Method and system for generating likelihood of heart failure with preserved ejection fraction (HFpEF)

Abstract

1. A method for providing a visualized likelihood of heart failure with preserved ejection fraction (HFpEF) for a subject, the method comprising: (i) receiving (120) results of an ultrasound analysis of the subject's heart; (ii) extracting (130) a plurality of ultrasound biomarkers from the received ultrasound analysis; (iii) receiving (122) cardiac stiffness measurements for the subject; (iv) receiving (124) clinical information regarding the subject; (v) analyzing (140) the plurality of ultrasound biomarkers, the cardiac stiffness measurements, and the clinical information regarding the subject using a trained heart failure model to generate a likelihood of at least one of a plurality of HFpEF etiologies, wherein the likelihood of the at least one of the plurality of HFpEF etiologies includes a likelihood that the subject suffers from heart failure with preserved ejection fraction (140); and (vi) displaying (150) a visualization of the generated likelihood of the at least one of the plurality of HFpEF etiologies.

Description

[Technical Field]

[0001] The present disclosure is generally directed to methods and systems for providing a visualized likelihood of heart failure with preserved ejection fraction for a subject. [Background technology]

[0002] Heart failure, defined as the inability of the heart to provide adequate cardiac output while maintaining normal filling pressures, affects at least 26 million people worldwide and is expected to increase by 46% by 2030. There are two types of heart failure: (1) heart failure with reduced ejection fraction (HFrEF) and (2) heart failure with preserved ejection fraction (HFpEF). HFpEF, which accounts for 50% of heart failure cases, is characterized by impaired left ventricular (LV) relaxation during diastole and increased filling pressures caused by altered LV mechanical properties, particularly increased stiffness. Conditions such as cardiac amyloidosis, coronary artery disease, valvular disease, hypertrophic cardiomyopathy (HCM), pericardial disease, and hypertension can cause HFpEF.

[0003] Echocardiography is the primary imaging modality for HFpEF. However, it cannot be directly used in the differential diagnosis. Current guidelines for the diagnosis of HFpEF include a history and physical examination, echocardiography, and cardiac catheterization, if necessary. However, these guidelines are complex and rarely followed. Even with these guidelines, identifying the underlying cause of HFpEF remains challenging.

[0004] As an example, cardiac amyloidosis is one of the most rapidly progressive forms of HFpEF. If untreated, the median survival from diagnosis is less than 6 months for light chain amyloidosis (AL) and 3–5 years for transthyretin amyloidosis (ATTR). Currently, a definitive diagnosis of ATTR amyloidosis is made using Tc-99m-PYP / DPD / HMDP imaging. Echocardiography is typically the first test performed in patients presenting with heart failure. However, the typical echocardiographic features of CA are most prominent in advanced disease and may be missed in early-stage disease, even when severe enough to cause heart failure. Especially in early-stage disease, echocardiography lacks the specificity to strictly distinguish amyloid from non-amyloid infiltrative disease or hypertrophic cardiac disease, such as left ventricular hypertrophy (LVH). Therefore, ultrasound currently does not play a role in the differential diagnosis of HFpEF, especially in the early stages. Summary of the Invention [Problem to be solved by the invention]

[0005] The cardiac imaging community agrees that standardization of the differential diagnosis of HFpEF is highly desirable to improve the efficiency and effectiveness of care and achieve better patient outcomes. Currently, there is no widely accepted, intelligent, patient-specific method for predicting the likelihood of various HFpEF etiologies, taking into account the upstream patient clinical circumstances across various institutions. Therefore, it is urgent for the field of cardiac care imaging to establish intelligent, data-driven decision support tools for the differential diagnosis of HFpEF. [Means for solving the problem]

[0006] Thus, there is an ongoing need for methods and systems for the differential diagnosis of HFpEF. Various embodiments and implementations herein are directed to methods and systems configured to generate and present a visualized likelihood of HFpEF. For example, a system, such as a patient analysis system, receives results of an ultrasound analysis of a subject's heart and extracts a plurality of ultrasound biomarkers for the patient from the received results of the ultrasound analysis. The system also receives cardiac stiffness measurements for the subject's heart and clinical information about the subject. The patient analysis system then analyzes the extracted plurality of ultrasound biomarkers, the received cardiac stiffness measurements, and the received clinical information about the subject as inputs using a trained heart failure model configured to output a likelihood of at least one of a plurality of HFpEF etiologies. The output of the trained model (the determined likelihood of at least one of a plurality of HFpEF etiologies) includes a likelihood that the subject suffers from heart failure with preserved ejection fraction. The system then displays a visualization of the generated likelihood of at least one of a plurality of HFpEF etiologies on a user interface of the system.

[0007] In general, in one aspect, a method is provided for providing a visualized likelihood of heart failure with preserved ejection fraction (HFpEF) for a subject, the method comprising: (i) receiving results of an ultrasound analysis of the subject's heart from a current ultrasound examination; (ii) extracting a plurality of ultrasound biomarkers from the received results of the ultrasound analysis; (iii) receiving cardiac stiffness measurements of the subject's heart from the current ultrasound examination and / or a previous ultrasound examination; (iv) receiving clinical information about the subject; (v) analyzing the extracted plurality of ultrasound biomarkers, the received cardiac stiffness measurements, and the received clinical information about the subject using a trained heart failure model to generate a likelihood of at least one of a plurality of HFpEF etiologies, wherein the generated likelihood of at least one of the plurality of HFpEF etiologies includes a likelihood that the subject suffers from heart failure with preserved ejection fraction; and (vi) displaying a visualization of the generated likelihood of the at least one of the plurality of HFpEF etiologies in a user interface.

[0008] According to one embodiment, multiple etiologies of HFpEF include cardiac amyloidosis, coronary artery disease, hypertension, pericardial disease, hypertrophic cardiomyopathy, and valvular disease.

[0009] According to one embodiment, the method further comprises receiving results of one or more previous imaging analyses of the subject's heart, wherein the imaging analyses are ultrasound imaging or another imaging modality, and receiving one or more ultrasound biomarkers from the previous imaging analyses, wherein the analyzing step using the trained heart failure model further comprises receiving the one or more previous imaging analyses and / or one or more ultrasound biomarkers from the previous imaging analyses.

[0010] According to one embodiment, the displaying step further comprises displaying in the user interface: (i) the subject's name; (ii) one or more details regarding the ultrasound analysis; (iii) the likelihood of each of the multiple HFpEF etiologies; and (iv) a treatment recommendation.

[0011] According to one embodiment, the method further comprises determining that one or more ultrasound biomarkers are missing from the extracted plurality of ultrasound biomarkers, generating a request for the missing one or more ultrasound biomarkers, and receiving at least one of the missing one or more ultrasound biomarkers in response to the request.

[0012] According to one embodiment, the plurality of ultrasound biomarkers include one or more of ejection fraction, longitudinal global strain, blood flow propagation velocity, early diastolic mitral inflow velocity, late diastolic mitral inflow velocity, early diastolic mitral annular velocity, late diastolic mitral annular velocity, left atrial volume index, left ventricular thickness, septum thickness, one or more valve thicknesses, right ventricular thickness, relative wall pressure, tricuspid regurgitation velocity, and left ventricular mass index.

[0013] According to one embodiment, the clinical information about the subject includes one or more of the ultrasound examination type, the reason for the ultrasound analysis, the subject's age, the subject's sex, the subject's body mass index, atrial fibrillation status or diagnosis, and coronary artery disease status or diagnosis.

[0014] According to one embodiment, cardiac stiffness is measured by the atrial kick method, the valve closure method, and / or the shear wave method.

[0015] According to a second aspect, there is provided a system for providing a visualized likelihood of heart failure with preserved ejection fraction (HFpEF) for a subject. The system includes a trained heart failure model; a processor configured to: (i) receive results of an ultrasound analysis of the subject's heart from a current ultrasound examination; (ii) extract a plurality of ultrasound biomarkers from the received results of the ultrasound analysis; (iii) receive cardiac stiffness measurements of the subject's heart from the current ultrasound examination and / or a previous ultrasound examination; (iv) receive clinical information about the subject; (v) analyze the extracted plurality of ultrasound biomarkers, the received cardiac stiffness measurements, and the received clinical information about the subject using the trained heart failure model to generate at least one likelihood of a plurality of HFpEF etiologies, wherein the generated likelihood of at least one of the plurality of HFpEF etiologies includes a likelihood that the subject suffers from heart failure with preserved ejection fraction; and (vi) generate a visualization of the generated likelihood of at least one of the plurality of HFpEF etiologies; and a user interface configured to provide the generated likelihood of at least one of the plurality of HFpEF etiologies.

[0016] According to one embodiment, the user interface is further configured to display (i) the subject's name, (ii) one or more details regarding the ultrasound analysis, (iii) the likelihood of each of multiple HFpEF etiologies, and (iv) a treatment recommendation.

[0017] According to one embodiment, the processor is further configured to (i) determine that one or more ultrasound biomarkers are missing from the extracted plurality of ultrasound biomarkers; (ii) generate a request for the missing one or more ultrasound biomarkers; and (iii) receive at least one of the missing one or more ultrasound biomarkers in response to the request.

[0018] According to a third aspect, there is provided a non-transitory computer-readable storage medium comprising computer program code instructions that, when executed by a processor, enable the processor to perform a method having the steps of: (i) receiving results of an ultrasound analysis of the subject's heart from a current ultrasound examination; (ii) extracting a plurality of ultrasound biomarkers from the received results of the ultrasound analysis; (iii) receiving cardiac stiffness measurements of the subject's heart from the current ultrasound examination and / or a previous ultrasound examination; (iv) receiving clinical information about the subject; (v) analyzing the extracted plurality of ultrasound biomarkers, the received cardiac stiffness measurements, and the received clinical information about the subject using a trained heart failure model to generate a likelihood of at least one of a plurality of HFpEF etiologies, wherein the generated likelihood of at least one of the plurality of HFpEF etiologies includes a likelihood that the subject suffers from heart failure with preserved ejection fraction; and (vi) displaying a visualization of the generated likelihood of at least one of the plurality of HFpEF etiologies on a user interface.

[0019] It should be understood that any combination of the above concepts and additional concepts discussed in more detail below (provided such concepts are not mutually inconsistent) is contemplated as being part of the inventive subject matter disclosed herein. In particular, any combination of claimed subject matter appearing at the end of this disclosure is contemplated as being part of the inventive subject matter disclosed herein. It should also be understood that technical terms expressly employed herein that also appear in any disclosure incorporated by reference should be given the meaning most consistent with the specific concepts disclosed herein.

[0020] These and other aspects of various embodiments will be apparent from and elucidated with reference to the embodiments described hereinafter.

[0021] In the drawings, like reference numerals generally refer to the same parts throughout the various views. The figures illustrating features and manners of implementing various embodiments should not be construed as limitations on other possible embodiments falling within the scope of the appended claims. Also, the drawings are not necessarily to scale; instead, emphasis is generally placed upon illustrating the principles of various embodiments. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a flowchart of a method for providing a visualized likelihood of HFpEF for a subject, according to one embodiment. [Figure 2] 1 is a schematic diagram of a patient analysis system, according to one embodiment. [Figure 3] FIG. 1 is a schematic diagram of cardiac stiffness measurements, according to one embodiment. [Figure 4] 1 is a flowchart of inputs and outputs to and from a trained heart failure model of a patient analysis system, according to one embodiment. [Figure 5] 1 is a flowchart of a method for training a heart failure model of a patient analysis system, according to one embodiment. [Figure 6] FIG. 1 is a schematic diagram of visualization of HFpEF, according to one embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0023] This disclosure describes various embodiments of systems and methods configured to generate and present a visualized likelihood of HFpEF for a subject. More generally, it has been recognized and appreciated that it would be beneficial to provide an intelligent, data-driven decision support tool for the differential diagnosis of HFpEF. Accordingly, a patient analysis system receives results of an ultrasound analysis of a subject's heart and extracts a plurality of ultrasound biomarkers for the patient from the received results of the ultrasound analysis. The system also receives cardiac stiffness measurements for the subject's heart and clinical information about the subject. The patient analysis system then analyzes the extracted plurality of ultrasound biomarkers, the received cardiac stiffness measurements, and the received clinical information about the subject as inputs using a trained heart failure model configured to output a likelihood of at least one of a plurality of HFpEF etiologies. The output of the trained model (the determined likelihood of at least one of a plurality of HFpEF etiologies) includes a likelihood that the subject suffers from heart failure with preserved ejection fraction. The system then displays a visualization of the generated likelihood of at least one of a plurality of HFpEF etiologies on a user interface of the system. The generated likelihood visualization can then be utilized by medical personnel to perform healthcare treatment for the subject.

[0024] According to one embodiment, the systems and methods described or otherwise contemplated herein may, in some non-limiting embodiments, be implemented as part of a commercially available product for ultrasound imaging or analysis, as part of a commercially available product for cardiovascular analysis such as the Philips® IntelliSpace Cardiovascular (ISCV) (available from Koninklijke Philips NV, the Netherlands), as part of a commercially available product for patient analysis or monitoring such as the Philips Patient Flow Capacity Suite (PFCS), or as part of any suitable system.

[0025] Referring to Figure 1, in one embodiment, the figure is a flowchart of a method 100 for analyzing or determining a patient's likelihood of HFpEF using a patient analysis system. It should be understood that the method described with respect to the figure is provided by way of example only and is not intended to limit the scope of the present disclosure. The patient analysis system can be any of the systems described or otherwise contemplated herein. The patient analysis system can be a single system or multiple different systems.

[0026] At step 110 of the method, a patient analysis system 200 is provided. For example, referring to one embodiment of patient analysis system 200 shown in FIG. 2, the system comprises one or more of a processor 220, a memory 230, a user interface 240, a communication interface 250, and storage 260 interconnected via one or more system buses 212. It will be understood that FIG. 2 constitutes an abstraction in some respects, and the actual organization of the components of system 200 may be different and more complex than that shown. Furthermore, patient analysis system 200 may be any of the systems described or otherwise contemplated herein. Other elements and components of patient analysis system 200 are disclosed and / or contemplated elsewhere herein.

[0027] In step 120 of the method, the patient analysis system receives results of an ultrasound analysis of the subject's heart. The ultrasound analysis of the subject's heart can be any analysis sufficient to provide ultrasound data about the subject that can be used in downstream steps of the method. The ultrasound analysis of the subject's heart can be acquired using any ultrasound methodology or device capable of providing ultrasound data used in downstream steps of the method. According to one embodiment, the ultrasound analysis of the subject's heart includes multiple images acquired by the ultrasound device and / or includes a report summary of the multiple images.

[0028] According to one embodiment, patient analysis system 200 includes an ultrasound device capable of acquiring the required ultrasound images or analysis. According to another embodiment, patient analysis system 200 is in wired or wireless communication with a local or remote ultrasound device capable of acquiring the required ultrasound images or analysis. According to another embodiment, patient analysis system 200 is in wired or wireless communication with a local or remote database that stores the ultrasound images or analysis. Patient analysis system 200 can obtain the required ultrasound images or analysis from one or more of these sources.

[0029] According to one embodiment, an ultrasound analysis of a subject's heart is obtained by an ultrasound imaging professional as part of a routine examination of the subject or in response to a possible or known medical problem the patient may have. The ultrasound analysis may be performed or obtained for immediate or upcoming analysis by methods and systems described or otherwise contemplated herein, or for future analysis by methods and systems described or otherwise contemplated herein.

[0030] According to one embodiment, the ultrasound analysis of the subject's heart includes 2D images or recordings, 3D images or recordings, and / or both.

[0031] In step 130 of the method, the patient analysis system extracts a plurality of ultrasound biomarkers from the received results of the ultrasound analysis. The plurality of ultrasound biomarkers may be any metrics, measurements, parameters, or other data extracted from the ultrasound analysis. According to one embodiment, the plurality of ultrasound biomarkers are quantitative parameters extracted from the received results of the ultrasound analysis or otherwise obtained during the ultrasound analysis. The ultrasound biomarkers may be extracted using any of a wide variety of methods for data extraction from ultrasound imaging. According to one embodiment, one or more of the plurality of ultrasound biomarkers are automatically acquired or extracted by software or algorithms associated with the ultrasound device or the patient analysis system. For example, one or more of the plurality of ultrasound biomarkers may be acquired using an ultrasound workstation solution. According to another embodiment, one or more of the plurality of ultrasound biomarkers are manually acquired or extracted during the ultrasound analysis.

[0032] According to one embodiment, the plurality of ultrasound biomarkers include one or more of ejection fraction, global longitudinal strain, blood flow propagation velocity, early diastolic mitral inflow velocity, late diastolic mitral inflow velocity, early diastolic mitral annular velocity, late diastolic mitral annular velocity, left atrial volume index, left ventricular thickness, septal thickness, one or more valve thicknesses, right ventricular thickness, relative wall pressure, tricuspid regurgitation velocity, and left ventricular mass index, although many other ultrasound biomarkers are possible.

[0033] The ultrasound biomarkers received or extracted by the patient analysis system may be immediately available before or after data processing, or may be stored in local or remote storage for use in further steps of the method.

[0034] According to one embodiment, one or more ultrasound biomarkers may be missing from the plurality of ultrasound biomarkers. Thus, in optional step 132 of the method, the system determines that one or more ultrasound biomarkers are missing from the received or extracted plurality of ultrasound biomarkers. According to one embodiment, the system may include a list of the minimum ultrasound biomarkers required for downstream analysis according to the method and may analyze the set of extracted or received ultrasound biomarkers to determine whether each of the minimum ultrasound biomarkers required for downstream analysis according to the method is present in the set. Thus, the system may determine that all required ultrasound biomarkers are present, or may determine that one or more required ultrasound biomarkers are missing from the set of received or extracted ultrasound biomarkers.

[0035] In optional step 134 of the method, the system generates a request for the missing one or more required ultrasound biomarkers in response to determining that one or more required ultrasound biomarkers are missing from the set of received or extracted ultrasound biomarkers. The request may include identification of the missing one or more required ultrasound biomarkers, instructions for obtaining the missing one or more required ultrasound biomarkers, and / or any other information. The request may be provided to a medical professional through another system, a user interface, or the like. The request may be communicated locally or remotely.

[0036] In optional step 136 of the method, the system receives at least one of the missing one or more ultrasound biomarkers in response to communicating the request. For example, after receiving the request, the medical professional acquires the missing one or more ultrasound biomarkers, such as by performing additional analysis of the ultrasound imaging or by performing additional ultrasound imaging to acquire the missing information. According to another embodiment, the request is communicated to another system, such as an ultrasound device or analysis system, which can automatically extract or otherwise identify the missing one or more ultrasound biomarkers and automatically return the acquired data to the patient analysis system.

[0037] In step 122 of the method, the patient analysis system receives or acquires cardiac stiffness measurements for the subject's heart. The cardiac stiffness measurements for the subject's heart may be acquired using one or more of several different methods for acquiring such measurements.

[0038] According to one embodiment, left ventricular (LV) filling following a late diastolic atrial kick (AK) generates LV myocardial stretch that propagates at a velocity related to myocardial stiffness. Because changes in myocardial stiffness have been shown to be associated with cardiac disease, particularly HFpEF, a cardiac stiffness measurement tool complements the differential diagnosis of HFpEF. However, because cardiac stiffness measurement is not part of existing in-clinic workflows, using cardiac stiffness as an input provides additional value and improved accuracy and reproducibility in estimating the likelihood of HFpEF etiology.

[0039] According to one embodiment, cardiac stiffness measurements of a subject's heart can be obtained using a semi-automated methodology for non-invasive estimation of cardiac stiffness, in which a combination of high-frame rate imaging modes and algorithms capable of processing tissue images automatically calculates cardiac tissue elasticity. Referring to Figure 3, in one embodiment, this figure is an illustration showing the output of the proposed cardiac stiffness signature, including the mean cardiac stiffness (wave velocity value), all valid velocity measurements, and a boxplot showing variability.

[0040] According to one embodiment, measurement of cardiac stiffness (wave velocity) may be based on other methods. For example, some HFpEF patients have symptoms of atrial fibrillation, and AK is lost in these patients, so measuring cardiac stiffness using AK-based features may not be optimal. In this group of HFpEF patients, cardiac stiffness may be measured based on other methods, such as measuring the natural shear wave velocity after mitral valve closure (late diastole) and aortic valve closure (early diastole), or measuring external shear wave velocity using push pulses generated by the ultrasound probe itself. The results of the stiffness measurement may then be utilized by downstream steps of the method for estimating the likelihood of the etiology of HFpEF.

[0041] Cardiac stiffness measurements received or extracted by the patient analysis system may be immediately available, before or after data processing, or may be saved in local or remote storage for use in further steps of the method.

[0042] In step 124 of the method, the patient analysis system receives clinical information about the subject. The clinical information about the subject can be any information relevant to or useful in any downstream step of the method, including input to a trained heart failure model configured to output a likelihood of at least one of multiple HFpEF etiologies. According to one embodiment, the clinical information about the subject includes one or more of the following: ultrasound exam type, reason for ultrasound analysis, subject age, subject sex, subject body mass index, atrial fibrillation status or diagnosis, coronary artery disease status or diagnosis, medical treatment, and medical diagnosis, among many other types of clinical information. For example, age affects the interpretation of diastolic parameters, including E (early diastolic mitral inflow velocity), A (late diastolic mitral inflow velocity), and E / A. Additionally, assessment of A and E / A is difficult in patients with AF, and E is difficult in patients with a history of CAD. Therefore, these clinical information data can be important factors influencing the diagnosis of HFpEF. Thus, the received information may be any information relevant to patient analysis as described or otherwise contemplated herein.

[0043] The patient analysis system can receive patient clinical information from a variety of different sources. According to one embodiment, the patient analysis system is in communication with an electronic medical record database from which the patient clinical information is obtained or received. According to one embodiment, the patient analysis system includes an electronic medical record database or system 270, which optionally communicates directly and / or indirectly with system 200. According to another embodiment, the patient analysis system obtains or receives the information from a device or medical professional that obtains the information directly from the patient.

[0044] Patient clinical information received by the patient analysis system is processed by the system according to methods for data handling and processing / preparation, including but not limited to, methods described or otherwise contemplated herein. The patient clinical information received by the patient analysis system may be available immediately, before or after processing, or may be stored in local or remote storage for use in further steps of the method.

[0045] In optional step 126 of the method, the patient analysis system receives the results of one or more previous imaging analyses of the subject's heart. According to one embodiment, the imaging analyses are ultrasound imaging or another imaging modality. According to one embodiment, the previous cardiac MR or CT images influence the final diagnostic decision, particularly if there is a discrepancy between parameters obtained from ultrasound and MRI, such as different longitudinal strain values ​​in ultrasound and MR.

[0046] In optional step 128 of the method, the patient analysis system receives one or more ultrasound biomarkers for the subject from a previous imaging analysis obtained for the subject. According to one embodiment, the ultrasound biomarkers from the previous analysis provide additional diagnostic value with respect to the trend data. For example, if a biomarker for suspected amyloidosis increases from the previous test to the current test, this may be a warning sign for amyloidosis. Many other examples are possible.

[0047] The received results of one or more previous imaging analyses of the subject's heart and / or the received one or more ultrasound biomarkers of the subject from previous imaging analyses obtained for the subject may be available immediately, before or after processing, or may be stored in local or remote storage for use in further steps of the method.

[0048] In step 140 of the method, the trained heart failure model of the patient analysis system analyzes the received input to generate a likelihood of at least one of a plurality of HFpEF etiologies. The generated likelihood of at least one of a plurality of HFpEF etiologies includes a likelihood that the subject has heart failure with preserved ejection fraction. According to one embodiment, the plurality of HFpEF etiologies include cardiac amyloidosis, coronary artery disease, hypertension, pericardial disease, hypertrophic cardiomyopathy, and valvular disease, although fewer or more HFpEF etiologies are possible.

[0049] According to one embodiment, inputs to the trained heart failure model of the patient analysis system include the extracted ultrasound biomarkers, received cardiac stiffness measurements, and received clinical information about the subject. According to another embodiment, inputs to the trained heart failure model of the patient analysis system further include received results of one or more previous imaging analyses of the subject's heart and / or received one or more ultrasound biomarkers of the subject from previous imaging analyses obtained for the subject. Other inputs to the trained heart failure model are possible.

[0050] Referring to Figure 4, in one embodiment, this diagram is an illustration 400 showing inputs and outputs to and from a trained heart failure model of a patient analysis system. According to one embodiment, inputs to the trained heart failure model of the patient analysis system include one or more of received cardiac stiffness measurements, extracted ultrasound biomarkers, received clinical information about the subject, received one or more ultrasound biomarkers of the subject from a previous imaging analysis obtained for the subject, and / or received results of one or more previous imaging analyses of the subject's heart. According to one embodiment, outputs from the trained heart failure model of the patient analysis system include likelihoods for one or more etiologies of HFpEF, such as cardiac amyloidosis, coronary artery disease, hypertension, valvular disease, pericardial disease, and hypertrophic cardiomyopathy, although fewer or more etiologies of HFpEF are possible.

[0051] According to one embodiment, the trained heart failure model of the patient analysis system may generate a likelihood of at least one of the multiple HFpEFs using a wide variety of different classifiers and / or machine learning algorithms as described or otherwise contemplated herein. According to one embodiment, the trained heart failure model of the patient analysis system may be trained according to a wide variety of methods and approaches. As one example, the model may include a neural network approach.

[0052] Referring to FIG. 5, in one embodiment, this figure is a flowchart of a method 500 for training a heart failure model of a patient analysis system. In step 510 of the method, the system receives a training dataset including training data for a plurality of patients, such as historical patient data. The training data may include inputs such as one or more of cardiac stiffness measurements, ultrasound biomarkers, clinical information about the patient, one or more received ultrasound biomarkers for the patient from a previous imaging analysis obtained for the patient, and / or received results of one or more previous imaging analyses of the patient's heart. The training data may also include a diagnosis of HFpEF or no HFpEF for each of a plurality of patients. The training data is stored in and / or received from one or more databases. The databases may be local and / or remote. For example, a patient readmission risk analysis system may include a database of training data.

[0053] According to one embodiment, the patient analysis system includes a data preprocessor or similar component or algorithm configured to process the received training data. For example, the data preprocessor analyzes the training data to remove noise, bias, errors, and other potential problems. The data preprocessor also analyzes the input data to remove low-quality data. Many other forms of data preprocessing or data point identification and / or extraction are possible.

[0054] In step 520 of the method, the system trains a machine learning algorithm, which is the algorithm utilized in analyzing the input information as described or otherwise envisioned. The machine learning algorithm is trained using a training data set according to known methods for training machine learning algorithms. According to one embodiment, the algorithm is trained using the processed training data set to generate a likelihood of at least one of a plurality of HFpEF etiologies. The generated likelihood of at least one of the plurality of HFpEF etiologies includes a likelihood that the subject suffers from heart failure with preserved ejection fraction. According to one embodiment, the algorithm is also trained using the processed training data set to generate one or more intervention recommendations based on the determined likelihood or likelihoods.

[0055] In step 530 of the method, the trained heart failure model of the patient analysis system is saved for future use. According to one embodiment, the model is saved in local or remote storage.

[0056] According to one embodiment, ground truth for the predicted likelihood of various HFpEF etiologies can be collected from the confirmed results of invasive / minimally invasive follow-up diagnostic tests (biopsy, PET, or CMR) obtained from HFpEF patients in retrospective or prospective studies, analyzed by a team of expert cardiologists for each given upstream patient's clinical situation. The combined data (current events obtained from ultrasound imaging and cardiac stiffness measurements, previous measurements from other imaging modalities, and past clinical parameters obtained from electronic medical records) are then stored and processed for training or display using the proposed AI model. This supervised learning approach can be an institution-independent tool for differential HFpEF likelihood estimation. The accuracy of an AI-based learning network, such as a self-learning algorithm, is enhanced over time by adding more data to it.

[0057] 1 , in step 150 of the method, a visualization of the generated likelihood of at least one of the plurality of HFpEF etiologies is displayed to a medical professional or other user via a user interface of the patient analysis system. According to one embodiment, the plurality of HFpEF etiologies include cardiac amyloidosis, coronary artery disease, hypertension, pericardial disease, hypertrophic cardiomyopathy, and valvular disease. According to one embodiment, the display further includes the subject's name, one or more details regarding the ultrasound analysis, the likelihood of each of the plurality of HFpEF etiologies, and / or a treatment recommendation, among other types of information.

[0058] According to one embodiment, the information is communicated to a user interface and / or another device via wired and / or wireless communication. For example, the system communicates the information to a mobile phone, a computer, a laptop, a wearable device, and / or any other device configured to enable display of reports and / or other communication. The user interface can be any device or system that enables transmission and / or reception of information, including a display, a mouse, and / or a keyboard for receiving user commands.

[0059] Referring to Figure 6, in one embodiment, this figure is a schematic illustration of a possible visualization of the generated likelihood of multiple HFpEF etiologies, including cardiac amyloidosis, coronary artery disease, hypertension, pericardial disease, hypertrophic cardiomyopathy, and valvular disease. For example, the likelihood of cardiac amyloidosis as the HFpEF etiology is 80%, which may exceed a predetermined threshold for concern, alarm, or other threshold. An 80% likelihood would result in the provision of the note "Suspected cardiac amyloidosis" and the recommendation "Follow-up PET scan recommended." The display also includes information such as the patient's name, exam date, and details about the current ultrasound exam.

[0060] According to one embodiment of the patient analysis system, the system may include a user interface for facilitating the methods described or otherwise contemplated herein. Thus, the user interface may include a "Decision Support Tool for Differential HFpEF Diagnosis" button or activator that appears on a workspace, such as the touch panel of an ultrasound scanner or the Philips Intellispace Cardiovascular (ISCV) platform, for a user to launch the application.

[0061] According to one embodiment of the patient analysis system, the system prompts the user to either initiate an automated cardiac stiffness measurement tool (for the current acquisition on the scanner) or load the results of a previous stiffness measurement (if the results are already available).

[0062] According to one embodiment of the patient analysis system, the AI ​​predictive model of the patient analysis system is automatically implemented using inputs including hardness, other ultrasound biomarkers, previous measurements from other modalities, and / or upstream patient clinical context. If some ultrasound biomarkers are missing, the user is prompted to provide / measure them, including using automated measurement tools.

[0063] According to one embodiment of the patient analysis system, the system includes a user interface dashboard showing the likelihood of various HFpEF etiologies. Any notes or recommendations may also appear in the user interface to recommend next steps for the user.

[0064] In addition to the likelihood of HFpEF etiology, other available in-house ultrasound-based features related to the cardiac diagnostic domain (LA index tool, reconstructed PV loops, calcification score, etc.) can be provided in the dashboard for additional clinical decision support in the differential diagnosis of HFpEF.

[0065] In optional step 160 of method 100 shown in FIG. 1 , the generated likelihood visualization may be utilized by a healthcare professional to implement healthcare treatment for the subject. For example, a physician or other decision maker utilizes the displayed generated likelihood of one or more HFpEF etiologies to make patient care decisions. For example, healthcare recommendations may include recommendations to initiate, continue, or discontinue specific treatments configured to address one or more HFpEF etiologies based on the determined likelihood of one or more HFpEF etiologies. Actions may include prescriptions, instructions, additional tests, and / or other actions. Many other actions are possible.

[0066] Referring to Figure 2, this figure is a schematic diagram of a patient analysis system 200. System 200 may be any of the systems described or otherwise contemplated herein and may include any of the components described or otherwise contemplated herein. It will be understood that Figure 2 constitutes an abstraction in some respects, and the actual organization of the components of system 200 may be different and more complex than that depicted.

[0067] According to one embodiment, system 200 comprises a processor 220 capable of executing instructions or otherwise processing data stored in memory 230 or storage 260, for example, to perform one or more steps of the method. Processor 220 may be formed of one or more modules. Processor 220 may take any suitable form, including, but not limited to, a microprocessor, a microcontroller, multiple microcontrollers, circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a single processor, or multiple processors.

[0068] Memory 230 may take any suitable form, including non-volatile memory and / or RAM. Memory 230 may include various memories, such as L1, L2, or L3 cache or system memory. As such, memory 230 may include static random access memory (SRAM), dynamic RAM (DRAM), flash memory, read-only memory (ROM), or other similar memory devices. The memory may store, among other things, an operating system. RAM is used by the processor for temporary storage of data. According to one embodiment, the operating system includes code that, when executed by the processor, controls the operation of one or more components of system 200. It will be apparent that if the processor implements one or more of the functions described herein in hardware, software described as corresponding to such functions in other embodiments may be omitted.

[0069] User interface 240 includes one or more devices for enabling communication with a user. The user interface may be any device or system that enables the transmission and / or reception of information, including a display, mouse, and / or keyboard for receiving user commands. In some embodiments, user interface 240 includes a command line interface or a graphical user interface that is presented to a remote terminal via communication interface 250. The user interface may be collocated with one or more other components of the system or may be located remotely from the system and communicate via a wired and / or wireless communication network.

[0070] The communication interface 250 includes one or more devices for enabling communication with other hardware devices. For example, the communication interface 250 includes a network interface card (NIC) configured to communicate according to the Ethernet protocol. The communication interface 250 also implements a TCP / IP stack for communicating according to the TCP / IP protocol. Various alternative or additional hardware or configurations for the communication interface 250 will be apparent.

[0071] Storage 260 includes one or more machine-readable storage media, such as read-only memory (ROM), random-access memory (RAM), magnetic disk storage media, optical storage media, flash memory devices, or similar storage media. In various embodiments, storage 260 stores instructions for execution by processor 220 or data on which processor 220 operates. For example, storage 260 stores operating system 261 for controlling various operations of system 200.

[0072] It will be apparent that various information described as being stored in storage 260 may be stored in addition to or instead of memory 230. In this regard, memory 230 may also be considered to constitute a storage device, and storage 260 may be considered a memory. Various other arrangements may also be apparent. Furthermore, memory 230 and storage 260 may both be considered non-transitory machine-readable media. As used herein, the term non-transitory will be understood to exclude transitory signals, but to include all forms of storage, including both volatile and non-volatile memory.

[0073] Although system 200 is shown as including one of each of the described components, in various embodiments, various components may be duplicated. For example, processor 220 may include multiple microprocessors configured to independently perform the methods described herein, or configured to perform steps or subroutines of the methods described herein, such that the multiple processors cooperate to achieve the functionality described herein. Furthermore, when one or more components of system 200 are implemented in a cloud computing system, the various hardware components may reside in separate physical systems. For example, processor 220 includes a first processor in a first server and a second processor in a second server. Many other variations and configurations are possible.

[0074] According to one embodiment, electronic medical record system 270 is an electronic medical record database from which information about a patient, including clinical information, is obtained or received. The electronic medical record database may be a local or remote database that is in direct and / or indirect communication with patient analysis system 200. Thus, according to one embodiment, the patient analysis system comprises electronic medical record database or system 270.

[0075] According to one embodiment, the system includes one or more ultrasound devices 280 capable of acquiring the required ultrasound images or analysis. According to another embodiment, the patient analysis system 200 is in wired or wireless communication with a local or remote ultrasound device 280 capable of acquiring the required ultrasound images or analysis. According to another embodiment, the patient analysis system 200 is in wired or wireless communication with a local or remote database 280 that stores the ultrasound images or analysis. The patient analysis system 200 can obtain the required ultrasound images or analysis from one or more of these sources.

[0076] According to one embodiment, storage 260 of system 200 stores one or more algorithms, modules, and / or instructions for performing one or more functions or steps of the methods described or otherwise contemplated herein. For example, the system includes ultrasound biomarker extraction instructions 262, trained heart failure model 263, and / or reporting instructions 264, among other instructions or data.

[0077] According to one embodiment, the ultrasound biomarker extraction instructions 262 instruct the system to extract a plurality of ultrasound biomarkers from the received results of the ultrasound analysis. The plurality of ultrasound biomarkers may be any metric, measurement, parameter, or other data extracted from the ultrasound analysis, including, but not limited to, one or more of: ejection fraction, global longitudinal strain, blood flow propagation velocity, early diastolic mitral inflow velocity, late diastolic mitral inflow velocity, early diastolic mitral annular velocity, late diastolic mitral annular velocity, left atrial volume index, left ventricular thickness, septal thickness, one or more valve thicknesses, right ventricular thickness, relative wall pressure, tricuspid regurgitation velocity, and left ventricular mass index. The ultrasound biomarkers may be extracted using any of a wide variety of methods for data extraction from ultrasound imaging. According to one embodiment, one or more of the plurality of ultrasound biomarkers are automatically acquired or extracted by software or algorithms associated with the ultrasound device or patient analysis system. For example, one or more of the plurality of ultrasound biomarkers may be acquired using an ultrasound workstation solution. According to another embodiment, one or more of the ultrasound biomarkers are manually acquired or extracted during the ultrasound analysis.

[0078] According to one embodiment, the trained heart failure model 263 is configured to generate a likelihood of at least one of a plurality of HFpEF etiologies. The generated likelihood of at least one of the plurality of HFpEF etiologies includes a likelihood that the subject suffers from heart failure with preserved ejection fraction. According to one embodiment, the plurality of HFpEF etiologies include cardiac amyloidosis, coronary artery disease, hypertension, pericardial disease, hypertrophic cardiomyopathy, and valvular disease, although fewer or more HFpEF etiologies are possible. According to one embodiment, inputs to the trained heart failure model of the patient analysis system include the extracted plurality of ultrasound biomarkers, received cardiac stiffness measurements, and received clinical information about the subject. According to another embodiment, inputs to the trained heart failure model of the patient analysis system further include received results of one or more previous imaging analyses of the subject's heart and / or received one or more ultrasound biomarkers of the subject from previous imaging analyses obtained for the subject. Other inputs to the trained heart failure model are also possible. The trained heart failure model 263 is trained using a training dataset as described or otherwise contemplated herein.

[0079] According to one embodiment, the reporting instructions 264 instruct the system to generate information including the generated visualization of the generated likelihood of at least one of the multiple HFpEF etiologies and provide the information to a user via a user interface. According to one embodiment, the display further includes the subject's name, one or more details regarding the ultrasound analysis, the likelihood of each of the multiple HFpEF etiologies, and / or a treatment recommendation, among other types of information. Any of the information is communicated via a user interface of the system or another device via wired and / or wireless communication. For example, the system communicates the information to a cell phone, a computer, a laptop, a wearable device, and / or any other device configured to enable display of reports and / or other communication. The user interface can be any device or system that enables transmission and / or reception of information, including a display, a mouse, and / or a keyboard for receiving user commands.

[0080] Accordingly, within the context of the present disclosure, aspects of the embodiments take the form of a computer program product embodied in one or more non-transitory computer-readable medium(s) having computer-readable program code embodied therein. Thus, according to one embodiment, there is provided a non-transitory computer-readable storage medium comprising computer program code instructions that, when executed by a processor, enable the processor to perform a method having the following steps: (i) receiving results of an ultrasound analysis of the subject's heart from a current ultrasound examination; (ii) extracting a plurality of ultrasound biomarkers from the received results of the ultrasound analysis; (iii) receiving cardiac stiffness measurements of the subject's heart from the current ultrasound examination and / or a previous ultrasound examination; (iv) receiving clinical information about the subject; (v) analyzing the extracted plurality of ultrasound biomarkers, the received cardiac stiffness measurements, and the received clinical information about the subject using a trained heart failure model to generate a likelihood of at least one of a plurality of HFpEF etiologies, wherein the generated likelihood of at least one of the plurality of HFpEF etiologies includes a likelihood that the subject suffers from heart failure with preserved ejection fraction; and (vi) displaying a visualization of the generated likelihood of the at least one of the plurality of HFpEF etiologies on a user interface. The program code may execute entirely on the user's computer, partly on the user's computer as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on a remote computer or server.

[0081] According to one embodiment, a patient analysis system is configured to process thousands or even millions of data points in input data used to train the system, as well as process and analyze a plurality of received mobile features. For example, generating a functional, proficient, trained system using automated processes such as feature identification and extraction and subsequent training requires processing millions of data points and generated features from the input data. Therefore, generating a new trained system from these millions of data points may require millions or even billions of calculations. The resulting trained system is novel and distinctive based on the input data and parameters of the machine learning algorithm, thereby improving the functionality of the patient analysis system. Therefore, generating a functional, proficient, trained system involves a process involving a large amount of calculation and analysis that the human brain cannot accomplish in a lifetime or multiple lifetimes. By providing improved patient analysis, this novel patient analysis system has a significant positive impact on patient diagnosis and care compared to prior art systems.

[0082] It is understood that all definitions, as defined and used herein, take precedence over dictionary definitions, definitions in documents incorporated by reference, and / or ordinary meanings of the defined terms.

[0083] As used herein, in the specification and claims, the indefinite articles "a" and "an" should be understood to mean "at least one," unless otherwise specified.

[0084] As used herein, in the specification and in the claims, the term "and / or" should be understood to mean "either or both" of the elements so conjoined, i.e., elements that are present conjointly in some cases and separately in other cases. Multiple elements listed with "and / or" should be construed in the same manner, i.e., "one or more" of the elements so conjoined. Other elements may optionally be present other than the elements specifically identified by the "and / or" clause, whether related or unrelated to such elements specifically identified.

[0085] As used herein, in the specification and in the claims, "or" should be understood to have the same meaning as "and / or," as defined above. For example, when separating items in a list, "or" or "and / or" should be interpreted as being inclusive, i.e., including not only at least one of several elements or a list of elements, but also two or more of them, and optionally including additional items not listed. Only terms clearly indicating otherwise, such as "only one of" or "exactly one of," or the use of "consisting of" in the claims, refer to the inclusion of exactly one element of several elements or a list of elements. In general, the term "or" as used herein should be interpreted as indicating exclusive alternatives (i.e., "one or the other, but not both") only when preceded by terms of exclusivity, such as "either," "one of," "only one of," or "exactly one of."

[0086] As used herein, in the specification and claims, the phrase "at least one" in reference to a list of one or more elements should be understood to mean selected from any one or more of the elements in the list of elements, but not necessarily including at least one of each element specifically named in the list of elements, and not excluding any combination of elements in the list of elements. This definition also allows for the optional presence of elements other than those specifically identified in the list of elements to which the phrase "at least one" refers, whether related or unrelated to such specifically identified elements.

[0087] Also, unless otherwise specified, it should be understood that in any method claimed herein that includes more than one step or action, the order of the method steps or actions is not necessarily limited to the order in which the method steps or actions are described.

[0088] In the claims, as well as in the above specification, all transitional phrases such as "comprise," "include," "carry," "have," "contain," "involve," "hold," "consist of," and the like, are to be understood to be open-ended, i.e., meaning including but not limited to. Only the transitional phrases "consisting of" and "consisting essentially of" shall be closed or semi-closed transitional phrases, respectively.

[0089] While several inventive embodiments have been described and illustrated, those skilled in the art will readily conceive of various other means and / or structures for performing the functions and / or obtaining the results and / or one or more of the advantages described herein, and each such variation and / or modification is deemed to be within the scope of the inventive embodiments described herein. More generally, those skilled in the art will readily appreciate that all parameters, dimensions, materials, and configurations described herein are meant to be exemplary, and that the actual parameters, dimensions, materials, and / or configurations will depend on the particular application or applications in which the inventive teachings are used. Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many equivalents to the specific inventive embodiments described herein. Accordingly, the foregoing embodiments are presented by way of example only and, within the scope of the appended claims and their equivalents, the inventive embodiments may be practiced otherwise than as specifically described and claimed. Inventive embodiments of the present disclosure are directed to each individual feature, system, article, material, kit, and / or method described herein. Furthermore, any combination of two or more such features, systems, articles, materials, kits and / or methods, if such features, systems, articles, materials, kits and / or methods are not mutually inconsistent, is included within the inventive scope of the present disclosure.

Claims

1. 1. A computer-implemented method for providing a visualized likelihood of heart failure with preserved ejection fraction (HFpEF) for a subject, the method comprising: receiving results of an ultrasound analysis of the subject's heart from a current ultrasound examination; extracting a plurality of ultrasound biomarkers from the received results of the ultrasound analysis; receiving cardiac stiffness measurements of the subject's heart from the current ultrasound examination and / or a previous ultrasound examination; receiving clinical information regarding the subject; analyzing the extracted ultrasound biomarkers, the received cardiac stiffness measurements, and the received clinical information about the subject using a trained heart failure model to generate a likelihood of at least one of a plurality of etiologies of HFpEF, wherein the generated likelihood of at least one of a plurality of etiologies of HFpEF includes a likelihood that the subject suffers from heart failure with preserved ejection fraction; displaying the generated visualization of the likelihood of at least one of a plurality of HFpEF etiologies in a user interface; 10. A computer-implemented method comprising:

2. 10. The method of claim 1, wherein the multiple etiologies of HFpEF include cardiac amyloidosis, coronary artery disease, hypertension, pericardial disease, hypertrophic cardiomyopathy, and valvular disease.

3. receiving results of one or more previous imaging studies of the subject's heart, the imaging studies being ultrasound imaging or another imaging modality; receiving one or more ultrasound biomarkers from a previous imaging analysis; and 2. The method of claim 1, wherein the step of analyzing using a trained heart failure model further comprises receiving the one or more previous imaging analyses and / or the one or more ultrasound biomarkers from previous imaging analyses.

4. 2. The method of claim 1, wherein the displaying step further comprises displaying (i) the subject's name, (ii) one or more details regarding the ultrasound analysis, (iii) the likelihood of each of multiple HFpEF etiologies, and (iv) a treatment recommendation on the user interface.

5. determining that one or more ultrasound biomarkers are missing from the extracted plurality of ultrasound biomarkers; generating a request for the one or more missing ultrasound biomarkers; receiving at least one of the one or more missing ultrasound biomarkers in response to the request; The method of claim 1 further comprising:

6. 2. The method of claim 1, wherein the plurality of ultrasound biomarkers comprises one or more of ejection fraction, longitudinal global strain, blood flow propagation velocity, early diastolic mitral inflow velocity, late diastolic mitral inflow velocity, early diastolic mitral annular velocity, late diastolic mitral annular velocity, left atrial volume index, left ventricular thickness, septum thickness, one or more valve thicknesses, right ventricular thickness, relative wall pressure, tricuspid regurgitation velocity, and left ventricular mass index.

7. 2. The method of claim 1, wherein the clinical information about the subject comprises one or more of: ultrasound exam type, reason for the ultrasound analysis, age of the subject, sex of the subject, body mass index of the subject, atrial fibrillation status or diagnosis, and coronary artery disease status or diagnosis.

8. The method of claim 1 , wherein cardiac stiffness is measured by the atrial kick method, the valve closure method, and / or the shear wave method.

9. 1. A system for providing a visualized likelihood of heart failure with preserved ejection fraction (HFpEF) for a subject, comprising: a trained heart failure model; (ii) extracting a plurality of ultrasound biomarkers from the received results of the ultrasound analysis of the subject's heart; (iii) receiving cardiac stiffness measurements of the subject's heart from the current ultrasound examination and / or a previous ultrasound examination; (iv) receiving clinical information about the subject; (v) analyzing the extracted plurality of ultrasound biomarkers, the received cardiac stiffness measurements, and the received clinical information about the subject using the trained heart failure model to generate a likelihood of at least one of a plurality of etiologies of HFpEF, wherein the generated likelihood of at least one of a plurality of etiologies of HFpEF includes a likelihood that the subject suffers from heart failure with preserved ejection fraction; and (vi) generating a visualization of the generated likelihood of at least one of a plurality of etiologies of HFpEF. a user interface providing the generated likelihood of at least one of a plurality of HFpEF etiologies; and A system comprising:

10. 10. The system of claim 9, wherein the multiple etiologies of HFpEF include cardiac amyloidosis, coronary artery disease, hypertension, pericardial disease, hypertrophic cardiomyopathy, and valvular disease.

11. 10. The system of claim 9, wherein the user interface further displays (i) the subject's name, (ii) one or more details regarding the ultrasound analysis, (iii) the likelihood of each of multiple HFpEF etiologies, and (iv) a treatment recommendation.

12. 10. The system of claim 9, wherein the processor further: (i) determines that one or more ultrasound biomarkers are missing from the extracted plurality of ultrasound biomarkers; (ii) generates a request for the one or more missing ultrasound biomarkers; and (iii) receives at least one of the one or more missing ultrasound biomarkers in response to the request.

13. 10. The system of claim 9, wherein the plurality of ultrasound biomarkers comprises one or more of ejection fraction, longitudinal global strain, blood flow propagation velocity, early diastolic mitral inflow velocity, late diastolic mitral inflow velocity, early diastolic mitral annular velocity, late diastolic mitral annular velocity, left atrial volume index, left ventricular thickness, septum thickness, one or more valve thicknesses, right ventricular thickness, relative wall pressure, tricuspid regurgitation velocity, and left ventricular mass index.

14. 10. The system of claim 9, wherein (i) the clinical information about the subject includes one or more of an ultrasound examination type, a reason for the ultrasound analysis, an age of the subject, a sex of the subject, a body mass index of the subject, a status or diagnosis of atrial fibrillation, and a status or diagnosis of coronary artery disease; and / or (ii) cardiac stiffness is measured by an atrial kick method, a valve closure method, and / or a shear wave method.

15. A non-transitory computer readable storage medium comprising computer program code instructions that, when executed by a processor, enable the processor to perform the method of claim 1.

Images