Medtronic, Inc.

Raphael Schneider

Lilian Kornet

Richard N Cornelussen

Richard J O'Brien

Daniel Becker

Tim D J Jongen

Pascalle H C M Reiters

Raja N Ghanem

Alfonso Aranda Hernandez

Vinayakrishnan Rajan

Hans-Juergen Bruns

Marc D Messier

A medical system including processing circuitry configured to receive a cardiac signal indicative of a cardiac characteristic of a patient from sensing circuitry and configured to receive a glucose signal indicative of a glucose level of the patient. The processing circuitry is configured to formulate a training data set including one or more training input vectors using the cardiac signal and one or more training output vectors using the glucose signal. The processing circuitry is configured to train a machine learning algorithm using the formulated training data set. The processing circuitry is configured to receive a current cardiac signal from the patient and determine a representative glucose level using the current cardiac signal and the trained machine learning algorithm.

Self-calibrating glucose monitor

In general, the disclosure describes techniques for predicting the occurrence of an arrhythmia based on an indication of heart rate turbulence. An example method comprises sensing a parameter indicative of heart rate turbulence, measuring heart rate turbulence based on the sensed parameter, and predicting an occurrence of an arrhythmia based on the measured heart rate turbulence.

Arrhythmia prediction based on heart rate turbulence

Methods, systems, and/or devices for selecting spinal cord stimulation (SCS) electrode array configurations to provide effective cardiac therapy. Physiological parameters related to the heart may be monitored and analyzed during the delivery of SCS using various SCS electrode array configurations to determine an effect SCS electrode array configuration.

Selection of spinal cord stimulation electrodes for use in cardiac therapy

A medical device system and associated method to control a laser Doppler unit to emit light from a coherent laser light source and collect a photodetector signal produced by the laser Doppler unit by a signal processor comprising a bandpass filter. The bandpass filter is applied to the photodetector signal to determine a tissue perfusion measurement from the filtered signal. A monitoring unit is enabled to receive the tissue perfusion measurement to detect a physiological condition of the patient in response to the tissue perfusion measurement.

Quantifying laser-doppler perfusion signal for arrhythmia detection and disease monitoring

Risk determination for a near fatal ventricular arrhythmia of a patient. An electrocardiogram of a heart of the patient is obtained. A parameter is measured, using an electrocardiogram of a heart of the patient, indicative of an autonomic nervous system of the patient. A numeric score is assigned for the parameter indicative of the conduction system of the heart. A numeric score is assigned for the parameter indicative of the autonomic nervous system. A ratio of the numeric score of the parameter indicative of the conduction system of the heart of the patient and the numeric score of the parameter indicative of the autonomic nervous system of the patient is calculated. The risk of the potentially near fatal ventricular arrhythmia of the patient is determined to be significant if the ratio is greater than a predetermined threshold. An action responsive to the determining step is taken.

Risk determination for ventricular arrhythmia

Systems, methods and devices for monitoring, analyzing, and processing a patient's heart rate signal for HRV characteristics are described herein. A first heart rate signal is acquired. The first heart rate signal includes at least one indication of an interval duration of cardiac activity. At least one accelerating portion and at least one decelerating portion of the first heart rate signal are identified. An average heart rate signal is acquired. The accelerating portion or the decelerating portion of the first heart rate signal is replaced with the average heart rate signal to produce a second heart rate signal. A frequency spectrum of the second heart rate signal may be obtained and utilized to predict or detect one or more autonomic conditions of a patient. Therapy may initiated or titrated in response to prediction or detection of the autonomic condition.

Heart rate variability distinction

A medical device system and method for monitoring a cardiac signal in a patient senses ventricular R-waves and computes a morphology metric of an R-wave and a corresponding preceding morphology metric of a preceding R-wave. One of a difference and a ratio of the R-wave morphology metric and the preceding R-wave morphology metric is compared to an established detection threshold for discriminating premature ventricular contractions from premature atrial contractions. A cardiac signal measurement is computed from the sensed R-waves in response to detecting a premature ventricular comparison based on the comparison.

Automatic detection of premature ventricular complexes for heart rate turbulence measurements

This disclosure describes techniques for generating a risk stratification indicator based on HRT measurements computed using physiological parameters sensed by an implantable medical device (IMD). In some examples, the HRT measurements may be computed by the IMD based on the physiological parameters. In other examples, the IMD may sense the physiological parameters, and transmit data representative of the parameters to an external computing device, such as an IMD programmer, which then computes the HRT measurements. Exemplary physiological parameters include cardiac signals.

Growing community of inventors

Maastricht, Netherlands

Raphael Schneider