A medical monitoring and treatment device that includes a therapy delivery interface, a plurality of therapy electrodes coupled to the therapy delivery interface, a plurality of electrocardiogram sensing electrodes to sense electrocardiogram signals of a patient, a sensor interface to receive the electrocardiogram signals and digitize the electrocardiogram signals, and at least one processor coupled to the sensor interface and the therapy delivery interface to analyze the digitized electrocardiogram signals, to detect a cardiac arrhythmia based on the digitized electrocardiogram signals, and to control the therapy delivery interface to apply electrical therapy to the patient based upon the detected cardiac arrhythmia. The at least one processor is further configured to analyze a frequency domain transform of the digitized electrocardiogram signals, to determine a metric indicative of a metabolic state of a heart of the patient, and to accelerate or delay application of the electrical therapy based upon the metric.

A computer-implemented system may include a stair-climbing machine configured to be manipulated by a user while the user performs a treatment plan, an interface comprising a display configured to present information associated with the treatment plan, and processing structure configured to receive, from one or more data sources, information associated with the user, wherein the information comprises one or more risk factors associated with a cardiac-related event; generate, using one or more trained machine learning models, the treatment plan for the user, wherein the treatment plan is generated based on the information associated with the user, and the treatment plan comprises one or more exercises associated with managing the one or more risk factors in order to reduce a probability that a cardiac intervention will occur; and transmit the treatment plan to cause the stair-climbing machine to implement the one or more exercises.

A computer-implemented method is disclosed. The method includes receiving, at a computing device, a first treatment plan designed to treat an invasive surgical-related health issue of a user. The first treatment plan comprises at least two exercise sessions that, based on the invasive surgical-related health issue, enable the user to perform an exercise at different exertion levels. Next, while the user uses the electromechanical machine to perform the first treatment plan, receiving, at the computing device, data from sensors configured to measure the data associated with the invasive surgical-related health issue and transmitting the data. One or more machine learning models are used to generate a second treatment plan. The second treatment plan modifies at least one exertion level, and the modification is based on a standardized measure comprising perceived exertion, the data, and the invasive surgical-related health issue. The method additionally includes receiving the second treatment plan.

Systems including an elliptical machine and a processing device. The processing device may be configured to receive, before or while a user operates the elliptical machine, one or more messages pertaining to the user or a use of the elliptical machine by the user. The processing device may be also configured to determine whether the one or more messages were received by the processing device. In response to determining that the one or more messages were not received by the processing device, the processing device may be configured to determine, via one or more machine learning models, one or more actions to perform. The one or more actions may include at least one of initiating a telecommunications transmission, stopping operation of the elliptical machine, and modifying one or more parameters associated with the operation of the elliptical machine.

A computer-implemented system may include a rowing machine configured to be manipulated by a user while the user performs a treatment plan, an interface comprising a display configured to present information associated with the treatment plan, and a processing device configured to receive, from one or more data sources, information associated with the user, wherein the information comprises one or more risk factors associated with a cardiac-related event; generate, using one or more trained machine learning models, the treatment plan for the user, wherein the treatment plan is generated based on the information associated with the user, and the treatment plan comprises one or more exercises associated with managing the one or more risk factors in order to reduce a probability that a cardiac intervention will occur; and transmit the treatment plan to cause the rowing machine to implement the one or more exercises.

A computer-implemented system includes a processing device configured to receive a plurality of user and blood vessel characteristics associated with a user, generate a selected set of user and blood vessel characteristics, determine, based on the selected set of the user and blood vessel characteristics, a probability that angiogenesis will occur, and generate, based on the probability and the selected set of the user and blood vessel characteristics, a treatment plan that includes one or more exercises directed to modifying the probability that angiogenesis will occur, and a treatment apparatus configured to implement the treatment plan while the treatment apparatus is being manipulated by the user.

A computer-implemented system includes one or more processing devices configured to receive user information associated with a user, generate a selected set of the user information, determine, based on the selected set of the user information, at least one of a first probability of surviving one or more procedures and a second probability indicating an improvement, resulting from the one or more procedures, in quality-of-life metrics for the user, generate, based on the at least one of the first probability and the second probability and on the selected set of the user information, one or more recommendations of whether the user should undergo the one or more procedures, and generate, based on the one or more recommendations, a treatment plan that includes one or more exercises directed to modifying the at least one of the first probability and the second probability.

A fabric strain gauge includes a knitted fabric and a plurality of conductive measuring fibers, a first high conductivity fiber, and a second high conductivity fiber. The conductive measuring fibers are threaded with the knitted fabric, the first high conductivity conductive fiber is threaded with the knitted fabric, and connected to one or more ends of the conductive measuring fibers, and the second high conductivity fiber is threaded with the knitted fabric, and connected to the other ends of at least part of the conductive measuring fibers. In addition, a fabric pressure gauge and a smart clothing are also disclosed herein.

Described herein is a smart bed system, which includes a number of different elements that operate together or may operate independently in connection with an existing conventional bed frame and/or mattress. Bed system includes an inclinable bed apparatus, which is configured to be situated on an existing bed frame or mattress and provide selective inclining/reclining of a patient or user. A sensor mat system is adapted to be situated on mattress. Sensor mat system includes a plurality of different layers to sense the position and movement of a patient. An inflatable bladder system includes a plurality of inflatable cells for selectively adjusting the position or pressure experienced by a patient using bed system. A support rail system supports a user in a bed. A microcontroller performs various control and data processing operations associated with system. User input for various controls of system may be provided from a remote control, which is in data communication with microcontroller.

Embodiments of the present invention include a system having at least one sensor configured to monitor a muscle oxygen saturation (SmO2) level of a patient who is undergoing cardiac arrest and to generate a signal representing SmO2 level; a user interface device; a processor communicably coupled to the user interface device, the processor configured to cause the user interface device to present an array of two or more possible nodes of a clinical decision support tree, wherein at least one of the nodes indicates cardiopulmonary resuscitation (CPR) treatment of the patient with no ventilation, and wherein at least another of the nodes indicates CPR treatment of the patient with active ventilation; determine which of the two or more possible nodes should be emphasized based on the SmO2 level; and update the array of the two or more possible nodes based on the determination.