for the measurement of multiple physiological parameters
The present disclosure relates to devices, systems, methods and computer program products for continuously monitoring, diagnosing and providing treatment assistance to patients using sensor devices, location-sensitive and power-sensitive communication systems, analytical engines, and remote systems. The method of non-invasively measuring multiple physiological parameters in a patient includes collecting photoplethysmograph (PPG) signal data from a wearable sensor device, applying one or more filters to correct the signal data and extracting a plurality of features from the corrected data to determine values for blood glucose, blood pressure, SpO2, respiration rate, and pulse rate of the patient. An alert may be automatically sent to one or more computing devices when the value falls outside a custom computed threshold range for the patient. The method offers ease of usage, allows continuous real-time monitoring of the patient in any setting for timely intervention, and results in improved accuracy of the signal data.
1. A method, comprising:
mounting a wearable sensor device to a position on a specific subject, the wearable sensor device comprising a microcontroller, transceiver circuitry enabled to communicate wirelessly, an optical emitter, and an optical sensor;
determining a physiological signal from the subject by interaction of the optical emitter and the optical sensor;
transmitting the physiological signal wirelessly to a nearby computerized appliance enabled to connect to the Internet network;
connecting the computerized appliance to an Internet-connected server;
transmitting the physiological signal to the Internet-connected server along with identification of the specific subject;
extracting, by software executing on a processor of the Internet-connected server, a plurality of features from the physiological signal, the plurality of features comprising at least systolic duration, diastolic duration, systolic slope, diastolic slope, pulse duration, overall mean, and peak amplitude;
providing the plurality of features to a machine-learning module trained to predict values for blood glucose, blood pressure, SpO2, respiration rate, and pulse rate;
predicting values for blood glucose, blood pressure, SpO2, respiration rate, and pulse rate for the specific subject by the machine-learning module;
computing a threshold range for blood glucose, blood pressure, SpO2, respiration rate, and pulse rate by the machine-learning module, based on stored vales of age, gender and disease status of the specific subject;
and
issuing an alert by an alert module to one or more persons when and if a value for the physiological parameter for the specific subject is determined to be out of the threshold range.
2. The method of claim 1 wherein the nearby computerized appliance is a Smartphone, further comprising the smartphone connecting to the Internet-connected server and transmitting the physiological signal.
3. A system, comprising:
a wearable sensor device mounted to a position on a specific subject, the wearable sensor device comprising a microcontroller, transceiver circuitry enabled to communicate wirelessly, an optical emitter, and an optical sensor;
a nearby computerized appliance enabled to connect to the Internet network receiving wirelessly a physiological signal from the wearable sensor device, the physiological signal determined by interaction of the optical emitter and the optical sensor;
an Internet-connected server coupled to a memory unit storing historical data for the specific subject and executing software;
wherein the nearby computerized appliance receives the physiological signal from the wearable sensor device along with identification of the specific subject, connects to the Internet-connected server, and transmits the physiological signal to the Internet-connected server along with the identification of the specific subject, and wherein the Internet-connected server extracts a plurality of features from the physiological signal, the plurality of features comprising at least systolic duration, diastolic duration, systolic slope, diastolic slope, pulse duration, overall mean, and peak amplitude, provides the plurality of features to a machine-learning module trained to predict values for blood glucose, blood pressure, SpO2, respiration rate, and pulse rate, the machine-learning module computes a threshold range for blood glucose, blood pressure, SpO2, respiration rate, and pulse rate for the specific subject, based on stored values of age, gender and disease status of the specific subject, and issues an alert by an alert module to one or more persons when and if the value for the physiological parameter for the specific subject is determined to be outside the threshold range.
4. The system of claim 3 wherein the nearby computerized appliance is a Smartphone, comprising the smartphone connecting to the Internet-connected server and transmitting the physiological signal.