Electrocardiogram device and methods

• US 10,524,680 B2
• Filed: 08/30/2016
• Issued: 01/07/2020
• Est. Priority Date: 08/31/2015
• Status: Active Grant

• Current Assignee: Ventrilink Corporation
• Original Assignee: Ventrilink Corporation
• Inventors: Baumann, Eric, Korzinov, Lev, Churchville, David
• Primary Examiner(s): Holmes, Rex R
• Application Number:
  US15/252,154
• Publication Number:
  US 20170055863A1
• Time in Patent Office: 1,225 Days
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/113 occurring during breathing
• CPC Class Codes: A61B 5/352 Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
• CPC Class Codes: A61B 5/361 Detecting fibrillation
• CPC Class Codes: A61B 5/363 Detecting tachycardia or bradycardia
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: A61B 5/742 using visual displays A61B5/339 takes precedence
• CPC Class Codes: A61B 5/746 Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms alarms per se G08B
• CPC Class Codes: G16H 40/67 for remote operation

Abstract

Devices and methods are described that provide improved diagnosis from the processing of physiological data. The methods include use of multiple algorithms and intelligently combing the results of multiple algorithms to provide a single optimized diagnostic result. The algorithms are adaptive and may be customized for particular data sets or for particular patients. Examples are shown with applications to electrocardiogram data, but the methods taught are applicable to many types of physiological data.

Claims

1. A method for acquiring and processing an electrocardiogram (ECG) signal of a user, the method comprising:

i) acquire a first set of ECG signal data from a first patient, using a device, the device comprising;

(1) a processor;

(2) one or more electrodes, attached to the user and configured to measure the ECG signal; and

,

(3) an output interface that provides a diagnosis of a patient'"'"'s cardio health to the medical professional; and

,

analyze the first set of ECG signal data with at least two algorithms each producing a diagnostic result,

ii) wherein the at least two algorithms are known to present different diagnoses when applied to the first set of ECG signal, and,

combining the diagnostic results of the at least two algorithms to provide a combined diagnostic result,

iii) wherein the combined diagnostic result is a weighted average of the diagnostic results produced by the at least two algorithms, each weighted by a weighting factor for each of the diagnostic results of the at least two algorithms, and,

iv) reporting the combined diagnostic result to the medical professional using the output interface.

2. The method of claim 1 wherein the weighting factor of the diagnostic results produced by the at least two algorithms is a confidence estimate for each of the diagnostic results produced by the at least two algorithms.

3. The method of claim 1 wherein a true diagnosis for the first patient is known and the weighting factors of the diagnostic results produced by the at least two algorithms are selected by a technician review such that the combined diagnostic result matches the true diagnosis.

4. The method of claim 1 wherein each of the at least two algorithms are selected on the basis of providing accurate diagnostic results for a group of patients that display ECG signal data similar to the first ECG signal data of the first patient, where accurate diagnostic results mean those results with low false positive rates.

5. The method of claim 1 wherein a true diagnosis for the first patient is known and the weighting factors for each of the diagnostic results produced by the at least two algorithms are determined by an adaptive algorithm.

6. The method of claim 1 wherein:

a) the first set of ECG signal data is acquired on a first day of a multiple day test, and,

b) wherein a true diagnosis for the first patient is known, and,

c) the weighting factors for each of the diagnostic results produced by the at least two algorithms are selected by a technician review such that the combined diagnostic result matches the true diagnosis of the first set of ECG signal data, and,

d) further acquiring a plurality of ECG signal data after the first ECG signal data, and, analyzing the plurality of ECG signal data acquired after the first set of ECG signal data using the weighting factors selected by the technician review of the first set of ECG signal data.