Abstract: Described herein are techniques for performing a task using a trained external machine learning model. In some embodiments, a user request comprising a task and one or more protected health information (PHI) parameters associated with a patient may be received. Using one or more trained machine learning models, the PHI parameters may be extracted and a revised user request may be generated by replacing the PHI parameters with one or more synthetic PHI parameters. The revised user request may be provided to the trained external machine learning model and a response to the task comprising the synthetic PHI parameters may be received. The trained machine learning models may generate a revised response to the task by replacing the synthetic PHI parameters with the PHI parameters of the user request.

Abstract: A wearable member may include a plurality of energy transmitters that are arranged on a surface of the wearable member, each of the energy transmitters being configured to project energy into tissue of a user. A wearable member may include a plurality of energy receivers each of which is configured to generate a signal based on a received portion of the energy that is projected by one or more of the energy transmitters and reflected by the tissue of the user, wherein at least one of the energy transmitters and the energy receivers are multi-dimensionally arranged on the wearable member such that energy reflected by the tissue of the user at locations that are multi-dimensionally different is incident on the plurality of energy receivers. The processor may be configured to calculate a biological metric based on signals generated by at least part of the plurality of energy receivers.

Abstract: Described herein are techniques for performing a task using a trained external machine learning model. In some embodiments, a user request comprising a task and one or more protected health information (PHI) parameters associated with a patient may be received. Using one or more trained machine learning models, the PHI parameters may be extracted and a revised user request may be generated by replacing the PHI parameters with one or more synthetic PHI parameters. The revised user request may be provided to the trained external machine learning model and a response to the task comprising the synthetic PHI parameters may be received. The trained machine learning models may generate a revised response to the task by replacing the synthetic PHI parameters with the PHI parameters of the user request.

Abstract: Systems and methods for determining if a wearable photoplethysmography device is correctly positioned in operating to medical signs of a user by using a classifier to determine if a signal is valid or invalid. In some embodiments, in using the classifier to determine in a signal is valid or invalid, a lean method of linear computational complexity and minimal memory complexity is provided for determining at the wearable photoplethysmography device if it is correctly positioned. In some embodiments, in using the classifier minimal computational complexity is used in determining at the wearable photoplethysmography device if it is correctly positioned.

Abstract: Systems and methods for non-invasive blood pressure measurement are disclosed. In some embodiments, a system comprises a wearable member configured to generate first and second signals (e.g., PPG signals), and a blood pressure calculation system. The blood pressure calculation system includes a wave selection module configured to identify subsets of waves of the signals, a feature extraction module configured to generate sets of feature vectors form the subsets of waves, and a blood pressure processing module configured to calculate an arterial blood pressure value based on the sets of feature vectors and an empirical blood pressure calculation model, the empirical blood pressure calculation model configured to receive the sets of feature vectors as input values. The blood pressure calculation system further includes a communication module configured to provide a message including or being based on the arterial blood pressure value.

Abstract: Systems and methods for non-invasive blood pressure measurement are disclosed. In some embodiments, a system comprises a wearable member configured to generate first and second signals, and a blood pressure calculation system. The blood pressure calculation system a pre-processing module configured to filter noise from the signals, and a wave selection module configured to identify subsets of waves of the signals, a feature extraction module configured to generate sets of feature vectors form the subsets of waves, and a blood pressure processing module configured to calculate an arterial blood pressure value based on the sets of feature vectors and an empirical blood pressure calculation model, the empirical blood pressure calculation model configured to receive the sets of feature vectors as input values. The blood pressure calculation system further includes a communication module configured to provide a message including or being based on the arterial blood pressure value.

Abstract: Systems and methods for determining if a wearable photoplethysmography device is correctly positioned in operating to medical signs of a user by using a classifier to determine if a signal is valid or invalid. In some embodiments, in using the classifier to determine in a signal is valid or invalid, a lean method of linear computational complexity and minimal memory complexity is provided for determining at the wearable photoplethysmography device if it is correctly positioned. In some embodiments, in using the classifier minimal computational complexity is used in determining at the wearable photoplethysmography device if it is correctly positioned.

Abstract: Systems and methods for non-invasive blood pressure measurement are disclosed. In some embodiments, a system comprises a wearable member configured to generate first and second signals, and a blood pressure calculation system. The blood pressure calculation system a pre-processing module configured to filter noise from the signals, and a wave selection module configured to identify subsets of waves of the signals, a feature extraction module configured to generate sets of feature vectors form the subsets of waves, and a blood pressure processing module configured to calculate an arterial blood pressure value based on the sets of feature vectors and an empirical blood pressure calculation model, the empirical blood pressure calculation model configured to receive the sets of feature vectors as input values. The blood pressure calculation system further includes a communication module configured to provide a message including or being based on the arterial blood pressure value.

Abstract: Systems and methods for non-invasive blood pressure measurement are disclosed. In some embodiments, a system comprises a wearable member configured to generate first and second signals, and a blood pressure calculation system. The blood pressure calculation system a pre-processing module configured to filter noise from the signals, and a wave selection module configured to identify subsets of waves of the signals, a feature extraction module configured to generate sets of feature vectors form the subsets of waves, and a blood pressure processing module configured to calculate an arterial blood pressure value based on the sets of feature vectors and an empirical blood pressure calculation model, the empirical blood pressure calculation model configured to receive the sets of feature vectors as input values. The blood pressure calculation system further includes a communication module configured to provide a message including or being based on the arterial blood pressure value.

Abstract: A wearable member may include a plurality of energy transmitters that are arranged on a surface of the wearable member, each of the energy transmitters being configured to project energy into tissue of a user. A wearable member may include a plurality of energy receivers each of which is configured to generate a signal based on a received portion of the energy that is projected by one or more of the energy transmitters and reflected by the tissue of the user, wherein at least one of the energy transmitters and the energy receivers are multi-dimensionally arranged on the wearable member such that energy reflected by the tissue of the user at locations that are multi-dimensionally different is incident on the plurality of energy receivers. The processor may be configured to calculate a biological metric based on signals generated by at least part of the plurality of energy receivers.

Abstract: A system includes a wearable member configured to receive first energy, generate first signals, select a first subset of the time series data, determine a standard deviation indicating a quality at a low percentile of values associated with first windows of the time series data and a high percentile of values associated with the first windows of the time series data, the signal assessment threshold being including at least the values of the lower percentile, receive second energy, generate second signals containing second time series data from the second energy, select a second subset of the time series data to assess, compare all or part of the second signals to the signal assessment threshold, and if all or part of the second signals include the second time series data that is within the values of the lower percentile, then remove the second signals from further processing.

Abstract: Systems and methods for non-invasive blood pressure measurement are disclosed. In some embodiments, a system comprises a wearable member configured to generate first and second signals (e.g., PPG signals), and a blood pressure calculation system. The blood pressure calculation system includes a wave selection module configured to identify subsets of waves of the signals, a feature extraction module configured to generate sets of feature vectors form the subsets of waves, and a blood pressure processing module configured to calculate an arterial blood pressure value based on the sets of feature vectors and an empirical blood pressure calculation model, the empirical blood pressure calculation model configured to receive the sets of feature vectors as input values. The blood pressure calculation system further includes a communication module configured to provide a message including or being based on the arterial blood pressure value.

Abstract: Systems and methods for determining if a wearable photoplethysmography device is correctly positioned in operating to medical signs of a user by using a classifier to determine if a signal is valid or invalid. In some embodiments, in using the classifier to determine in a signal is valid or invalid, a lean method of linear computational complexity and minimal memory complexity is provided for determining at the wearable photoplethysmography device if it is correctly positioned. In some embodiments, in using the classifier minimal computational complexity is used in determining at the wearable photoplethysmography device if it is correctly positioned.

Abstract: In some embodiments, a system comprises a wearable member configured to receive first energy, generate first signals, select a first subset of the time series data, determine a standard deviation indicating a quality at a low percentile of values associated with first windows of the time series data and a high percentile of values associated with the first windows of the time series data, the signal assessment threshold being including at least the values of the lower percentile, receive second energy, generate second signals containing second time series data from the second energy, select a second subset of the time series data to assess, compare all or part of the second signals to the signal assessment threshold, and if all or part of the second signals include the second time series data that is within the values of the lower percentile, then remove the second signals from further processing.

Abstract: Systems and methods for determining if a wearable photoplethysmography device is correctly positioned in operating to medical signs of a user by using a classifier to determine if a signal is valid or invalid. In some embodiments, in using the classifier to determine in a signal is valid or invalid, a lean method of linear computational complexity and minimal memory complexity is provided for determining at the wearable photoplethysmography device if it is correctly positioned. In some embodiments, in using the classifier minimal computational complexity is used in determining at the wearable photoplethysmography device if it is correctly positioned.

Abstract: Systems and methods for non-invasive blood pressure measurement are disclosed. In some embodiments, a system comprises a wearable member configured to generate first and second signals (e.g., PPG signals), and a blood pressure calculation system. The blood pressure calculation system includes a wave selection module configured to identify subsets of waves of the signals, a feature extraction module configured to generate sets of feature vectors form the subsets of waves, and a blood pressure processing module configured to calculate an arterial blood pressure value based on the sets of feature vectors and an empirical blood pressure calculation model, the empirical blood pressure calculation model configured to receive the sets of feature vectors as input values. The blood pressure calculation system further includes a communication module configured to provide a message including or being based on the arterial blood pressure value.

Abstract: A wearable member may include a plurality of energy transmitters that are arranged on a surface of the wearable member, each of the energy transmitters being configured to project energy into tissue of a user. A wearable member may include a plurality of energy receivers each of which is configured to generate a signal based on a received portion of the energy that is projected by one or more of the energy transmitters and reflected by the tissue of the user, wherein at least one of the energy transmitters and the energy receivers are multi-dimensionally arranged on the wearable member such that energy reflected by the tissue of the user at locations that are multi-dimensionally different is incident on the plurality of energy receivers. The processor may be configured to calculate a biological metric based on signals generated by at least part of the plurality of energy receivers.

Abstract: Systems and methods for non-invasive blood pressure measurement are disclosed. In some embodiments, a system comprises a wearable member configured to generate first and second signals, and a blood pressure calculation system. The blood pressure calculation system a pre-processing module configured to filter noise from the signals, and a wave selection module configured to identify subsets of waves of the signals, a feature extraction module configured to generate sets of feature vectors form the subsets of waves, and a blood pressure processing module configured to calculate an arterial blood pressure value based on the sets of feature vectors and an empirical blood pressure calculation model, the empirical blood pressure calculation model configured to receive the sets of feature vectors as input values. The blood pressure calculation system further includes a communication module configured to provide a message including or being based on the arterial blood pressure value.

Abstract: A wearable member may include a plurality of energy transmitters that are arranged on a surface of the wearable member, each of the energy transmitters being configured to project energy into tissue of a user. A wearable member may include a plurality of energy receivers each of which is configured to generate a signal based on a received portion of the energy that is projected by one or more of the energy transmitters and reflected by the tissue of the user, wherein at least one of the energy transmitters and the energy receivers are multi-dimensionally arranged on the wearable member such that energy reflected by the tissue of the user at locations that are multi-dimensionally different is incident on the plurality of energy receivers. The processor may be configured to calculate a biological metric based on signals generated by at least part of the plurality of energy receivers.

Abstract: In some embodiments, a system comprises a wearable member configured to receive first energy, generate first signals, select a first subset of the time series data, determine a standard deviation indicating a quality at a low percentile of values associated with first windows of the time series data and a high percentile of values associated with the first windows of the time series data, the signal assessment threshold being including at least the values of the lower percentile, receive second energy, generate second signals containing second time series data from the second energy, select a second subset of the time series data to assess, compare all or part of the second signals to the signal assessment threshold, and if all or part of the second signals include the second time series data that is within the values of the lower percentile, then remove the second signals from further processing.