Obviousness

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.