This disclosure provides a fetal-blood-oxygen-saturation estimation technique using a deep neural network without performing explicit fetal signal extraction from mixed maternal-fetal photoplethysmogram (PPG) signals. In one aspect, the disclosed fetal-blood-oxygen-saturation estimation technique receives multiple channels of PPG signals from two or more photodetectors detecting transabdominal diffused light from two or more light sources emitting two or more distinct wavelengths, wherein the photodetectors and light sources are positioned on a maternal abdomen. Note that each channel of the multiple channels of PPG signals includes mixed maternal-fetal PPG signals. Next, the disclosed estimation technique processes the received PPG signals using a trained deep neural network to directly estimate fetal-blood-oxygen-saturation by: tagging the PPG signals with a set of signal-quality levels; feeding the tagged PPG signals as inputs to the deep neural network; and directly inferring, by the deep neural network, fetal-blood-oxygen-saturation estimations and associated confidence levels based on the tagged PPG signals.

This disclosure provides a fetal-blood-oxygen-saturation estimation technique using a deep neural network without performing explicit fetal signal extraction from mixed maternal-fetal photoplethysmogram (PPG) signals. In one aspect, the disclosed fetal-blood-oxygen-saturation estimation technique receives multiple channels of PPG signals from two or more photodetectors detecting transabdominal diffused light from two or more light sources emitting two or more distinct wavelengths, wherein the photodetectors and light sources are positioned on a maternal abdomen. Note that each channel of the multiple channels of PPG signals includes mixed maternal-fetal PPG signals. Next, the disclosed estimation technique processes the received PPG signals using a trained deep neural network to directly estimate fetal-blood-oxygen-saturation by: tagging the PPG signals with a set of signal-quality levels; feeding the tagged PPG signals as inputs to the deep neural network; and directly inferring, by the deep neural network, fetal-blood-oxygen-saturation estimations and associated confidence levels based on the tagged PPG signals.

Systems, devices, and methods for performing trans-abdominal fetal oximetry and/or trans-abdominal fetal pulse oximetry using physiological characteristics and/or a calibration factor may receive a physiological characteristic of a pregnant mammal and determine one or more potential impact(s) of the physiological characteristic on a behavior of an optical signal projected into the abdomen of the pregnant mammal Then a calibration factor for the optical signal responsively to the impact. The calibration factor may then be used to calibrate a fetal detected electronic signal so that a level of fetal hemoglobin oxygen saturation may be determined.

Systems, devices, and methods for performing trans-abdominal fetal oximetry and/or trans-abdominal fetal pulse oximetry using physiological characteristics and/or a calibration factor may receive a physiological characteristic of a pregnant mammal and determine one or more potential impact(s) of the physiological characteristic on a behavior of an optical signal projected into the abdomen of the pregnant mammal Then a calibration factor for the optical signal responsively to the impact. The calibration factor may then be used to calibrate a fetal detected electronic signal so that a level of fetal hemoglobin oxygen saturation may be determined.

A plurality of sets of simulated optical inputs that is simulated to travel through an animal model of tissue, thereby generating simulated light transmission data, and corresponding oximetry vales may be used to train a simulated fetal oximetry model to predict, or calculate, oximetry values for subsequently received sets of simulated light transmission data. The simulated fetal oximetry model may be adapted to train an in vivo fetal oximetry model that may be configured to predict, or calculate, fetal oximetry values for subsequently received sets of light transmission data received from an in vivo study of a pregnant mammal and her fetus.

A plurality of sets of simulated optical inputs that is simulated to travel through an animal model of tissue, thereby generating simulated light transmission data, and corresponding oximetry vales may be used to train a simulated fetal oximetry model to predict, or calculate, oximetry values for subsequently received sets of simulated light transmission data. The simulated fetal oximetry model may be adapted to train an in vivo fetal oximetry model that may be configured to predict, or calculate, fetal oximetry values for subsequently received sets of light transmission data received from an in vivo study of a pregnant mammal and her fetus.

Transvaginal and/or transcervical fetal oximetry probes may be configured to take measurements in the endocervical canal of a pregnant mammal that may be used to determine a fetal hemoglobin oxygen saturation level using, for example, oximetry, pulse oximetry, and/or tissue oxygen saturation calculations. Transurethral fetal oximetry probes may be configured to be inserted into a urethra of a pregnant mammal and be positioned proximate to a wall of a bladder of the pregnant mammal proximate to the fetus. Once in position, the Transurethral fetal oximetry probe may take measurements that may be used to determine a fetal hemoglobin oxygen saturation level using, for example, oximetry, pulse oximetry, and/or tissue oxygen saturation calculations.

Transvaginal and/or transcervical fetal oximetry probes may be configured to take measurements in the endocervical canal of a pregnant mammal that may be used to determine a fetal hemoglobin oxygen saturation level using, for example, oximetry, pulse oximetry, and/or tissue oxygen saturation calculations. Transurethral fetal oximetry probes may be configured to be inserted into a urethra of a pregnant mammal and be positioned proximate to a wall of a bladder of the pregnant mammal proximate to the fetus. Once in position, the Transurethral fetal oximetry probe may take measurements that may be used to determine a fetal hemoglobin oxygen saturation level using, for example, oximetry, pulse oximetry, and/or tissue oxygen saturation calculations.

In one aspect, an apparatus for monitoring a physiological condition of a patient is disclosed. The apparatus includes a body having an attachment portion configured to be inserted into the skin of a patient to affix the body to the patient. The apparatus includes a sensor coupled to the body that is configured to generate sensor data corresponding to a physiological condition of the patient when the body is secured to the skin of the patient. The apparatus further includes a reference sensor that is remote from the sensor coupled to the body and is configured to engage an outer surface of skin to generate reference data against which the sensor data is compared.

Systems and methods are described, and one method includes determining a fetal blood oxygenation level, including: activating at least one light source with at least two distinct wavelengths of light on an abdomen of a pregnant mammal to direct light into a maternal abdomen toward a fetus; receiving a set of mixed signals from a set of photodetectors positioned at different locations on the maternal abdomen from reflected light that traverses maternal tissue or maternal tissue and fetal tissue; determining the fetal blood oxygenation level by performing computations on a composite fetal signal produced from the mixed signals; and ensuring a skin temperature of the maternal abdomen does not rise to unsafe levels due to activating the at least one light source.