US 11484284

A concise summary of US Patent 11,484,284 is provided below, based on a review of the patent records.

Title: Methods and devices for processing heart sounds

Assignee: Florida International University FIU

Inventors: Valentina Dargam, Joshua Hutcheson

Filing Date: February 7, 2022

Issue Date: November 1, 2022

Abstract: Provided are the methods and devices to detect and quantify microstructural and functional differences in valve and cardiac disease using heart sounds, specifically for subjects suffering from early stages of valve remodeling. Such methods and devices can be used to detect and quantify microstructural and/or functional differences in, for example, aortic valves of subjects having bicuspid aortic valves and/or suffering from early Calcific Aortic Valve Disease (CAVD).

Overview of Independent Claims:

This patent contains two independent claims, which outline the core inventions.

Independent Claim 1 describes a system for processing heart sound signals. In plain language, this claim covers a system that includes:

• A device to record a phonocardiogram (a recording of heart sounds).
• A processor connected to the recording device.
• A display to show the results.
• A machine-readable medium (like a hard drive or memory) with instructions for the processor to:
  • Measure a heart sound signal.
  • Break down the signal into smaller segments.
  • Extract specific acoustic features from these segments.
  • Use an unsupervised machine learning process to categorize the heart sound based on a stage of a disease.
  • Recommend that a subject receive an "anti-remodeling therapy" if the acoustic features differ from a predetermined value. The claim then lists a variety of potential therapies.

Independent Claim 17 also describes a system for processing heart sound signals, but it is more detailed and combines many of the features described in the dependent claims of the patent into a single, comprehensive claim. In essence, it specifies a wearable phonocardiogram recording device with an integrated processor, display, and machine-readable medium. The system performs a detailed series of steps, including:

• Segmenting the heart sound signal by selecting a region of interest and calculating the sum of squares error to identify cardiac cycles.
• Extracting a wide range of acoustic features, such as temporal and spectral features, dominant frequency, power spectral density, and eigenvalues from a principal component analysis.
• Using an unsupervised machine learning process that involves clustering eigenvalues with a k-means algorithm and correlating heart sound features with disease stages as measured by echocardiogram parameters.
• The system further includes a treatment system with a reservoir and a device to administer a compound to the subject if the area under the curve of the power spectral density is outside a predetermined range.
• Finally, it reiterates the recommendation for an anti-remodeling therapy based on deviations in acoustic features, listing the same broad categories of therapies as in Claim 1.

A search of the dockets for the Court of Appeals for the Federal Circuit (CAFC) for the year 2026 was conducted, and no litigation involving US Patent 11,484,284 was found as of the date of this analysis. However, it should be noted that the absence of a result does not definitively mean no litigation exists, as there can be delays in docketing or other factors.