According to the present application, a computer-implemented method of predicting thyroid eye disease is disclosed. The method comprising: preparing a conjunctival hyperemia prediction model, a conjunctival edema prediction model, a lacrimal edema prediction model, an eyelid redness prediction model, and an eyelid edema prediction model, obtaining a facial image of an object, obtaining a first processed image and a second processed image from the facial image, wherein the first processed image is different from the second processed image, obtaining predicted values for each of a conjunctival hyperemia, a conjunctival edema and a lacrimal edema by applying the first processed image to the conjunctival hyperemia prediction model, the conjunctival edema prediction model, and the lacrimal edema prediction model, and obtaining predicted values for each of an eyelid redness and an eyelid edema by applying the second processed image to the eyelid redness prediction model and the eyelid edema prediction model.

A monitoring device for monitoring the fluid balance of an animal or human body. The device includes a body weight sensor for continuously or periodically weighing the body, a fluid delivery device for providing a controllable supply of fluid to the body, a urine output sensor for determining the urine output of the body, a processor. The processor is adapted for determining a total fluid outtake of the body and a fluid outtake due to perspiration and respiration by taking a signal provided by the body weight sensor and a signal provided by the urine output sensor into account, and providing a control signal to the fluid delivery device to regulate a volume, flow velocity or flow rate of the fluid delivered to the body, so as to maintain a predetermined fluid balance in the body.

A measurement device is disclosed for measuring a change in one or more of a circumference or a perimeter of at least a portion of an object having a surface. The measurement device includes a first part for attachment to the object, a second part having a first portion moveable relative to a first portion of the first part, a determining device for determining a displacement of the first portion of the second part relative to the first portion of the first part caused by the object changing, and a biasing device for biasing the first part and the second part towards engagement. The measured displacement is for use in determining the change in one or more of a circumference or a perimeter of the object.

A system and method for detecting brain concussion includes detecting and measuring of acceleration at one or more points on a subject's head. Sensors, which can be accelerometers placed against the head, detect and measure natural motions of the patient's head due to blood flow in the brain and resultant movement of tissue in the brain. The acceleration data are then analyzed, including as to frequency of motions of the skull at the subject location in a frequency range of about 1 to 20 Hz. An observation is then made, as compared with data corresponding to non-concussion, of a change in frequency response pattern exhibited when accelerations are plotted as a function of time or frequency, to identify probable concussion if the frequency response pattern indicates concussion. Preferably the observation and comparison are made by a computer using an algorithm.

The present application relates to endotracheal tubes and to systems and methods for detecting airway edema and evaluating breathing with an endotracheal tube. An example endotracheal tube includes a distal portion, a proximal portion, and a linker portion. The linker potion couples the distal portion and the proximal portion. The linker portion includes at least two struts. The struts extend between the distal portion and the proximal portion. Also, there is at least one opening defined between and along the length of the struts. The linker portion is configured to contact the vocal cords of the subject when in use.

A fabrication process is disclosed for the production of flexible triboelectric nanogenerator (TENG) fiber, which can comprise a copper core surrounded by a silicone cladding. The TENG fibers are fabricated using a coaxial micro-extrusion process that enables 2D and 3D constructs to be fabricated with the fibers via 3D printing on both stationary and moving substrates to form mechanosensors as membranes, meshes, and hollow 3D structures. The mechanosensors can be integrated into wearable items for human activity monitoring, or can be formed on organs for organ monitoring, e.g., monitoring of perfused organs. The mechanosensors can be integrated into facemasks and uses for silent speech recognition, such as words mouthed in the absence of sound production by the speaker. The mechanosensors are self-powered and have high stretchability.

The invention provides a system for characterizing a patient including a substrate, a first electrode, a second electrode, and an electrical system. The electrical system is connected to the substrate and worn entirely on the patient's body. The electrical system in electrical contact with both the first and second electrodes and configured to inject an alternating electrical current through the first electrode and into the region of tissue. The electrical system is configured to measure a first electrical signal from the region of tissue through the second electrode. The electrical system is configured to measure a second electrical signal from the region of tissue. The first electrical signal or a signal determined therefrom indicates a resistance of the region of tissue and the second electrical signal or a signal determined therefrom indicates a reactance of the region of tissue.

A system for monitoring a health status of a person remotely from a medical facility, includes a display device to be installed in the medical facility, a wireless sensor device attachable to a leg of the person to acquire measurement information on a state of the leg of the person, and a compute server in wireless communication with the sensor device to acquire the measurement information. The compute server is configured to determine a risk of an arterial disease and a venous disease of the leg based on the acquired measurement information, and output, to the display device, information on the determined risk of the arterial disease and the venous disease of the leg.

The present disclosure relates to cardiac health assessment system for use with a handheld electronic device for assessing cardiac health of a user and a method for assessing cardiac health of a user. The disclosure further relates to systems and methods for training a machine learning model to estimate intracardiac pressure data.

Disclosed herein are systems, methods, and devices for classifying ophthalmic images according to disease type, state, and stage. The disclosed invention details systems, methods, and devices to perform the aforementioned classification based on weighted-linkage of an ensemble of machine learning models. In some parts, each model is trained on a training data set and tested on a test dataset. In other parts, the models are ranked based on classification performance, and model weights are assigned based on model rank. To classify an ophthalmic image, that image is presented to each model of the ensemble for classification, yielding a probabilistic classification score—of each model. Using the model weights, a weighted-average of the individual model-generated probabilistic scores is computed and used for the classification.