A catastrophe-theoretic approach is provided for predicting an occurrence of an ischemic myocardial event (e.g., acute myocardial infarction) for a human patient based on a time series of monitored vital signs values measured from a patient, and in some instances, for providing advanced notice to clinicians or caregivers when such an ischemic event is forecasted or modifying treatment for the patient, according to the predicted likelihood. In particular, an ischemic heart disease management system is provided for determining a likelihood of near-term future significant myocardial ischemia in persons with coronary artery disease. Embodiments of the disclosure described herein may provide a forecasted risk for future significant myocardial ischemia within a time horizon comprising a future time interval. In one embodiment, the future time interval is from 30 min to approximately 4 hours into the future, and may be dependent on the frequency of vital signs measurements.

A computing device may receive a first one or more features associated with a patient. The computing device may determine, based on the first one or more features, a second one or more features associated with the patient. The determining the second one or more features associated with the patient may comprise feature engineering to generate features that improve the accuracy of one or more machine learning models. For example, the second one or more features may be determined based on a combination of at least a subset of the first one or more features. The computing device may generate, based on the one or more machine learning models, a prediction associated with the patient, which may comprise a mortality rate for the patient in the intensive care unit (ICU) or a length of stay in the ICU for the patient.

Methods and systems determine risks of deterioration of hospitalized or other monitored or cared-for patients, for example in a treatment facility such as a hospital or under home-health care. In embodiments, a warning or other instruction is issued to medical professionals to alert them that certain patients have moderate or high risk of transfer to a higher level of care or should be monitored more frequently. A medical professional can accept alerts regarding prediction of deterioration, causing a prophylactic transfer or increased monitoring, or a transfer or monitoring order can occur automatically. Data relating to all patients in a unit of a medical facility can be viewed including warnings relating to risk of transfer or deterioration, so that a medical facility can intervene prior to an event such as a cardiac event and/or plan to accommodate patients at higher levels of care or monitoring.

The perceptive faculties of a subject are determined by way of a brain-computer interface 20. At least two mutually distinguishable types of stimuli S.sub.A, S.sub.B which are applicable to a subject are prescribed. A multiplicity of temporally successive stimuli are applied to the subject and combined to form blocks. Calibration data are created from the EEG data ascertained thus by virtue of a number of ascertained EEG data and stimuli associated with these EEG data are combined to form calibration blocks. A classification function is ascertained by a classification analysis on the basis of ascertained calibration blocks. The classification function specifies a position of the stimulus of the first type in the respective calibration block. Finally, the EEG data of a number of test blocks selected from the blocks are subjected to the classification function.

Respiratory variables are estimated on a per-breath basis from airway pressure and flow data acquired by airway pressure and flow sensors (20, 22). A breath detector (28) detects a breath interval. A per-breath respiratory variables estimator (30) fits the airway pressure and flow data over the detected breath interval to an equation of motion of the lungs relating airway pressure, airway flow, and a single-breath parameterized respiratory muscle pressure profile (40, 42) to generate optimized parameter values for the single-breath parameterized respiratory muscle pressure profile. Respiratory muscle pressure is estimated as a function of time over the detected breath interval as the single-breath parameterized respiratory muscle pressure profile with the optimized parameter values, and may for example be displayed as a trend line on a display device (26, 36) or integrated (32) to generate Work of Breathing (WoB) for use in adjusting settings of a ventilator (10).

A method for collecting and analyzing urine at the time it is released uses a urine collecting tube joined with a canister. Suction is produced in the collecting tube to join the tube with a penis or to the exterior surface of a female urethra orifice. Once suction is achieved the collecting tube stays in place by suction action. When urine flows into the urine collecting tube a sensor triggers a vacuum pump to produce a higher level of suction to flush the urine into the canister where a level sensor determines the quantity of urine received. Various sensors in the canister determine levels of non-urine partials such as occult blood, drugs, salt, and other substances. When urine is no longer detected within the urine tube, the vacuum pump is turned off and a low-level vacuum remains to assure interconnection with the urine tube.

A wireless near-infrared spectrometry sensor includes a light source for emitting near-infrared energy into tissue and a light receiver for receiving the near-infrared energy after it exits the tissue. The sensor may include a portable energy source for supplying energy to the light source. A processing module may control the light source and process readings in connection with the light source. A wireless transceiver may be coupled to the processing module for at least one of transmitting and receiving information, wherein the light source emits near-infrared energy at predetermined intervals in order to conserve energy in the portable energy source. The portable energy source may include at least one of a battery, a capacitor, a thermoelectric generator, a kinetic energy transducer, electricity derived from RF energy, and any combination thereof. The sensor may further include a substrate for support and which may be part of a sterile bandage.

A method and system for continually monitoring oxygenation levels in real-time in compartments of an animal limb, such as in a human leg or a human thigh or a forearm, can be used to assist in the diagnosis of a compartment syndrome. The method and system can include one or more near infrared compartment sensors in which each sensor can be provided with a compartment alignment mechanism and a central scan depth marker so that each sensor may be precisely positioned over a compartment of a living organism. The method and system may comprise hardware or software (or both) may adjust one or more algorithms based on whether tissue being monitored was traumatized or is healthy. The method and system can also monitor the relationship between blood pressure and oxygenation levels and activate alarms based on predetermined conditions relating to the oxygenation levels or blood pressure or both.

Apparatus, such as a respiratory therapy device 4000, may generate a signal representing an estimate of a patient breathing pattern when using a flow therapy device with an un-sealed patient interface. The device may include a blower and may generate a flow of air at a controlled flow rate. The apparatus may include a controller. The generation may involve computing an estimate of the breathing pattern as a function of a device flow rate signal; a device pressure signal; a device conductance; a patient conductance; and a coupling parameter that characterizes a degree of coupling between the interface and the patients nares. An estimate of an exit pressure representative of a pressure of a flow of air generated by the therapy device just outside an orifice of the unsealed interface may also be computed. An estimate of a flushing flow rate from the estimated exit pressure may also be computed.

The present document relates to a method of manufacturing a flexible sensor belt suitable for being worn around an abdominal part of a human body, in particular a baby. The method comprising casting of a support layer using a flexible material in a first mould part, such that the support layer comprises one or more holes. Then, one or more electrodes are applied onto the support layer, such that these protrude the one or more holes. The electrodes are made of an electrically conductive material. The method further includes casting of a longitudinal belt section onto the support layer using a second mould part complementary to the first mould part, the casting applying the flexible material. The one or more electrodes are covered with the belt section formed on the support layer. The step of casting the belt section comprises a step of retaining the one or more electrodes using one or more retaining elements.