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.

As of May 1, 2026, a comprehensive search of publicly available patent litigation databases, including the PACER Case Locator, the U.S. Court of Appeals for the Federal Circuit (CAFC) docket, and the Unified Patents portal, reveals no known litigation involving US patent 11,484,284.

Proceedings overview

There are no AIA trial proceedings on file for US Patent 11,484,284 as of May 1, 2026. This indicates that the patent has not been challenged in an inter partes review (IPR), post-grant review (PGR), or covered business method (CBM) review before the Patent Trial and Appeal Board (PTAB). For a defendant, this means the patent has not been "hardened" through PTAB scrutiny, and all claims remain untested by these administrative trial processes.

Strategic summary

As of the current date, no claims of US Patent 11,484,284 have been canceled, sustained, or even tested in any PTAB proceeding. All claims, including independent claims 1 and 17, remain unadjudicated by the PTAB. Consequently, there is no estoppel landscape to consider under 35 U.S.C. § 315(e)(2), as no petitioner has raised or could have raised any prior-art grounds in an AIA trial. There are no pattern signals, such as multiple IPR filings by the same petitioner or aggressive PTAB appeals by the patent owner, simply because no proceedings have been initiated.

Recommended next steps

Since no PTAB activity exists for US Patent 11,484,284, a defendant facing assertion of this patent would find that all prior art grounds remain available for potential challenge. The absence of PTAB activity suggests that the patent has not yet been significantly asserted in a way that would provoke an AIA trial. If a demand letter cites this patent, a defendant has the full range of PTAB defenses available for consideration.

Inventors

The named inventors are Valentina Dargam and Joshua Hutcheson. Both were employed by Florida International University (FIU) at the time of filing, as indicated by the assignment of their interest to "THE FLORIDA INTERNATIONAL UNIVERSITY BOARD OF TRUSTEES" (Reel 058909/0423). No unusual patterns, such as departure from the original assignee, are discernable from the provided information.

Original assignee

The original assignee named on the issued patent is Florida International University (FIU). FIU is a public research university whose primary line of business is education and scientific research. As a research institution, FIU develops technologies and intellectual property, which it may then license, rather than directly shipping commercial products embodying the claims. The university is currently operating.

Assignment timeline

• 2021-02-19 (executed) / recorded 2022-02-07 — Reel 058909/0423
  • Conveyance: ASSIGNMENT
  • Assignor: DARGAM, VALENTINA; HUTCHESON, JOSHUA
  • Assignee: THE FLORIDA INTERNATIONAL UNIVERSITY BOARD OF TRUSTEES
  • Correspondent: MCGRAW, MARIEL K. ESQ.; FLORIDA INTERNATIONAL UNIVERSITY; OFFICE OF RESEARCH & ECONOMIC DEVELOPMENT; 11200 SW 8TH STREET, MARC 430; MIAMI, FL 33199. This correspondent appears to be internal counsel for Florida International University.
  • Context: Original assignment of inventor rights to their employing university.

Timeline diagram

timeline
    title Ownership of US 11484284
    2020 : Provisional filed
    2021 : Parent filed
    2022 : Inventors assigned to FIU
         : Divisional filed
         : Patent issued

NPE / troll-pattern signals

1. Shell-entity transfer — Not present. The only recorded transfer is from individual inventors to Florida International University, a public research institution (Reel 058909/0423).
2. Known asserter in the chain — Not present. Florida International University is not identified as a known patent asserter or NPE.
3. Repeat correspondent across the chain — Not present. Only one assignment is recorded, and the correspondent (MCGRAW, MARIEL K. ESQ.; FLORIDA INTERNATIONAL UNIVERSITY; OFFICE OF RESEARCH & ECONOMIC DEVELOPMENT) appears to be internal counsel for the university (Reel 058909/0423).
4. Cascading transfers — Not present. There is only one recorded assignment in the chain.
5. Pre-litigation transfer — Not present. No litigation involving this patent has been identified, and the only assignment is the initial inventor-to-university transfer that occurred prior to patent issuance.
6. Bankruptcy fire-sale — Not present. Florida International University is an active, operating educational institution and not in bankruptcy.
7. Privateering — Not present. There is no indication of an operating company transferring the patent to an NPE for assertion against competitors.
8. Defensive aggregator (anti-NPE) — Not present. The patent is currently owned by Florida International University, not a defensive aggregator.

Verdict

Insufficient data. Based on the USPTO Assignment Center records, only one assignment is on file for US Patent 11,484,284, which is the original transfer from the individual inventors to Florida International University (Reel 058909/0423, recorded 2022-02-07). There are no subsequent transfers or any other indicators typically associated with NPE activity. Therefore, there is insufficient evidence to classify this patent as an NPE asset.

USPTO Assignment Center Search for US11484284

Prior Art Analysis for US Patent 11,484,284

Based on the patent file wrapper for US patent 11,484,284, the following prior art references were cited by the USPTO examiner during prosecution. An analysis of each reference and its potential impact on the patent's claims is detailed below.

---

1. WO2004035137A1: Acoustic cardiac assessment

• Full Citation: Gavriely, Noam. "Acoustic cardiac assessment." World Intellectual Property Organization, Publication No. WO2004035137A1.
• Publication Date: April 29, 2004 (Filing Date: October 21, 2002)
• Brief Description: This international patent application describes a method and system for the acoustic assessment of cardiac function. It discloses recording heart sounds and analyzing their features, such as frequency and timing, to detect cardiac abnormalities. The system can analyze the S1 and S2 heart sounds and correlate acoustic parameters with physiological conditions of the heart. The stated purpose is to provide a non-invasive diagnostic tool.
• Potential Anticipation of Claims:
  • Claim 1: This reference appears to disclose several key elements of claim 1, including a device for recording heart sounds (a phonocardiogram recording device), a processor for analyzing the signal, and the extraction of acoustic features from segments of the heart sound. The core concept of using acoustic analysis for cardiac assessment is central to this prior art. However, WO2004035137A1 does not explicitly teach or suggest the use of an unsupervised machine learning process to group heart sounds according to a disease stage, nor does it recommend a specific list of anti-remodeling therapies based on the deviation of acoustic features. These appear to be the novel elements of claim 1.
  • Claim 17: Similar to its impact on claim 1, this reference discloses the foundational elements of recording and analyzing heart sounds. It does not, however, detail the specific segmentation technique using a "sum of squares error" between envelopes of a region of interest (ROI), nor the use of principal component analysis to identify eigenvalues, or a k-means clustering algorithm for unsupervised learning. Furthermore, it does not disclose a "treatment system" that administers a compound based on the analysis. Therefore, it does not anticipate the more detailed and specific combination of features recited in claim 17.

---

2. US20080001735A1: Mesh network personal emergency response appliance

• Full Citation: Tran, Bao. "Mesh network personal emergency response appliance." United States Patent Application Publication No. US20080001735A1.
• Publication Date: January 3, 2008 (Filing Date: June 30, 2006)
• Brief Description: This patent application describes a wearable personal emergency response system that can monitor various physiological signs of a user, including heart rate. The system is designed to detect an emergency and automatically send an alert. It mentions the capability to monitor heart sounds via a device that can be worn by the user. The primary focus is on the emergency alert and communication network aspects.
• Potential Anticipation of Claims:
  • Claim 1 & 17: This reference is relevant in that it discloses a wearable device for monitoring physiological signals, which could include heart sounds. The concept of a wearable phonocardiogram recording device as mentioned in claim 9 (dependent on claim 1) and specified in claim 17 is touched upon. However, the core of the invention in US 11,484,284 is the detailed processing of the heart sound signals—specifically, the segmentation method, the extraction of detailed acoustic features (like power spectral density and eigenvalues), the use of unsupervised machine learning for classification, and the recommendation of specific therapies. US20080001735A1 does not teach these specific signal processing and diagnostic/therapeutic steps. Its focus is on the hardware and network for emergency alerts, not the nuanced analysis of heart sounds for early disease detection. Therefore, it does not anticipate the claims of US 11,484,284.

---

3. US20140364945A1: Annuloplasty device

• Full Citation: "Annuloplasty device." Lc Therapeutics, Inc. United States Patent Application Publication No. US20140364945A1.
• Publication Date: December 11, 2014 (Filing Date: June 5, 2013)
• Brief Description: This patent application is directed to a medical device, specifically an annuloplasty device used for repairing heart valves, particularly the mitral valve. The disclosure is focused on the mechanical structure and implantation of the device to treat valve regurgitation.
• Potential Anticipation of Claims:
  • Claim 1 & 17: This reference is cited as general background art related to heart valve disease and its treatment. It describes a treatment for a heart valve condition but does not disclose any method or system for the diagnosis of such conditions using heart sound analysis. The subject matter of this reference is entirely different from the claimed invention in US 11,484,284. It does not involve phonocardiograms, signal processing, acoustic feature extraction, or machine learning. Consequently, this reference does not anticipate any of the claims of US 11,484,284. It was likely cited to provide context for the problem that the invention of US 11,484,284 aims to solve (i.e., the need for early detection to avoid invasive procedures like those described in this reference).

Obviousness Analysis of US Patent 11,484,284 under 35 U.S.C. § 103

This analysis evaluates the claims of US patent 11,484,284 for obviousness by considering combinations of the prior art references cited during prosecution. The analysis is grounded in the perspective of a Person Having Ordinary Skill in the Art (PHOSITA) at the time of the invention (priority date: February 14, 2020), who would be familiar with medical signal processing, basic machine learning techniques, and cardiac physiology.

---

Analysis of Independent Claim 1

Claim 1 recites a system for processing a heart sound signal that measures, segments, and extracts acoustic features, then uses an unsupervised machine learning process to group the sound by disease stage, and finally recommends an anti-remodeling therapy if the features deviate from a norm.

Obviousness Combination: Claim 1 is likely obvious over WO2004035137A1 (Gavriely) in view of the general knowledge of a PHOSITA regarding the application of machine learning to signal processing.

1. Base Reference (Gavriely): Gavriely discloses the core of the claimed system. It teaches a system comprising a device for recording heart sounds, a processor, and methods for analyzing those sounds by segmenting them (into S1/S2 components) and extracting acoustic features like frequency and timing to assess cardiac function. This directly teaches the elements of recording, segmenting, and extracting acoustic features from a phonocardiogram for diagnostic purposes.

2. Missing Elements in Gavriely: Gavriely does not explicitly teach the use of an unsupervised machine learning process for classification or the specific step of recommending an anti-remodeling therapy.

3. Motivation to Combine with General Knowledge (Machine Learning): By the priority date of 2020, machine learning was a well-established and pervasive tool for pattern recognition and classification across numerous technical fields, including medical signal analysis. A PHOSITA, tasked with improving the accuracy and automating the diagnostic process taught by Gavriely, would have found it obvious to apply a known machine learning technique to the extracted acoustic feature data. Unsupervised learning, specifically clustering, is a fundamental approach for identifying inherent groupings or stages within a dataset without pre-existing labels. The motivation for this step would be to replace subjective, manual analysis of the acoustic features with an objective, data-driven method to classify the heart sounds, thereby making the diagnostic more reliable and scalable. This is not an inventive leap but rather the application of a conventional tool (machine learning) to a known problem (classifying physiological signals from feature data).

4. Motivation to Add Therapy Recommendation: The final step of recommending a therapy is a logical and obvious consequence of a positive diagnostic finding. The anti-remodeling therapies listed in the claim (e.g., angiotensin-converting enzyme inhibitors) represent the standard of care for many cardiac conditions. A PHOSITA developing a system to detect early-stage heart valve remodeling would be motivated to have the system provide actionable information. Linking the output of the automated diagnostic (a specific disease stage) to a recommendation for the corresponding, well-known clinical therapy would be a natural and predictable design choice for any medical diagnostic system intended for clinical use.

Conclusion for Claim 1: A PHOSITA would have been motivated to take the cardiac sound analysis system of Gavriely and apply a standard unsupervised machine learning algorithm to automate the classification of the extracted features, and subsequently recommend a standard therapy based on the classification. This renders the claims of Claim 1 obvious.

---

Analysis of Independent Claim 17

Claim 17 recites a highly specific, wearable, and integrated system that includes a particular segmentation method (sum of squares error), specific feature extraction techniques (PCA, PSD), a specific machine learning algorithm (k-means clustering), and an integrated, closed-loop treatment system that administers a compound based on the analysis.

Obviousness Combination: Claim 17 is likely obvious over Gavriely in view of US20080001735A1 (Tran) and further in view of the general knowledge of a PHOSITA regarding standard signal processing and machine learning techniques.

1. Base Combination (Gavriely and Tran): Gavriely provides the foundational acoustic analysis system. Tran teaches a wearable personal monitoring appliance for physiological signals, including heart sounds. A PHOSITA would have been motivated to combine the teachings of Gavriely and Tran to make the diagnostic system more practical for long-term or ambulatory monitoring, improving patient convenience and data richness. Integrating the processor and display into a wearable form factor, as taught by Tran, would be a predictable and desirable improvement to the system of Gavriely.

2. Motivation to Add Specific Known Techniques: The detailed methods recited in claim 17 are standard, off-the-shelf techniques that a PHOSITA would have readily available to implement the broader concepts of the base references.

   • Segmentation: The use of "sum of squares error between envelopes" is a textbook method for template matching, which is a common way to find repeating patterns like cardiac cycles in a time-series signal. This is merely one of a few well-known and predictable ways to implement the "segmenting" step taught by Gavriely.
   • Feature Extraction: Power Spectral Density (PSD) and Principal Component Analysis (PCA) are fundamental tools for signal processing and data analysis. A PHOSITA tasked with extracting the most discriminative features from heart sounds would naturally turn to these standard techniques.
   • Unsupervised Learning: K-means clustering is one of the most widely known and implemented clustering algorithms. For the task of "grouping" data into disease stages, it represents an obvious first choice for an engineer to try.

3. Motivation to Add the Treatment System: The addition of a closed-loop treatment system (reservoir and administration device) represents the automation of a known medical paradigm: diagnose, then treat. The concept of closed-loop therapeutic devices was well-established by 2020, with the most prominent example being the artificial pancreas (glucose sensor and insulin pump). A PHOSITA, having created a wearable real-time monitor for a cardiac biomarker (e.g., the PSD's area under the curve), would be motivated to connect it to an automated drug delivery system. The motivation is compelling: to provide immediate therapeutic intervention at the moment of detection, potentially preventing disease progression and improving patient outcomes without requiring patient or clinician action. This would be seen as the next logical step in advancing the technology from a mere monitor to an active therapeutic device.

Conclusion for Claim 17: While Claim 17 is highly detailed, it represents a combination of known elements. A PHOSITA would be motivated to make the analysis system of Gavriely wearable (as suggested by Tran), implement its functions using standard, well-known algorithms (SSE, PSD, PCA, k-means), and connect its output to a known type of device (an automated drug pump) to create a closed-loop system. Each step in this combination is a predictable solution to a known problem, rendering the claimed combination as a whole obvious.

Patent Term and Expiration Analysis for US Patent 11,484,284

Date of Analysis: May 1, 2026

An analysis of the prosecution history and legal status of US patent 11,484,284 reveals the following details regarding its term, application history, and projected expiration date.

Application and Family History

• Divisional Application Status: US patent 11,484,284, which issued from application Ser. No. 17/665,814 (filed February 7, 2022), is a divisional application of U.S. application Ser. No. 17/175,192 (filed February 12, 2021).
• Parent Patent: The parent application, Ser. No. 17/175,192, has issued as US Patent 11,272,900.
• Provisional Priority: Both patents in this family claim the benefit of U.S. Provisional Application Ser. No. 62/976,584, filed on February 14, 2020. This provisional application establishes the priority date for the invention.
• Continuations: There is no record of any continuation or divisional applications that claim priority to US patent 11,484,284.

The patent family consists of the following members:

• US 62/976,584: Provisional application, Filed Feb 14, 2020.
• US 17/175,192: Parent application, Filed Feb 12, 2021 (Now US 11,272,900).
• US 17/665,814: Divisional application, Filed Feb 7, 2022 (Now US 11,484,284).

Patent Term and Expiration

• Standard Term Calculation: The term of a U.S. patent is 20 years from the filing date of the earliest U.S. non-provisional application from which it claims priority. In this case, the earliest non-provisional filing date is that of the parent application (17/175,192), which is February 12, 2021.
• Statutory Expiration Date: Based on the 20-year term, the original statutory expiration date is February 12, 2041.
• Patent Term Adjustment (PTA): There is no indication of any Patent Term Adjustment (PTA) being awarded for this patent. The USPTO may grant PTA to compensate for certain administrative delays during the prosecution of a patent application. In this case, the absence of any adjustment means the term is not extended beyond the standard 20 years.
• Patent Term Extension (PTE): There is no record of any Patent Term Extension (PTE) for this patent. PTE is typically granted to compensate for regulatory review delays (e.g., by the FDA) and is not applicable here.

Projected Expiration Date

Based on the filing date of the earliest related non-provisional application and the absence of any term adjustments, the projected expiration date for US Patent 11,484,284 is February 12, 2041.

Defensive Disclosure and Prior Art Derivations for US 11,484,284

Publication Date: May 1, 2026
Subject: Defensive publication of technical derivations and alternative embodiments related to US patent 11,484,284, "Methods and devices for processing heart sounds."
Purpose: To place in the public domain a series of technical disclosures that expand upon, vary, and apply the core concepts of US patent 11,484,284. This document is intended to serve as prior art against future patent applications for incremental or obvious improvements in the field of acoustic signal processing for physiological monitoring and automated therapy.

---

Derivations of Independent Claim 1: System for Processing Heart Sound Signals

Claim 1 of US 11,484,284 describes a system comprising a phonocardiogram recorder, processor, and display that measures, segments, and extracts acoustic features from heart sounds, using unsupervised machine learning to group the sounds by disease stage and recommend therapy. The following are derivative embodiments.

1. Material & Component Substitution

1.1. Piezoelectric MEMS Sensor Array for Acoustic Recording

• Enabling Description: The phonocardiogram recording device is substituted with a flexible, conformable patch containing an array of Micro-Electro-Mechanical System (MEMS) piezoelectric acoustic sensors. Each sensor in the 2D array (e.g., 8x8) is fabricated on a silicon substrate with a PZT (lead zirconate titanate) thin film. The array provides spatial resolution across the chest, allowing the system to capture sounds from different valve locations simultaneously. A multiplexer (MUX) scans the array, and the signals are fed into a multi-channel analog-to-digital converter (ADC). The processor then uses beamforming algorithms to isolate sound sources, enhancing the signal-to-noise ratio for the target heart valve (e.g., aortic or mitral) and rejecting noise from other physiological sources like respiration or digestion. This component substitution improves signal source separation beyond what a single-point sensor can achieve.

• Diagram:

  graph TD
      subgraph Conformable Patch
          A[MEMS Sensor 1,1] --> MUX;
          B[MEMS Sensor 1,2] --> MUX;
          C[...] --> MUX;
          D[MEMS Sensor 8,8] --> MUX;
      end
      MUX --> ADC[Multi-Channel ADC];
      ADC --> Processor;
      Processor --> DSP{Digital Signal Processor};
      DSP -- Beamforming Algorithm --> Feature_Extraction[Feature Extraction Module];
      Feature_Extraction --> ML[Unsupervised ML Module];
      ML --> Display[Display/Therapy Recommendation];
  

1.2. Neuromorphic Spike-Based Processing Unit

• Enabling Description: The general-purpose processor is replaced with a neuromorphic processing unit (NPU), such as an asynchronous spiking neural network (SNN) hardware accelerator (e.g., Intel Loihi or IBM TrueNorth architecture). The digitized audio signal from the ADC is first converted into a sequence of spikes using a delta modulator. The segmentation and feature extraction steps are implemented as layers within the SNN. The network learns to recognize temporal patterns corresponding to S1 and S2 sounds through spike-timing-dependent plasticity (STDP), an unsupervised learning rule. This approach significantly reduces power consumption, as computation is event-driven (i.e., occurs only when spikes are present), making it ideal for continuous, long-term monitoring in a battery-powered wearable device. The clustering of disease stages is an emergent property of the network's learned representations.

• Diagram:

  sequenceDiagram
      participant ADC
      participant DeltaMod as Delta Modulator
      participant NPU as Neuromorphic Processor (SNN)
      participant Memory as Machine-Readable Medium
  
      ADC->>DeltaMod: Digitized audio stream
      DeltaMod->>NPU: Asynchronous spike train
      NPU->>NPU: Process spikes via STDP
      Note right of NPU: Segmentation and feature extraction occur as emergent properties of the network's learned weights.
      NPU->>Memory: Store learned cluster centroids
      Memory-->>NPU: Load centroids for inference
      NPU->>Display: Output Disease Stage / Recommendation
  

2. Cross-Domain Application

2.1. Aerospace: Acoustic Monitoring of Turbine Blade Health

• Enabling Description: The system is adapted for monitoring the health of jet engine turbine blades during operation. The phonocardiogram recorder is replaced by a set of high-temperature, wide-bandwidth piezoelectric sensors mounted on the engine casing. The "heart sound" is the acoustic signature of the rotating blades. The system segments the continuous acoustic signal based on blade passing frequency, isolating the signature of each blade. Acoustic features extracted include spectral kurtosis, dominant resonance frequencies, and power spectral density in ultrasonic bands. The unsupervised machine learning algorithm (e.g., k-means or DBSCAN) clusters these feature sets to identify deviations from a healthy blade signature, indicating the early formation of micro-cracks or material fatigue. This allows for predictive maintenance before a catastrophic failure occurs.

• Diagram:

  flowchart LR
      subgraph Engine Casing
          S1[Sensor 1]
          S2[Sensor 2]
          S3[Sensor N]
      end
      subgraph Processing Unit
          Processor -- Segmentation by Blade Freq. --> Segments[Blade Signatures]
          Segments -- Feature Extraction --> Features[Spectral Kurtosis, PSD, etc.]
          Features -- Unsupervised Clustering --> Clusters[Health States: Healthy, Warning, Critical]
          Clusters --> Maint[Maintenance Alert System]
      end
      S1 & S2 & S3 --> Processor
  

2.2. AgTech: Non-Invasive Bovine Cardiopulmonary Monitoring

• Enabling Description: The device is reconfigured as a durable bolus that is ingested by cattle and resides in the reticulum, or as a ruggedized ear tag. The acoustic sensor is a robust, waterproof transducer. The system continuously monitors bovine heart and lung sounds. The unsupervised machine learning model is trained to distinguish between normal cardiac and respiratory sounds and signatures indicative of conditions like Bovine Respiratory Disease (BRD) or hardware disease. By analyzing trends in heart rate variability, S1/S2 amplitude ratios, and the presence of wheezing or crackling in the lung sounds, the system can provide early warning of illness for an individual animal, allowing for isolation and treatment before the disease spreads throughout the herd. Data is transmitted wirelessly via a LoRaWAN network to a central farm management system.

• Diagram:

  graph TD
      A[Ear Tag/Bolus Sensor] --> B{Signal Processing};
      B --> C[Feature Extraction (HRV, S1/S2 Ratio, Wheeze Freq)];
      C --> D{Unsupervised ML Classifier};
      D --> E{Health Status};
      E --> F[LoRaWAN TX];
      F --> G((Farm Management Dashboard));
      D -- Anomaly Detected --> E;
      subgraph On-Animal Device
          A
          B
          C
          D
          E
          F
      end
  

2.3. Industrial Manufacturing: Gearbox Fault Prediction

• Enabling Description: The method is applied to predict failures in industrial gearboxes. A vibration sensor (accelerometer) and a high-frequency acoustic sensor are attached to the gearbox housing. The "cardiac cycle" is one full rotation of the primary gear shaft, with a tachometer providing the timing reference for segmentation. The system extracts acoustic and vibrational features such as the energy of gear mesh frequencies and their sidebands, as well as oil-film-induced acoustic emissions. The unsupervised machine learning algorithm clusters the operational states of the gearbox over time. A gradual shift in cluster centroids indicates progressive wear (e.g., pitting, spalling), while a sudden jump indicates an acute fault like a tooth breakage. This provides a real-time health assessment and enables condition-based maintenance.

• Diagram:

  stateDiagram-v2
      [*] --> Healthy
      Healthy --> GradualWear: Feature vector drifts
      GradualWear --> ImpendingFailure: Cluster centroid crosses threshold
      ImpendingFailure --> MaintenanceAlert
      Healthy --> AcuteFault: Sudden feature shift
      GradualWear --> AcuteFault: Sudden feature shift
      AcuteFault --> ShutdownAlert
      MaintenanceAlert --> [*]
      ShutdownAlert --> [*]
  
      note left of Healthy
        Acoustic features
        (e.g., gear mesh sidebands)
        are stable within a defined cluster.
      end note
  

3. Integration with Emerging Tech

3.1. Federated Learning for Privacy-Preserving Model Training

• Enabling Description: To train the unsupervised machine learning model without centralizing sensitive patient heart sound data, a federated learning architecture is employed. Each wearable device (client) runs the segmentation and feature extraction steps locally. It then uses its local data to compute an update to a global clustering model (e.g., updated centroid positions for a k-means model). Only these non-identifiable model updates are encrypted and sent to a central server. The server aggregates the updates from many users (e.g., using Federated Averaging) to create an improved global model, which is then sent back to the clients. This process repeats, allowing the model to learn from a diverse population dataset while raw physiological data never leaves the user's device, thus preserving privacy.

• Diagram:

  sequenceDiagram
      participant Client1 as Wearable Device 1
      participant Client2 as Wearable Device 2
      participant Server
  
      loop Training Round
          Server-->>Client1: Send Global Model
          Server-->>Client2: Send Global Model
          Client1->>Client1: Compute model update on local data
          Client2->>Client2: Compute model update on local data
          Client1-->>Server: Send encrypted model update
          Client2-->>Server: Send encrypted model update
          Server->>Server: Aggregate updates (Federated Averaging)
          Server->>Server: Create new Global Model
      end
  

---

Derivations of Independent Claim 17: Wearable System with Automated Treatment

Claim 17 of US 11,484,284 details a specific wearable system with an integrated treatment device that administers a compound based on real-time analysis of acoustic features like the area under the curve (AUC) of the power spectral density (PSD).

1. Material & Component Substitution

1.1. Transdermal Microneedle Array for Drug Delivery

• Enabling Description: The treatment system, described as a reservoir and administration device, is implemented as a disposable patch containing a microneedle array. The needles are fabricated from a biodegradable polymer (e.g., polylactic-co-glycolic acid, PLGA) and are loaded with the anti-remodeling therapy. The patch is communicatively coupled to the main processing unit. When the processor determines that the PSD's AUC has crossed a predetermined threshold, it sends a signal to an actuator in the patch. The actuator, which can be a micro-pump or a system that applies a small electrical current to trigger electro-responsive polymer needles, initiates the delivery of the drug transdermally. This provides a minimally invasive, painless, and controlled delivery mechanism compared to a conventional pump and catheter.

• Diagram:

  classDiagram
      class ProcessingUnit {
          +analyzeHeartSound()
          +calculatePsdAuc()
          +triggerDelivery()
      }
      class MicroneedlePatch {
          -drugReservoir
          -actuator
          -microneedleArray
          +administerDrug()
      }
      ProcessingUnit "1" -- "1" MicroneedlePatch : sends trigger signal
  

2. Operational Parameter Expansion

2.1. High-Pressure Environment Closed-Loop Decompression Sickness Mitigation

• Enabling Description: The system is adapted for deep-sea divers to monitor cardiac stress and mitigate decompression sickness (DCS). The wearable device is housed in a pressure-resistant titanium casing rated to 30 ATM. The processor analyzes heart sounds for specific acoustic signatures associated with the formation of nitrogen microbubbles in the bloodstream, which can cause cardiac strain and DCS. The extracted feature is not just PSD but also higher-order spectral analysis (bispectrum) to detect non-linearities caused by bubble transit. The reservoir contains a PFO (Perfluorooctane) emulsion, a high-efficiency oxygen carrier. If acoustic markers of high bubble load are detected, the system administers a micro-dose of the PFO emulsion via an integrated intramuscular autoinjector. This enhances off-gassing of nitrogen, providing a real-time, closed-loop intervention to reduce DCS risk during ascent.

• Diagram:

  flowchart TD
      A[Acoustic Sensor in Pressure Housing] --> B{Processor};
      B -- Bispectrum Analysis --> C[Bubble Signature Detection];
      C -- Threshold Exceeded --> D{Trigger Autoinjector};
      D --> E[Administer PFO Emulsion];
      subgraph Diver-Worn System
          A --> B --> C --> D --> E
      end
  

3. Integration with Emerging Tech

3.1. AI-Driven Reinforcement Learning for Therapy Optimization

• Enabling Description: The drug administration logic is controlled by a reinforcement learning (RL) agent running on the device's processor. The "state" is the vector of acoustic features extracted from the heart sound. The "action" is the dosage and timing of the compound administered from the reservoir. The "reward" is a function that positively scores the return of the acoustic features to a predetermined healthy baseline and negatively scores the amount of drug used (to prevent overuse). The RL agent, using an algorithm like Q-learning or Deep Q-Networks (DQN), learns a personalized policy for the patient over time, optimizing the therapy to be maximally effective with minimal dosage by observing the acoustic response to each administration event.

• Diagram:

  graph LR
      State[Acoustic Feature Vector] --> Agent[RL Agent];
      Agent -- Action --> Env[Patient & Treatment System];
      Env -- Reward --> Agent;
      Env -- Next_State --> State;
      subgraph Legend
          direction LR
          State_Def[State: Current heart sound features]
          Action_Def[Action: Drug dosage/timing]
          Reward_Def[Reward: Return to baseline vs. drug cost]
      end
  

3.2. Blockchain for Verifiable Treatment Audit Trail

• Enabling Description: To ensure regulatory compliance and patient safety for the automated treatment system, every critical event is logged as a transaction on a private, permissioned blockchain (e.g., Hyperledger Fabric). When the processor measures a heart sound, a hash of the raw data and the extracted feature vector is created and stored. When a treatment is administered, a new transaction is created containing a timestamp, the feature vector that triggered the event, the dosage administered, and a cryptographic link to the previous transaction. This creates an immutable, tamper-proof, and auditable log of the device's diagnostic and therapeutic actions, which can be securely reviewed by clinicians and regulatory bodies without compromising patient privacy.

• Diagram:

  erDiagram
      BLOCK {
          string BlockHash PK
          string PreviousBlockHash
          string Timestamp
          string MerkleRoot
      }
      TRANSACTION {
          string TxID PK
          string Timestamp
          string FeatureVectorHash
          string Dosage
          string TriggerCondition
      }
      BLOCK ||--o{ TRANSACTION : contains
  

4. The "Inverse" or Failure Mode

4.1. Fail-Safe Administration via "Heartbeat" Signal

• Enabling Description: The drug administration mechanism is designed to be inherently fail-safe. The main processor, in addition to its analytical tasks, generates a continuous, encrypted "heartbeat" signal (e.g., a 1 Hz square wave with a rolling code) as long as it is operating correctly. This signal is sent to a separate, low-power safety microcontroller that directly controls the gate of the administration device (e.g., the power to the pump or microneedle actuator). If this heartbeat signal ceases for any reason—such as the main processor crashing, the device detaching from the skin (leading to a poor signal), or a battery failure—the safety microcontroller immediately and irrevocably shuts down the administration pathway. This prevents any possibility of accidental overdose due to software or hardware failure.

• Diagram:

  sequenceDiagram
      participant MainPU as Main Processor
      participant SafetyMCU as Safety Microcontroller
      participant Actuator as Drug Delivery Actuator
  
      loop Normal Operation
          MainPU->>SafetyMCU: Encrypted Heartbeat Signal
          SafetyMCU->>Actuator: Maintain 'Enable' State
      end
  
      break Main Processor Fails
          MainPU-xSafetyMCU: Heartbeat Signal Stops
          SafetyMCU->>SafetyMCU: Timeout Exceeded
          SafetyMCU-xActuator: De-assert 'Enable' Signal (Fail-Safe)
      end
  

---

Combination Prior Art with Open-Source Standards

1. Integration with TensorFlow Lite for Microcontrollers: The entire signal processing pipeline of US 11,484,284—specifically the sum of squares error segmentation, Fast Fourier Transform for PSD calculation, and k-means clustering algorithm—is implemented using the open-source TensorFlow Lite for Microcontrollers library. The models are quantized to 8-bit integers for execution on a low-power ARM Cortex-M4 microcontroller. This enables the complete system of claim 17 to operate on a coin-cell battery for weeks, making the device smaller and more accessible. The implementation details, including the C++ code for feature extraction and model inference, are hereby disclosed.

2. Integration with HL7 FHIR Standard: The output of the system is formatted according to the Health Level Seven (HL7) Fast Healthcare Interoperability Resources (FHIR) R4 standard. The calculated Power Spectral Density is stored as a DiagnosticReport resource with a series of Observation components representing the power at different frequency bands. The output of the unsupervised machine learning model (the disease stage) is an Observation resource with a LOINC code. The recommendation for therapy (Claim 1) or the record of an automated administration (Claim 17) is captured as a MedicationRequest or MedicationAdministration resource, respectively. This enables plug-and-play interoperability with any compliant Electronic Health Record (EHR) system.

3. Use of MQTT Protocol for Data Telemetry: For applications involving remote monitoring, the wearable device acts as an MQTT client. After local processing, it publishes a JSON payload containing key extracted features (e.g., S1/S2 duration, PSD AUC, dominant frequency, assigned cluster ID) to a specific topic on an MQTT broker. This lightweight, open-source publish/subscribe protocol minimizes bandwidth and battery consumption. A secure connection is established using TLS, and the payload is structured for easy ingestion by cloud-based analytics platforms for longitudinal patient tracking or population health studies. Raw audio data is not transmitted to preserve privacy.