Systems and methods for identifying s3 / s4 sounds in electrocardiogram (ECG) / phonocardiogram (PCG) data

Abstract

Systems and methods for identifying third heart sounds (S3) and fourth heart sounds (S4) within phonocardiogram (PCG) and electrocardiogram (ECG) data are disclosed herein. An example computer-implemented method includes collecting (i) PCG data and (ii) ECG data of a user via a digital stethoscope and applying a cardiac acoustic algorithm to the PCG data and the ECG data to identify an S3 or an S4. The example method further includes extracting a respective portion of the PCG data and the ECG data that includes the S3 or the S4, generating a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data, and causing the GUI to be displayed for viewing by a second user.

Description

Attorney Docket: 33149 / 70207 APATENT APPLICATIONSYSTEMS AND METHODS FOR IDENTIFYING S3 / S4 SOUNDS IN ELECTROCARDIOGRAM (ECG) / PHONOCARDIOGRAM (PCG) DATACROSS REFERENCES TO RELATED APPLICATIONS

[0001] This application claims priority to U.S. Provisional Application No. 63 / 690,695, which was filed on September 4, 2024, and is titled “Systems and Methods for Identifying S3 / S4 Sounds In Electrocardiogram (ECG) / Phonocardiogram (PCG) Data,” the entirety of which is hereby incorporated by reference herein.TECHNICAL FIELD

[0002] The present disclosure generally relates to healthcare monitoring technologies, and more particularly, to systems for enhancing cardiac care through remote patient monitoring and data analysis, such as, the use of algorithms for detecting specific heart sounds and conditions.BACKGROUND

[0003] In the realm of medical diagnostics, particularly cardiovascular health monitoring, the integration of phonocardiogram (PCG) and electrocardiogram (ECG) data has proven essential for comprehensive patient assessment. At-home digital stethoscope technology enables patients to independently acquire ECG or PCG data, leading to potentially more efficient cardiac healthcare by reducing the emphasis on patients physically visiting a healthcare provider’s practicing location. However, despite this benefit, conventional techniques still suffer from several drawbacks.

[0004] Conventionally, the analysis of PCG and ECG data has been conducted separately, requiring healthcare professionals to manually correlate findings from each data set. Even in certain diagnostic configurations where PCG and ECG data are collected simultaneously, healthcare professionals are still required to manually correlate findings between the two data sets (e.g., to determine electromechanical activation time (EMAT)). This separation can lead to inefficiencies and potential inaccuracies in diagnosis due to the disjointed review process. Moreover, conventional systems have lacked effective mechanisms for directly linking specific cardiac events detected in ECG data with corresponding auditory data from PCG recordings, thus complicating the diagnostic process.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0005] Furthermore, existing technologies have faced challenges in efficiently identifying specific cardiac anomalies such as S3 / S4 heart sounds from PCG data and cardiac dysfunction resulting therefrom. Traditional signal analysis techniques often struggle with accurately detecting these subtle acoustic signatures amid the background noise and other cardiac sounds that can prevent further analysis to identify potential / future cardiac dysfunction. This difficulty is compounded by limitations in processing power and algorithmic sophistication, which hinder the automatic identification and annotation of relevant cardiac events. Thus, conventional systems generally lack the ability to effectively identify subtle cardiac anomalies (e.g., S3 / S4 sounds), leading to delayed diagnosis of critical conditions.

[0006] Further complicating all of these issues is the lack of adequate instruction conventionally preventing patients from effectively utilizing a digital stethoscope while at home or otherwise without the supervision of a healthcare provider. Cardiac analysis typically requires precision placement (potentially at multiple sequential locations) of a stethoscope or other audio device to ensure that the sensed / measured data captures the exact physical phenomenon of interest. Misalignment of the stethoscope invariably leads to low-quality signals (e.g., high noise, complete lack of physical phenomena of interest), which results in low-quality and / or otherwise misleading conclusions that overlook crucial data absent from the low-quality signals. Current techniques for guiding a patient to position a digital stethoscope to maximize the quality of cardiac data capture often rely on rudimentary instructions that fail to effectively convey the required adjustments to the user and / or otherwise lack the precision needed for optimal data acquisition. The inability to dynamically adjust recording parameters in response to real-time analysis of cardiac audio data further limits the efficacy of these approaches.

[0007] Therefore, in general, accurate and efficient patient cardiac monitoring is an area of great interest, and conventional techniques can be insufficient for providing such accurate, efficient monitoring. Accordingly, a need exists for techniques that provide users with accurate, efficient patient cardiac monitoring and thereby mitigate the negative effects stemming from inaccurate, inefficient conventional techniques.SUMMARY

[0008] In some aspects, the techniques described herein relate to a computing system including: one or more processors; and one or more memories having stored thereon computer-Attorney Docket: 33149 / 70207 A PATENT APPLICATION executable instructions that, when executed by the one or more processors, cause the computing system to: collect, via a digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user, apply a cardiac acoustic algorithm to the PCG data and the ECG data to identify a third heart sound (S3) or a fourth heart sound (S4), extract a respective portion of the PCG data and the ECG data that includes the S3 or the S4, generate a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data, and cause the GUI to be displayed for viewing by a second user.

[0009] In some aspects, the techniques described herein relate to a computing system, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.

[0010] In some aspects, the techniques described herein relate to a computing system, further including computer-executable instructions that, when executed by the one or more processors, cause the computing system to: apply the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

[0011] In some aspects, the techniques described herein relate to a computing system, further including computer-executable instructions that, when executed by the one or more processors, cause the computing system to: connect to a digital stethoscope configured to collect the PCG data and the ECG data; transmit a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receive the PCG data and the ECG data from the digital stethoscope.

[0012] In some aspects, the techniques described herein relate to a computing system, further including computer-executable instructions that, when executed by the one or more processors, cause the computing system to: (a) receive, via the digital stethoscope, a set of preliminary cardiac data of the user; (b) apply a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and (c) cause the digital stethoscope to display the one or more repositioning instructions for viewing by the user.Attorney Docket: 33149 / 70207 A PATENT APPLICATION

[0013] In some aspects, the techniques described herein relate to a computing system, further including computer-executable instructions that, when executed by the one or more processors, cause the computing system to: iteratively perform actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

[0014] In some aspects, the techniques described herein relate to a computing system, further including computer-executable instructions that, when executed by the one or more processors, cause the computing system to: cause the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

[0015] In some aspects, the techniques described herein relate to a computing system, further including computer-executable instructions that, when executed by the one or more processors, cause the computing system to: receive an input from the second user corresponding to the link; cause a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; and cause the computing device to simultaneously (i) output audio corresponding to the respective portion of the PCG data and (ii) visually indicate the respective portion of the ECG data corresponding to the output audio.

[0016] In some aspects, the techniques described herein relate to a computer-implemented method including: collecting, by one or more processors, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user via a digital stethoscope; applying, by the one or more processors, a cardiac acoustic algorithm to the PCG data and the ECG data to identify a third heart sound (S3) or a fourth heart sound (S4); extracting, by one or more processors, a respective portion of the PCG data and the ECG data that includes the S3 or the S4; generating, by one or more processors, a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; and causing, by one or more processors, the GUI to be displayed for viewing by a second user.

[0017] In some aspects, the techniques described herein relate to a computer-implemented method, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trainedAttorney Docket: 33149 / 70207 A PATENT APPLICATION using a plurality of PCG data and a plurality of training ECG data to output a plurality of trainingS3 data and a plurality of S4 data.

[0018] In some aspects, the techniques described herein relate to a computer-implemented method, further including: applying, by the one or more processors, the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

[0019] In some aspects, the techniques described herein relate to a computer-implemented method, further including: connecting to a digital stethoscope configured to collect the PCG data and the ECG data; transmitting, by the one or more processors, a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receiving the PCG data and the ECG data from the digital stethoscope.

[0020] In some aspects, the techniques described herein relate to a computer-implemented method, further including: (a) receiving, via the digital stethoscope, a set of preliminary cardiac data of the user; (b) applying, by the one or more processors, a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and (c) causing, by the one or more processors, the digital stethoscope to display the one or more repositioning instructions for viewing by the user.

[0021] In some aspects, the techniques described herein relate to a computer-implemented method, further including: iteratively performing actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

[0022] In some aspects, the techniques described herein relate to a computer-implemented method, further including: causing, by the one or more processors, the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

[0023] In some aspects, the techniques described herein relate to a computer-implemented method, further including: receiving, by the one or more processors, an input from the second user corresponding to the link; causing, by the one or more processors, a computing device associated with the second user to render a second GUI including the interactive visualAttorney Docket: 33149 / 70207 APATENT APPLICATION representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; and causing, by the one or more processors, the computing device to simultaneously (i) output audio corresponding to the respective portion of the PCG data and (ii) visually indicate the respective portion of the ECG data corresponding to the output audio.

[0024] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium storing instructions that, when executed by a computer, cause the computer to: collect, via a digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user; apply a cardiac acoustic algorithm to the PCG data and the ECG data to identify a third heart sound (S3) or a fourth heart sound (S4); extract a respective portion of the PCG data and the ECG data that includes the S3 or the S4; generate a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; and cause the GUI to be displayed for viewing by a second user.

[0025] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data, and the instructions, when executed by the computer, further cause the computer to: apply the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

[0026] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium, wherein the instructions, when executed by the computer, further cause the computer to: (a) receive, via a digital stethoscope, a set of preliminary cardiac data of the user; (b) apply a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; (c) cause the digital stethoscope to display the one or more repositioning instructions for viewing by the user; and iteratively perform actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

[0027] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium, wherein the instructions, when executed by the computer, further cause theAttorney Docket: 33149 / 70207 A PATENT APPLICATION computer to: receive an input from the second user corresponding to the link; cause a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; and cause the computing device to simultaneously (i) output audio corresponding to the respective portion of the PCG data and (ii) visually indicate the respective portion of the ECG data corresponding to the output audio.BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The Figures described below depict preferred embodiments for purposes of illustration only. One skilled in the art will readily recognize from the following discussion that alternative embodiments of the systems and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.

[0029] Figure 1 depicts an example computing system in which various embodiments of the present disclosure may be implemented.

[0030] Figure 2A depicts an example repositioning instruction workflow, in accordance with various embodiments described herein.

[0031] Figure 2B depicts an example set of repositioning instruction GUIs, in accordance with various embodiments described herein.

[0032] Figure 3A depicts an example PCG / ECG data extraction and analysis workflow, in accordance with various embodiments described herein.

[0033] Figure 3B depicts an example extracted PCG / ECG data and predicted cardiac dysfunction GUI, in accordance with various embodiments described herein.

[0034] Figure 3C depicts an example data summary GUI, in accordance with various embodiments described herein.

[0035] Figure 3D depicts a first example detailed multi-day report GUI, in accordance with various embodiments described herein.

[0036] Figure 3E depicts a second example detailed multi-day report GUI, in accordance with various embodiments described herein.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0037] Figure 3F depicts a third example detailed multi-day report GUI, in accordance with various embodiments described herein.

[0038] Figure 4A depicts an example interactive GUI generation and audio / visual output workflow, in accordance with various embodiments described herein.

[0039] Figure 4B depicts an example PCG / ECG audio / visual data GUI generation sequence, in accordance with various embodiments described herein.

[0040] Figures 5A-5C depict various flow diagrams representing example computer- implemented methods, in accordance with various embodiments described herein.DETAILED DESCRIPTION

[0041] The present techniques relate to advanced computing systems and methods for enhancing the analysis and interpretation of phonocardiogram (PCG) and electrocardiogram (ECG) data through the use of digital stethoscopes and sophisticated algorithms. These techniques aim to address and overcome several limitations associated with conventional approaches to cardiac health monitoring, particularly in the context of identifying specific cardiac anomalies such as the third (S3) and fourth (S4) heart sounds, and the potential cardiac dysfunctions they may indicate. By integrating simultaneous PCG and ECG data analysis and enabling patients to optimally position stethoscopes for cardiac data capture, the present techniques offer a more comprehensive and efficient approach to cardiac monitoring, which is crucial for early detection and management of cardiac conditions.

[0042] A significant improvement introduced by these techniques is the utilization of a cardiac acoustic algorithm, potentially incorporating ML methodologies, to analyze collected PCG and ECG data. This algorithm is designed to accurately identify the presence of S3 or S4 heart sounds within the data, which are critical markers of potential cardiac dysfunction. By analyzing received cardiac audio data and generating indications of detected S3 / S4 sounds, the system can generate alerts for healthcare professionals, potentially including predictions of cardiac dysfunction associated with these sounds. This capability not only enhances the accuracy of cardiac health monitoring but also streamlines the process by reducing the reliance on manual analysis and interpretation of cardiac audio data. The use of ML algorithms further enables theAttorney Docket: 33149 / 70207 A PATENT APPLICATION system to learn from a wide range of cardiac sound profiles, thereby improving its accuracy and reliability in identifying S3 and S4 sounds.

[0043] In typical systems, S3 / S4 sounds are identified most frequently when evaluated by a medical professional in a clinical environment, but many patients do not visit medical professionals regularly (e.g., weekly, monthly). However, S3 / S4 sounds can indicate potential issues that may develop in between such infrequent visits (e.g., on weekly / monthly timescales), making their early detection paramount. Thus, catching / identifying these S3 / S4 sounds is typically a low probability occurrence at least because the frequency of patient screenings (e.g., PCGs) is very low (less than five per year).

[0044] The present techniques improve the probability of identifying / detecting these S3 / S4 sounds at least by enabling more frequent access to and intelligent analysis of a patient’s PCG / ECG data. By taking more frequent PCGs, each patient has a higher probability of any S3 / S4 sounds being represented / identified within the PCG data over time, which consequently improves patient outcomes by, for example, improving the chances that any S3 / S4 sounds can be detected in sufficient time to be leveraged for appropriate medical intervention. This increased frequency also helps patients receive more tailored care based on the potential evolution of any S3 / S4 sounds over time that may indicate, for example, worsening conditions that require more intense medical attention or improving conditions that may require less intense medical attention.

[0045] Another of the primary improvements introduced by these techniques is the generation of a GUI including interactive links to visual and auditory representations of the PCG and ECG data that allows healthcare professionals (and potentially patients) to simultaneously view and listen to the cardiac data, facilitating a more intuitive and comprehensive analysis. Thus, the GUIs described herein are designed to enhance the user experience by providing visual markers and links for easy access to and interpretation of ECG and PCG data. By categorizing or sorting the data, for instance, chronologically, and generating links that transfer users to interfaces where they can view bioelectric data and listen to cardiac audio data simultaneously, the system offers a more integrated and intuitive approach to cardiac data analysis. These GUIs also support interactive tools for annotating the data, such as marking the occurrence of S3 or S4 sounds, which can be stored alongside the original data for future reference. This interactive andAttorney Docket: 33149 / 70207 APATENT APPLICATION integrated approach to data review therefore enhances the user’s ability to accurately interpret the cardiac data, leading to more informed clinical decisions.

[0046] Furthermore, the techniques described herein include providing positioning adjustment instructions for measuring devices to optimally capture cardiac audio data. Through the use of a positioning algorithm, the system can analyze cardiac audio data and / or user image data to determine the optimal positioning of the measuring device, thereby improving the quality of the captured data. This approach addresses the challenge of ensuring precise placement of digital stethoscopes or other audio devices, which is essential for capturing high-quality cardiac signals. The algorithm provides users with real-time feedback on how to adjust the placement of the digital stethoscope to ensure optimal data quality. By analyzing preliminary cardiac data for noise levels, known frequency amplitudes, and / or other criteria, and / or by analyzing image data of the user to determine potential misplacement of the stethoscope, the algorithm can issue precise repositioning instructions to the user. By iteratively providing instructions, the system ensures that the measuring device is optimally positioned, thereby enhancing the reliability of the captured cardiac audio data.

[0047] These improvements collectively address several key challenges in the field of cardiac health monitoring. By offering a more integrated approach to reviewing cardiac data, enhancing the automatic detection of specific cardiac sounds (e.g., S3 / S4 sounds), and optimizing the capture of cardiac audio data, the techniques described herein significantly improve upon conventional methods. These advancements not only enhance the functionality and efficiency of cardiac health monitoring systems but also contribute to more accurate and timely diagnoses of cardiac conditions. Through the strategic application of these techniques, healthcare professionals can achieve a more comprehensive and nuanced understanding of cardiac health, ultimately leading to improved patient outcomes.

[0048] The techniques of the present disclosure thus also improve the functionality of a computing device (e.g., a hosting server such as a central server) at least by analyzing data in a particular way to enhance the accuracy and efficiency of the computing device. The cardiac acoustic algorithm and positioning algorithm, executing on the computing device, collect, analyze, and utilize PCG / ECG and / or other acoustic data to output repositioning instructions, S3 / S4 detections, and / or predicted cardiac dysfunctions with an accuracy and efficiency notAttorney Docket: 33149 / 70207 A PATENT APPLICATION achieved using conventional techniques. That is, the present disclosure describes improvements in the functioning of the computer itself because the computing device more accurately and efficiently analyzes / utilizes data as a direct result of the cardiac acoustic algorithm and positioning algorithm. This improves over the prior art at least because existing systems are incapable of accurately interpreting S3 / S4 sounds, provide little / no user guidance regarding correct stethoscope placement, utilize highly inefficient manual processes, and / or are otherwise unable to analyze data with the accuracy and efficiency resulting from the disclosed cardiac acoustic algorithm and positioning algorithm.

[0049] Still further, the present disclosure includes specific features other than what is well- understood, routine, conventional activity in the field, or adding unconventional steps that demonstrate, in various embodiments, particular useful applications, e.g., applying a cardiac acoustic algorithm to the PCG data and the ECG data to identify a third heart sound (S3) or a fourth heart sound (S4), extracting a respective portion of the PCG data and the ECG data that includes the S3 or the S4, and / or generating a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data, among others.

[0050] Of course, it should be appreciated that the advantages and technical improvements described above and elsewhere herein are not the only advantages and / or technical improvements that may be realized as a result of the techniques described herein. Other advantages and / or technical improvements to the functioning of a computer itself or other technologies or technical fields may be apparent to one of ordinary skill in the art. Moreover, while described herein primarily in the health care context, the techniques described herein may be readily applied in any suitable field for any suitable purpose.

[0051] To provide a better understanding of the techniques described herein, Figure 1 depicts an example computing environment in which techniques of the present disclosure may be implemented, and Figures 2A-2B illustrate how some of these system components may interact and / or otherwise process data to collect audio data and determine / generate repositioning instructions, and / or other output. Figures 3A-3B illustrate how some of these system components may interact and / or otherwise process data to collect PCG / ECG data, extract portions of the data, and determine / generate S3 / S4 sounds, predicted cardiac dysfunctions,Attorney Docket: 33149 / 70207 APATENT APPLICATION and / or other output. Figures 4A-4B illustrate how some of these system components may interact and / or otherwise process data to dctcrminc / gcncratc GUIs with interactive links, output visual / audio data, and / or other output. Figures 5A-5C illustrate example computer-implemented methods for accurate and efficient patient cardiac monitoring.EXAMPLE COMPUTING SYSTEM

[0052] Figure 1 depicts an example computing system 100 in which various embodiments of the present disclosure may be implemented. Depending on the embodiment, the example computing system 100 may determine / generate S3 / S4 sounds, extracted portions of measured / sensed data, predicted cardiac dysfunctions, positioning instructions, and / or any related values or combinations thereof. Of course, it should be appreciated that, while the various components of the example computing system 100 (e.g., central server 102, computing device 104, external server 106, digital stethoscope 105, etc.) are illustrated in Figure 1 as single components, the example computing system 100 may include multiple (e.g., dozens, hundreds, thousands) of computing devices 104, digital stethoscopes 105, and external servers 106 that are simultaneously connected to the network 108 at any given time.

[0053] Generally, the example computing system 100 includes a central server 102, a computing device 104, a digital stethoscope 105, and an external server 106. Each of the central server 102, the computing device 104, the digital stethoscope 105, and the external server 106 may communicate with the other devices (e.g., transmit data, instructions, etc.) across the network 108. As an example, the computing device 104 and / or the external server 106 may belong to a healthcare provider or hospital, the digital stethoscope 105 may belong to a patient choosing to monitor their cardiac health at-home, and the central server 102 may belong to a cardiac monitoring entity that aggregates / collects data from the digital stethoscope 105 for analysis and potential communication with the healthcare provider or hospital.

[0054] In this example, the patient using the digital stethoscope 105 may perform scans, sets of readings, and / or otherwise collect data (e.g., PCG data, ECG data) that the digital stethoscope 105 uploads to the central server 102. The central server 102 may then receive this data and execute the cardiac acoustic application 102b 1 to generate S3 / S4 sound indications, extracted portions from collected PCG / ECG data, positioning instructions, and / or any other suitable data or combinations thereof based on the data received from the digital stethoscope 105. The centralAttorney Docket: 33149 / 70207 A PATENT APPLICATION server 102 may also make any of the processed data accessible to the healthcare provider via the computing device 104 and / or external server 106, so the healthcare provider may review the data to review the S3 / S4 sounds, extracted portions of the PCG / ECG data, predicted cardiac dysfunction, and / or any other suitable actions or combinations thereof.

[0055] In another example, the computing device 104 and the digital stethoscope 105 may be owned / operated by a patient, the central server 102 may belong to the cardiac monitoring entity, and the external server 106 may belong to the healthcare provider. In this example, the patient may execute the mobile application 104bl of the computing device 104 to operate the device 104 in conjunction with the digital stethoscope 105, capture data using the digital stethoscope 105, and the digital stethoscope 105 and / or the computing device 104 may transmit the data to the central server 102 for further analysis.

[0056] More specifically, the central server 102 includes one or more processors 102a, the memory 102b, and a networking interface 102c. The memory 102b stores executable instructions that are configured to, when executed by the one or more processors 102a, cause the one or more processors 102a to analyze data e.g., PCG / ECG data) received at the central server 102 and output various values (e.g., extracted portions of the data, S3 / S4 sound indications, GUIs, predicted cardiac dysfunctions, etc.). The cardiac acoustic application 102b 1, the cardiac acoustic algorithm 102b2, and the application data 102b4 may all include such executable instructions, as well as other data. The memory 102b may also store additional data and / or databases. It should be appreciated that the central server 102 can include one or multiple computing devices that are co-located or distributed. Additionally, in certain embodiments, the cardiac acoustic application 102b 1 includes the cardiac acoustic algorithm 102b2.

[0057] The central server 102 receives data set 104bl from the computing device 104 connected to the server 102 through a network 108 and processes the data set 104bl in accordance with one or more sets of instructions stored in a memory 102b to output any of the values described herein. The central server 102 executes the cardiac acoustic application 102b 1, which in turn, accesses and applies the cardiac acoustic algorithm 102b2, the positioning algorithm 102b3, and / or the application data 102b4 to the data received from the digital stethoscope 105 and / or the computing device 104. As mentioned, this data generally includes PCG / ECG data corresponding to a particular patient. Some / all of this data and / or outputs of theAttorney Docket: 33149 / 70207 APATENT APPLICATION various algorithms / models of the central server 102 may eventually be stored as part of the application data 102b4 and / or stored in an external storage location (e.g., data set 106b 1 of the external server 106).

[0058] Generally speaking, the digital stethoscope 105 is configured to measure / record data corresponding to the cardiac function of a patient. The digital stethoscope 105 includes one or more processors 105a, one or more memories 105b, a networking interface 105c, and a set of cardiac sensors 105d. The set of cardiac sensors 105d generally convert the acoustic / electrical energy of heart sounds into digital signals, which can then be amplified, filtered, and processed to provide clear and detailed data for clinical analysis and diagnosis. As such, the set of cardiac sensors 105d may generally be or include any suitable sensors configured to capture PCG / ECG data of a patient, such as electrodes, piezoelectric sensors, electret microphones, etc. In certain embodiments, the set of cardiac sensors 105d may include a single sensor, but in other embodiments, the set of cardiac sensors 105d may include two or more sensors.

[0059] In practice, a patient may utilize the digital stethoscope 105 in conjunction with the computing device 104 by executing the mobile application 104bl to connect with the digital stethoscope 105. The patient may then proceed to position the digital stethoscope 105 on their torso to begin a PCG / ECG recording via the set of cardiac sensors 105d. When the patient initiates the PCG / ECG recording, the digital stethoscope 105 may measure / record cardiac acoustic data and cardiac electrical signal data and may preprocess and / or otherwise analyze the data locally via the processors 105a. Additionally, or alternatively, the digital stethoscope 105 may transmit some / all of the data to the computing device 104 and / or the central server 102 for display or further analysis, as described herein. For example, during the PCG / ECG recording, the patient may receive some initial feedback regarding their cardiac health or metrics through the mobile application 104b I executing on the computing device 104. Moreover, the digital stethoscope 105 may simultaneously transmit data in real-time to the central server 102 for analysis via the cardiac acoustic application 102bl and / or any other associated algorithms / instructions (e.g., cardiac acoustic algorithm 102b2).

[0060] As mentioned, when the patient has successfully performed the PCG / ECG data acquisition, the digital stethoscope 105 may transmit the data directly to the central server 102 and / or to the computing device 104 for transmission to the central server 102. Upon receipt, theAttorney Docket: 33149 / 70207 APATENT APPLICATION central server 102 executes the cardiac acoustic application 102b 1 to analyze the received PCG / ECG data. In particular-, the application 102b 1 may cause the processors 102a to execute the cardiac acoustic algorithm 102b2 to analyze the PCG / ECG data.

[0061] The cardiac acoustic application 102b 1 receives the data from the digital stethoscope 105, identifies features (e.g., SI, S2, S3, S4 sounds) within the data, and extracts portions of the data that indicate S3 / S4 sounds and / or predict cardiac dysfunctions indicated by the data by accessing / applying the cardiac acoustic algorithm 102b2 to the PCG / ECG data. The extracted portions of the PCG / ECG data may generally correspond to specific S3 / S4 sounds and / or other sounds (e.g., first heart sounds (SI), second heart sounds (S2), etc.) or signal characteristics that are predicted / estimated to indicate one or more cardiac issues. The predicted cardiac dysfunctions generally indicate one or more dysfunctions (e.g., heart failure, murmurs, stenosis, valve abnormalities, etc.) that may correspond to the extracted portions of PCG / ECG data.

[0062] In any event, the cardiac acoustic algorithm 102b2 analyzes the PCG / ECG data to determine one or more portions / segments of the data that include signal characteristics that exceed certain thresholds and / or arc otherwise abnormal (e.g., otherwise healthy adult patient with an S3 and S4 sound). The cardiac acoustic algorithm 102b2 then determines a suitable beginning and ending for these abnormal portions / segments of the data and extracts the abnormal portions from the larger data file of the PCG / ECG data. At this point, the cardiac acoustic algorithm 102b2 may further annotate the extracted portions with indications of the particular signal characteristics of interest along with an identification of the likely associated cardiac phenomenon. For example, the cardiac acoustic algorithm 102b2 may extract a portion of the PCG / ECG data because the portion includes an S2 sound that has abnormal signal characteristics (e.g., amplitude, power, length of time, etc.). The cardiac acoustic algorithm 102b2 may annotate this portion of the PCG / ECG data with an indication that the particular waveform associated with the S2 sound is an abnormal S2 sound.

[0063] In certain embodiments, the cardiac acoustic algorithm 102b2 determines the SI amplitude and an S3 / S4 amplitude (e.g., in millivolts, millimeters, or other suitable units) included as part of the ECG data and / or the PCG data. Generally, S 1 amplitude is related to contractility of a patient’ s heart. The S3 is caused by a sudden deceleration of blood flow into the left ventricle during early diastole and correlates with left ventricular filling pressures, but asAttorney Docket: 33149 / 70207 APATENT APPLICATION previously mentioned, the S3 (and S4) are typically difficult to hear. The cardiac acoustic algorithm 102b2 may utilize the SI amplitude and the S3 amplitude to confirm the presence of the S3 by comparing the SI amplitude with the S3 amplitude, as a higher S3 / S1 ratio generally indicates a more pronounced S3 sound. In particular, the algorithm 102b2 may determine whether the S3 / S1 amplitude ratio satisfies (e.g., meets or exceeds) a ratio threshold that indicates the presence of the S3. The algorithm 102b2 may use this S3 / S1 ratio to predict various cardiac conditions, such as decompensation where the heart is unable to maintain adequate blood circulation, and which may lead to other conditions e.g., decompensated heart failure).

[0064] The cardiac acoustic algorithm 102b2 may further determine predicted cardiac dysfunctions based on the extracted portions of the PCG / ECG data, as well as confidence values associated with each predicted cardiac dysfunction. In certain embodiments, to determine the predicted cardiac dysfunctions, the cardiac acoustic algorithm 102b2 may utilize the most up to date PCG / ECG data along with historical PCG / ECG data for the patient to analyze trends associated with the patient’s cardiac health over time. For example, the cardiac acoustic algorithm 102b2 may analyze a patient’s cardiac PCG / ECG data over the prior 30 days to determine that the amplitude associated with the patient’s S3 sound is growing steadily (e.g., a “ventricular gallop”), such that the patient may be at risk of experiencing heart failure.Depending on the particular amplitude of the S3 sound in the most recent PCG / ECG data and the rate of increase of the S3 amplitude over the prior 30 days, the cardiac acoustic algorithm 1202b2 may determine a confidence value and / or a predicted timeline associated with the predicted heart failure. Continuing the prior example, the cardiac acoustic algorithm 102b2 may determine that the patient is 85% likely to experience heart failure and / or is at risk of experiencing heart failure within the next six months based on the PCG / ECG data.

[0065] Further, the cardiac acoustic application 102b 1 may be configured to generate GUIs with interactive links associated with the PCG / ECG data from the digital stethoscope 105. In particular, the cardiac acoustic algorithm 102b2 may extract portions of the PCG / ECG data that include abnormalities (e.g., related to S3 / S4 sounds), and the cardiac acoustic application 102b 1 may automatically generate one or more interactive links (e.g., a symbolic link, a hard link, a uniform resource locator (URL)) that may direct the user to the extracted data portions. When the user (e.g., a second user, such as a healthcare professional) interacts (e.g., click, taps, swipes,Attorney Docket: 33149 / 70207 A PATENT APPLICATION gestures, voice command) with the interactive link(s), the application 102b 1 may take the user to another GUI where the user may simultaneously review the relevant portions of the PCG / ECG data.

[0066] For example, the cardiac acoustic algorithm 102b2 may output extracted portions of a patient’s PCG / ECG data indicating that the patient has an S3 sound represented by PCG / ECG data captured at a first position on the patient’s torso and an S4 sound represented by PCG / ECG data captured at a second position on the patient’s torso. The cardiac acoustic application 102bl may receive these extracted portions and automatically generate a first interactive link associated with the S3 sound and a second interactive link associated with the S4 sound. The cardiac acoustic application 102b 1 may display the interactive links within a GUI, and when a second user (e.g., healthcare professional) interacts with the links, the application 102b 1 may follow the links and display the PCG / ECG data representing the S3 sound and / or the PCG / ECG data representing the S4 sound. At this point, the second user may simultaneously hear the PCG data (e.g., cardiac acoustic data) and view the ECG data (e.g., electrical signal data), as well as any annotations provided by the cardiac acoustic algorithm 102b2 (e.g., indicating the S3 / S4 sounds in both the PCG and ECG data). In certain embodiments where the patient experiences multiple abnormalities, the application 102b 1 may generate a single interactive link that includes each of the relevant extracted data portions.

[0067] In certain embodiments, a ML model accessed / utilized as part of the cardiac acoustic algorithm 102b2 is stored in a remote location from the central server 102 (e.g., a cloud-based server). In these embodiments, the cardiac acoustic application 102b 1 accesses the ML model by transmitting inputs (e.g., PCG / ECG data, S3 / S4 sound characteristics) to the cloud-based server. The ML model analyzes the inputs, generates outputs (e.g., extracted / annotated portions of PCG / ECG data, predicted cardiac dysfunctions), and the cloud-based server returns these outputs to the cardiac acoustic application 102b 1.

[0068] More generally, the computing device 104 is or includes any device that is associated with (e.g., owned and / or operated by) a particular entity that may provide data that is transmitted to and / or is otherwise accessible by the central server 102, the digital stethoscope 105, and / or the external server 106 through the network 108. In certain embodiments, the computing device 104 is a personal computing device of the entity / user, such as a smartphone, a tablet, smart glasses, orAttorney Docket: 33149 / 70207 A PATENT APPLICATION any other suitable device or combination of devices (e.g., a smart watch plus a smartphone) with wireless communication capability. In the embodiment of Figure 1, the computing device 104 includes a processor 104a, a memory 104b, a networking interface 104c, and an input / output (VO) interface 104d. The memory 104b stores the mobile application 104b 1 and a positioning algorithm 104b2.

[0069] As mentioned, the mobile application 104bl generally establishes a connection with the digital stethoscope 105 to enable a patient to acquire PCG / ECG data and thereby self-monitor their cardiac health. As part of this connection with the digital stethoscope 105, the mobile application 104b 1 may also execute the positioning algorithm 104b2 to assist the patient with aligning the digital stethoscope 105 on the patient’s torso. The patient may position the digital stethoscope 105 on their torso, and the mobile application 104b 1 may receive initial signals / readings from the stethoscope 105 representing the acoustic / electric properties recorded / measured by the stethoscope 105 at the initial position. The positioning algorithm 104b2 may analyze these properties / signals / readings to determine a set of repositioning instructions that will enable the patient to readily adjust the digital stethoscope’s 105 alignment and thereby record / measure cardiac properties with significantly more clarity / accuracy.

[0070] Typically, PCG / ECG recordings include placing the digital stethoscope 105 (or other suitable device) at multiple locations on a patient’s torso to measure data for specific cardiac function / phenomena. For example, the apex of the heart, typically auscultated at the fifth intercostal space along the midclavicular line, is ideal for detecting mitral valve abnormalities and S3 or S4 heart sounds indicative of heart failure or diastolic dysfunction. The left sternal border, particularly around the second to fourth intercostal spaces, is suitable for assessing aortic and pulmonic valve functions, where systolic murmurs related to aortic stenosis or pulmonic stenosis might be detected. The right sternal border, especially at the second intercostal space, is a key area for evaluating aortic valve issues, such as aortic regurgitation. The Erb's point, located at the third intercostal space left of the sternum, is a strategic location for capturing sounds from multiple heart valves and can be particularly useful for detecting the presence of aortic or pulmonic valve murmurs.

[0071] Thus, at each position, the positioning algorithm 104b2 may assess the signal characteristics captured by the stethoscope 105 to determine whether the patient has adequatelyAttorney Docket: 33149 / 70207 APATENT APPLICATION positioned the stethoscope 105 for data capture. In particular, the positioning algorithm 104b2 may simultaneously analyze audio data associated with a PCG and electrical activity data associated with an ECG to determine whether the patient has adequately positioned the digital stethoscope 105. For example, the positioning algorithm 104b2 may evaluate the signal characteristics at each position the patient may place the digital stethoscope 105 to determine whether excessive ambient or friction noise is present in the PCG data (e.g., indicating low- quality contact with the patient’s skin) and / or whether the PCG data exhibits the presence of the SI and S2 sounds with appropriate amplitude and sharpness, indicating the closure of the heart valves. Further, the positioning algorithm 104b2 may evaluate the ECG data to determine whether the ECG data displays a clear P wave, QRS complex, and T wave in each cardiac cycle, indicating the electrical activity of the heart. The positioning algorithm 104b2 may further determine whether the ECG baseline is stable without significant drift and the amplitude of the QRS complex is consistent, reflecting proper electrode contact and placement.

[0072] Additionally, or alternatively, the positioning algorithm 104b2 may utilize image data corresponding to the patient to determine whether the patient has adequately positioned the stethoscope 105 for each relevant position of the PCG / ECG recording. For example, the mobile application 104bl may request the patient to position the stethoscope 105 on their torso to capture PCG / ECG data at a first position, and the application 104b 1 may cause a camera (e.g., part of the VO interface 104d) of the computing device 104 to capture image data of the patient. The positioning algorithm 104b2 may analyze the image data to determine that the stethoscope 105 is slightly lower and to the right of the ideal location and may generate a specific set of instructions to guide the patient to move the stethoscope 105 head / leads slightly up and to the left. For example, positioning algorithm 104b2 may generate text for display on the VO interface 104d (e.g., a display of the computing device 104) indicating approximate distances for the patient to move the digital stethoscope 105 and / or may include visual indicators of desired positioning on the torso. In certain embodiments, the positioning algorithm 104b2 may overlay an image of the patient with the digital stethoscope 105 with an estimated / predicted optimal location for the digital stethoscope 105 to help the patient visually align the stethoscope 105 in a more optimal location. In certain embodiments, the digital stethoscope 105 and / or the central server 102 may store and / or otherwise execute a positioning algorithm 105b 1, 102b3 to perform the functions described herein.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0073] In certain embodiments, the algorithms (e.g., cardiac acoustic algorithm 102b2, positioning algorithm 102b3) described herein may utilizc / cmploy ML / Al techniques. These machine learning models described herein (e.g., cardiac acoustic algorithm 102b2) may employ supervised learning, which involves identifying patterns in existing data to make predictions about subsequently received data. Specifically, the machine learning models may be “trained” using training data, which includes example inputs and associated example outputs. Based upon the training data, the machine learning models generate a predictive function which maps outputs to inputs and utilize the predictive function to generate machine learning outputs based upon data inputs. The example inputs and example outputs of the training data may include any of the data inputs or machine learning outputs described above. In the exemplary embodiment, a processing element may be trained by providing it with a large sample of data with known characteristics or features. In various embodiments, the implemented machine learning methods and algorithms are directed toward at least one of a plurality of categorizations of machine learning, such as supervised learning.

[0074] In some embodiments, the ML models described herein (e.g., cardiac acoustic algorithm 102b2, positioning algorithm 102b3) employ unsupervised learning, which involves finding meaningful relationships in unorganized data. Unlike supervised learning, unsupervised learning does not involve user-initiated training based upon example inputs with associated outputs / labels. Rather, in unsupervised learning, the machine learning model organizes unlabeled data according to a relationship determined by at least one machine learning method / algorithm employed by the machine learning model. Unorganized data may include any combination of data inputs and / or machine learning outputs, as described above.

[0075] It is to be understood that supervised machine learning and / or unsupervised machine learning may also comprise retraining, relearning, or otherwise updating models with new, or different, information, which may include information received, ingested, generated, or otherwise used over time. Further, it should be appreciated that, as previously mentioned, the machine learning model described herein may be used to output S3 / S4 sounds, predicted cardiac dysfunctions, repositioning instructions, confidence values, and / or any other values, responses, or combinations thereof using artificial intelligence (e.g., a machine learning model of the cardiac acoustic algorithm 102b2 and / or positioning algorithm 102b3) or, in alternative aspects, without using artificial intelligence.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0076] Any of the ML / AI models described herein may utilize any suitable ML / AI model types and / or architectures. For example, the ML models described herein (e.g., cardiac acoustic algorithm 102b2, positioning algorithm 102b3) may utilize a neural network (e.g., convolutional neural network (CNN), recurrent neural network (RNN)), a random forest model, a support vector machine (SVM), a gradient boosting machine (GBM), a decision tree, a k-nearest neighbors algorithm (KNN), and / or any other suitable ML / AI technique or combinations thereof.

[0077] The computing device 104 is communicatively coupled to the central server 102, the digital stethoscope 105, and / or the external server 106. For example, the computing device 104, the central server 102, the digital stethoscope 105, and / or the external server 106 may communicate via USB, Bluetooth, Wi-Fi Direct, Near Field Communication (NFC), etc. For example, the central server 102 may transmit a data object indicating one or more ranked locations, confidence values, entity type data, periods, and / or any other values or combinations thereof to the computing device 104 via the networking interface 102c, which the computing device 104 may receive via the networking interface 104c.

[0078] The external server 106 may be or include computing servers and / or combinations of multiple servers storing data that may be accessed / retrieved by the central server 102 and / or the computing device 104. In certain embodiments, the external server 106 receives data from the central server 102 and / or the computing device 104 and retrieves / accesses information stored in memory 106b for transmission back to the central server 102 and / or the computing device 104. The external server 106 may include a processor 106a, a memory 106b, and a networking interface 106c. It should be appreciated that the external server 106 can include one or multiple computing devices that are co-located or distributed.

[0079] Further, in certain embodiments, the external server 106 includes a data set 106b 1 including data from the computing device 104, the digital stethoscope 105, and / or the central server 102. In one such example, the external server 106 is a server located in and / or otherwise associated with a hospital or other healthcare provider, and the data set 106b 1 includes electronic health records in memory 106b. As another example, the external server 106 serves as a database for some or all of the application data 102b4. In some embodiments, the example computing system 100 does not include the external server 106.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0080] Each of the processors 102a, 104a, 105a, 106a may include any suitable number of processors and / or processor types. For example, the processors 102a, 104a, 105a, 106a may each include one or more CPUs and one or more graphics processing units (GPUs). Generally, each of the processors 102a, 104a, 105a, 106a may be configured to execute software instructions stored in each of the corresponding memories 102b, 104b, 105b, 106b. The memories 102b, 104b, 105b, 106b may each include one or more persistent memories (e.g., a hard drive and / or solid-state memory) and may store one or more applications, modules, and / or models, such as the cardiac acoustic application 102b 1.

[0081] The networking interface 102c may enable the central server 102 to communicate with the computing device 104, the digital stethoscope 105, the external server 106, and / or any other suitable devices or combinations thereof. More specifically, the networking interface 102c enables the central server 102 to communicate with each component of the example computing system 100 across the network 108 through their respective networking interfaces 104c, 105c, 106c. The networking interfaces 102c, 104c, 105c, 106c may support wired or wireless communications, such as USB, Bluetooth, Wi-Fi Direct, Near Field Communication (NFC), etc. The networking interface 102c may enable the central server 102 to communicate with the various components of the example computing system 100 via a wireless communication network such as a fifth-, fourth-, or third-generation cellular network (5G, 4G, or 3G, respectively), a Wi-Fi network (802.11 standards), a WiMAX network, or any other suitable wide area network (WAN), local area network (LAN), or personal area network (PAN), etc.

[0082] Moreover, the network 108 may be a single communication network, or may include multiple communication networks of one or more types (e.g., one or more wired and / or PANs or LANs, and / or one or more WANs such as the Internet). In some embodiments, the network 108 includes multiple, entirely distinct networks (e.g., one or more networks for communications between central server 102 and computing device 104, and a separate, Bluetooth or wireless LAN (WLAN) network for communications between central server 102 and computing device 104, and so on).

[0083] It will be understood that the above disclosure is one example and does not necessarily describe every possible embodiment. As such, it will be further understood that alternate embodiments may include fewer, alternate, and / or additional steps or elements.Attorney Docket: 33149 / 70207 APATENT APPLICATIONEXAMPLE WORKFLOWS AND GRAPHICAL USER INTERFACES (GUIs)

[0084] Figure 2A depicts an example repositioning instruction workflow 200, in accordance with various embodiments described herein. The example repositioning instruction workflow 200 broadly illustrates a sequence of actions, which may be performed by central server 102 (e.g., processor 102a and / or other components of central server 102) of Figure 1, for example, to determine positioning (also referenced herein as “repositioning”) instructions. The example repositioning instruction workflow 200 illustrated in Figure 2A is for the purposes of discussion only, and additional / al ternative repositioning instruction sequences may also, or instead, be utilized.

[0085] The example repositioning instruction workflow 200 includes receiving preliminary cardiac data. The preliminary cardiac data generally represents acoustic / electrical activity data corresponding to a patient’s heart. For example, a patient may intend to take a PCG / ECG with a digital stethoscope (e.g., 105), and may initially place the stethoscope on their torso. This initial placement may not always be optimal, so the stethoscope and / or other devices (e.g., computing device 104) may collect the preliminary cardiac data for a positioning algorithm (e.g., algorithm 102b3) to analyze.

[0086] At block 202 the example repositioning instruction workflow 200 includes analyzing the preliminary cardiac data (e.g., via a positioning algorithm) to determine the repositioning instructions. The repositioning instructions may include any suitable visual, audio, haptic, and / or any other type of feedback or combinations thereof that indicate how the patient should reposition the digital stethoscope to position the stethoscope more optimally on the patient’s torso. For example, the repositioning instructions may include arrows, written instructions, or image overlays displayed on a user interface (e.g., via TO interface 104d), audible instructions, haptic feedback indicating proximity to the optimal location, and / or any other suitable feedback. The repositioning instructions may generally be displayed on a user device (e.g., computing device 104) and / or may be displayed on the digital stethoscope (e.g., digital stethoscope 105) or a combination of both. For example, the user interface of the user device may display arrows or other suitable visual indicators (e.g., color coded instructions or zones), and the digital stethoscope may simultaneously provide haptic feedback that corresponds to the displayedAttorney Docket: 33149 / 70207 APATENT APPLICATION instructions on the user interface to enable the user to quickly evaluate how to reposition the stethoscope.

[0087] In any event, the positioning algorithm may analyze the signal characteristics of the preliminary cardiac data to determine, for example, whether the relevant physical phenomena are adequately represented based on the position of the digital stethoscope on the patient’s torso. As an example, the positioning algorithm may generally evaluate ambient or friction noise levels in the PCG data to determine whether the patient has made good skin contact with the digital stethoscope. At each of the specific locations where a patient is instructed to place the digital stethoscope to perform the PCG / ECG recordings, the specific signal characteristics may vary.

[0088] For example, when the patient is instructed (e.g., by the digital stethoscope, mobile application, or other suitable components described herein) to position the stethoscope near / on the heart apex (or mitral area), the positioning algorithm may compare the amplitude / power of the SI sound to relatively high SI threshold values, as it is generally strongest at this location due to its proximity to the mitral valve. Moreover, in instances where a patient has an S3 sound, the positioning algorithm may also compare the S3 sound signal (if present) to relatively high amplitude / power S3 threshold values, as S3 sounds may also be more easily detected at the heart apex location. The positioning algorithm may also evaluate the clarity of the R wave progression in the ECG signal to determine whether the patient has properly placed the stethoscope on the heart apex.

[0089] As another example, when the patient is instructed (e.g., by the digital stethoscope, mobile application, or other suitable components described herein) to position the stethoscope near / on the left sternal border, the positioning algorithm may compare the amplitude / power of the SI sound and / or an S4 sound (if present) to relatively high respective threshold values. The positioning algorithm may also evaluate the overall consistency of the ECG signal, and evaluate the clarity of the P waves, QRS complexes, and T waves.

[0090] As yet another example, when the patient is instructed (e.g., by the digital stethoscope, mobile application, or other suitable components described herein) to position the stethoscope near / on the right sternal border, the positioning algorithm may compare the amplitude / power of the S2 sound to a relatively high S2 threshold value, as it is generally loud in this area due to itsAttorney Docket: 33149 / 70207 APATENT APPLICATION proximity to the aortic valve. At this position, the positioning algorithm may compare all / portions the ECG signal to a standard ECG signal waveform to determine a distortion level.

[0091] As still another example, when the patient is instructed (e.g., by the digital stethoscope, mobile application, or other suitable components described herein) to position the stethoscope near / on the second left intercostal space, the positioning algorithm may again compare the amplitude / power of the S2 sound to a relatively high S2 threshold value. Similar to the right sternal border, the positioning algorithm may compare all / portions the ECG signal to a standard ECG signal waveform to determine a distortion level.

[0092] As yet another example, when the patient is instructed (e.g., by the digital stethoscope, mobile application, or other suitable components described herein) to position the stethoscope near / on Erb's Point, the positioning algorithm may generally evaluate the quality of the audio data to determine if the noise levels are sufficiently to avoid interference with potential detection of dysfunction such as murmurs associated with both aortic and pulmonic valve issues. The positioning algorithm may compare all / portions the ECG signal to other ECG signals from the other locations to determine that the signal remains clear’ and consistent with the other locations.

[0093] Regardless, when the patient receives the repositioning instructions, the example repositioning instruction workflow 200 includes the patient repositioning the digital stethoscope (block 204) to record / measure updated cardiac data. The updated cardiac data includes the same data types as the preliminary cardiac data (e.g., acoustic / electrical activity data), except that the updated cardiac data is recorded from a different position on the patient’s torso relative to the position where the preliminary cardiac data was recorded. Thus, the updated cardiac data will likely have different signal characteristics than the preliminary cardiac data, such that when the positioning algorithm receives the updated cardiac data (at block 202), the positioning algorithm may determine different repositioning instructions than were determined in response to the preliminary cardiac data.

[0094] As illustrated in Figure 2A, this example repositioning instruction workflow 200 may continue iteratively until the patient has adequately / optimally positioned the digital stethoscope on their torso. Further, this workflow 200 may be performed multiple times for any given PCG / ECG recording, such that the patient may position the stethoscope optimally at each required location.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0095] To better understand the instructions provided as part of the example repositioning instruction workflow 200, Figure 2B depicts an example set of repositioning instruction GUIs 220, in accordance with various embodiments described herein. Each GUI generally represents the types of instruction a patient may receive to position and / or adjust / reposition a digital stethoscope when attempting to perform a PCG / ECG recording.

[0096] The example set of repositioning instruction GUIs 220 includes an initial recording GUI 222 illustrating how the systems described herein may instruct a patient to obtain a first recording as part of a PCG / ECG recording. This initial recording GUI 222 indicates where the patient is intended to position the digital stethoscope, the patient’s current heart rate, and how far into the recording the system has progressed. While recording, the patient may experience several issues that the system will need to correct via instructions (e.g., repositioning instructions).

[0097] For example, many patients fail to make adequate contact between the digital stethoscope and their skin, such that the stethoscope sensors are unable to adequately record the necessary data. As such, the system may determine before / during the recording that the received signals include substantial noise and / or otherwise indicate the patient has not made sufficient skin contact. In this case, the system may provide the patient with the second GUI 224, which instructs the patient to “[p]lace the digital stethoscope on your skin,” “[t]o get a recording, all 3 sensors require contact with skin,” and further provides a visual indication of how the patient may make better contact with the digital stethoscope (as indicated by the arrow).

[0098] As another example, many patients fail to adequately position the digital stethoscope on their torso, such that the stethoscope sensors will not record the intended data and / or will not record the data with sufficient clarity. As such, the system may determine before / during the recording that the received signals do not include the expected signal characteristics and / or otherwise indicate the patient has not properly positioned the stethoscope. In this case, the system may provide the patient with the third GUI 226, which instructs the patient to “[s]lightly adjust the digital stethoscope” and further provides a visual indication of the direction in which the patient should adjust the digital stethoscope (as indicated by the arrow).

[0099] When the patient successfully completes one or more of the PCG / ECG recordings, the system may provide the user with the fourth GUI 228, indicating the patient has completed theAttorney Docket: 33149 / 70207 A PATENT APPLICATION respective recording. The system may then provide the patient with the fifth GUI 230 indicating a subsequent position where the patient is intended to position the digital stethoscope to continue the PCG / ECG recording process. Thus, at each recording position of a PCG / ECG recording, the system may provide one or more GUIs of the example set of repositioning instruction GUIs 220 to help guide the patient to capture high-quality PCG / ECG data.

[0100] After a patient has completed a some / all of a PCG / ECG recording, the digital stethoscope and / or user computing device (e.g., computing device 104) may transmit the PCG / ECG data to a central server (e.g., central server 102) for analysis. Figure 3A depicts an example PCG / ECG data extraction and analysis workflow 300, in accordance with various embodiments described herein. The example PCG / ECG data extraction and analysis workflow 300 broadly illustrates a sequence of actions, which may be performed by central server 102 (e.g., processor 102a and / or other components of central server 102) of Figure 1, for example, to generate / determine S3 / S4 data, extracted portions of the PCG / ECG data, and / or predicted cardiac dysfunctions. The example PCG / ECG data extraction and analysis workflow 300 illustrated in Figure 3A is for the purposes of discussion only, and additional / altemative PCG / ECG data extraction and analysis sequences may also, or instead, be utilized.

[0101] The example PCG / ECG data extraction and analysis workflow 300 includes receiving PCG / ECG data. At block 302, the example PCG / ECG data extraction and analysis workflow 300 further includes analyzing the PCG / ECG data to determine the presence of an S3 sound and / or an S4 sound. When the system (e.g., cardiac acoustic algorithm 102b2) determines the presence of an S3 sound and / or an S4 sound, the example PCG / ECG data extraction and analysis workflow 300 further includes extracting one or more portions of the PCG / ECG data that include the S3 sound and / or the S4 sound (block 304).

[0102] For example, the extracted PCG / ECG data may generally include data similar to the example PCG data 306. This example PCG data 306 includes an S4 sound indication 306al, an SI sound indication 306b 1, an S2 sound indication 306c 1, and an S3 sound indication 306dl. Accordingly, this example PCG data 306 includes at least two cardiac abnormalities (306al, 306dl), as identified by the cardiac acoustic algorithm. The algorithm may also annotate each of the identified phenomena with an indication corresponding to the physical phenomena. For example, the cardiac acoustic algorithm may annotate the S4 sound indication 306al with theAttorney Docket: 33149 / 70207 APATENT APPLICATION annotation “S4” 306a2, the SI sound indication 306b 1 with the annotation “SI” 306b2, the S2 sound indication 306c 1 with the annotation “S2” 306c2, and / or the S3 sound indication 306dl with the annotation “S3” 306d2.

[0103] The system may include this example PCG data 306 and the corresponding ECG data (not shown) in a GUI where a user (e.g., healthcare professional) may review the example PCG data 306 and the corresponding ECG data. Moreover, the cardiac acoustic algorithm may further evaluate the extracted portions of the PCG / ECG data to determine one or more predicted cardiac dysfunctions (optional block 308). As previously mentioned, the cardiac acoustic algorithm may evaluate the signal characteristics of the extracted portions of the PCG / ECG data in conjunction with prior patient data (e.g., historical PCG / ECG data) and / or any other portions of the original PCG / ECG data from which the portions were extracted to determine predicted cardiac dysfunctions.

[0104] For example, the S4 sound is generally caused by the atria contracting forcefully to push blood into a stiff or hypertrophic left ventricle that does not relax properly during diastole. This sound is often associated with conditions such as left ventricular hypertrophy, resulting from long-standing hypertension, ischemic heart disease, and / or aortic stenosis. The presence of an S4 sound suggests that the heart is working harder to fill the ventricles, indicating a potential for heart failure with preserved ejection fraction and / or an overall increased risk of cardiovascular events. Accordingly, the cardiac acoustic algorithm may evaluate the S4 sound indication 306al and determine that the patient likely suffers from diastolic dysfunction, decreased ventricular compliance, and / or other associated cardiac dysfunction(s). The cardiac acoustic algorithm may output this predicted cardiac dysfunction for display along with the PCG / ECG data in a GUI.

[0105] As mentioned, these outputs of the cardiac acoustic algorithm and / or other components may be displayed within a GUI for review by a user (e.g., healthcare professional). Figure 3B depicts an example extracted PCG / ECG data and predicted cardiac dysfunction GUI 320, in accordance with various embodiments described herein. Generally, the example extracted PCG / ECG data and predicted cardiac dysfunction GUI 320 illustrates a variety of data that a patient may track when monitoring their overall health. For example, the example extracted PCG / ECG data and predicted cardiac dysfunction GUI 320 includes a cardiacAttorney Docket: 33149 / 70207 APATENT APPLICATION monitoring section 322, a cardiac prediction section 324, a 30-day general health section 326, and a 30-day symptom section 328.

[0106] The cardiac monitoring section 322 includes a plurality of data that is related to the patient’s cardiac health. For example, the cardiac monitoring section 322 includes indicators corresponding to measurements that exceeded and / or otherwise failed to satisfy one or more thresholds associated with the corresponding metric, such as weight increases, blood pressure, heart rate, etc. As part of these indicators, the GUI 320 includes a PCG subsection 322a that includes interactive links to PCG recordings taken by a patient. Namely, each speaker icon in the PCG subsection 322a is an interactive link that, when a user interacts with the link, causes the system to take the user to a different GUI to review the corresponding PCG / ECG data simultaneously with the actual cardiac acoustic data and electrical activity data from the PCG / ECG recording performed at the time indicated by the interactive link within the PCG subsection 322a.

[0107] As an example, the cardiac monitoring section 322 includes a first PCG recording data set 322b captured at a first time, a second PCG recording data set 322c captured at a second time, and a third PCG recording data set 322d captured at a third time. As illustrated in Figure 3B, the first PCG recording data set 322b includes an indication that the PCG / ECG data captured at the first time may include an S3 sound. Thus, when the user interacts with the interactive link (e.g., speaker icon), the user may view the PCG / ECG data simultaneously to review the suspected S3 sound.

[0108] The second PCG recording data set 322c includes indications that the PCG / ECG data captured at the second time is acoustically normal but is captured when the patient reported a weight increase, high blood pressure, and an elevated heart rate. Thus, when the user interacts with the interactive link (e.g., speaker icon), the user may view the PCG / ECG data simultaneously to validate the “normal” classification.

[0109] The third PCG recording data set 322d includes an indication that the PCG / ECG data captured at the third time may include an S3 sound and an S4 sound and was captured when the patient reported high blood pressure, an elevated heart rate, and an electromechanical activation time (EMAT) greater than 13.8. Thus, when the user interacts with the interactive link (e.g.,Attorney Docket: 33149 / 70207 APATENT APPLICATION speaker icon), the user may view the PCG / ECG data simultaneously to review the suspected S3 / S4 sounds, in view of the additional physiological symptoms experienced by the patient.

[0110] The cardiac prediction section 324 generally includes outputs of the cardiac acoustic algorithm, such as predicted cardiac dysfunctions indicated by the PCG / ECG data represented in the cardiac monitoring section 322 and / or other sections 326, 328. As illustrated in Figure 3B, the cardiac prediction section 324 indicates that the patient may experience a “significant cardiac event within the next 60 days,” and further indicates that the patient should be observed for indications and / or symptoms of multiple cardiac dysfunctions (e.g., heart failure, hypertensive heart disease, etc.). Based on the information presented in the cardiac prediction section 324, the user viewing the example extracted PCG / ECG data and predicted cardiac dysfunction GUI 320 may orient their diagnosis and / or treatment recommendations. As previously mentioned, these predictions may be based on any of the PCG / ECG data represented in the cardiac monitoring section 322 and / or any other data across any suitable time period (e.g., 30 days, 60 days, 6 months, 1 year; etc.).

[0111] The 30-day general health section 326 and the 30-day symptom section 328 generally include a variety of health markers the patient may track along with their PCG / ECG data. For example, the 30-day general health section 326 includes specific weight change values, systolic and diastolic blood pressure differential values, heart rate range values, percentage EMAT range values, and / or a table indicating acceptable ranges for each set of values. The 30-day symptom section 328 includes patient-specified and / or extrapolated quality values associated with a variety of symptoms, including whether the patient experienced coughing, dyspnea, peripheral edema, orthopnea, paroxysmal nocturnal dyspnea, high / low activity level, fatigue, and / or diuretic effectiveness. These values and / or others not shown (e.g., stored in application data 102b4, data set 106b 1) may impact and / or otherwise be utilized by the cardiac acoustic algorithm when evaluating the PCG / ECG data to determine, for example, whether a detected S3 / S4 sound is valid and / or what predicted cardiac dysfunction(s) a patient is likely to be experiencing and / or will experience.

[0112] Figure 3C depicts an example data summary GUI 330, in accordance with various embodiments described herein. The example data summary GUI 330 may generally serve as a comprehensive interface displaying a range of biomedical data associated with a patient / user,Attorney Docket: 33149 / 70207 APATENT APPLICATION that the patient / user may have acquired through devices like a digital stethoscope. Within this GUI 330, various sections arc available to provide a detailed overview of the patient's health status across a data comparison period (e.g., two weeks). The GUI includes a variety of data display sections, including a patient data overview section 331, a data summary section 332, a, escalation data section 333, an EMAT data section 334, a weight change data section 335, a blood pressure data section 336, a Kansas City Cardiomyopathy Questionnaire (KCCQ) section 337, and a symptoms summary section 338.

[0113] The data acquired by the patient / user may facilitate the generation of this (and other) GUI 330, as described herein. For example, the patient / user may acquire data using a digital stethoscope, and the data processing components described herein may interpret this acquired data to determine whether any data contained therein should be escalated for review (e.g., by the patient’s clinical team), which data should be included and / or otherwise indicated as part of this escalation, and which data should be included in the GUI 330.

[0114] The patient data overview 331 may provide a snapshot of key patient / user information (e.g., patient name, ID, gender, date of birth, age, etc.), while the data summary section 332 may provide a summarized interpretation of the recent health data. For example, in the GUI 330, the section 332 indicates that the patient indicated by the section 331 has a variety of data value changes (e.g., EMAT, weight, blood pressure, KCCQ) during the most recent data acquisition. Based on this data represented in the summary section and / or other data, the escalation data section 333 may flag any significant concerns or developments that necessitate further attention or intervention. For example, the section 333 indicates that the patient’s EMAT value may be elevated and that their data may indicate a new S4 sound. The data represented in the escalation section 333 may represent the particular data used to trigger the generation of the GUI 330 and / or any sections therein, and the escalation reasons / logic may be structured reasons / logic for escalating data findings based on certain protocol(s).

[0115] The data summary section 332 may include data from any of the various data sections 334-337, and the systems described herein may generate the data summary section 332 using a variety of triggering rules. For example, the systems described herein may analyze the acquired EMAT data (e.g., in the EMAT data section 334) to determine the average of the last three days with non-zero values. The systems described herein may then determine the EMAT change asAttorney Docket: 33149 / 70207 APATENT APPLICATION the difference between the calculated absolute EMAT value and the baseline average for the patient, where the baseline EMAT may be the moving average of non- zero EMAT values recorded over the previous 14 days for the patient.

[0116] The systems described herein may perform similar analysis and determinations associated with some / all of the data acquired by a patient and / or included as part of the GUI 330. For example, the systems described herein may analyze the patient’s weight trends (e.g., from the weight change data section 335) to determine whether there has been a weight increase of more than 2.5 pounds over the previous 24 hours within the past three days. The systems described herein may also monitor weight changes for increases exceeding 5 pounds over the last three days compared to the prior 7-day period, disregarding zero or non-acquired values to ensure accurate assessments of the patient’s weight fluctuations.

[0117] As another example, the systems described herein may evaluate the patient’s systolic blood pressure (SBP) e.g., from the blood pressure data section 336) by identifying instances where a single-day value exceeds 180mmHg within the last three days. The systems described herein may also signal if there is a single-day SBP value increase equal to or greater than 20 mmHg from the patient's established baseline. The systems described herein may determine the patient’s baseline SBP value as the moving average of non-zero values recorded over the previous 14 days. Of course, while described herein primarily in terms of SBP, the systems described herein may also monitor and / or analyze the patient’s diastolic blood pressure (DBP).

[0118] In yet another example, the systems described herein may identify and report the detection of new atrial fibrillation (Afib) occurrences within the last three days, marking the first instance of Afib being detected in a patient as "new Afib." In certain embodiments, persistent or regular Afib detections by the systems / devices described herein may not be indicated in one of the data sections 334-337 illustrated in the GUI 330. Instead, each individual Afib detection may be visually highlighted on a data plot (e.g., in the set of heart rate data 366 of Figure 3E), providing a detailed representation of the temporal occurrence and frequency of the patient’ s Afib events for comprehensive monitoring and analysis. Moreover, the systems described herein may analyze the patient’s responses to the KCCQ (e.g., in the KCCQ section 337) and may input values from these responses in the event, e.g., one or more of the patient’s responses are less than ten or more from the previous month, presuming the last month KCCQ was captured.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0119] Additionally, the GUI includes specific sections dedicated to different types of data, e.g., that may be most relevant to the escalation of the acquired data and / or the generation of the GUI 330. Each data section {e.g., 334-337) may represent data indicated by and / or otherwise relevant to the data indicated in the sections 332 and / or 333. For example, the EMAT data section 334 indicates data related to the patient’s EMAT values, offering insight into the patient’s cardiac cycle and potential abnormalities. The weight change data section 335 may track fluctuations in the patient's weight across the data comparison period e.g., over the past two weeks) and may provide valuable information for monitoring the patient’s overall health and potential fluid imbalances. The blood pressure data section 336 may highlight trends and patterns in the patient's blood pressure readings, offering insights into their cardiovascular health. The KCCQ section 337 displays the patient's KCCQ score, helping to assess the impact of heart failure on the patient's quality of life. In certain embodiments, the KCCQ section 337 may include the patient’s responses to the 12-Item version of the KCCQ, often referenced as “KCCQ- 12”. Of course, it should be appreciated that the responses and / or other data included as pail of this section 337 may be associated with the patient’s answers to any suitable question set, such as the 23-item version of the KCCQ, and / or any other suitable question set or combinations thereof.

[0120] The symptoms summary section 338 may list any notable symptoms reported by the patient that may have changed over the past two weeks or since the last data acquisition, providing clinicians with a holistic view of the patient's health status and changes in their condition. For example, the section 338 illustrated in Figure 3C indicates that the patient has experienced a variety of simultaneously worsening symptoms in the past 24 hours {e.g., swelling, cough, fatigue), one or more independently worsening symptoms {e.g., cough) in the last seven days, and / or one or more persistent symptoms {e.g., fatigue) in the last seven days. Overall, the GUI 330 offers a user-friendly and comprehensive platform for reviewing and analyzing biomedical data to support informed clinical decision-making and patient care.

[0121] The systems described herein may utilize a variety of logical frameworks to populate the symptoms summary section 338. For example, the systems described herein may analyze symptom questionnaire {e.g., KCCQ) submissions from patients within a 48-hour timeframe and / or within the prior seven days. Initially, the latest response may be compared with the previous response for each symptom, assessing the severity ratings provided. The severity ratings may be from one to three, where one is the lowest severity and three is the highestAttorney Docket: 33149 / 70207 APATENT APPLICATION severity. For example, when a patient is describing their experience coughing over the past 24 hours, a one on the severity scale may correspond to a response “No” to the question “Arc you coughing?” Similarly, if the patient indicates a two in response, that answer may correspond to the response “Some”, and a three in response may correspond to an answer “Frequently.” However, it should be appreciated that the severity ratings described herein are for the purposes of discussion only, and that the systems described herein may utilize any suitable severity rating s / scale.

[0122] In any event, if the severity rating of the latest response is higher than the previous response, the systems described herein may classify the symptom as "Worsening". If the latest response and the previous response are equal and rated as symptomatic (e.g., severity ID / scale = 2 or 3), the systems described herein may classify the symptom as "Persistent" or “Persistence.” If the latest response indicates a lower severity rating than the previous response, the systems described herein may classify the symptom as “Improving” or "Improvement." Subsequently, based on these classifications, the systems described herein may generate an overall symptom summary for each patient, providing a comprehensive evaluation of symptom trends and changes over the specified period, such as depicted in the symptoms summary section 338.

[0123] Depending on the timeframe in which these symptoms are reported, the verbiage populated into the symptoms summary section 338 may change. For example, assume a patient indicates that they have experienced worsening coughing, sleep quality, activity limitation, and / or fatigue, persistent swelling and paroxysmal nocturnal dyspnea (PND), and improved diuretic effectiveness and shortness of breath within the last 24 hours. In this example, the systems described herein may indicate these symptom change types e.g., worsening, persistent, improved) in the section 338 with their related 24-hour timeframe, such as “Symptoms diuretic effectiveness and shortness of breath improved within the last 24 hours.” In another example, assume a patient indicates that they have experienced worsening PND and swelling, persistent activity limitation and shortness of breath, and improved coughing, sleep quality, diuretic effectiveness and fatigue within the last seven days. In this example, the systems described herein may indicate these symptom change types (e.g., worsening, persistent, improved) in the section 338 with their related 24-hour timeframe, such as “Worsening symptoms PND and swelling were reported by patient in the last 7 days.” Of course, it should be appreciated that theAttorney Docket: 33149 / 70207 A PATENT APPLICATION systems described herein may acquire, interpret, and / or generate outputs based on data acquired over any suitable timeframe (e.g., 24 hours, seven days, one month, two months, one year, etc.).

[0124] Figure 3D depicts a first example detailed multi-day report GUI 350, in accordance with various embodiments described herein. The first example detailed multi-day report GUI 350 generally includes a cardio data section 352 and a symptom tracker section 354, which may represent data acquired by the patient during one or more days. The cardio data section 352 may include data related to one or more cardiac-related tests, such as a phonocardiogram, EMAT data collection, and / or Afib determinations.

[0125] For example, the section 352 includes a set of phonocardiogram data elements, represented by the audio file graphical indicators depicted in FIG. 3D. The section may include rows associated with each of the four positions a patient may position a stethoscope (e.g., digital stethoscope) to acquire the PCG data, such as the right upper sternal border (RUSB), the left upper sternal border (LUSB), the left lower sternal border (LLSB), and the apex of the heart (APEX). The indicators in each of the rows may correspond to the presence (e.g., black / active indicators) or absence (e.g., greyed-out / inactive indicators) of PCG data associated with a particular position, and the data may be present or absent for a variety of reasons. As an example, the data represented in the column 4 / 1 (e.g., acquired on April 1st) may have data associated with the third position (LLSB), but none of the first, second, or fourth positions, which may be the result of a patient acquiring the data at the third position and not at the other positions. When a user (e.g., clinical team member) interacts with one of the indicators in the section 352 corresponding with the PCG data, the systems described herein may transition to another interface where the user may view and interact with the corresponding audio and / or visual data of the PCG and / or any corresponding ECG data, as described herein. In certain embodiments, the indicators illustrated in Figure 3D may also correspond to and / or otherwise indicate whether the audio recordings captured by the patient are high-quality audio recordings. For example, a greyed-out indicator may suggest that the patient failed to adequately position the digital stethoscope over the position of interest, and / or the indicators may include a variety of pattemings, gradations, colors, etc. indicating the quality of the recording in addition to the recording’s presence.Attorney Docket: 33149 / 70207 A PATENT APPLICATION

[0126] As also depicted in the section 352 is EMAT data and Afib indications. Similar to the PCG data, the EMAT data may include data corresponding to each of the four positions the user may acquire cardiac data using a stethoscope. The various indications in the EMAT data section may be color coded to visually indicate EMAT values that are in various ranges (e.g., in target, high, very high), and / or may include any other suitable indications or combinations thereof. The Afib indication may generally represent the detected presence (e.g., “1”) or the absence (e.g., “0”) of Afib in the cardiac data acquired by the user. The section 352 may also include a legend below that represents the various visual indications that may apply to the EMAT data.

[0127] The symptom tracker section 354 may include various symptoms a patient may experience, and each symptom may include up to, e.g., two weeks of representative data. The indications associated with each symptom may represent the relative degree to which the patient experienced any particular- symptom on a given day. For example, the cough symptom includes indications from the user regarding the extent to which they experienced coughing on any given day. The first day (e.g., 4 / 1), the user may have indicated that they experienced a “fair” amount of coughing, the second day (e.g., 4 / 2), the user may not have provided any indicated regarding whether they experienced a coughing, and the third day (e.g., 4 / 3), the user may have indicated that they experienced a “good” amount of coughing (e.g., lower than the first day). These indications may have similar implications for the other symptoms represented in the symptom tracker section 354. The symptoms included in the symptom tracker section 354 may include, e.g., cough, breathing, swelling, sleep, gasping at night, activity level, fatigue, and / or fluid pills (e.g., diuretics). Of course, these are for the purposes of discussion only, and the section 354 may include any suitable symptoms, such as medication classes that may be relevant to the patient (e.g., Angiotensin Receptor Neprilysin Inhibitors (ARNIs), beta blockers, Mineralocorticoid Receptor Antagonists (MRAs), and / or SGLT 2 inhibitors).

[0128] Figure 3E depicts a second example detailed multi-day report GUI 360, in accordance with various embodiments described herein. The second example detailed multi-day report GUI 360 generally includes a variety of biometric data a patient may acquire using a digital stethoscope and / or other devices, as described herein, and that may enable the logic associated with the applications described herein to determine when / whether to escalate the data for clinical review. The GUI 360 represents a set of weight data 362, a set of EMAT data 364, a set of heart rate data 366, and a set of blood pressure data 368. Each of these sets of data 362-368 mayAttorney Docket: 33149 / 70207 APATENT APPLICATION represent data taken by the patient over the course of any suitable period of time, such as two weeks.

[0129] The set of data 362-368 may also include various additional indications that accompany the acquired data. The set of weight data 362 may include a set of error bars, which may represent any suitable deviation from the patient’ s ideal weight, average weight, and / or any other suitable weight target. For example, the error bars indicated in the set of weight data 362 may represent deviations from the patient’s target weight by plus or minus two pounds. The set of heart rate data 366 may also include Afib indications {e.g., triangles) that represent measurements that likely indicate the presence of Afib. Additionally, the set of blood pressure data 368 may include graphical indicators associated with the diastolic and systolic blood pressure.

[0130] Figure 3F depicts a third example detailed multi-day report GUI 380, in accordance with various embodiments described herein. The third example detailed multi-day report GUI 380 may generally include results of the patient’s KCCQ and the full clinical notes the clinical team evaluating the patient’s data may have provided. The GUI 380 may thus include a KCCQ data section 382 and a clinical notes section 384.

[0131] The KCCQ data section 382 may include and / or otherwise indicate the patient’s responses to the questions included as part of the KCCQ. For example, the section 382 includes scored rows corresponding to each of physical limitations, social limitations, symptom frequency, quality of life, and overall impact associated with a patient’s cardiomyopathy. Each of these rows may include a prior score {e.g., from a prior day or within the last 48 hours), along with a most recent score {e.g., from the last 24 hours) and some graphical indication of the relative difference between the most recent score and the prior score.

[0132] The clinical notes section 384 may include a set of written notes provided by the clinical review team, which may generally include their determinations associated with the data acquired by the user {e.g., as represented in FIGs. 3A-3F). In certain embodiments, these notes included in the section 384 may be automatically generated by one or more of the models described herein. For example, the systems described herein may utilize a machine learning model or other artificial intelligence model that is trained and / or otherwise configured to intake the various data and / or responses acquired / provided by the user to determine the one or moreAttorney Docket: 33149 / 70207 APATENT APPLICATION notes included in the clinical notes section 384. These outputs that are included in the clinical notes section 384 may also be interpreted by a machine learning model (e.g., a large language model (LLM) or other language model(s)) to inform the logic of the application(s) described herein. For example, the models described herein may interpret the notes included in the section 384 to trigger the data that should be included, e.g., in the data summary section 332, the escalation section 333, and / or any of the other sections 334-338 included as part of the GUI 330.

[0133] As discussed, from this example extracted PCG / ECG data and predicted cardiac dysfunction GUI 320 and / or other data (e.g., from section 352), a user (e.g., healthcare professional) may interact with the interactive links (e.g., speaker icons in the PCG subsection 322a) to transition to a second GUI where the user may simultaneously review the PCG / ECG acoustic data and electrical activity data. Figure 4A depicts an example interactive GUI generation and audio / visual output workflow 400, in accordance with various embodiments described herein. The example interactive GUI generation and audio / visual output workflow 400 broadly illustrates a sequence of actions, which may be performed by central server 102 (e.g., processor 102a and / or other components of central server 102) of Figure I, for example, to generate / determine a second GUI that enables the user to review visual / audio data from one or more PCG / ECG recordings. The example interactive GUI generation and audio / visual output workflow 400 illustrated in Figure 4A is for the purposes of discussion only, and additional / altemative interactive GUI generation and audio / visual output sequences may also, or instead, be utilized.

[0134] The example interactive GUI generation and audio / visual output workflow 400 includes receiving extracted portions of the PCG / ECG data and generating a GUI with interactive links (block 402). For example, the GUI with interactive links may be or include the cardiac monitoring section 404, which is similar to the cardiac monitoring section 322 of Figure 3B. This cardiac monitoring section 404 includes a PCG subsection 404a and has multiple, distinct recordings captured at different times. Namely, the PCG subsection 404a includes, for example, a first PCG recording data set 404b, a second PCG recording data set 404d, and a third PCG recording data set 404d, each of which may be similar to the corresponding data sets in Figure 3B.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0135] The example interactive GUI generation and audio / visual output workflow 400 further includes receiving a user input at block 406 and transitioning the user from the GUI including the cardiac monitoring section 404 to a second GUI. This second GUI generally includes the relevant extracted portions of the PCG / ECG data and provides a visual indication of the electrical activity data and the acoustic data and enables the user to listen to the acoustic data simultaneously (i.e., synchronized) with a tracking animation indicating the portions of the electrical activity data and the acoustic data represented by the audible acoustic data. In response to receiving a second user input at block 408, the example interactive GUI generation and audio / visual output workflow 400 further includes outputting the tracking animation across the visual representation of the electrical activity data and the acoustic data that is synchronized with the audible acoustic data output.

[0136] Figure 4B depicts an example PCG / ECG audio / visual data GUI generation sequence 420, in accordance with various embodiments described herein. The example PCG / ECG audio / visual data GUI generation sequence 420 generally includes a processing module 426 analyzing a set of ECG data 422 and a set of PCG data 424 to output an interactive GUI 428. The processing module 426 includes the cardiac acoustic application 102b 1 and the cardiac acoustic algorithm 102b2 of Figure 1.

[0137] More specifically, the ECG data 422 includes a plurality of signal phenomena 422a-e that are each representative of a corresponding physical phenomenon. For example, the first signal phenomenon 422a represents a P wave corresponding to atrial depolarization, the second signal phenomenon 422b represents a QRS complex corresponding to ventricular depolarization, the third signal phenomenon 422c represents a T wave corresponding to ventricular repolarization, and the fourth signal phenomenon 422d and the fifth signal phenomenon 422e represent a subsequent P wave and QRS complex, respectively. The PCG data 424 also includes a plurality of signal phenomena 424a-f that each correspond to a physical phenomenon. The first signal phenomenon 424a represents an S4 sound, the second signal phenomenon 424b represents an S 1 sound, the third signal phenomenon 424c represents an S2 sound, the fourth signal phenomenon 424d represents an S3 sound, and the fifth signal phenomenon 424e and the sixth signal phenomenon 424f represent subsequent S4 and SI sounds, respectively.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0138] The processing module 426 receives this ECG data 422 and the PCG data 424 and generates the second GUI 428, which includes an ECG trace 430, a PCG trace 432, and an acoustic cardiograph section 435. The ECG trace 430 includes a set of signal phenomena 430a-e and the PCG trace 432 includes a set of signal phenomena 432a-f that are similar’ to the signal phenomena 422a-e, 424a-f. When a user interacts with the second GUI 428, the system may overlay and / or otherwise animate the progression of the ECG trace 430 and the PCG trace 432 in a direction illustrated by the arrow 434 that is synchronized with a replay / playback of the acoustic data represented by the PCG trace 432. In this manner, the user (e.g., healthcare professional) may simultaneously review the PCG / ECG data in conjunction with the audible acoustic data represented by the PCG trace 432.

[0139] Additionally, the user may review the indicated partitions within the acoustic cardiograph section 435, such as the EMAT partition 436, the LVST partition 438, and the LDPT partition 438. The EMAT partition 436 generally indicates the time between the Q wave onset to the mitral component of the SI sound. The LVST partition 438 generally indicates the time between the SI sound to the S2 sound, and the LDPT partition 438 generally indicates the time between the S2 sound and the subsequent Q wave onset. By reviewing these partitions 436-440, the user may quickly determine when such partitions are abnormal and / or otherwise may indicate abnormalities within the data represented and / or otherwise provided by the second GUI 428.EXAMPLE COMPUTER-IMPLEMENTED METHODS

[0140] Figure 5 A depicts a first flow diagram representing an example computer- implemented method 500, in accordance with various embodiments described herein. The method 500 may be implemented by one or more processors of the example computing system 100, such as the processor 102a of central server 102 (e.g., by cardiac acoustic application 102b 1 ), for example.

[0141] The method 500 includes receiving, via a digital stethoscope, a set of preliminary cardiac data of a user (block 502). The method 500 further includes applying a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope (block 504). The method 500 further includes causing the digital stethoscope to display the one or more repositioning instructions for viewing by the user (block 506).Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0142] The method 500 further includes collecting, via the digital stethoscope, (i) PCG data and (ii) ECG data of the user (block 508). The method 500 further includes generating a GUI that includes a link to an interactive visual representation of (i) the PCG data and (ii) the ECG data (block 510). The method 500 further includes causing the GUI to be displayed for viewing by a second user (block 512).

[0143] In certain embodiments, the method 500 further includes applying a cardiac acoustic algorithm to the PCG data and the ECG data to identify an S3 sound and / or an S4 sound; and extracting a respective portion of the PCG data and the ECG data that includes the S3 or the S4 for inclusion in the second GUI. In these embodiments, the cardiac acoustic algorithm is an ML algorithm and / or a ML model utilizing one or more ML models trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data. Additionally, or alternatively, the cardiac acoustic algorithm is an unsupervised ML model utilizing one or more unsupervised ML algorithms.

[0144] In some embodiments, the method 500 further includes applying the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

[0145] In certain embodiments, the method 500 further includes connecting to a digital stethoscope configured to collect the PCG data and the ECG data; transmitting a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receiving the PCG data and the ECG data from the digital stethoscope.

[0146] In some embodiments, the method 500 further includes (a) receiving, via the digital stethoscope, a set of preliminary cardiac data of the user; (b) applying a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and (c) causing the digital stethoscope to display the one or more repositioning instructions for viewing by the user. In certain embodiments, the method 500 further includes iteratively performing actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0147] In certain embodiments, the method 500 further includes causing the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

[0148] In some embodiments, the method 500 further includes receiving an input from the second user corresponding to the link; causing a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the PCG data and (ii) the ECG data; and causing the computing device to simultaneously (i) output audio corresponding to the PCG data and (ii) visually indicate the ECG data corresponding to the output audio.

[0149] Of course, it is to be appreciated that the actions of the method 500 may be performed any suitable number of times, and that the actions described in reference to the method 500 may be performed in any suitable order.

[0150] Figure 5B depicts a second flow diagram representing an example computer- implemented method 520, in accordance with various embodiments described herein. The method 520 may be implemented by one or more processors of the example computing system 100, such as the processor 102a of central server 102 (e.g., by cardiac acoustic application 102b 1), for example.

[0151] The method 520 includes collecting (i) PCG data and (ii) ECG data of a user via a digital stethoscope (block 522). The method 520 further includes applying a cardiac acoustic algorithm to the PCG data and the ECG data to identify an S3 sound and / or an S4 sound (block 524). The method 520 further includes extracting a respective portion of the PCG data and the ECG data that includes the S3 or the S4 (block 526).

[0152] The method 520 further includes generating a GUI that includes a link to an interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data (block 528). The method 520 further includes causing the GUI to be displayed for viewing by a second user (block 530).

[0153] In certain embodiments, the cardiac acoustic algorithm is an ML algorithm and / or a ML model utilizing one or more ML models trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.Attorney Docket: 33149 / 70207 APATENT APPLICATIONAdditionally, or alternatively, the cardiac acoustic algorithm is an unsupervised ML model utilizing one or more unsupcrviscd ML algorithms.

[0154] In some embodiments, the method 520 further includes applying the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

[0155] In certain embodiments, the method 520 further includes connecting to a digital stethoscope configured to collect the PCG data and the ECG data; transmitting a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receiving the PCG data and the ECG data from the digital stethoscope.

[0156] In some embodiments, the method 520 further includes (a) receiving, via the digital stethoscope, a set of preliminary cardiac data of the user; (b) applying a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and (c) causing the digital stethoscope to display the one or more repositioning instructions for viewing by the user. In these embodiments, the method 520 further includes iteratively performing actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

[0157] In certain embodiments, the method 520 further includes causing the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

[0158] In some embodiments, the method 520 further includes receiving an input from the second user corresponding to the link; causing a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; and causing the computing device to simultaneously (i) output audio corresponding to the respective portion of the PCG data and (ii) visually indicate the respective portion of the ECG data corresponding to the output audio.Attorney Docket: 33149 / 70207 A PATENT APPLICATION

[0159] Of course, it is to be appreciated that the actions of the method 520 may be performed any suitable number of times, and that the actions described in reference to the method 520 may be performed in any suitable order.

[0160] Figure 5C depicts a first flow diagram representing an example computer- implemented method 540, in accordance with various embodiments described herein. The method 540 may be implemented by one or more processors of the example computing system 100, such as the processor 102a of central server 102 (e.g., by cardiac acoustic application 102bl), for example.

[0161] The method 540 includes collecting, at one or more processors via a digital stethoscope, (i) PCG data and (ii) ECG data of a user (block 542). The method 540 further includes identifying an S3 sound and / or an S4 sound within the PCG data or the ECG data (block 544). The method 540 further includes generating a first graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the PCG data and (ii) the ECG data for display to a second user (block 546).

[0162] The method 540 further includes receiving an input from the second user corresponding to the link (block 548). The method 540 further includes causing a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the PCG data and (ii) the ECG data (block 550). The method 540 further includes causing the computing device to simultaneously (i) output audio corresponding to the PCG data and (ii) visually indicate the ECG data corresponding to the output audio (block 552).

[0163] In certain embodiments, the method 540 further includes applying a cardiac acoustic algorithm to the PCG data and the ECG data to identify the S3 and / or the S4; and extracting a respective portion of the PCG data and the ECG data that includes the S3 or the S4 for inclusion in the second GUI.

[0164] In some embodiments, the cardiac acoustic algorithm is an ML algorithm and / or a ML model utilizing one or more ML models trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.Additionally, or alternatively, the cardiac acoustic algorithm is an unsupervised ML model utilizing one or more unsupervised ML algorithms.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0165] In certain embodiments, the method 540 further includes applying the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

[0166] In some embodiments, the method 540 further includes connecting to a digital stethoscope configured to collect the PCG data and the ECG data; transmitting a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receiving the PCG data and the ECG data from the digital stethoscope.

[0167] In certain embodiments, the method 540 further includes (a) receiving, via the digital stethoscope, a set of preliminary cardiac data of the user; (b) applying a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and (c) causing the digital stethoscope to display the one or more repositioning instructions for viewing by the user. In some embodiments, the method 540 further includes iteratively performing actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

[0168] In some embodiments, the method 540 further includes causing the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

[0169] Of course, it is to be appreciated that the actions of the method 540 may be performed any suitable number of times, and that the actions described in reference to the method 540 may be performed in any suitable order.EXAMPLES

[0170] Example 1. A computing system comprising: one or more processors; and one or more memories having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computing system to: collect, via a digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user, apply a cardiac acoustic algorithm to the PCG data and the ECG data to identify a third heart sound (S3) or a fourth heart sound (S4), extract a respective portion of the PCG data and the ECG data that includes the S3 or the S4, generate a graphical user interface (GUI) that includes a link to anAttorney Docket: 33149 / 70207 APATENT APPLICATION interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data, and cause the GUI to be displayed for viewing by a second user.

[0171] Example 2. The computing system of example 1, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.

[0172] Example 3. The computing system of any of examples 1 or 2, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: apply the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

[0173] Example 4. The computing system of any of examples 1-3, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: connect to a digital stethoscope configured to collect the PCG data and the ECG data; transmit a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receive the PCG data and the ECG data from the digital stethoscope.

[0174] Example 5. The computing system of example 4, further comprising computerexecutable instructions that, when executed by the one or more processors, cause the computing system to: (a) receive, via the digital stethoscope, a set of preliminary cardiac data of the user;(b) apply a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and(c) cause the digital stethoscope to display the one or more repositioning instructions for viewing by the user.

[0175] Example 6. The computing system of example 5, further comprising computerexecutable instructions that, when executed by the one or more processors, cause the computing system to: iteratively perform actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

[0176] Example 7. The computing system of any of examples 5 or 6, further comprising computer-executable instructions that, when executed by the one or more processors, cause theAttorney Docket: 33149 / 70207 A PATENT APPLICATION computing system to: cause the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

[0177] Example 8. The computing system of any of examples 1-7, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: receive an input from the second user corresponding to the link; cause a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; and cause the computing device to simultaneously (i) output audio corresponding to the respective portion of the PCG data and (ii) visually indicate the respective portion of the ECG data corresponding to the output audio.

[0178] Example 9. The computing system of any of examples 1-8, wherein applying the cardiac acoustic algorithm to identify the S3 / S4 sounds further comprises: determining (i) a first heart sound (SI) amplitude and (ii) an S3 amplitude within the ECG data; and identifying the S3 based on a ratio of the S3 amplitude to the SI amplitude.

[0179] Example 10. A computer-implemented method comprising: collecting, by one or more processors, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user via a digital stethoscope; applying, by the one or more processors, a cardiac acoustic algorithm to the PCG data and the ECG data to identify a third heart sound (S3) or a fourth heart sound (S4); extracting, by one or more processors, a respective portion of the PCG data and the ECG data that includes the S3 or the S4; generating, by one or more processors, a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; and causing, by one or more processors, the GUI to be displayed for viewing by a second user.

[0180] Example 11. The computer-implemented method of example 10, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.

[0181] Example 12. The computer-implemented method of any of examples 10 or 11, further comprising: applying, by the one or more processors, the cardiac acoustic algorithm to the PCGAttorney Docket: 33149 / 70207 APATENT APPLICATION data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

[0182] Example 13. The computer-implemented method of any of examples 10-12, further comprising: connecting to a digital stethoscope configured to collect the PCG data and the ECG data; transmitting, by the one or more processors, a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receiving the PCG data and the ECG data from the digital stethoscope.

[0183] Example 14. The computer-implemented method of example 13, further comprising: (a) receiving, via the digital stethoscope, a set of preliminary cardiac data of the user; (b) applying, by the one or more processors, a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and (c) causing, by the one or more processors, the digital stethoscope to display the one or more repositioning instructions for viewing by the user.

[0184] Example 15. The computer-implemented method of example 14, further comprising: iteratively performing actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

[0185] Example 16. The computer-implemented method of any of examples 14 or 15, further comprising: causing, by the one or more processors, the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

[0186] Example 17. The computer-implemented method of any of examples 10-16, further comprising: receiving, by the one or more processors, an input from the second user corresponding to the link; causing, by the one or more processors, a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; and causing, by the one or more processors, the computing device to simultaneously (i) output audio corresponding to the respective portion of the PCG data and (ii) visually indicate the respective portion of the ECG data corresponding to the output audio.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0187] Example 18. A non-transitory computer-readable medium storing instructions that, when executed by a computer, cause the computer to: collect, via a digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user; apply a cardiac acoustic algorithm to the PCG data and the ECG data to identify a third heart sound (S3) or a fourth heard sound (S4); extract a respective portion of the PCG data and the ECG data that includes the S3 or the S4; generate a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; and cause the GUI to be displayed for viewing by a second user.

[0188] Example 19. The non-transitory computer-readable medium of example 18, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data, and the instructions, when executed by the computer, further cause the computer to: apply the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

[0189] Example 20. The non-transitory computer-readable medium of example 18 or 19, wherein the instructions, when executed by the computer, further cause the computer to: receive an input from the second user corresponding to the link; cause a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; and cause the computing device to simultaneously (i) output audio corresponding to the respective portion of the PCG data and (ii) visually indicate the respective portion of the ECG data corresponding to the output audio.

[0190] Example 21. A computing system comprising: one or more processors; and one or more memories having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computing system to: collect, via a digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user, identify a third heart sound (S3) or a fourth heart sound (S4) within the PCG data or the ECG data, generate a first graphical user interface (GUI) that includes a link to an interactive visual representation ofAttorney Docket: 33149 / 70207 APATENT APPLICATION(i) the PCG data and (ii) the ECG data for display to a second user, receive an input from the second user corresponding to the link, cause a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the PCG data and (ii) the ECG data, and cause the computing device to simultaneously (i) output audio corresponding to the PCG data and (ii) visually indicate the ECG data corresponding to the output audio.

[0191] Example 22. The computing system of example 21, further comprising computerexecutable instructions that, when executed by the one or more processors, cause the computing system to: apply a cardiac acoustic algorithm to the PCG data and the ECG data to identify the S3 or the S4; and extract a respective portion of the PCG data and the ECG data that includes the S3 or the S4 for inclusion in the second GUL

[0192] Example 23. The computing system of example 2, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.

[0193] Example 24. The computing system of any of examples 22 or 23, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: apply the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

[0194] Example 25. The computing system of any of examples 21-24, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: connect to a digital stethoscope configured to collect the PCG data and the ECG data; transmit a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receive the PCG data and the ECG data from the digital stethoscope.

[0195] Example 26. The computing system of example 25, further comprising computerexecutable instructions that, when executed by the one or more processors, cause the computing system to: (a) receive, via the digital stethoscope, a set of preliminary cardiac data of the user;(b) apply a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and(c) cause the digital stethoscope to display the one or more repositioning instructions for viewing by the user.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0196] Example 27. The computing system of example 26, further comprising computer- executable instructions that, when executed by the one or more processors, cause the computing system to: iteratively perform actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

[0197] Example 28. The computing system of any of examples 26 or 27, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: cause the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

[0198] Example 29. A computer-implemented method comprising: collecting, at one or more processors via a digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user; identifying, by the one or more processors, a third heart sound (S3) or a fourth heart sound (S4) within the PCG data or the ECG data; generating, by the one or more processors, a first graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the PCG data and (ii) the ECG data for display to a second user; receiving, by the one or more processors, an input from the second user corresponding to the link; causing, by the one or more processors, a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the PCG data and (ii) the ECG data; and causing, by the one or more processors, the computing device to simultaneously (i) output audio corresponding to the PCG data and (ii) visually indicate the ECG data corresponding to the output audio.

[0199] Example 30. The computer-implemented method of example 29, further comprising: applying, by the one or more processors, a cardiac acoustic algorithm to the PCG data and the ECG data to identify the S3 or the S4; and extracting, by the one or more processors, a respective portion of the PCG data and the ECG data that includes the S3 or the S4 for inclusion in the second GUI.

[0200] Example 31. The computer-implemented method of example 30, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.Attorney Docket: 33149 / 70207 A PATENT APPLICATION

[0201] Example 32. The computer-implemented method of any of examples 30 or 31 , further comprising: applying, by the one or more processors, the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

[0202] Example 33. The computer-implemented method of any of examples 29-32, further comprising: connecting to a digital stethoscope configured to collect the PCG data and the ECG data; transmitting, by the one or more processors, a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receiving the PCG data and the ECG data from the digital stethoscope.

[0203] Example 34. The computer-implemented method of example 33, further comprising: (a) receiving, via the digital stethoscope, a set of preliminary cardiac data of the user; (b) applying, by the one or more processors, a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and (c) causing, by the one or more processors, the digital stethoscope to display the one or more repositioning instructions for viewing by the user.

[0204] Example 35. The computer-implemented method of example 34, further comprising: iteratively performing actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

[0205] Example 36. The computer-implemented method of any of examples 34 or 35, further comprising: causing, by the one or more processors, the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

[0206] Example 37. A non-transitory computer-readable medium storing instructions that, when executed by a computer, cause the computer to: collect, via a digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user; identify a third heart sound (S3) or a fourth heart sound (S4) within the PCG data or the ECG data; generate a first graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the PCG data and (ii) the ECG data for display to a second user; receive an input from the second user corresponding to the link; cause a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the PCG data and (ii)Attorney Docket: 33149 / 70207 A PATENT APPLICATION the ECG data; and cause the computing device to simultaneously (i) output audio corresponding to the PCG data and (ii) visually indicate the ECG data corresponding to the output audio.

[0207] Example 38. The non-transitory computer-readable medium of example 37, wherein the instructions, when executed by the computer, further cause the computer to: apply a cardiac acoustic algorithm to the PCG data and the ECG data to identify the S3 or the S4; and extract a respective portion of the PCG data and the ECG data that includes the S3 or the S4 for inclusion in the second GUI.

[0208] Example 39. The non-transitory computer-readable medium of example 38, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data, and the instructions, when executed by the computer, further cause the computer to: apply the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

[0209] Example 40. The non-transitory computer-readable medium of any of examples 37- 39, wherein the instructions, when executed by the computer, further cause the computer to: (a) receive, via a digital stethoscope, a set of preliminary cardiac data of the user; (b) apply a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; (c) cause the digital stethoscope to display the one or more repositioning instructions for viewing by the user; and iteratively perform actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

[0210] Example 41. A computing system comprising: one or more processors; and one or more memories having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computing system to: (a) receive, via a digital stethoscope, a set of preliminary cardiac data of a user, (b) apply a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope, (c) cause a user device to display the one or more repositioning instructions for viewing by the user, collect, via the digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of the user, generate aAttorney Docket: 33149 / 70207 A PATENT APPLICATION graphical user interface (GUT) that includes a link to an interactive visual representation of (i) the PCG data and (ii) the ECG data, and cause the GUI to be displayed for viewing by a second user.

[0211] Example 42. The computing system of example 41, further comprising computerexecutable instructions that, when executed by the one or more processors, cause the computing system to: apply a cardiac acoustic algorithm to the PCG data and the ECG data to identify a third heart sound (S3) or a fourth heart sound (S4); and extract a respective portion of the PCG data and the ECG data that includes the S3 or the S4 for inclusion in the second GUI.

[0212] Example 43. The computing system of example 42, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.

[0213] Example 44. The computing system of any of examples 42 or 43, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: apply the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

[0214] Example 45. The computing system of any of examples 41-44, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: connect to a digital stethoscope configured to collect the PCG data and the ECG data; transmit a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receive the PCG data and the ECG data from the digital stethoscope.

[0215] Example 46. The computing system of any of examples 41-45, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: iteratively perform actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

[0216] Example 47. The computing system of any of examples 41-46, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: cause the digital stethoscope to provide feedback to the user indicating theAttorney Docket: 33149 / 70207 A PATENT APPLICATION one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

[0217] Example 48. The computing system of any of examples 41-47, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: receive an input from the second user corresponding to the link; cause a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the PCG data and (ii) the ECG data; and cause the computing device to simultaneously (i) output audio corresponding to the PCG data and (ii) visually indicate the ECG data corresponding to the output audio.

[0218] Example 49. A computer-implemented method comprising: (a) receiving, via a digital stethoscope, a set of preliminary cardiac data of a user; (b) applying, by one or more processors, a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; (c) causing, by the one or more processors, a user device to display the one or more repositioning instructions for viewing by the user; collecting, via the digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of the user; generating, by the one or more processors, a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the PCG data and (ii) the ECG data; and causing, by one or more processors, the GUI to be displayed for viewing by a second user.

[0219] Example 50. The computer-implemented method of example 49, further comprising: applying, by the one or more processors, a cardiac acoustic algorithm to the PCG data and the ECG data to identify a third heart sound (S3) or a fourth heart sound (S4); and extracting, by the one or more processors, a respective portion of the PCG data and the ECG data that includes the S3 or the S4 for inclusion in the second GUI, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.

[0220] Example 51. The computer-implemented method of example 50, further comprising: applying, by the one or more processors, the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0221] Example 52. The computer-implemented method of any of examples 49-51 , further comprising: connecting to a digital stethoscope configured to collect the PCG data and the ECG data; transmitting, by the one or more processors, a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receiving the PCG data and the ECG data from the digital stethoscope.

[0222] Example 53. The computer-implemented method of example 52, further comprising: (a) receiving, via the digital stethoscope, a set of preliminary cardiac data of the user; (b) applying, by the one or more processors, a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and (c) causing, by the one or more processors, the digital stethoscope to display the one or more repositioning instructions for viewing by the user.

[0223] Example 54. The computer-implemented method of example 53, further comprising: iteratively performing actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

[0224] Example 55. The computer-implemented method of any of examples 53 or 54, further comprising: causing, by the one or more processors, the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

[0225] Example 56. The computer-implemented method of any of examples 49-55, further comprising: receiving, by the one or more processors, an input from the second user corresponding to the link; causing, by the one or more processors, a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the PCG data and (ii) the ECG data; and causing, by the one or more processors, the computing device to simultaneously (i) output audio corresponding to the PCG data and (ii) visually indicate the ECG data corresponding to the output audio.

[0226] Example 57. A non-transitory computer-readable medium storing instructions that, when executed by a computer, cause the computer to: (a) receive, via a digital stethoscope, a set of preliminary cardiac data of a user; (b) apply a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; (c) cause a user device to display the one or moreAttorney Docket: 33149 / 70207 APATENT APPLICATION repositioning instructions for viewing by the user; collect, via the digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of the user; generate a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the PCG data and (ii) the ECG data; and cause the GUI to be displayed for viewing by a second user.

[0227] Example 58. The non-transitory computer-readable medium of example 57, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data, and the instructions, when executed by the computer, further cause the computer to: apply the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify a third heart sound (S3) or a fourth heart sound (S4) and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

[0228] Example 59. The non-transitory computer-readable medium of any of examples 57 or58, wherein the instructions, when executed by the computer, further cause the computer to: iteratively perform actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

[0229] Example 60. The non-transitory computer-readable medium of any of examples 57-59, wherein the instructions, when executed by the computer, further cause the computer to: receive an input from the second user corresponding to the link; cause a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the PCG data and (ii) the ECG data; and cause the computing device to simultaneously (i) output audio corresponding to the PCG data and (ii) visually indicate the ECG data corresponding to the output audio.ADDITIONAL CONSIDERATIONS

[0230] Throughout this specification, plural instances may implement components, operations, or structures described as a single instance. Although individual operations of one or more methods are illustrated and described as separate operations, one or more of the individual operations may be performed concurrently, and nothing requires that the operations be performed in the order illustrated. Structures and functionality presented as separate components in example configurations may be implemented as a combined structure or component.Similarly, structures and functionality presented as a single component may be implemented asAttorney Docket: 33149 / 70207 APATENT APPLICATION separate components. These and other variations, modifications, additions, and improvements fall within the scope of the subject matter herein.

[0231] The systems and methods described herein are directed to an improvement to computer functionality, and improve the functioning of conventional computers. Additionally, certain embodiments are described herein as including logic or a number of routines, subroutines, applications, or instructions. These may constitute either software (e.g., code embodied on a non-transitory, machine-readable medium) or hardware. In hardware, the routines, etc., are tangible units capable of performing certain operations and may be configured or arranged in a certain manner. In example embodiments, one or more computer systems (e.g., a standalone, client or server computer system) or one or more hardware modules of a computer system (e.g., a processor or a group of processors) may be configured by software (e.g., an application or application portion) as a hardware module that operates to perform certain operations as described herein.

[0232] In various embodiments, a hardware module may be implemented mechanically or electronically. For example, a hardware module may comprise dedicated circuitry or logic that is permanently configured (e.g., as a special-purpose processor, such as a field programmable gate array (FPGA) or an application- specific integrated circuit (ASIC)) to perform certain operations. A hardware module may also comprise programmable logic or circuitry (e.g., as encompassed within a general -purpose processor or other programmable processor) that is temporarily configured by software to perform certain operations. It will be appreciated that the decision to implement a hardware module mechanically, in dedicated and permanently configured circuitry, or in temporarily configured circuitry (e.g., configured by software) may be driven by cost and time considerations.

[0233] Accordingly, the term “hardware module” should be understood to encompass a tangible entity, be that an entity that is physically constructed, permanently configured (e.g., hardwired), or temporarily configured (e.g., programmed) to operate in a certain manner or to perform certain operations described herein. Considering embodiments in which hardware modules are temporarily configured (e.g., programmed), each of the hardware modules need not be configured or instantiated at any one instance in time. For example, where the hardware modules include a general-purpose processor configured using software, the general-purposeAttorney Docket: 33149 / 70207 APATENT APPLICATION processor may be configured as respective different hardware modules at different times. Software may accordingly configure a processor, for example, to constitute a particular hardware module at one instance of time and to constitute a different hardware module at a different instance of time.

[0234] Hardware modules can provide information to, and receive information from, other hardware modules. Accordingly, the described hardware modules may be regarded as being communicatively coupled. Where multiple of such hardware modules exist contemporaneously, communications may be achieved through signal transmission (e.g., over appropriate circuits and buses) that connect the hardware modules. In embodiments in which multiple hardware modules are configured or instantiated at different times, communications between such hardware modules may be achieved, for example, through the storage and retrieval of information in memory structures to which the multiple hardware modules have access. For example, one hardware module may perform an operation and store the output of that operation in a memory device to which it is communicatively coupled. A further hardware module may then, at a later time, access the memory device to retrieve and process the stored output. Hardware modules may also initiate communications with input or output devices, and can operate on a resource (e.g., a collection of information).

[0235] The various operations of example methods described herein may be performed, at least partially, by one or more processors that are temporarily configured (e.g., by software) or permanently configured to perform the relevant operations. Whether temporarily or permanently configured, such processors may constitute processor- implemented modules that operate to perform one or more operations or functions. The modules referred to herein may, in some example embodiments, comprise processor- implemented modules.

[0236] Similarly, the methods or routines described herein may be at least partially processor-implemented. For example, at least some of the operations of a method may be performed by one or more processors or processor- implemented hardware modules. The performance of certain of the operations may be distributed among the one or more processors, not only residing within a single machine, but deployed across a number of machines. In some example embodiments, the processor or processors may be located in a single location (e.g.,Attorney Docket: 33149 / 70207 APATENT APPLICATION within a home environment, an office environment or as a server farm), while in other embodiments the processors may be distributed across a number of locations.

[0237] The performance of certain of the operations may be distributed among the one or more processors, not only residing within a single machine, but deployed across a number of machines. In some example embodiments, the one or more processors or processor-implemented modules may be located in a single geographic location (e.g., within a home environment, an office environment, or a server farm). In other example embodiments, the one or more processors or processor-implemented modules may be distributed across a number of geographic locations.

[0238] It should also be understood that, unless a term is expressly defined in this patent using the sentence “As used herein, the term ‘ ’ is hereby defined to mean...” or a similar sentence, there is no intent to limit the meaning of that term, either expressly or by implication, beyond its plain or ordinary meaning, and such term should not be interpreted to be limited in scope based upon any statement made in any section of this patent (other than the language of the claims). To the extent that any term recited in the claims at the end of this disclosure is referred to in this disclosure in a manner consistent with a single meaning, that is done for sake of clarity only so as to not confuse the reader, and it is not intended that such claim term be limited, by implication or otherwise, to that single meaning.

[0239] Unless specifically stated otherwise, discussions herein using words such as “processing,” “computing,” “calculating,” “determining,” “presenting,” “displaying,” or the like may refer to actions or processes of a machine (e.g., a computer) that manipulates or transforms data represented as physical (e.g., electronic, magnetic, or optical) quantities within one or more memories (e.g., volatile memory, non-volatile memory, or a combination thereof), registers, or other machine components that receive, store, transmit, or display information.

[0240] As used herein any reference to “one embodiment” or “an embodiment” means that a particular element, feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. The appearances of the phrase “in one embodiment” in various places in the specification are not necessarily all referring to the same embodiment.Attorney Docket: 33149 / 70207 APATENT APPLICATION

[0241] As used herein, the terms “comprises,” “comprising,” “includes,” “including,” “has,” “having” or any other variation thereof, arc intended to cover a non-cxclusivc inclusion. For example, a process, method, article, or apparatus that comprises a list of elements is not necessarily limited to only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Further, unless expressly stated to the contrary, “or” refers to an inclusive or and not to an exclusive or. For example, a condition A or B is satisfied by any one of the following: A is true (or present) and B is false (or not present), A is false (or not present) and B is true (or present), and both A and B are true (or present).

[0242] In addition, use of the “a” or “an” are employed to describe elements and components of the embodiments herein. This is done merely for convenience and to give a general sense of the description. This description, and the claims that follow, should be read to include one or at least one and the singular also may include the plural unless it is obvious that it is meant otherwise.

[0243] Upon reading this disclosure, those of skill in the ail will appreciate still additional alternative structural and functional designs through the principles disclosed herein. Therefore, while particular embodiments and applications have been illustrated and described, it is to be understood that the disclosed embodiments are not limited to the precise construction and components disclosed herein. Various modifications, changes and variations, which will be apparent to those skilled in the art, may be made in the arrangement, operation and details of the method and apparatus disclosed herein without departing from the spirit and scope defined in the appended claims.

[0244] The patent claims at the end of this patent application are not intended to be construed under 35 U.S.C. § 112(f) unless traditional means-plus-function language is expressly recited, such as “means for” or “step for” language being explicitly recited in the claim(s).

Claims

Attorney Docket: 33149 / 70207 APATENT APPLICATIONCLAIMSWhat is claimed is:Identifying S3 / S4 Sounds Within PCG / ECG Data1. A computing system comprising: one or more processors; and one or more memories having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computing system to: collect, via a digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user, apply a cardiac acoustic algorithm to the PCG data and the ECG data to identify a third heart sound (S3) or a fourth heart sound (S4), extract a respective portion of the PCG data and the ECG data that includes the S3 or the S4, generate a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data, and cause the GUI to be displayed for viewing by a second user.

2. The computing system of claim 1, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.

3. The computing system of claim 1, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: apply the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

4. The computing system of claim 1, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: connect to a digital stethoscope configured to collect the PCG data and the ECG data;Attorney Docket: 33149 / 70207 APATENT APPLICATION transmit a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receive the PCG data and the ECG data from the digital stethoscope.

5. The computing system of claim 4, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to:(a) receive, via the digital stethoscope, a set of preliminary cardiac data of the user;(b) apply a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and(c) cause the digital stethoscope to display the one or more repositioning instructions for viewing by the user.

6. The computing system of claim 5, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: iteratively perform actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

7. The computing system of claim 5, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: cause the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

8. The computing system of claim 1, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: receive an input from the second user corresponding to the link; cause a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; andAttorney Docket: 33149 / 70207 APATENT APPLICATION cause the computing device to simultaneously (i) output audio corresponding to the respective portion of the PCG data and (ii) visually indicate the respective portion of the ECG data corresponding to the output audio.

9. The computing system of claim 1, wherein applying the cardiac acoustic algorithm to identify the S3 / S4 sounds further comprises: determining (i) a first heart sound (SI) amplitude and (ii) an S3 amplitude within the ECG data; and identifying the S3 based on a ratio of the S3 amplitude to the SI amplitude.

10. A computer-implemented method comprising: collecting, by one or more processors, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user via a digital stethoscope; applying, by the one or more processors, a cardiac acoustic algorithm to the PCG data and the ECG data to identify a third heart sound (S3) or a fourth heart sound (S4); extracting, by one or more processors, a respective portion of the PCG data and the ECG data that includes the S3 or the S4; generating, by one or more processors, a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; and causing, by one or more processors, the GUI to be displayed for viewing by a second user.

11. The computer-implemented method of claim 10, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.

12. The computer-implemented method of claim 10, further comprising: applying, by the one or more processors, the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.Attorney Docket: 33149 / 70207 APATENT APPLICATION13. The computer-implemented method of claim 10, further comprising: connecting to a digital stethoscope configured to collect the PCG data and the ECG data; transmitting, by the one or more processors, a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receiving the PCG data and the ECG data from the digital stethoscope.

14. The computer-implemented method of claim 13, further comprising:(a) receiving, via the digital stethoscope, a set of preliminary cardiac data of the user;(b) applying, by the one or more processors, a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and(c) causing, by the one or more processors, the digital stethoscope to display the one or more repositioning instructions for viewing by the user.

15. The computer-implemented method of claim 14, further comprising: iteratively performing actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

16. The computer-implemented method of claim 14, further comprising: causing, by the one or more processors, the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

17. The computer- implemented method of claim 10, further comprising: receiving, by the one or more processors, an input from the second user corresponding to the link; causing, by the one or more processors, a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; andAttorney Docket: 33149 / 70207 APATENT APPLICATION causing, by the one or more processors, the computing device to simultaneously (i) output audio corresponding to the respective portion of the PCG data and (ii) visually indicate the respective portion of the ECG data corresponding to the output audio.

18. A non-transitory computer-readable medium storing instructions that, when executed by a computer, cause the computer to: collect, via a digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user; apply a cardiac acoustic algorithm to the PCG data and the ECG data to identify a third heart sound (S3) or a fourth heart sound (S4); extract a respective portion of the PCG data and the ECG data that includes the S3 or the S4; generate a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; and cause the GUI to be displayed for viewing by a second user.

19. The non-transitory computer-readable medium of claim 18, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data, and the instructions, when executed by the computer, further cause the computer to: apply the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

20. The non-transitory computer-readable medium of claim 18, wherein the instructions, when executed by the computer, further cause the computer to: receive an input from the second user corresponding to the link; cause a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the respective portion of the PCG data and (ii) the respective portion of the ECG data; andAttorney Docket: 33149 / 70207 APATENT APPLICATION cause the computing device to simultaneously (i) output audio corresponding to the respective portion of the PCG data and (ii) visually indicate the respective portion of the ECG data corresponding to the output audio.Attorney Docket: 33149 / 70207 APATENT APPLICATIONGenerating GUIs with Interactive Links to Simultaneously Review PCG / ECG Data21. A computing system comprising: one or more processors; and one or more memories having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computing system to: collect, via a digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user, identify a third heart sound (S3) or a fourth heart sound (S4) within the PCG data or the ECG data, generate a first graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the PCG data and (ii) the ECG data for display to a second user, receive an input from the second user corresponding to the link, cause a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the PCG data and (ii) the ECG data, and cause the computing device to simultaneously (i) output audio corresponding to the PCG data and (ii) visually indicate the ECG data corresponding to the output audio.

22. The computing system of claim 21, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: apply a cardiac acoustic algorithm to the PCG data and the ECG data to identify the S3 or the S4; and extract a respective portion of the PCG data and the ECG data that includes the S3 or the S4 for inclusion in the second GUI.

23. The computing system of claim 22, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.Attorney Docket: 33149 / 70207 APATENT APPLICATION24. The computing system of claim 22, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: apply the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

25. The computing system of claim 21, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: connect to a digital stethoscope configured to collect the PCG data and the ECG data; transmit a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receive the PCG data and the ECG data from the digital stethoscope.

26. The computing system of claim 25, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to:(a) receive, via the digital stethoscope, a set of preliminary cardiac data of the user;(b) apply a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and(c) cause the digital stethoscope to display the one or more repositioning instructions for viewing by the user.

27. The computing system of claim 26, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: iteratively perform actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

28. The computing system of claim 26, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: cause the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.Attorney Docket: 33149 / 70207 APATENT APPLICATION29. A computer-implemented method comprising: collecting, at one or more processors via a digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user; identifying, by the one or more processors, a third heart sound (S3) or a fourth heart sound (S4) within the PCG data or the ECG data; generating, by the one or more processors, a first graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the PCG data and (ii) the ECG data for display to a second user; receiving, by the one or more processors, an input from the second user corresponding to the link; causing, by the one or more processors, a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the PCG data and (ii) the ECG data; and causing, by the one or more processors, the computing device to simultaneously (i) output audio corresponding to the PCG data and (ii) visually indicate the ECG data corresponding to the output audio.

30. The computer-implemented method of claim 29, further comprising: applying, by the one or more processors, a cardiac acoustic algorithm to the PCG data and the ECG data to identify the S3 or the S4; and extracting, by the one or more processors, a respective portion of the PCG data and the ECG data that includes the S3 or the S4 for inclusion in the second GUI.

31. The computer- implemented method of claim 30, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.

32. The computer- implemented method of claim 30, further comprising:Attorney Docket: 33149 / 70207 APATENT APPLICATION applying, by the one or more processors, the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

33. The computer-implemented method of claim 29, further comprising: connecting to a digital stethoscope configured to collect the PCG data and the ECG data; transmitting, by the one or more processors, a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receiving the PCG data and the ECG data from the digital stethoscope.

34. The computer-implemented method of claim 33, further comprising:(a) receiving, via the digital stethoscope, a set of preliminary cardiac data of the user;(b) applying, by the one or more processors, a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and(c) causing, by the one or more processors, the digital stethoscope to display the one or more repositioning instructions for viewing by the user.

35. The computer-implemented method of claim 34, further comprising: iteratively performing actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

36. The computer-implemented method of claim 34, further comprising: causing, by the one or more processors, the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

37. A non-transitory computer-readable medium storing instructions that, when executed by a computer, cause the computer to: collect, via a digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of a user;Attorney Docket: 33149 / 70207 APATENT APPLICATION identify a third heart sound (S3) or a fourth heart sound (S4) within the PCG data or the ECG data; generate a first graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the PCG data and (ii) the ECG data for display to a second user; receive an input from the second user corresponding to the link; cause a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the PCG data and (ii) the ECG data; and cause the computing device to simultaneously (i) output audio corresponding to the PCG data and (ii) visually indicate the ECG data corresponding to the output audio.

38. The non-transitory computer-readable medium of claim 37, wherein the instructions, when executed by the computer, further cause the computer to: apply a cardiac acoustic algorithm to the PCG data and the ECG data to identify the S3 or the S4; and extract a respective portion of the PCG data and the ECG data that includes the S3 or the S4 for inclusion in the second GUI.

39. The non-transitory computer-readable medium of claim 38, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data, and the instructions, when executed by the computer, further cause the computer to: apply the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

40. The non-transitory computer-readable medium of claim 37, wherein the instructions, when executed by the computer, further cause the computer to:(a) receive, via a digital stethoscope, a set of preliminary cardiac data of the user;(b) apply a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope;Attorney Docket: 33149 / 70207 A PATENT APPLICATION(c) cause the digital stethoscope to display the one or more repositioning instructions for viewing by the user; and iteratively perform actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.Attorney Docket: 33149 / 70207 APATENT APPLICATIONGenerating and Providing Digital Stethoscope Position Adjustments41. A computing system comprising: one or more processors; and one or more memories having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computing system to:(a) receive, via a digital stethoscope, a set of preliminary cardiac data of a user,(b) apply a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope,(c) cause a user device to display the one or more repositioning instructions for viewing by the user, collect, via the digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of the user, generate a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the PCG data and (ii) the ECG data, and cause the GUI to be displayed for viewing by a second user.

42. The computing system of claim 41, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: apply a cardiac acoustic algorithm to the PCG data and the ECG data to identify a third heart sound (S3) or a fourth heart sound (S4); and extract a respective portion of the PCG data and the ECG data that includes the S3 or the S4 for inclusion in the second GUI.

43. The computing system of claim 42, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.

44. The computing system of claim 42, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to:Attorney Docket: 33149 / 70207 A PATENT APPLICATION apply the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

45. The computing system of claim 41, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: connect to a digital stethoscope configured to collect the PCG data and the ECG data; transmit a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receive the PCG data and the ECG data from the digital stethoscope.

46. The computing system of claim 41, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: iteratively perform actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

47. The computing system of claim 41, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: cause the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

48. The computing system of claim 41, further comprising computer-executable instructions that, when executed by the one or more processors, cause the computing system to: receive an input from the second user corresponding to the link; cause a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the PCG data and (ii) the ECG data; and cause the computing device to simultaneously (i) output audio corresponding to the PCG data and (ii) visually indicate the ECG data corresponding to the output audio.

49. A computer-implemented method comprising:(a) receiving, via a digital stethoscope, a set of preliminary cardiac data of a user;Attorney Docket: 33149 / 70207 A PATENT APPLICATION(b) applying, by one or more processors, a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope;(c) causing, by the one or more processors, a user device to display the one or more repositioning instructions for viewing by the user; collecting, via the digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of the user; generating, by the one or more processors, a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the PCG data and (ii) the ECG data; and causing, by one or more processors, the GUI to be displayed for viewing by a second user.

50. The computer-implemented method of claim 49, further comprising: applying, by the one or more processors, a cardiac acoustic algorithm to the PCG data and the ECG data to identify a third heart sound (S3) or a fourth heart sound (S4); and extracting, by the one or more processors, a respective portion of the PCG data and the ECG data that includes the S3 or the S4 for inclusion in the second GUI, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.

51. The computer-implemented method of claim 50, further comprising: applying, by the one or more processors, the cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify the S3 or the S4 and (ii) output a predicted cardiac dysfunction based on the S3 or the S4.

52. The computer-implemented method of claim 49, further comprising: connecting to a digital stethoscope configured to collect the PCG data and the ECG data; transmitting, by the one or more processors, a control instruction that causes the digital stethoscope to collect the PCG data and the ECG data; and receiving the PCG data and the ECG data from the digital stethoscope.Attorney Docket: 33149 / 70207 APATENT APPLICATION53. The computer-implemented method of claim 52, further comprising:(a) receiving, via the digital stethoscope, a set of preliminary cardiac data of the user;(b) applying, by the one or more processors, a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope; and(c) causing, by the one or more processors, the digital stethoscope to display the one or more repositioning instructions for viewing by the user.

54. The computer-implemented method of claim 53, further comprising: iteratively performing actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

55. The computer- implemented method of claim 53, further comprising: causing, by the one or more processors, the digital stethoscope to provide feedback to the user indicating the one or more repositioning instructions, the feedback including at least one of (i) haptic feedback or (ii) audio feedback.

56. The computer-implemented method of claim 49, further comprising: receiving, by the one or more processors, an input from the second user corresponding to the link; causing, by the one or more processors, a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the PCG data and (ii) the ECG data; and causing, by the one or more processors, the computing device to simultaneously (i) output audio corresponding to the PCG data and (ii) visually indicate the ECG data corresponding to the output audio.

57. A non-transitory computer-readable medium storing instructions that, when executed by a computer, cause the computer to:(a) receive, via a digital stethoscope, a set of preliminary cardiac data of a user;Attorney Docket: 33149 / 70207 APATENT APPLICATION(b) apply a positioning algorithm to the set of preliminary cardiac data to determine one or more repositioning instructions indicating how the user should reposition the digital stethoscope;(c) cause a user device to display the one or more repositioning instructions for viewing by the user; collect, via the digital stethoscope, (i) phonocardiogram (PCG) data and (ii) electrocardiogram (ECG) data of the user; generate a graphical user interface (GUI) that includes a link to an interactive visual representation of (i) the PCG data and (ii) the ECG data; and cause the GUI to be displayed for viewing by a second user.

58. The non-transitory computer-readable medium of claim 57, wherein the instructions, when executed by the computer, further cause the computer to: apply a cardiac acoustic algorithm to the PCG data and the ECG data to (i) identify a third heart sound (S3) or a fourth heart sound (S4) and (ii) output a predicted cardiac dysfunction based on the S3 or the S4, wherein the cardiac acoustic algorithm is a machine learning (ML) algorithm trained using a plurality of PCG data and a plurality of training ECG data to output a plurality of training S3 data and a plurality of S4 data.

59. The non-transitory computer-readable medium of claim 57, wherein the instructions, when executed by the computer, further cause the computer to: iteratively perform actions (a)-(c) until the positioning algorithm determines that an audio characteristic of the set of preliminary cardiac data satisfies an audio threshold.

60. The non-transitory computer-readable medium of claim 57, wherein the instructions, when executed by the computer, further cause the computer to: receive an input from the second user corresponding to the link; cause a computing device associated with the second user to render a second GUI including the interactive visual representation of (i) the PCG data and (ii) the ECG data; andAttorney Docket: 33149 / 70207 A PATENT APPLICATION cause the computing device to simultaneously (i) output audio corresponding to the PCG data and (ii) visually indicate the ECG data corresponding to the output audio.

Images