Method and device to monitor patients with kidney disease

摘要

A medical monitoring device for monitoring electrical signals from the body of a subject is described. The medical monitoring device monitors electrical signals originating from a cardiac cycle of the subject and associates each cardiac cycle with a time index. The medical monitoring device applies a forward computational procedure to generate a risk score indicative of hyperkalemia, hypokalemia or arrhythmia of the subject. The medical monitoring device can adjust the forward computational procedure based upon clinical data obtained from the subject.

主权项

1. A medical monitor, comprising:
a medical device for determining body potassium status by monitoring electrical signals of the body of a subject; a processor for applying a forward computational procedure to the electrical signals monitored from the body in communication with the medical device; and a communication system indicating a condition of hyperkalemia, hypokalemia or arrhythmia of the subject based on at least one risk score; wherein the medical device associates a cardiac cycle of the subject with a time index and calculates the at least one risk score, wherein the at least one risk score is associated with the time index; wherein the at least one risk score is calculated by the forward computational procedure by the addition of a plurality of features converted to scalar feature scores on a common scale, wherein the addition of the feature scores can be weighted or non-weighted as provided in Equation 4: Risk Score=
Σk=1nWk*Pk  (Eq. 4) wherein Wk is a weighting factor, Pk is a feature score, k is a feature number, and n is a number of features; and wherein the addition of the features scores is non-weighted when Wk=1; wherein the processor is configured to receive clinical information regarding the physiological state of the subject associated with the time index and makes an adjustment to the forward computational procedure based upon an error between the at least one risk score and the clinical information, and wherein the adjustment to the forward computational procedure based upon an error between the at least one risk score and the clinical information is done by the processor using a backward computational procedure, wherein the backward computational procedure adjusts exponential factors used to calculate the scalar feature score.