A respiratory therapy device that is adapted to matingly connect with two standardized respiratory devices simultaneously to allow for combination, enhanced, single device, respiratory treatments. It monitors the number of PEP treatment events utilizing a motion sensor, and presents a resettable, visual stimulus for each event as well as providing a record of the events in each therapy cycle.

A method of determining a biophysical model for a lung of a patient from multiple x-ray measurements corresponding to different breathing phases of the lung is provided. The method includes extracting multiple displacement fields of lung tissue from the multiple x-ray measurements corresponding to different breathing phases of the lung. Each displacement field represents movement of the lung tissue from a first breathing phase to a second breathing phase and each breathing phase has a corresponding set of biometric parameters. The method includes calculating one or more biophysical parameters of a biophysical model of the lung using the multiple displacement fields of the lung tissue between different breathing phases of the lung and the corresponding sets of biometric parameters.

A garment for real time detection of body deformation during an image scan includes a front portion, made of a compression material and having a plurality of fiber Bragg gratings (FBGs). The garment includes a plurality of light emitters, each light emitter configured to pulse light waves through a corresponding FBGs and a plurality of light sensors, each light sensor attached to a corresponding FBG and configured to receive pulsed light waves. A processor obtains data through a data acquisition module configured to receive from the light sensors peak wavelengths reflected by the FBG Based on the effective shifts of the Bragg wavelengths of the FBGs aligned along the cartesian coordinate system, the processor may correct acquired image data or re-direct an external beam treatment to compensate for body deformation during an image scan.

A lung function analysis system includes motion sensing devices each including accelerometers, gyros, battery, processor, and ireless transmitter, the processor configured to read motion data from the accelerometers and gyros and transmit the motion data over the wireless transmitter. The system includes a data collection device receiving the motion data and recording the motion data in a database; and a computing device with a lung function data analysis routine adapted to analyze the motion data to provide information useful in treating pulmonary disease. In embodiments, the lung function analysis routine includes a classifier trained on a database of motion data and diagnoses. In embodiments, the accelerometers and gyros are three-axis and/or the devices include electromyographic sensors. In embodiments, the system includes remote sensors such as a stereo camera with or without markers, millimeter-wave radar, or an ultrasonic echolocation device. In embodiments the information produced may include FEV1, FVC, FEV1/FVC and FEF25/75.

A lung function analysis system includes motion sensing devices each including accelerometers, gyros, battery, processor, and ireless transmitter, the processor configured to read motion data from the accelerometers and gyros and transmit the motion data over the wireless transmitter. The system includes a data collection device receiving the motion data and recording the motion data in a database; and a computing device with a lung function data analysis routine adapted to analyze the motion data to provide information useful in treating pulmonary disease. In embodiments, the lung function analysis routine includes a classifier trained on a database of motion data and diagnoses. In embodiments, the accelerometers and gyros are three-axis and/or the devices include electromyographic sensors. In embodiments, the system includes remote sensors such as a stereo camera with or without markers, millimeter-wave radar, or an ultrasonic echolocation device. In embodiments the information produced may include FEV1, FVC, FEV1/FVC and FEF25/75.

A garment for real time detection of body deformation during an image scan includes a front portion, made of a compression material and having a plurality of fiber Bragg gratings (FBGs). The garment includes a plurality of light emitters, each light emitter configured to pulse light waves through a corresponding FBGs and a plurality of light sensors, each light sensor attached to a corresponding FBG and configured to receive pulsed light waves. A processor obtains data through a data acquisition module configured to receive from the light sensors peak wavelengths reflected by the FBG Based on the effective shifts of the Bragg wavelengths of the FBGs aligned along the cartesian coordinate system, the processor may correct acquired image data or re-direct an external beam treatment to compensate for body deformation during an image scan.

A multi-sensor smart patch is disclosed that can be worn by a user to monitor multiple physiological systems of the user. The multi-sensor smart patch can make use of two or more acoustic sensors, such as accelerometer contact microphones (ACMs), to collect acoustic data from multiple locations on the user's body. The multi-sensor smart patch can include electrodes for detecting the heart's electrical activity and/or assessing the user's bioimpedance. The multi-sensor smart patch can provide useful data associated with the user's cardiovascular system, respiratory system, and electrical characteristics. The multi-sensor smart patch can be in the form of a reusable electronics module couplable to a disposable patch adhesive.

The present invention is directed to the measurement of a baseline respiratory level in a patient so that changes in respiratory activity can be easily reported. The baseline measurement is collected by a sensor in the patient's chest and a sensor on the patient's abdomen, and is transmitted to a computing device. The computing device measures normal breathing for 60 seconds and uses the waveform collected over this period of time to generate a baseline RR, tidal volume, and minute ventilation. From this point, the patient's RR, tidal volume, and minute ventilation are recorded and compared to the baseline measurements, and if a change from the baseline measurement that exceeds a predetermined threshold is detected, the doctor is alerted that action must be taken for the patient's safety.

In an embodiment, there is provided a method of predicting respiratory motion in real-time. The method includes training, by a training module, a recurrent neural network circuitry in real time. The training is performed over a training time interval. The training is based, at least in part, on a training data set. The training data set includes a training number of measured position samples. The measured position samples are related to respiratory motion of a patient target region. The method further includes predicting, by the trained recurrent neural network circuitry, a future position of the patient target region at a future point in time based, at least in part, on a prediction data set. The future point in time is a look ahead time interval in the future relative to a prediction time interval. The prediction data set includes a prediction number of measured position samples.

In an embodiment, there is provided a method of predicting respiratory motion in real-time. The method includes training, by a training module, a recurrent neural network circuitry in real time. The training is performed over a training time interval. The training is based, at least in part, on a training data set. The training data set includes a training number of measured position samples. The measured position samples are related to respiratory motion of a patient target region. The method further includes predicting, by the trained recurrent neural network circuitry, a future position of the patient target region at a future point in time based, at least in part, on a prediction data set. The future point in time is a look ahead time interval in the future relative to a prediction time interval. The prediction data set includes a prediction number of measured position samples.