A method includes: receiving first data including physiological information obtained from a subject and a first result that a disease is developing; specifying a first time point at which the physiological information included in the first data is obtained; receiving second data including the physiological information obtained from the subject and a second result that the disease is not developing; specifying a second time point at which the physiological information included in the second data is obtained; upon determining that a time interval between the first time point and the second time point is smaller than a first predetermined value, assigning, to the second data, a first training label indicating that the disease is developing and a weighting index that is capable of taking a plurality of values according to the time interval; and performing machine learning of a model by using the second data as training data.

Patient sleep is staged using personalized circadian models built with data collected by wearable devices over daytime and nighttime hours, thus capturing a patient's personal circadian rhythms. The circadian model is used to identify sleep intervals in incoming nightly data for the patient. The identified sleep intervals are analyzed by the machine learning system which stages epochs of sleep. Methods include receiving patient heart rate data from over a plurality of circadian cycles; creating a circadian model for the patient with a defined operation for applying sleep labels to new data from the wearable device; applying the circadian model to nightly test data from the device to identify a sleep interval; and assigning, with a classifier, sleep stages to epochs of the sleep interval.

Disclosed are a biometric information measuring apparatus and method. An external device according to an embodiment includes a dipole antenna and a cavity reflecting an electro-magnetic field, radiated by the dipole antenna, in a direction toward an inside of a body having a target analyte. The external device may be attached to the exterior of the body having the target analyte.

An apparatus including a controller can determine a rate of change of a blood glucose level of a subject from blood glucose data and determine if there is a risk of the blood glucose level going high or low.

A wireless, patient-worn, physiological sensor configured to, among other things, help manage a patient that is at risk of forming one or more pressure ulcers is disclosed. According to an embodiment, the sensor includes a base having a top surface and a bottom surface. The sensor also includes a substrate layer including conductive tracks and connection pads, a top side, and a bottom side, where the bottom side of the substrate layer is disposed above the top side of the base. Mounted on the substrate layer are a processor, a data storage device, a wireless transceiver, an accelerometer, and a battery. In use, the sensor senses a patient's motion and wirelessly transmits information indicative of the sensed motion to, for example, a patient monitor. The patient monitor receives, stores, and processes the transmitted information.

There is provided a system for monitoring transpulmonary pressure of a mechanically ventilated individual, comprising: a feeding tube, at least one esophageal body, a pressure sensor, and a memory having stored thereon code for: computing an estimate of esophageal wall pressure according to pressure in the esophageal body when inflated and contacting the inner wall of the esophagus, computing the transpulmonary pressure of the mechanically ventilated target individual according to the esophageal wall pressure, periodically inflating and deflating the esophageal body for periodic monitoring of the transpulmonary pressure of the mechanically ventilated target patient while the feeding tube is in use, and computing instructions for adjustment of parameter(s) of a mechanical ventilator that automatically ventilates the target individual according to the computed transpulmonary pressure, wherein the instructions for adjustment of parameter(s) of the mechanical ventilator are computed while the feeding tube is in place without removal of the feeding tube.

Rather than rely on variation from physician to physician and limited imaging information for assessing plaque vulnerability of a patient, medical imaging and other information are used by a machine-implemented classifier to predict plaque rupture. Anatomical, morphological, hemodynamic, and biochemical features are used in combination to classify plaque.

Systems and methods for monitoring patients with multiple chronic diseases are described. A system may include a health status monitor that receives diagnostic data including physiological signals sensed from a patient. The system may produce at least a first risk indication of the patient developing a first disease and a second risk indication of the patient developing a different second disease. The system may detect the first and second diseases from the physiological signals, and generate a composite health status indicator using the detections of the first and second diseases and the first and second risk indications. An alert of worsening health status may be generated if the composite detection score exceeds an alert threshold.

An example device for detecting one or more parameters of a cardiac signal is disclosed herein. The device includes one or more electrodes and sensing circuitry configured to sense a cardiac signal via the one or more electrodes. The device further includes processing circuitry configured to determine an R-wave of the cardiac signal and determine whether the R-wave is noisy. Based on the R-wave being noisy, the processing circuitry is configured to determine whether the cardiac signal around a determined T-wave is noisy. Based on the cardiac signal around the determined T-wave not being noisy, the processing circuitry is configured to determine a QT interval or a corrected QT interval based on the determined T-wave and the determined R-wave.

System monitors and methods of monitoring a system are disclosed. In one arrangement a system monitor predicts a future state of a system. A data receiving unit receives system data representing a set of one or more measurements performed on the system. A first statistical model is fitted to the system data. The first statistical model is compared to each of a plurality of dictionary entries in a database. Each dictionary entry comprises a second statistical model. The second statistical model is of the same general class as the first statistical model and obtained by fitting the second statistical model to data representing a set of one or more previous measurements performed on a system of the same type as the system being monitored and having a known subsequent state. A prediction of a future state of the system being monitored is output based on the comparison. The first statistical model and the second statistical model are each a stochastic process or approximation to a stochastic process.