Artificial intelligence-enhanced screening for cardiac amyloidosis using electrocardiogram recordings.

Abstract

Provided herein are methods, systems, and computer program products for detection of cardiac amyloidosis (CA), the methods, systems, and computer program products including receiving voltage-time data for multiple leads of an electrocardiograph of a subject, generating a feature vector from the voltage-time data, providing the feature vector to a pre-trained learning system, and receiving an indication of the presence or absence of CA in the subject from the pre-trained learning system.

Description

Technical Field

[0001] Related Applications This application claims the benefit of priority of U.S. Provisional Application No. 63 / 336,493, filed Apr. 29, 2022, which is hereby incorporated by reference in its entirety.

[0002] Embodiments of the present disclosure relate to methods for the detection and treatment of cardiac amyloidosis.

Background Art

[0003] Cardiac amyloidosis (CA) was once thought to be rare and universally fatal but is now recognized as an important cause of heart failure, especially in patients with preserved ejection fraction. Advances in treatment have led to a marked improvement in outcomes, but survival is hampered by a life-threatening delay in diagnosis. While more than 30 proteins can misfold and cause amyloidosis, two major types are associated with cardiac light chain-related amyloid (AL) resulting from clonal plasma cell disorders of the bone marrow and transthyretin amyloid (ATTR) associated with misfolding of transthyretin produced by the liver. ATTR can result from either a genetic mutation in the transthyretin gene (ATTRv) or “wild-type” (genetically normal) transthyretin deposition (ATTRwt). Treatments are available for both AL amyloidosis and ATTR amyloidosis and are rapidly improving. 4,5 If untreated, cardiac AL amyloidosis progresses rapidly and is fatal. Despite improvements in chemotherapy, approximately 25% of patients with AL amyloidosis die from progressive heart disease within 6 months of diagnosis. Cardiac ATTR amyloidosis progresses more slowly, with a median survival of approximately 3.5 years for ATTRwt and somewhat shorter for ATTRv.

Summary of the Invention

Problems to be Solved by the Invention

[0004] Accordingly, embodiments of the present invention disclosed herein include algorithms applied to electrocardiograms (ECGs), which are non-invasive procedures, in diagnostic examinations for CA detection and patient stratification based on CA risk, thereby enabling earlier diagnosis and intervention. [Means for solving the problem]

[0005] Embodiments of this disclosure provide a method and a computer program product for detecting cardiac amyloidosis (CA).

[0006] In some aspects of the present invention, the Specified Description provides a method for receiving voltage-time data of a subject, wherein the voltage-time data includes voltage data from a plurality of leads of an electrocardiograph; generating a feature vector from the voltage-time data; providing the feature vector to a pre-trained learning system; and receiving an indication from the pre-trained learning system of the presence or absence of cardiac amyloidosis in the subject.

[0007] Aspects of the invention disclosed herein also include a system comprising: an electrocardiograph having a plurality of leads; and a computing node having a computer-readable storage medium embodied by program instructions, wherein the program instructions are executable by a processor of the computing node, the processor performing a method including receiving voltage-time data of a subject from the echocardiograph, the voltage-time data including voltage data of the plurality of leads; generating a feature vector from the voltage-time data; providing the feature vector to a pre-trained learning system; and receiving an indication from the pre-trained learning system of the presence or absence of cardiac amyloidosis in the subject.

[0008] In particular aspects of the invention, the Specified Description of a computer program product for detecting cardiac amyloidosis, comprising a computer-readable storage medium embodied in program instructions, wherein the program instructions are executable by a processor, the processor performing a method comprising receiving voltage-time data of a subject from an echocardiograph, wherein the voltage-time data includes voltage data of a plurality of leads; generating a feature vector from the voltage-time data; providing the feature vector to a pre-trained learning system; and receiving an indication from the pre-trained learning system of the presence or absence of cardiac amyloidosis in the subject. [Brief explanation of the drawing]

[0009] [Figure 1] This is a schematic diagram of a system for detecting CA according to the embodiments of this disclosure. [Figure 2] This flowchart shows a method for detecting cardiac amyloidosis according to an embodiment of the present disclosure. [Figure 3] A computing node according to one embodiment of this disclosure is shown. [Figure 4] The images show a general outline of the research design (left), a clinical case of early detection of cardiac amyloid using AI-enhanced ECG before clinical diagnosis (center, top), a normal 12-lead ECG at the point when the model predicted cardiac amyloid (center, bottom), and model performance (right). [Figure 5] The receiver operating characteristic curves for a 12-lead model are shown. The test set receiver operating characteristic curves for a 12-lead network trained to distinguish between a control and a control with cardiac amyloidosis. Using an optimal probability threshold of 0.485, the sensitivity is 0.84 and the specificity is 0.85. AUC is the area under the receiver operating characteristic curve. [Figure 6] The calibration curve is shown. Calibration involves comparing the amyloid probability predicted by the model (x-axis) with the amyloid rate observed in the population (y-axis). The dashed line represents a fully calibrated model. [Figure 7]This shows a Violin plot of predicted amyloid probabilities in the control group. The model prediction distribution is for the control group only. The white dot represents the median probability, and the thick bars represent the interquartile range. The ends of the thin needles represent the upper and lower neighbor values. Observations above and below these values ​​are often suspected to be outliers. The width of the plot represents the number of observations. [Figure 8] This figure shows a violin plot of predicted amyloid probability in patients with cardiac amyloidosis accompanied by at least one electrocardiogram (ECG) from more than 6 months prior to diagnosis. See Figure 4 for an explanation of the violin plot components. Here, available ECGs were categorized into 6-month groups up to 5 years prior to clinical diagnosis. For patients with multiple ECGs in each bin, the median probability was used. "n" represents the number of patients with ECGs within the corresponding time window. Light chain (AL) cardiac amyloid is shown in Figure 8A, and wild-type transthyretin amyloid (ATTRwt) is shown in Figure 8B. [Figure 9] Figures 9A and 9B show artificial intelligence (AI)-enhanced electrocardiogram (ECG) for early detection of cardiac amyloidosis (CA): model development, performance, and clinical cases. In a 67-year-old male with unexplained heart failure (HF), the AI ​​model predicted amyloidosis when the echocardiogram was not interpreted as consistent with amyloidosis, showing only a borderline increase in left ventricular wall thickness. When the AI ​​model first predicted cardiac amyloidosis, the 12-lead ECG was interpreted as normal. AL, light chain amyloid. [Figure 10] This shows a model architecture used with inputs consisting of raw ECG waveform data and a binary output predicting the presence or absence of CA. [Modes for carrying out the invention]

[0010] Patients with systemic amyloidosis are generally evaluated by multiple providers before a diagnosis is established and often require referral to a national center. While cardiologists generally evaluate these patients, only 18.7% of them are correctly diagnosed in one study. Early symptoms are often ambiguous and may be attributable to other causes, requiring a high degree of suspicion index. Advances in cardiac imaging have improved diagnosis, but classic findings are not always present or may become unrecognizable, especially when amyloidosis has not been suggested by the reference provider. Because cardiac involvement in systemic amyloidosis is the most important determinant of survival, there is a critical need for early diagnosis to facilitate timely and effective treatment.

[0011] Classical electrocardiographic findings for AL CA include low voltage and pseudoinfarct patterns, which are present in approximately 45% of patients, but neither normal voltage nor ECG criteria for left ventricular hypertrophy (LVH) rule out the diagnosis. Despite more severe myocardial infiltration, low voltage is present in only about 25% of ATTRwt patients. Conduction system disorders and ST segment and T wave abnormalities are common but nonspecific in both types of CA. Artificial intelligence (AI)-driven models have been reported to enable the identification of latent and imminent disease from ECG findings that appear nonspecific or insignificant to expert reviewers. 12

[0012] This specification discloses the development of an artificial intelligence (AI)-based tool for detecting cardiac amyloidosis (CA) from standard 12-lead electrocardiograms (ECGs). A novel AI ECG network was developed to test an AI-driven model for the early detection of CA. Convolutional neural networks provide a comprehensive approach to analyzing and interpreting the vast amounts of data generated from a single ECG. The algorithm was developed using 12-lead ECG data collected from 2541 patients with light chain or transthyretin CA seen at the Mayo Clinic from 2000 to 2019. Cases were age and sex-matched nearest neighbors, with 2454 controls. A deep neural network was trained using a subset of 2997 (60%) cases and controls to predict the presence of CA in an internal validation set (n=999; 20%) and a randomly selected holdout test set (n=999; 20%). (Figure 4) Experiments were conducted using single-lead and 6-lead ECG subsets. Furthermore, since smartphone-compatible electrodes enable point-of-care diagnosis with single-lead and 6-lead options, compatible networks were developed and tested.

[0013] All models used voltage-time information from 12 lead ECGs as input. The modeling techniques investigated included convolutional neural networks with different structures, such as using all 12 reads as a single input, groups of six reads as separate inputs where each read is converted to a spectrogram, a single read as input, and combinations of these methods. Therefore, embodiments of the invention disclosed herein involve the use of at least 1 to 12 reads. Furthermore, diseases may also include underlying genetic components supported by the detection of these diagnostic signals prior to diagnosis. The methods disclosed herein may be combined with gene panels to provide further specificity and sensitivity. Similarly, such methods may be used with gene and biomarker panels (e.g., cardiac biomarkers such as B-type natriuretic peptide (BNP), N-terminal (NT) prohormone BNP (NT-proBNP), and troponin) for early and accurate detection of diseases and for the detection of novel biomarkers of diseases.

[0014] Thus, in some aspects of the present invention, this specification discloses a method that includes receiving voltage-time data of a subject, where the voltage-time data includes voltage data of a plurality of leads of an electrocardiograph; generating a feature vector from the voltage-time data; providing the feature vector to a pre-trained learning system; and receiving, from the pre-trained learning system, an indication of the presence or absence of cardiac amyloidosis in the subject. Generating the feature vector may include generating a spectrogram based on the voltage data of the plurality of leads. In some embodiments, generating the feature vector includes grouping the voltage data of the plurality of leads into a plurality of subsets.

[0015] In some embodiments, such a method further includes receiving demographic information of the subject, and generating the feature vector includes adding the demographic information to the feature vector. In some such embodiments, the method further includes receiving genomic information of the subject. Generating the feature vector may include adding the genomic information to the feature vector. Without being bound by any particular methodology or theory, the genomic data may be derived from a biological sample from a hereditary ATTR patient carrying a mutation. Such mutations are known in the art and may include, without limitation or exclusion, mutations V30M, Y114C, G47R, S50I, T49S, F33V, A45T, E89K, E89Q, and V122I. In some such embodiments, the learning system comprises a convolutional neural network. Such a convolutional neural network may include at least one residual connection.

[0016] In some embodiments, the voltage-time data of the subject is received from an electrocardiograph. In further embodiments, the voltage-time data of the subject is received from an electronic medical record.

[0017] In some embodiments, the method further includes providing a display to an electronic health record system for storage in a health record associated with a subject. In some embodiments, the method further includes providing a display to a computing node for display to a user.

[0018] In some embodiments of the methods disclosed herein, the feature vector comprises a matrix having a plurality of rows and a plurality of columns, where the rows correspond to the time dimension and the columns correspond to the spatial dimension. In some such embodiments, each of the plurality of rows corresponds to one of a plurality of reads, and each of the plurality of columns corresponds to a timestamp. In some embodiments, the time dimension has a resolution of 500 Hz. The convolutional neural network disclosed herein may comprise at least nine convolutional blocks and two fully connected blocks.

[0019] Referring now to FIG. 1, a system for detecting cardiac amyloidosis according to an embodiment of the present disclosure is shown. As outlined above, in various embodiments, patient information including electrocardiogram (ECG) data is provided to a learning system to determine the presence of cardiac amyloidosis. Accordingly, aspects of the invention disclosed herein include an electrocardiograph having a plurality of leads and a computing node comprising a computer-readable storage medium embodied with program instructions, the program instructions being executable by a processor of the computing node, whereby the processor is configured to receive voltage-time data of a subject from an echocardiograph, the voltage-time data including voltage data of a plurality of leads, generate a feature vector from the voltage-time data, provide the feature vector to a pre-trained learning system, and receive an indication of the presence or absence of cardiac amyloidosis in the subject from the pre-trained learning system. The system also includes a computing node for performing a method including generating a spectrogram based on the voltage data of the plurality of leads. In some embodiments, generating the feature vector includes grouping the voltage data of the plurality of leads into a plurality of subsets.

[0020] In some embodiments, such a system further includes receiving demographic information of a subject, and generating a feature vector includes adding the demographic information to the feature vector. In some embodiments, such a system further includes receiving genomic information of a subject. Generating a feature vector may include adding the genomic information to the feature vector. Without being bound by any particular methodology or theory, the genomic data may be derived from biological samples from hereditary ATTR patients carrying mutations. Such mutations are known in the art and may include, without limitation or exclusion, mutations V30M, Y114C, G47R, S50I, T49S, F33V, A45T, E89K, E89Q, and V122I. In some embodiments, the learning system comprises a convolutional neural network. Such a convolutional neural network may include at least one residual connection.

[0021] In some embodiments, the subject's voltage-time data is received from an electrocardiograph. In further embodiments, the subject's voltage-time data is received from an electronic medical record.

[0022] In some embodiments, the system further includes providing a display to an electronic health record system for storage in a health record associated with the subject. In some embodiments, the system further includes providing a display to a computing node for display to a user.

[0023] In some embodiments of the systems disclosed herein, the feature vector comprises a matrix having multiple rows and multiple columns, where the multiple rows correspond to the time dimension and the multiple columns correspond to the spatial dimension. In some such embodiments, each of the multiple columns corresponds to one of multiple reads, and each of the multiple columns corresponds to a timestamp. In some embodiments, the time dimension has a resolution of 500 Hz. In some embodiments, the convolutional neural network comprises at least nine convolutional blocks and two fully connected blocks.

[0024] Patient data may be received from an Electronic Health Record (EHR) 101. An Electronic Health Record (EHR) or Electronic Medical Record (EMR) may refer to a systematic collection of patient and population health information stored electronically in digital format. These records can be shared between different healthcare settings. Records can be shared through a networked enterprise-wide information system or other information networks and exchanges. An EHR may include a variety of data, including demographics, medical history, medications and allergies, immune status, laboratory results, radiographic images, vital signs, age and weight, and other personal statistics, as well as billing information. The EHR system may be designed to store data and capture the patient's condition over time. In this way, there is no need to track the patient's previous paper medical records.

[0025] Electrocardiogram (ECG) data may be received directly from the electrocardiogram recording device 102. In an exemplary 12-lead ECG, 10 electrodes are placed on the surface of the patient's limbs and chest. The overall magnitude of the cardiac potential is then measured from 12 different angles (leads) and recorded over a period of time (usually 10 seconds). In this way, the overall magnitude and direction of the cardiac electrical depolarization are captured at each moment throughout the cardiac cycle.

[0026] An additional data store 103 may contain additional patient information as described herein. Suitable data stores include databases, flat files, and other structures known in the art.

[0027] It may be understood that ECG data may be stored in the EHR for later retrieval. It may also be understood that ECG data may be cached rather than delivered directly to the learning system for further processing.

[0028] The learning system 104 receives patient information from one or more of the EHR 101, ECG 102, and additional data stores 103. As described above, in some embodiments, the learning system comprises a convolutional neural network. In various embodiments, the input to the convolutional neural network includes voltage-time information ECG, which in some embodiments is paired with additional patient information such as demographic or genetic information.

[0029] The learning system 104 may be pre-trained using appropriate population data as described in the embodiments to generate an indication of the presence or absence of cardiac amyloidosis. In some embodiments, the indication is binary. In some embodiments, the indication is a probability value indicating the likelihood of cardiac amyloidosis given input patient data.

[0030] In some embodiments, the learning system 104 provides a display of cardiac amyloidosis for storage as part of the EHR. In this way, a computer-aided diagnosis is provided that can be referenced by a clinician. In some embodiments, the learning system 104 provides the display of cardiac amyloidosis to a remote client 105. For example, the remote client may be a health app, a cloud service, or another consumer of diagnostic data. In some embodiments, the learning system 104 is integrated into the ECG machine to provide immediate feedback to the user during testing.

[0031] In some embodiments, a feature vector is provided to the learning system. Based on the input features, the learning system generates one or more outputs. In some embodiments, the output of the learning system is a feature vector.

[0032] In some embodiments, the learning system comprises an SVM. In other embodiments, the learning system comprises an artificial neural network. In some embodiments, the learning system is pre-trained using training data. In some embodiments, the training data is retrospective data. In some embodiments, the retrospective data is stored in a data store. In some embodiments, the learning system may be further trained by manual curation of previously generated outputs.

[0033] In some embodiments, the learning system is a trained classifier. In some embodiments, the trained classifier is a random decision forest. However, it may be understood that various other classifiers, including linear classifiers, support vector machines (SVMs), or neural networks such as recurrent neural networks (RNNs), are suitable for use relating to this disclosure.

[0034] Appropriate artificial neural networks include, but are not limited to, feedforward neural networks, radial basis function networks, self-organizing maps, learning vector quantization, recurrent neural networks, Hopfield networks, Boltzmann machines, echo state networks, long and short-term memory, bidirectional recurrent neural networks, hierarchical recurrent neural networks, probabilistic neural networks, modular neural networks, associative neural networks, deep neural networks, deep belief networks, convolutional neural networks, convolutional deep belief networks, mass memory retrieval neural networks, deep Boltzmann machines, deep stacking networks, tensor deep stacking networks, spike and slab-restricted Boltzmann machines, complex hierarchical deep models, deep coding networks, multilayer kernel machines, or deep Q networks.

[0035] In machine learning, a convolutional neural network (CNN) is a type of feedforward artificial neural network applicable to the analysis of visual images and other natural signals. A CNN consists of an input layer, an output layer, and multiple hidden layers. The hidden layers of a CNN typically consist of convolutional layers, pooling layers, fully connected layers, and normalization layers. The convolutional layer applies a convolution operation to the input and passes the result to the next layer. Convolution emulates the response of individual neurons to a stimulus. Each convolutional neuron processes data only for its receptive field.

[0036] Convolution allows for a reduction in free parameters compared to fully connected feedforward networks. In particular, tiling a given kernel makes it possible to learn a fixed number of parameters regardless of image size. This also reduces the memory footprint of a given network.

[0037] The parameters of a convolutional layer consist of a set of learnable filters (or kernels) that have a small receptive field but extend across the entire depth of the input volume. During the forward pass, each filter is convolved across the width and height of the input volume, calculating the inner product between the filter's entry and the input to generate a two-dimensional activation map of that filter. As a result, the network learns which filters to activate when it detects some specific type of feature at some spatial location in the input.

[0038] In the exemplary convolution, the kernel contains multiple weights w1...w9. The size provided here is merely illustrative, and it should be understood that any kernel dimension can be used as described herein. The kernel is applied to each tile of the input (e.g., an image). The result for each tile is an element of a feature map. It should be understood that multiple kernels may be applied to the same input to generate multiple feature maps.

[0039] The entire output volume of the convolutional layer is formed by stacking all the kernel feature maps. Therefore, every entry in the output volume can also be interpreted as the output of a neuron that looks at a small region in the input and shares parameters with the neuron in the same feature map.

[0040] Convolutional neural networks may be implemented on a variety of hardware, including hardware CNN accelerators and GPUs.

[0041] Referring here to Figure 2, a flowchart is provided illustrating a method for detecting cardiac amyloidosis according to an embodiment of the present disclosure. In 201, voltage-time data of the subject is received. The voltage-time data includes voltage data from multiple leads of an electrocardiograph. In 202, a feature vector is generated from the voltage-time data. In 203, the feature vector is provided to a pre-trained learning system. In 204, an indication of the presence or absence of cardiac amyloidosis in the subject is received from the pre-trained learning system.

[0042] Referring here to Figure 3, a schematic diagram of an example of a computing node is shown. Computing node 10 is merely an example of a suitable computing node and is not intended to imply any limitation on the scope of use or functionality of the embodiments described herein. Nevertheless, computing node 10 can implement and / or perform any of the above functions.

[0043] Computing node 10 has computer systems / servers 12 that operate in a number of other general-purpose or dedicated computing system environments or configurations. Examples of well-known computing systems, environments, and / or configurations that may be suitable for use with computer systems / servers 12 include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments that include any of the above systems or devices.

[0044] The computer system / server 12 can be described in the general context of computer system executable instructions, such as program modules, that are executed by the computer system. Generally, a program module may include routines, programs, objects, components, logic, data structures, etc., that perform a specific task or implement a specific abstract data type. The computer system / server 12 may be implemented in a distributed cloud computing environment where tasks are executed by remote processing devices linked via a communication network. In a distributed cloud computing environment, program modules may reside on both local and remote computer system storage media, including memory storage devices.

[0045] As shown in Figure 3, the computer system / server 12 within the computing node 10 is represented in the form of a general-purpose computing device. The components of the computer system / server 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and a bus 18 that connects various system components, including the system memory 28, to the processor 16.

[0046] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, peripheral buses, accelerated graphics ports, and processor or local buses using any of the various bus architectures. Examples, but not limited to, such architectures include the Industry Standard Architecture (ISA) bus, Microchannel Architecture (MCA) bus, Extended ISA (EISA) bus, Video Electronics Standards Association (VESA) local bus, Peripheral Component Interconnect (PCI) bus, Peripheral Component Interconnect Express (PCIe), and Advanced Microcontroller Bus Architecture (AMBA).

[0047] The computer system / server 12 typically includes various computer system-readable media. Such media may be any available media accessible by the computer system / server 12, and include both volatile and non-volatile media, removable and non-removable media.

[0048] The system memory 28 may include computer system-readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer system / server 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. As just one example, a storage system 34 may be provided for reading from and writing to a non-removable non-volatile magnetic medium (not shown, typically called a “hard drive”). Not shown, a magnetic disk drive for reading from and writing to removable non-volatile magnetic disks (e.g., “floppy disks”) and an optical disk drive for reading from and writing to removable non-volatile optical disks such as CD-ROMs, DVD-ROMs, or other optical media may be provided. In such cases, each may be connected to the bus 18 by one or more data media interfaces. As further shown and described below, the memory 28 may include at least one program product having a set of program modules (e.g., at least one of the program modules) configured to perform the functions of embodiments of the present disclosure.

[0049] A program / utility 40 having a set of program modules 42 (at least one of the program modules 42) may be stored, but not limited to, memory 28, as well as an operating system, one or more application programs, other program modules, and program data. Each of the operating system, one or more application programs, other program modules, and program data, or any combination thereof, may include an implementation of a networking environment. The program modules 42 generally perform the functions and / or methodologies of the embodiments described herein.

[0050] Furthermore, the computer system / server 12 may communicate with one or more external devices 14 such as a keyboard, pointing device, and display 24, one or more devices that allow a user to interact with the computer system / server 12, and / or any devices that allow the computer system / server 12 to communicate with one or more other computing devices (e.g., a network card, modem, etc.), and such communication can be performed via the input / output (I / O) interface 22. In addition, the computer system / server 12 may communicate with one or more networks such as a local area network (LAN), a general-purpose wide area network (WAN), and / or a public network (e.g., the Internet) via the network adapter 20. As shown in the figure, the network adapter 20 communicates with other components of the computer system / server 12 via the bus 18. It should be understood that other hardware and / or software components, not shown in the figure, can be used with the computer system / server 12. Examples include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archive storage systems.

[0051] This disclosure may be embodied as a system, method, and / or computer program product. For example, in some embodiments or in the present invention, this specification provides a computer program product for detecting cardiac amyloidosis, comprising a computer-readable storage medium embodied in program instructions, the program instructions being executable by a processor, the processor performing a method comprising receiving voltage-time data of a subject from an echocardiograph, wherein the voltage-time data includes voltage data of a plurality of leads; generating a feature vector from the voltage-time data; providing the feature vector to a pre-trained learning system; and receiving an indication from the pre-trained learning system of the presence or absence of cardiac amyloidosis in the subject. Generating the feature vector may include generating a spectrogram based on the voltage data of a plurality of leads. In some embodiments, generating the feature vector includes grouping the voltage data of a plurality of leads into a plurality of subsets.

[0052] In some embodiments, such a computer program product further includes receiving demographic information of a subject, and generating a feature vector includes adding the demographic information to the feature vector. In some such embodiments, the computer program further includes receiving genomic information of a subject. Generating a feature vector may include adding the genomic information to the feature vector. Without being bound by any particular methodology or theory, the genomic data may be derived from a biological sample from a hereditary ATTR patient carrying mutations. Such mutations are known in the art and may include, without limitation or exclusion, mutations V30M, Y114C, G47R, S50I, T49S, F33V, A45T, E89K, E89Q, and V122I. In some such embodiments, the computer program product comprises a convolutional neural network. Such a convolutional neural network may include at least one residual connection.

[0053] In some embodiments, the subject's voltage-time data is received from an electrocardiograph. In further embodiments, the subject's voltage-time data is received from an electronic medical record.

[0054] In some embodiments, the computer program product further includes providing a display to an electronic health record system for storing in health records associated with a subject. In some embodiments, the computer program product further includes providing a display to a computing node for display to a user.

[0055] In some embodiments of the computer program products disclosed herein, the feature vector may include a matrix having a plurality of rows and a plurality of columns, where the rows correspond to the time dimension and the columns correspond to the spatial dimension. In some such embodiments, each of the plurality of columns corresponds to one of a plurality of reads, and each of the plurality of columns corresponds to a timestamp. In some embodiments, the time dimension has a resolution of 500 Hz. In some embodiments, the convolutional neural network comprises at least nine convolutional blocks and two fully connected blocks.

[0056] The computer program products provided herein may include a computer-readable storage medium (or a set of computer-readable storage mediums) having computer-readable program instructions for causing a processor to perform aspects of this disclosure.

[0057] A computer-readable storage medium can be a tangible device capable of holding and storing instructions for use by an instruction execution device. A computer-readable storage medium may, but is not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. A non-exhaustive list of more specific examples of computer-readable storage media includes, namely, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital multipurpose disks (DVDs), memory sticks, floppy disks, mechanically encoded devices such as punched cards or grooved raised structures on which instructions are recorded, and any suitable combination thereof. The computer-readable storage media used herein should not be construed as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses passing through optical fiber cables), or transient signals themselves, such as electrical signals transmitted through wires.

[0058] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium or via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network, to an external computer or external storage device to each computing / processing device. The network may include copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface within each computing / processing device receives computer-readable program instructions from the network and transfers the computer-readable program instructions for storage in a computer-readable storage medium within the respective computing / processing device.

[0059] The computer-readable program instructions for performing the operations of the Disclosure may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk and C++, and conventional procedural programming languages ​​such as the C programming language or similar programming languages. The computer-readable program instructions may run entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or a connection may be made to an external computer (for example, via the Internet using an Internet service provider). In some embodiments, for example, an electronic circuit including a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA) may execute computer-readable program instructions by personalizing the electronic circuit using state information of computer-readable program instructions in order to perform an aspect of the present disclosure.

[0060] Aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It can be understood that each block in a flowchart and / or block diagram, and combinations of blocks in a flowchart and / or block diagram, can be implemented by computer-readable program instructions.

[0061] These computer-readable program instructions may be provided to a general-purpose computer, a dedicated computer, or a processor of another programmable data processing device in order to manufacture a machine such that instructions executed via the processor of a computer or other programmable data processing device create means for performing functions / operations specified in one or more blocks of a flowchart and / or block diagram. Alternatively, these computer-readable program instructions may be stored in a computer-readable storage medium that can be instructed to function in a particular manner, such that the storage medium containing the stored instructions includes articles containing instructions that perform the modes of functions / operations specified in one or more blocks of a flowchart and / or block diagram.

[0062] Furthermore, computer-readable program instructions may be loaded onto a computer, another programmable device, or another device to generate a computer implementation process by causing the computer, another programmable device, or other device to execute a series of steps on the computer, another programmable device, or other device so that the instructions executed on the computer, another programmable device, or other device perform the functions / operations specified in one or more blocks of a flowchart and / or block diagram.

[0063] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or part of instructions containing one or more executable instructions for implementing a specified logical function. In some alternative embodiments, the functions described in a block may be performed in a different order than shown in the figure. For example, two blocks shown consecutively may actually be executed substantially simultaneously, or blocks may sometimes be executed in reverse order depending on the functions they relate to. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs a specified function or operation, or a combination of dedicated hardware and computer instructions.

[0064] The descriptions of the various embodiments of this disclosure are presented for illustrative purposes only and are not intended to be exhaustive or limitful to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the embodiments described. The terms used herein have been chosen to best describe the principles of the embodiments, their practical applications or technical improvements to the technology found in the market, or to enable those skilled in the art to understand the embodiments disclosed herein.

[0065] example Example 1: Method Data Source and Study Population: The CA cohort consisted of 2,541 patients seen at the Mayo Clinic between January 1, 2000 and May 31, 2019, identified from the institutional amyloid database. Inclusion criteria included a diagnosis of ATTR or AL with cardiac involvement, and a digital 12-lead ECG within 180 days of diagnosis. Diagnosis of AL required a biopsy (cardiac or non-cardiac) with positive amyloid staining and typing by immunohistochemistry, immunofluorescence, or laser microdissection mass spectrometry. ATTR was diagnosed based on either a histological diagnosis or abnormalities detected by technetium Tc 99m pyrophosphate scintigraphy in the absence of evidence of AL amyloidosis. For AL and ATTRv, cardiac involvement was defined as any of the following: interventricular septal thickness greater than 12 mm, troponin T levels greater than 0.03 ng / L or N-terminal pro-B natriuretic peptide levels greater than 332 pg / mL, or any cardiac symptoms not attributable to other cardiac conditions. All patients with ATTRwt were considered to have cardiac involvement. Exclusion criteria included normal findings on endocardial biopsy, transthoracic echocardiography interpreted as negative for cardiac amyloid, and ventricular pacing at the time of ECG acquisition. Controls were selected from Mayo Clinic practices that were not present in the amyloid cohort and had performed at least one digital 12-lead ECG within 180 days of transthoracic echocardiography. Controls with echocardiograms interpreted as consistent with amyloidosis or infiltrative cardiomyopathy were excluded. Patients with prior cardiovascular surgery, poorly reported ECGs and echocardiograms, ECGs with invalid waveforms or ventricular pacing, and left ventricular ejection fraction less than 50% were excluded from the control group. Cases and controls were matched using the nearest neighbor algorithm for age and sex at a 1:1 ratio. ECGs in both the amyloid and control groups were digital, standard, 10-second, 12-lead ECGs acquired in the supine position. In addition to 12-lead ECG, single-lead and 6-lead ECG records were also obtained.

[0066] Model Development: Three datasets—training (n=2997; 60%), validation (n1 / 4999; 20%), and trial (n=999; 20%)—were prepared by assigning cases and controls by outcome-stratified random sampling. These proportions were selected to ensure an appropriate number of cases within each subset, and each patient was uniquely assigned to a single group.

[0067] The model architecture used is shown in Figure 10, and the input consists of raw ECG waveform data and a binary output predicting the presence or absence of CA. It should be noted that only raw data was used, and no manually extracted features were used.

[0068] The inventors implemented a convolutional neural network (CNN) using the Keras Framework with a Tensorflow (Google, Mountain View, California) backend and Python. While CNNs are primarily applied to images, the inventors tuned the network architecture to include spatial and temporal feature extraction layers. The network operates by adjusting the weights of convolutional filters during training to extract meaningful and relevant features in an unsupervised manner. The network was constructed using stacked blocks of convolution, max pooling, and batch normalization, followed by a nonlinear activation function for each block. After the first group of blocks extracted temporal features, another spatial block was used to fused the data from all reads, and then the extracted features were used in the fully connected network. Notably, the only data input for training was raw digital 12-lead ECG signals and the relevant classifications for each individual. Figure 10 summarizes the network architecture of the exemplary network. Hyperparameters (batch size, initial learning rate, number of neurons in the fully connected layer, and number of convolutional layers) were modified during training to obtain the optimal model based on the validation set.

[0069] Initial experiments were conducted using transfer learning, with the weights of the existing network being updated very slowly or completely frozen, but the best performance was found by retraining from scratch. Training consisted of 30 epochs with a batch size of 32 and a learning rate of 0.001. Category cross-entropy loss was used with either ATTR or AL one-hot coded labels for the positive case and Noamyloid for the negative case. The optimizer was Adam, and the final layer activation was softmax. 16 Alternative combinations of batch size and learning rate were systematically evaluated using a validation set with the highest-performing combination reported herein. During training, after each epoch, the network was evaluated on the validation set and the area under the receiver operating characteristic curve (AUC) was recorded. At the end of 30 epochs, the model with the highest validation set AUC was selected as optimal and evaluated on the test set.

[0070] To classify a given patient, the output probability was compared to a threshold that could be adjusted to different clinical scenarios, such as emphasizing sensitivity over specificity. Our primary analysis adjusted the threshold toward a balance between the two by selecting a point on the receiver operating characteristic curve of the validation set with the highest Youden index and designating the corresponding threshold as optimal. Single-lead and six-lead models were developed using similar architectures but with adapted layer shapes.

[0071] Main Analysis: AI-enabled ECG for detecting CA: The effectiveness of the model for detecting CA was evaluated using the nearest 12-lead ECG within 180 days of diagnosis. The performance in distinguishing patients with CA from non-amyloid controls was evaluated using receiver operating characteristic curves, with sensitivity and specificity assessed using two thresholds: one supporting higher sensitivity and the other maximizing the Youden index. Secondary analyses were performed using single-lead and 6-lead traces.

[0072] Subgroup analysis: Model performance was evaluated in subsets of patients based on age, sex, and amyloid subtype (AL, ATTRwt, and ATTRv), as well as in patients meeting the ECG criteria for low voltage, LVH, or "normal" ECG. Furthermore, baseline comorbidities and 12-lead ECG findings for CA patients and controls were reported. Categorical variables were reported as absolute numbers and percentages, while continuous variables were reported as mean values ​​with respect to standard deviation. Categorical variables were compared using the c² test, and continuous variables were compared using Student's t-test. R software package v3.6.2. 18 Statistical analysis was performed using [tool name], and the model was developed using TensorFlow 2.1.0 and Python 3.7.7. AP values ​​less than 0.005 were considered statistically significant.

[0073] Time Analysis: A time analysis was performed to evaluate the model's ability to detect CA before the clinical diagnosis date. For each patient with CA, all available ECGs recorded 6 months to 5 years prior to diagnosis were searched. The model output of amyloid probability was recorded for each follow-up, and the time from acquisition to the diagnosis date was recorded. The distribution of amyloid probability over time was evaluated using a violin plot. For patients with multiple ECGs within a given time bin, the median of the predicted amyloid probability score was used.

[0074] Example 2: Results Study population: Baseline characteristics, comorbidities, and 12-lead ECG findings at diagnosis are summarized in Tables 1-4. Most ATTRwt patients were male and over 60 years of age. CA patients, more commonly, had 12-lead ECG abnormalities compared to controls in all categories except left bundle branch block and QT interval prolongation. Atrial arrhythmias and conduction disorders were more common in ATTRwt than in AL, but low voltage ECG was more common in AL. Criteria for LVH were present in approximately 20% of ATTRwt patients. ECG characteristics were comparable between the training, test, and validation sets (Table 4).

[0075] [Table 1]

[0076] [Table 2]

[0077] [Table 3]

[0078] [Table 4]

[0079] Model Performance: The test set receiver operating characteristic curve for the 12-lead network is shown in Figure 5. An AUC of 0.91 (95% CI, 0.90–0.93) indicates excellent performance. Using an optimal probability threshold of 0.485, the sensitivity was 0.84 and the specificity was 0.85. In this 1:1 matched population, the positive predictive value was 0.86 and the negative predictive value was 0.84. The calibration curve (Figure 6) shows excellent linearity. Table 5 shows examples of performance at different probability thresholds and prevalence rates, including the equilibrium threshold and thresholds selected to make the test highly specific. Model predictions of CA probabilities in the control group are shown as a violin plot in Figure 7.

[0080] [Table 5]

[0081] The performance of single-lead and six-lead models was evaluated. V5 was the best single-lead model with an AUC of 0.86 and an accuracy of 0.78, and the other single-lead models performed similarly. The top six-lead models (1, 2, 3, aVR, aVL, aVF) had an AUC of 0.90 and an accuracy of 0.85.

[0082] Subgroup analysis: Model performance was similar across sex, age, and amyloid subtype (Table 6). Specificity was lower in individuals with low voltage or LVH, and while sensitivity was lower, specificity was higher in individuals with normal ECG interpretations.

[0083] [Table 6]

[0084] Time Analysis: ECGs were available in 396 CA patients within the range of 5 to 6 months prior to clinical diagnosis. Among patients with CA and pre-diagnostic ECG studies, the AI ​​model successfully predicted the presence of CA more than 6 months prior to clinical diagnosis in 234 (59%), identifying AL in 46% and ATTRwt in 70%. Figures 8A-8B show the distribution of amyloid probability over time prior to diagnosis with a 6-month increase in AL and ATTRwt. For AL patients, approximately half of the patients met the threshold of 0.485 digits 12 months prior to diagnosis, and for ATTR, most patients had scores above the median 48 months prior to diagnosis. An example of amyloid detection by the AI-ECG model 28 months prior to clinical diagnosis of AL amyloidosis is outlined in Figures 9A-B.

[0085] Example 3: Discussion Amyloid heart disease is associated with high morbidity and mortality, often leading to delayed diagnosis and poor outcomes. Given the emergence of effective treatments, there is an urgent clinical need for easily deployable and scalable trials for early detection. Because 12-lead ECGs are universal and inexpensive, they are ideally suited to be transformed into a tool to facilitate early diagnosis of CA by adding AL. This study yields four key findings. First, CA can be accurately predicted using AI 12-lead ECGs alone. Second, the model performed well across amyloid subtypes. Third, in a subset of patients with available serial ECGs, the model showed CA was nearly 60% ahead of clinical diagnosis. Fourth, the tool can be adapted to 6-lead and single-lead ECG acquisition and enables point-of-care screening with smartphone-compatible electrodes.

[0086] Cardiac amyloidosis has long been considered a rare disease, but research suggests that it is poorly diagnosed. The true prevalence of CA is unknown, but it is an area of ​​active investigation. Light chain (AL) amyloidosis still appears to be relatively rare, but recent evidence suggests that ATTRwt is perhaps not rare at all, as it is present in over 15% of patients undergoing transcatheter aortic valve replacement and 13% of patients with heart failure with preserved ejection fraction. The V122I TTR mutation is present in 3%–4% of Africans in the United States, resulting in a population of approximately 1.5 million individuals at risk of CA. Unfortunately, CA patients are often misdiagnosed as hypertrophic cardiomyopathy, hypertensive heart disease, or other causes of heart failure, leading to delayed or inadequate treatment.

[0087] The pathophysiological mechanisms of CA are complex, involving not only myocardial infiltration but also direct toxic effects on the heart; therefore, the term toxic invasive cardiomyopathy is more accurate. In addition to extracellular infiltration of the myocardium and replacement of cardiac tissue by electrically inactive amyloid deposits, the circulating light chain in AL amyloidosis causes myocyte dysfunction, and similar toxic effects can occur in ATTR amyloidosis. Myocyte hypertrophy has been reported in ATTRwt amyloidosis, which may explain the electrocardiographic findings of LVH in nearly 20% of these patients.

[0088] Because the AI ​​model can detect multiple simultaneous electrocardiogram features, it has the potential to detect these complex physiological changes early in the course of the disease. In other conditions such as ischemia and left ventricular dysfunction, electrical changes appear before structural changes are detected by echocardiography and well before the onset of symptoms. Despite significant differences in baseline 12-lead characteristics, the superior performance of the model in both AL and ATTR suggests that the AI ​​model can "see" amyloid-specific physiological changes that are not recognized by conventional ECG interpretation.

[0089] Advances in non-invasive imaging, including echocardiography and magnetic resonance imaging, have significantly improved the diagnosis of AL amyloidosis (CA). While echocardiography is a powerful tool for suggesting a diagnosis, it remains difficult to distinguish CA from other causes of increased wall thickness. Variations in the degree and distribution of CA can lead to non-classical echocardiographic and magnetic resonance imaging findings, potentially resulting in delayed diagnosis. Some patients with AL amyloidosis have normal or slightly increased wall thickness despite the rapidly progressing disease, and establishing a diagnosis several months in advance can allow valuable time to respond to treatment.

[0090] Therefore, the key to diagnosing CA is the index of high clinical suspicion. Most patients ultimately diagnosed with CA had undergone an ECG at some point in the diagnostic process. Since diagnostic algorithms are readily available, the important thing for clinicians is to consider the diagnosis. Apart from developing a final diagnostic test, a method of utilizing data already obtained by electrocardiography is disclosed herein. Early diagnosis is important in both cases, and since typing is done by other techniques and by including ATTR, the usefulness of this model is extended to the "not so rare" forms of amyloid, AL and ATTR were included. The AI ​​model is intended to maximize the diagnostic yield of ECG, including suggesting diagnoses that have not yet been considered. The studies disclosed herein have found that an AI model using only ECG can accurately predict CA without requiring other clinical or imaging variables. The accuracy of single-lead and six-lead acquisitions enables implementation on mobile devices.

[0091] We evaluated the model's performance across various amyloid subtypes and, for the first time, demonstrated the ability of an AI-ECG tool to detect amyloid heart disease before clinical diagnosis. The 12-lead model was extended to include previously unreported single-lead and 6-lead ECG acquisition.

[0092] To address the loss of AI-enhanced models for ECG analysis in detecting low ejection fraction, atrial fibrillation, and hypertrophic cardiomyopathy, an "AI-ECG Dashboard" was created for use in clinical practice. This tool is accessible via electronic medical records and can be easily integrated into implementation. Further validation suggests that incorporating AI-ECG models for CA detection provides a crucial new tool for facilitating timely diagnosis and improved outcomes.

[0093] The use of AI-ECG models may prove useful in determining prognosis, the risk of sudden cardiac death, and the response to treatment. This model may enable early detection of cardiac involvement in ATTRv carriers or in patients with ATTR detected in non-cardiac tissues such as the carpal tunnel and spinal ligaments. While ATTRwt amyloidosis has been reported to have a male-dominant prevalence of over 90% in most previous studies, women also develop this condition and may be poorly diagnosed. AI-ECG models may suggest a diagnosis of ATTRwt amyloidosis in women without classical echocardiographic findings. The ability to use single-lead and six-lead acquisitions makes it promising for simple, cost-effective, and comprehensive screening, particularly in at-risk populations with limited access to advanced cardiac imaging.

[0094] Cardiac amyloidosis can occur well before clinical diagnosis, resulting in electrocardiogram changes detectable by the application of AI to standard ECGs, a universal and inexpensive test. Despite increased awareness and improvements in imaging techniques, delays in diagnosing CA still have tragic consequences. The use of this AI-ECG model to detect CA could facilitate early diagnosis and the initiation of potential life-saving treatments.

[0095] References 1. Muchtar E, Gertz MA, Kumar SK, et al. Improved outcomes of newly diagnosed AL amyloidosis from 2000 to 2014: Cracking the glass ceiling of early mortality. Blood. 2017;129(15):2111-2119. 2. Lousada I, Comenzo RL, Landau H, Guthrie S, Merlini G. Light chain amyloidosis: A patient experience survey from the Amyloidosis Research Consortium. Adv Ther. 2015;32(10):920-928. 3. Ruber FL, Grogan M, Hanna M, Kelly JW, Maurer MS. Trans-thyretin amyloid cardiomyopathy: JACC cutting-edge review. J Am Coll Cardiol. 2019;73(22):2872-2891. 4. Alexander KM, Evangelisti A, Witteles RM. Diagnosis and treatment of cardiac amyloidosis associated with plasma cell abnormalities. Cardiol Clin. 2019;37(4):487-495. 5. Maurer MS, Schwartz JH, Gundapaneni B, et al. Treatment of patients with transthyretin amyloid cardiomyopathy with tafamidis. N Engl J Med. 2018;379(11):1007-1016. 6. Falk RH, Alexander KM, Liao R, Dorbala S. AL (light chain) cardiac amyloidosis: A review of diagnosis and treatment. J Am Coll Cardiol. 2016;68(12):1323-1341. 7. Gertz MA, Dispenzieri A, Sher T. Pathophysiology and treatment of cardiac amyloidosis. Nat Rev Cardiol. 2015;12(2):91-102. 8. Grogan M, Scott CG, Kyle RA, et al. Natural history of wild-type transthyretin cardiac amyloidosis and risk stratification using a novel staging system. [Correction published in J Am Coll Cardiol. 2017;69(23):2882]. J Am Coll Cardiol. 2016;68(10):1014-1020. 9. Gillmore D, Maurer MS, Falk RH, et al. Non-biopsy diagnosis of cardiac transthyretin amyloidosis. 2016;133(24):2404-2412. 10. Sperry BW, Ikram A, Hachamovitch R, et al. Efficacy of chemotherapy for light chain amyloidosis in patients presenting with symptomatic heart failure. J Am Coll Cardiol. 2016;67(25):2941-2948. 11. Murtagh B, Hammill SC, Gertz MA, Kyle RA, Tajik AJ, Grogan M. Electrocardiographic findings in primary systemic amyloidosis and biopsy-proven cardiac lesions. Am J Car-Diol. 2005;95(4):535-537. 12. Ko WY, Siontis KC, Attia ZI, et al. Detection of hypertrophic cardiomyopathy using convolutional neural network-enabled electrocardiogram. J Am Coll Cardiol. 2020;75(7):722-733. 13. Vrana JA. Classification of amyloidosis by proteomic analysis based on laser microdissection and mass spectrometry in clinical biopsy specimens. Blood. 2009;114(24):4957-4959. 14. Dorbala S, Ando Y, Bokhari S, et al. Expert consensus recommendations on multimodality imaging in ASNC / AHA / ASE / EANM / HFSA / ISA / SCMR / SNMMI cardiac amyloidosis: Part 2 of 2D diagnostic criteria and appropriate use. J Card Fail. 2019;25(11):854-865. 15. Attia ZI, Friedman PA, Noseworthy PA, et al. Age and sex estimation using artificial intelligence from standard 12-lead ECG. Circ Arrhythm Electrophysiol. 2019;12(9):e007284. 16. Goodfellow I, Bengio Y, Courville A. Deep Learning. Cambridge, MA: The MIT Press; 2016. 17. Youden WJ Index for evaluating diagnostic tests. Cancer. 1950;3(1):32-35. 18. R Core Team. R: Language and Environment for Statistical Computing, Version 3.5.3. Vienna, Austria: R Foundation for Statistical Computing; 2019. 19. Gurwitz JH, Maurer MS. A costly treatment for a relatively common disease using tafamidisda. JAMA Cardiol. 2020;5(3):247-248. 20. Castano A, Narotsky DL, Hamid N, et al. Elucidation of transthyretin cardiac amyloidosis and its predictors in elderly patients with severe aortic stenosis undergoing transcatheter aortic valve replacement. Eur Heart J. 2017;38(38):2879-2887. 21. Gonzalez-Lopez E, Gallego-Delgado M, Guzzo-Merello G, et al. Wild-type transthyretin amyloidosis as a cause of heart failure with preserved ejection fraction. Eur Heart J. 2015;36(38):2585-2594. 22. Buxbaum JN, Ruberg FL. Transthyretin V122I (pV142I)* cardiac amyloidosis: An age-related autosomal dominant heart disease that is not so common as to be overlooked as a cause of serious heart disease in elderly African Americans. Genet Med. 2017;19(7):733-742. 23. Rapezzi C, Merlini G, Quarta CC. Systemic cardiac amyloidoses: Disease profiles and clinical courses of three major types. Circulation. 2009;120(13):1203-1212. 24. Maleszewski JJ. Cardiac amyloidosis: Pathology, nomenclature, and typing. Cardiovascular Pathway. 2015;24(6):343-350. 25. Fealey ME, Edwards WD, Buadi FK, Syed IS, Grogan M. Echocardiographic characteristics of cardiac amyloidosis presenting as endocardial cardiomyopathy in a 54-year-old male. J Cardiol. 2009;54(1):162-166. 26. Suresh R. Advanced cardiac amyloidosis associated with normal ventricular septal thickness: A rare symptom of infiltrative cardiomyopathy. J Am Soc Echocardiography 2014;27(4):440-447. 27. Tison GH, Zhang J, Delling FN, Deo RC. Automated, preconfigurable patient ECG profiling for disease detection, tracking, and discovery. Qual outcomes for circulatory cardiovascular disease. 2019;12(9):e005289.

[0096] All publications (including patents, patent applications, and sequence access numbers referenced herein) are incorporated herein by reference in whole, as if each individual publication were specifically and individually incorporated by reference. In case of any conflict, the present application, including any definitions herein, shall prevail.

[0097] Those skilled in the art will recognize many equivalents to the specific embodiments of the invention described herein, or can confirm them by routine experimentation alone. Such equivalents are intended to be covered by the following claims.

Claims

1. Receiving voltage-time data from a subject, wherein the voltage-time data includes voltage data from multiple leads of an electrocardiograph. The process involves generating a feature vector from the aforementioned voltage-time data, The feature vector is provided to a learning system that has been pre-trained to determine the presence or absence of cardiac amyloidosis (CA), The pre-trained learning system receives an indication of the presence or absence of CA in the subject, A method that includes this.

2. The method according to claim 1, wherein generating the feature vector includes generating a spectrogram based on the voltage data of the plurality of leads.

3. The method according to claim 1, wherein generating the feature vectors includes grouping the voltage data of the plurality of leads into a plurality of subsets.

4. The process further includes receiving demographic information of the subject, and generating the feature vector includes adding the demographic information to the feature vector. The method according to claim 1.

5. The process further includes receiving the genomic information of the subject, and generating the feature vector includes adding the genomic information to the feature vector. The method according to claim 1.

6. The method according to claim 1, wherein the learning system comprises a convolutional neural network.

7. The method according to claim 6, wherein the convolutional neural network includes at least one residual connection.

8. The method according to claim 1, wherein the voltage-time data of the subject is received from an electrocardiograph.

9. The method according to claim 1, wherein the voltage-time data of the subject is received from an electronic medical record.

10. To provide the display to an electronic health record system for storage in a health record associated with the subject. The method according to claim 1, further comprising:

11. Provide the computing node with the display for display to the user. The method according to claim 1, further comprising:

12. The method according to claim 1, wherein the feature vector includes a matrix having a plurality of rows and a plurality of columns, the plurality of rows corresponding to the time dimension and the plurality of columns corresponding to the spatial dimension.

13. The method according to claim 12, wherein each of the plurality of rows corresponds to a timestamp and each of the plurality of columns corresponds to one of the plurality of reads.

14. The method according to claim 12, wherein the time dimension has a resolution of 500 Hz.

15. The method according to claim 6, wherein the convolutional neural network comprises at least nine convolutional blocks and two fully connected blocks.

16. An electrocardiograph equipped with multiple leads, A computing node comprising a computer-readable storage medium embodied by program instructions, wherein the program instructions are executable by the processor of the computing node, and thereby the processor, Receiving voltage-time data of a subject from an echocardiograph, wherein the voltage-time data includes the voltage data of the plurality of leads. The process involves generating a feature vector from the aforementioned voltage-time data, The feature vector is provided to a learning system that has been pre-trained to determine the presence or absence of cardiac amyloidosis (CA), The pre-trained learning system receives an indication of the presence or absence of CA in the subject, A computing node that performs a method including, A system equipped with these features.

17. The system according to claim 16, wherein generating the feature vector includes generating a spectrogram based on the voltage data of the plurality of leads.

18. The system according to claim 16, wherein generating the feature vectors includes grouping the voltage data of the plurality of leads into a plurality of subsets.

19. The process further includes receiving demographic information of the subject, and generating the feature vector includes adding the demographic information to the feature vector. The system according to claim 16.

20. The process further includes receiving the genomic information of the subject, and generating the feature vector includes adding the genomic information to the feature vector. The system according to claim 16.

21. The system according to claim 16, wherein the learning system comprises a convolutional neural network.

22. The system according to claim 21, wherein the convolutional neural network includes at least one residual connection.

23. The system according to claim 16, wherein the voltage-time data of the subject is received from an electrocardiograph.

24. The system according to claim 16, wherein the voltage-time data of the subject is received from an electronic medical record.

25. To provide the display to an electronic health record system for storage in a health record associated with the subject. The system according to claim 16, further comprising:

26. Provide the computing node with the display for display to the user. The system according to claim 16, further comprising:

27. The system according to claim 16, wherein the feature vector includes a matrix having a plurality of rows and a plurality of columns, the plurality of rows corresponding to the time dimension and the plurality of columns corresponding to the spatial dimension.

28. The system according to claim 27, wherein each of the plurality of rows corresponds to a timestamp, and each of the plurality of columns corresponds to one of the plurality of reads.

29. The system according to claim 27, wherein the time dimension has a resolution of 500 Hz.

30. The system according to claim 21, wherein the convolutional neural network comprises at least nine convolutional blocks and two fully connected blocks.

31. A computer program product for detecting cardiac amyloidosis (CA), comprising a computer-readable storage medium embodied in program instructions, wherein the program instructions are executable by a processor, and thereby the processor, Receiving voltage-time data of a subject, wherein the voltage-time data includes voltage data from multiple leads of an echocardiograph. The process involves generating a feature vector from the aforementioned voltage-time data, The feature vector is provided to a learning system that has been pre-trained to determine the presence or absence of CA, The pre-trained learning system receives an indication of the presence or absence of CA in the subject, A computer program product that performs a method including the following.

32. The computer program product according to claim 31, wherein generating the feature vectors includes generating a spectrogram based on the voltage data of the plurality of reads.

33. The computer program product according to claim 31, wherein generating the feature vectors includes grouping the voltage data of the plurality of leads into a plurality of subsets.

34. The process further includes receiving demographic information of the subject, and generating the feature vector includes adding the demographic information to the feature vector. The computer program product according to claim 31.

35. The process further includes receiving the genomic information of the subject, and generating the feature vector includes adding the genomic information to the feature vector. The computer program product according to claim 31.

36. The computer program product according to claim 31, wherein the learning system comprises a convolutional neural network.

37. The computer program product according to claim 36, wherein the convolutional neural network includes at least one residual connection.

38. The computer program product according to claim 31, wherein the voltage-time data of the subject is received from an electrocardiograph.

39. The computer program product according to claim 31, wherein the voltage-time data of the subject is received from an electronic medical record.

40. To provide the display to an electronic health record system for storage in a health record associated with the subject. The computer program product according to claim 31, further comprising:

41. Provide the computing node with the display for display to the user. The computer program product according to claim 31, further comprising:

42. The computer program product according to claim 31, wherein the feature vector includes a matrix having a plurality of rows and a plurality of columns, the plurality of rows corresponding to the time dimension and the plurality of columns corresponding to the spatial dimension.

43. The computer program product according to claim 42, wherein each of the plurality of rows corresponds to a timestamp and each of the plurality of columns corresponds to one of the plurality of reads.

44. The computer program product according to claim 42, wherein the time dimension has a resolution of 500 Hz.

45. The computer program product according to claim 36, wherein the convolutional neural network comprises at least nine convolutional blocks and two fully connected blocks.

Images