SYSTEM, METHOD, AND COMPUTER PROGRAM PRODUCT FOR MANAGING AUTOMATED HEALTHCARE DATA APPLICATIONS USING ARTIFICIAL INTELLIGENCE - Patent application

Abstract

A system for managing an automated healthcare data application using artificial intelligence (AI) is provided, the system comprising at least one processor configured to receive healthcare data from a data source and determine a classification of the healthcare data using a machine learning model, the machine learning model configured to provide a predicted classification of one of a plurality of automated healthcare data analysis applications based on an input, and the at least one processor programmed or configured to provide the healthcare data to the automated healthcare data analysis application based on the classification of the healthcare data. Methods and computer program products are also disclosed.

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. Provisional Patent Application No. 63 / 319,983, filed March 15, 2022, the disclosure of which is incorporated by reference herein in its entirety.

[0002] The present disclosure relates generally to managing health informatics applications and, in some non-limiting embodiments, to systems, methods, and computer program products that provide for managing automated healthcare data analysis applications using artificial intelligence, in particular machine learning models. [Background technology]

[0003] Health informatics may refer to the field of science and engineering that develops methods and techniques for acquiring, processing, and / or studying healthcare data associated with patients (e.g., medical data, patient data, etc.). In some cases, the healthcare data may come from different sources and / or modalities, such as electronic medical records (e.g., electronic health records), diagnostic test results, and / or medical scans. Health informatics applications may include solutions to problems encountered with medical data and the analysis of such medical data using computational techniques.

[0004] Artificial intelligence (AI) may be used in healthcare as a way to mimic human cognition in analyzing, presenting, and / or understanding healthcare data. AI may describe the ability of a computer program, such as a computer algorithm, to approach a conclusion based on input data, which may be medical data. In some cases, computer algorithms may be used to recognize patterns in the data and create logic to identify such patterns. Such computer algorithms may include machine learning models trained to perform specific tasks using large amounts of input data. In some cases, health informatics applications may include AI-based health informatics applications.

[0005] However, health informatics applications may be implemented in settings where complex programming and processing resources are required to provide input data in the form of patient-associated healthcare data to the health informatics applications for data analysis tasks. Thus, manually programmed processes developed to provide input data to the health informatics applications may require significant network resources, may require constant manual updates, and may be inaccurate. Summary of the Invention [Problem to be solved by the invention]

[0006] Accordingly, disclosed are systems, methods, and computer program products that provide for managing automated healthcare data analysis applications using artificial intelligence (AI), in particular machine learning models. [Means for solving the problem]

[0007] Clause 1: A system for managing an automated healthcare data analytic application using artificial intelligence (AI), comprising at least one processor configured to receive healthcare data from a data source and determine a classification of the healthcare data using a machine learning model, the machine learning model configured to provide a predicted classification of one automated healthcare data analytic application of a plurality of automated healthcare data analytic applications based on an input, and provide healthcare data to the automated healthcare data analytic application based on the classification of the healthcare data, the system comprising at least one processor programmed or configured to:

[0008] Clause 2: The system of clause 1, wherein the at least one processor is further programmed or configured to transmit output of the automated healthcare data analysis application to a destination system.

[0009] Clause 3: The system of clause 1 or 2, wherein the destination system comprises a picture archiving and communication system (PACS), an electronic medical record (EMR) system, a data reporting system, a communication device associated with a medical device, or a user device associated with a patient.

[0010] Clause 4: The system of any of clauses 1 to 3, wherein at least one processor is further programmed or configured to train a machine learning model based on historical healthcare data from a plurality of data sources.

[0011] Clause 5: The system of any of clauses 1 to 4, wherein the machine learning model is configured to receive as input a data record, the data record including at least one feature, the at least one feature including at least one feature associated with an anatomical aspect of the body, at least one feature associated with a protocol of the device, at least one feature associated with a natural language processing characteristic, at least one feature associated with manual configuration of the device, or any combination thereof.

[0012] Clause 6: The system of any of clauses 1 to 5, wherein the machine learning model is configured to determine whether the at least one feature includes a categorical feature associated with an anatomical aspect of the body, a categorical feature associated with a protocol of the device, a categorical feature associated with a characteristic of natural language processing, a categorical feature associated with a manual configuration of the device, or any combination thereof.

[0013] Clause 7: The system of any of clauses 1 to 6, wherein the data source comprises an electronic medical record (EMR) system, a medical imaging system, a communication device associated with a medical device, a fluid injection system, a pathology information system, a laboratory information system, or a user device associated with a patient.

[0014] Clause 8: The system of any of clauses 1 to 7, wherein the automated healthcare data analysis application comprises an AI-based healthcare data analysis application.

[0015] Clause 9: A computer program product for managing an automated healthcare data analytic application using artificial intelligence (AI), comprising: at least one non-transitory computer-readable medium including one or more instructions that, when executed by at least one processor, cause the at least one processor to receive healthcare data from a data source and determine a classification of the healthcare data using a machine learning model, the machine learning model being configured to provide a predicted classification of one of a plurality of automated healthcare data analytic applications based on an input, and provide healthcare data to the automated healthcare data analytic application based on the classification of the healthcare data.

[0016] Clause 10: The computer program product of clause 9, wherein the one or more instructions further cause the at least one processor to transmit output of the automated healthcare data analysis application to a destination system.

[0017] Clause 11: A computer program product as described in clause 9 or 10, wherein the destination system comprises a picture archiving and management system (PACS), an electronic medical record (EMR) system, a data reporting system, a communication device associated with a medical device, or a user device associated with a patient.

[0018] Clause 12: The computer program product of any of clauses 9 to 11, wherein the one or more instructions further cause at least one processor to train a machine learning model based on historical healthcare data from a plurality of data sources.

[0019] Clause 13: The computer program product of any of clauses 9 to 12, wherein the machine learning model is configured to receive as input a data record, the data record including at least one feature, the at least one feature including at least one feature associated with an anatomical aspect of the body, at least one feature associated with a protocol of the device, at least one feature associated with a natural language processing characteristic, at least one feature associated with manual configuration of the device, or any combination thereof.

[0020] Clause 14: The computer program product of any of clauses 9 to 13, wherein the machine learning model is configured to determine whether the at least one feature includes a categorical feature associated with an anatomical aspect of the body, a categorical feature associated with a protocol of the device, a categorical feature associated with a characteristic of natural language processing, a categorical feature associated with a manual configuration of the device, or any combination thereof.

[0021] Clause 15: A computer program product described in any of clauses 9 to 14, wherein the data source comprises an electronic medical record (EMR) system, a medical imaging system, a communication device associated with a medical device, a fluid injection system, a pathology information system, a laboratory information system, or a user device associated with a patient.

[0022] Clause 16: The computer program product of any of clauses 9 to 15, wherein the automated healthcare data analysis application comprises an artificial intelligence (AI)-based healthcare data analysis application.

[0023] Clause 17: A method for managing an automated healthcare data analysis application using artificial intelligence, the method comprising: receiving healthcare data from a data source; determining a classification of the healthcare data using a machine learning model, the machine learning model configured to provide a predicted classification of one automated healthcare data analysis application of a plurality of automated healthcare data analysis applications based on an input; and providing the healthcare data to the automated healthcare data analysis application based on the classification of the healthcare data.

[0024] Clause 18: The method of clause 17, further comprising transmitting an output of the automated healthcare data analysis application to a destination system.

[0025] Clause 19: The method of clause 17 or 18, further comprising training a machine learning model based on historical healthcare data from a plurality of data sources.

[0026] Clause 20: The method of any of clauses 17 to 19, wherein the machine learning model is configured to receive as input a data record, the data record including at least one feature, the at least one feature including at least one feature associated with an anatomical aspect of the body, at least one feature associated with a protocol of the device, at least one feature associated with a natural language processing characteristic, at least one feature associated with manual configuration of the device, or any combination thereof.

[0027] These and other features and characteristics of the present disclosure, as well as the method of operation and function of the associated elements of structure, and the combination of parts and economies of manufacture, will become more apparent from a consideration of the following description and the appended claims, with reference to the accompanying drawings, all of which form a part hereof, and in which like reference numerals indicate corresponding parts in the various views. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the present disclosure. As used in this specification and claims, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise.

[0028] Further advantages and details of the non-limiting embodiments are explained in more detail below with reference to exemplary embodiments illustrated in the accompanying schematic drawings. [Brief description of the drawings]

[0029] [Figure 1] FIG. 1 illustrates a non-limiting embodiment of an environment in which the systems, methods, and / or computer program products described herein may be implemented in accordance with the present disclosure. [Diagram 2] FIG. 2 is a diagram of a non-limiting embodiment of components of one or more devices and / or one or more systems of FIG. [Diagram 3] 1 is a flowchart of a non-limiting embodiment of a process for managing an automated healthcare data analysis application using artificial intelligence (AI). [Figure 4] FIG. 1 is a diagram of a non-limiting embodiment of an AI data management system. [Figure 5A] FIG. 1 illustrates a non-limiting embodiment of an implementation of a process for managing an automated healthcare data analytics application using AI. [Figure 5B] FIG. 1 illustrates a non-limiting embodiment of an implementation of a process for managing an automated healthcare data analytics application using AI. [Figure 5C]FIG. 1 illustrates a non-limiting embodiment of an implementation of a process for managing an automated healthcare data analytics application using AI. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0030] For purposes of the following description, the terms "end", "top", "bottom", "right", "left", "vertical", "horizontal", "top", "bottom", "lateral", "longitudinal", and their derivatives shall refer to the present disclosure as oriented in the drawings. However, it should be understood that the present disclosure may contemplate various alternative variations and sequences of steps unless expressly specified to the contrary. It should also be understood that the specific devices and processes illustrated in the accompanying drawings and described in the following specification are merely exemplary embodiments of the present disclosure. Thus, specific dimensions and other physical characteristics associated with the embodiments disclosed herein are not to be considered as limiting, unless otherwise indicated.

[0031] As used herein, aspects, components, elements, structures, acts, steps, functions, instructions, and the like should not be construed as critical or required unless expressly stated as such. Also, as used herein, the articles "a" and "an" are intended to include one or more items and may be used interchangeably with "one or more" and "at least one." Additionally, as used herein, the term "set" is intended to include one or more items (e.g., related items, unrelated items, combinations of related and unrelated items, etc.) and may be used interchangeably with "one or more" or "at least one." When only one item is intended, the term "one" or similar terms are used. Also, as used herein, terms such as "has," "have," "having," and the like are intended to be open-ended terms. Additionally, the phrase "based on" is intended to mean "based at least in part on" unless otherwise specified. The phrase "based on" may also mean "in response to" where appropriate.

[0032] As used herein, the terms "communication" and "communicating" can refer to receiving, accepting, sending, forwarding, providing, etc., information (e.g., data, signals, messages, instructions, commands, etc.). One unit (e.g., a device, a system, a component of a device or system, combinations thereof, etc.) communicating with another unit means that one unit can directly or indirectly receive information from the other unit and / or transmit information to the other unit. This may refer to a direct or indirect connection that is wired and / or wireless in nature. Furthermore, two units can communicate with each other even if the transmitted information is modified, processed, relayed, and / or routed between the first unit and the second unit. For example, a first unit can communicate with a second unit even if the first unit passively receives information and does not actively transmit information to the second unit. As another example, a first unit can communicate with a second unit if at least one intermediate unit (e.g., a third unit located between the first unit and the second unit) processes information received from the first unit and transmits the processed information to the second unit. In some non-limiting embodiments, information may refer to network packets containing data (e.g., data packets, etc.).

[0033] Systems, methods, and computer program products are disclosed that provide solutions to the above-mentioned problems. For example, as disclosed herein, a system for managing an automated healthcare data analysis application using artificial intelligence (AI) may include at least one processor programmed or configured to receive healthcare data from a data source, determine a classification of the healthcare data using a machine learning model, the machine learning model configured to provide a predicted classification of one of a plurality of automated healthcare data analysis applications based on an input, and provide the healthcare data to the automated healthcare data analysis application based on the classification of the healthcare data.

[0034] In some non-limiting embodiments, the at least one processor is further programmed or configured to send an output of the automated healthcare data analysis application to a destination system. In some non-limiting embodiments, the destination system comprises a picture archiving and communication system (PACS), an electronic medical record (EMR) system, a data reporting system, a communication device associated with the medical device, and / or a user device associated with the patient. In some non-limiting embodiments, the at least one processor is further programmed or configured to train a machine learning model based on the healthcare data from the multiple data sources.

[0035] In some non-limiting embodiments, the machine learning model is configured to receive as input a data record, the data record including at least one feature, the at least one feature including at least one feature associated with an anatomical aspect of the body, at least one feature associated with a protocol of the device, at least one feature associated with a natural language processing characteristic, and / or at least one feature associated with a manual configuration of the device. In some non-limiting embodiments, the machine learning model is configured to determine whether the at least one feature includes a category feature associated with an anatomical aspect of the body, a category feature associated with a protocol of the device, a category feature associated with a natural language processing characteristic, and / or a category feature associated with a manual configuration of the device.

[0036] In some non-limiting embodiments, the data source comprises an EMR system, a medical imaging system, a communication device associated with a medical device, a fluid injection system, a pathology information system, a laboratory information system, and / or a user device associated with a patient. In some non-limiting embodiments, the automated healthcare data analysis application comprises an AI-based healthcare data analysis application.

[0037] In this manner, the present disclosure provides a system for managing automated healthcare data analysis applications using AI that reduces the amount of network resources required compared to manually programmed processes. Additionally, the system reduces the need for manually updating process rules for managing the automated healthcare data analysis applications and improves accuracy regarding how healthcare data is provided to the automated healthcare data analysis applications.

[0038] Reference is now made to Figure 1, which is a diagram of a non-limiting embodiment of an environment 100 in which the devices, systems, methods, and / or computer program products described herein may be implemented. As shown in Figure 1, the environment 100 includes an artificial intelligence (AI) data management system 102, data sources 104-1 to 104-N (hereinafter, individually referred to as a data source 104 or collectively referred to as multiple data sources 104, as appropriate), destination systems 106-1 to 106-N (hereinafter, individually referred to as a destination system 106 or multiple destination systems 106, as appropriate), and AI application systems 108-1 to 108-N (hereinafter, individually referred to as an AI application system 108 or collectively referred to as multiple AI application systems 108, as appropriate).

[0039] The AI ​​data management system 102 may interconnect (e.g., establish connections to communicate, etc.) with the data sources 104, the destination systems 106, and / or the AI ​​application systems 108 via a communications network 112. In some non-limiting embodiments, the AI ​​data management system 102 may interconnect (e.g., establish connections to communicate, etc.) with the data sources 104, the destination systems 106, and / or the AI ​​application systems 108 via wired connections, wireless connections, or a combination of wired and wireless connections.

[0040] In some non-limiting embodiments, the AI ​​data management system 102 may include one or more devices capable of communicating with the data sources 104, the destination system 106, and / or the AI ​​application system 108 via the communication network 112. For example, the AI ​​data management system 102 may include a server, a group of servers, a telecommunications gateway (e.g., a network gateway), a universal gateway, a router, and / or other similar devices. Additionally or alternatively, the AI ​​data management system 102 may include a computing device such as a desktop computer, a mobile device (e.g., a tablet, a smartphone, a wearable device, etc.). In some non-limiting embodiments, the AI ​​data management system 102 may include one or more (e.g., multiple) applications (e.g., software applications) that perform a set of functions on an external application programming interface (API) to send data to an external system, such as the destination system 106 or the AI ​​application system 108 associated with the external API, and receive data from an external system associated with the external API. In some non-limiting embodiments, the AI ​​data management system 102 may include one or more subsystems. For example, the AI ​​data management system 102 may include one or more subsystems that perform anatomical intelligence (e.g., body part detection), one or more subsystems that perform modality (e.g., modality of patient procedure associated with the healthcare data) detection, and / or one or more subsystems that perform text analysis intelligence (e.g., word or phrase identification and analysis, such as natural language processing). By way of example, the AI ​​data management system 102 may include a smart AI router that accepts image data and other associated healthcare data from multiple sources related to the patient's image data.The data may include DICOM data, Health Level 7 (HL7) order information, EMR data, laboratory data, prescription (e.g., Rx) information, previous AI reports and additional reports from the AI, pathology data, wearable data, healthcare billing codes, and other healthcare data.

[0041] DICOM data may include inputs used for processing. DICOM data may be sent to the smart AI router from a PACS or modality (e.g., a device included in a healthcare system such as a fluid injection system) or retrieved from a modality and / or PACS. DICOM data may be from any medical equipment (e.g., medical imaging equipment) including but not limited to CT, MRI, X-ray, mammogram, ultrasound, positron emission tomography (PET) exam, and / or single photon emission computed tomography exam. HL7 order information may include data that can provide additional details about the imaging study, such as the reason for the exam. EMR data may include data that can provide additional details about the patient's health history, such as tobacco use (e.g., smoking history). Laboratory data may include data that provides information that can be used in addition to image data to evaluate associated disease states. Prescription information may include data identifying medications that the patient is taking / has taken, which may be used to evaluate the relevance of the AI ​​process and track disease progression, for example, for clinical trial eligibility / effectiveness of the medication as assessed by the image data. Previous AI reports and additional reports from the AI ​​may include data regarding the output of one AI application to determine other AI applications to send research to. For example, a lung nodule detection AI application may provide an output that is sent to a nodule characterization AI application. Wearable data may include data from continuous glucose monitoring devices, single-lead EKG devices, etc. Other health data may include data from other data sources that track patient health information that may be relevant to disease management use cases.

[0042] In such an example, the smart AI router may include an image analyzer module that uses pixel information, and in some cases, without relying on DICOM header data such as a study description, to detect body parts and their anatomical contexts (e.g., body parts such as lungs, and anatomical contexts such as carina, prone or supine, etc.) present in the image data. The image analyzer module may operate based on pixel data in the same way on both de-identified and non-de-identified data.

[0043] The image analyzer module may verify if the image data has all series and / or images required to consider the study complete according to the protocol used to acquire the images. For example, if the study is a brain MRI, the image analyzer module will verify if T1, T2 diffusion weighted imaging (DWI) series are present for a brain tumor assessment protocol. Additionally, the smart AI router will analyze this image to determine if contrast was applied and differentiate AI applications that require contrast examination for successful processing. The image analyzer module also verifies image quality to ensure that the image data is useful if sent to the AI ​​for processing.

[0044] The smart AI router may include a matching module that takes the output of the image analyzer module and compares the output with the input requirement parameters of all AI applications for the body region to identify AI applications that may be eligible for processing. The matching module has a database of AI applications and corresponding input requirements. The matching module provides a user interface for an administrator to view and add new AI applications or change parameters as needed.

[0045] The matching module may compare the list of eligible AI applications to be processed with the customer's guidelines for processing. The customer guidelines may be driven by the need to limit unnecessary processing or processing that the patient cannot reimburse and / or pay for. The smart AI router saves the applied customer guidelines as a preset for use in subsequent processing. In the absence of customer-specific guidelines for the use of the AI ​​application, the matching module matches the list against standard guidelines (e.g., national / regional / industry standard guidelines), such as the lung cancer screening guidelines by the U.S. Centers for Medicare / Medicaid Services (CMS), which recommend patients over 50 years of age and a smoking history of at least 20 pack years to undergo screening. The matching module has a database of guidelines (e.g., customer-specific and / or industry-specific standard) and provides a user interface for the administrator to view and add new AI applications or change the guidelines as needed. In the CMS guideline example, the CMS guideline changed from 55 to 50 years, and the user interface allows updating the guidelines when they change. Guideline inputs can also come from other AI application processing.

[0046] The smart AI router may include a recommendation module that evaluates disease conditions that need to be assessed by the AI ​​application for diagnosis, detection, quantification, or adjunctive screening based on patient health data or outcome measures. In some examples, the recommendation module may operate in the absence of customer or industry guidelines.

[0047] The Smart AI Router may assign priorities for AI processing. AI applications that assist with diagnosis are executed first and any ad-hoc screening is scheduled thereafter by the Smart AI Router to allow optimal processing bandwidth utilization. The Smart AI Router allows easy configuration of recommendation modules for existing disease use cases and addition of new disease management use cases. The Smart AI Router provides a framework where health data points from new data sources or additional data points from existing sources can be added / modified in the logic of the modules. The Smart AI Router provides a method to monitor the performance of the solution and learn from usage.

[0048] In some examples, the smart AI router may include a continuous learning module where the smart AI router learns from the results of past recommendations. For example, radiology reports, patient diagnoses, and / or disease progression are tracked with each recommendation decision as input to the continuous learning. In such an example, if the recommendation module did not recommend lung cancer screening but a subsequent chest CT revealed a cancerous lung nodule, or vice versa, the smart AI router may update appropriately. In some examples, the smart AI router may include a smart protocol module to ensure that input parameter requirements are met for successful AI application processing for disease management use cases. Inputs to this process are patient imaging scheduling data, such as radiation and contrast dose management and patient health care, including data from contrast injectors. The smart protocol module assesses the AI ​​required based on the reason for the exam, identifies additional screening opportunities that would be valuable to the patient, and recommends protocols to meet these screenings.

[0049] A disease management use case framework may include receiving a type of image data type and detecting a body part. Disease states may be mapped to image data types and body parts, and for each disease state, AI applications that can assist in detecting and / or quantifying the disease may be identified along with input parameters for the AI ​​application, industry guidelines, customer guidelines, and / or recommendation rules (e.g., Calantic recommendation rules), healthcare data used in determining the relevance of ad-hoc screening, and sources of data. In this manner, the smart AI router may use the reason for testing to drive the use of the AI ​​application. Additionally, the smart AI router (e.g., recommendation module) may suggest additional relevant AI based on the health data or in the absence of reasons for testing and prioritization for AI processing.

[0050] An example of a chest disease management use case framework may include receiving image data types including fully detected contrast and non-contrast chest CT / bilateral lungs. Disease conditions mapped to the image data types include lung cancer, cardiac calcification, pulmonary embolism (PE), chronic obstructive pulmonary disease (COPD) / interstitial lung disease (ILD), and / or chronic thromboembolic pulmonary hypertension (CTEPH).

[0051] For each disease state, such as lung cancer, an AI application that can assist in disease detection and / or quantification may operate by analyzing the clear read CT. Input parameters for the AI ​​application include non-contrast chest CT with greater than 5 mm slice thickness. Industry guidelines for analysis may include automatically screening patients over 50 years old who smoke 20 packs of cigarettes per year. There may be no customer guidelines and the recommendation may receive as input that the reason for the test is suspected pulmonary embolism, EMR A1C value indicating hypertension, smoking history and age over 50 years old, and / or pre-diabetes from EMR data. The smart AI router may decide to run the PE AI application at high priority, decide to run the CTEPH AI application as a lower priority, decide to run the clear read lung nodule detection AI application as a medium priority, and recommend cardiac artery calcification (CAC) score assessment as a low priority.

[0052] In some non-limiting embodiments, the data sources 104 may include one or more devices capable of communicating with the AI ​​data management system 102, the destination system 106, and the AI ​​application system 108 via the communication network 112 and capable of performing a fluid injection procedure. For example, the data sources 104 may include a server, a computing device such as a desktop computer, a mobile device (e.g., a tablet, a smartphone, a wearable such as a wearable health sensor, etc.), etc. In some non-limiting embodiments, the data sources 104 may include devices associated with an institution such as a hospital information system (HIS), an EMR system, a medical imaging system (e.g., an imaging scanner), a fluid injection system (e.g., a fluid injector), a communication device associated with a medical device (e.g., a handheld medical device, a wearable medical device such as a portable health sensor, etc.), a fluid injection system, a pathology information system, a laboratory information system, and / or a device associated with a patient (e.g., a user device such as a computing device operated by a patient).

[0053] In some non-limiting embodiments, the fluid injection system may include one or more injection devices (e.g., one or more fluid injection devices). In some non-limiting embodiments, the fluid injection system is configured to administer (e.g., inject, deliver, etc.) a contrast fluid including a contrast agent to the patient, and / or administer an aqueous fluid, such as saline, to the patient before, during, and / or after administration of the contrast fluid. For example, the fluid injection system may inject one or more prescribed doses of contrast fluid directly into the patient's bloodstream via a hypodermic needle and syringe. In some non-limiting embodiments, the fluid injection system may be configured to continuously administer aqueous fluid to the patient via a peripheral intravenous line (PIV) and a catheter, or one or more prescribed doses of contrast fluid may be introduced into the PIV and administered to the patient via the catheter. In some non-limiting embodiments, the fluid injection system is configured to inject a fixed dose of contrast fluid followed by administration of a specific volume of aqueous fluid. In some non-limiting embodiments, the fluid injection system may be any of those disclosed in U.S. Patent Application No. 09 / 715,330, filed November 17, 2000, and issued as U.S. Patent No. 6,643,537; U.S. Patent Application No. 09 / 982,518, filed October 18, 2001, and issued as U.S. Patent No. 7,094,216; U.S. Patent Application No. 10 / 825,866, filed April 16, 2004, and issued as U.S. Patent No. 7,556,619; U.S. Patent Application No. 10 / 825,866, filed May 7, 2009, and issued as U.S. Patent No. 7,556,619; No. 12 / 437,011, filed Jun. 2, 2009 and issued as U.S. Patent No. 8,337,456; U.S. Patent Application No. 12 / 476,513, filed Jun. 2, 2009 and issued as U.S. Patent No. 8,147,464; and U.S. Patent Application No. 11 / 004,670, filed Dec. 3, 2004 and issued as U.S. Patent No. 8,540,698, the disclosures of each of which are incorporated herein by reference in their entireties.In some non-limiting embodiments, the fluid injection system may include a MEDRAD® Stellant CT Injection System, a MEDRAD® Stellant Flex CT Injection System, a MEDRAD® MRXperion MR Injection System, a MEDRAD® Mark 7 Arterion Injection System, a MEDRAD® Intego PET Injection System, or a MEDRAD® Centargo CT Injection System, all of which are provided by Bayer Healthcare LLC.

[0054] In some non-limiting embodiments, the HIS may include one or more subsystems, such as a patient procedure tracking system (e.g., a system that operates a modality worklist, a system that provides patient demographic information for fluid injection procedures and / or medical imaging procedures, etc.), a fluid injector management system, a picture archiving and communication system (e.g., a Picture Archiving and Communication System (PACS)), a radiology information system, and / or a radiology analysis system (e.g., Radimetrics Enterprise Application sold and marketed by Bayer Healthcare LLC).

[0055] In some non-limiting embodiments, the medical imaging system may include an ultrasound system, an echocardiography system, a magnetic resonance imaging (MRI) system, an electromagnetic radiation system (e.g., conventional 2D x-ray, a 3D computed tomography (CT) scanning system, a fluoroscopy system, etc.) and may be capable of communicating over the communications network 112 and performing medical imaging procedures, including medical imaging procedures involving the use of radiological contrast agents. In some non-limiting embodiments, the medical imaging system may provide images of the patient and / or data associated with the images of the patient (e.g., images of the patient as a result of an imaging study). The data associated with the images of the patient may include Digital Imaging and Communications in Medicine (DICOM) formatted data, which may include metadata, pixel data, and / or additional data associated with an imaging procedure performed on the patient to provide the image.

[0056] In some non-limiting embodiments, a fluid injection system service and control system may include a system designed to provide functionality for a user (e.g., service personnel of a company that sells and / or operates the fluid injection system) to interact with the fluid injection system. For example, the fluid injection system service and control system may provide functionality for a user to perform upgrades, perform restore operations, log operations, perform data backup operations, etc.

[0057] In some non-limiting embodiments, a laboratory information system (e.g., a Laboratory Information Management System (LIMS) or Laboratory Management System (LMS)) can include a system designed to support the operation of a laboratory (e.g., a medical laboratory). A laboratory information system may include functionality such as workflow, data tracking, flexible architecture, and / or data exchange interfaces to support the use of laboratories in regulated environments. In some non-limiting embodiments, a laboratory information system may include enterprise resource planning tools designed to manage aspects of laboratory informatics (e.g., patient data associated with laboratory processes and / or laboratory tests).

[0058] In some non-limiting embodiments, pathology information systems can include systems designed to register specimens, record gross and / or microscopic findings, coordinate laboratory workflow, generate and / or sign reports, distribute reports to intended recipients throughout the health system, support quality assurance measurements, and the like.

[0059] In some non-limiting embodiments, the destination system 106 may include one or more devices capable of communicating with the AI ​​data management system 102, the data sources 104, and / or the AI ​​application system 108 via the communication network 112. For example, the destination system 106 may include a server, a group of servers, a computing device such as a desktop computer, a mobile device (e.g., a tablet, a smartphone, a wearable device, etc.), etc. In some non-limiting embodiments, the destination system 106 may include one or more (e.g., multiple) applications (e.g., software applications) that perform a set of functions, including activating workflows and delivering results. In some non-limiting embodiments, the destination system 106 may include one or more applications that perform a set of functions on an external API to send data to an external system, such as the AI ​​data management system 102 or the AI ​​application system 108 associated with the external API, and to receive data from an external system associated with the external API. In some non-limiting embodiments, the destination system 106 may include a medical image storage PACS, an EMR system, a reporting system (e.g., a system that generates medical reports based on healthcare data), devices associated with a facility (e.g., a hospital), and / or devices associated with a patient.

[0060] In some non-limiting embodiments, the AI ​​application system 108 may include one or more devices capable of communicating with the AI ​​data management system 102, the data source 104, and / or the destination system 106 via the communication network 112. For example, the AI ​​application system 108 may include a server, a group of servers, a computing device such as a desktop computer, a mobile device (e.g., a tablet, a smartphone, a wearable device, etc.), etc. In some non-limiting embodiments, the AI ​​application system 108 may include one or more automated healthcare data analysis applications. For example, the AI ​​application system 108 may include one or more automated healthcare data analysis applications stored in a memory device of the AI ​​application system 108. In another example, the AI ​​application system 108 may include one or more automated healthcare data analysis applications each stored on a device (e.g., a server). In some non-limiting embodiments, the one or more automated healthcare data analysis applications may execute a set of functions on an external API to send data to an external system, such as the AI ​​data management system 102 or another AI application system 108 associated with the external API, and to receive data from the AI ​​application system 108 associated with the external API.

[0061] In some non-limiting embodiments, the automated healthcare data analysis application may include an AI software application that performs an analysis (e.g., an automated analysis) of healthcare data. In some non-limiting embodiments, the AI ​​software application may perform an analysis that includes predicting a diagnosis for a medical condition. Additionally or alternatively, the AI ​​software application may perform an analysis that includes making recommendations regarding a patient's treatment.

[0062] In some non-limiting embodiments, the communications network 112 may include one or more wired and / or wireless networks. For example, the communications network 112 may include a cellular network (e.g., a Long Term Evolution (LTE) network, a third generation (3G) network, a fourth generation (4G) network, a fifth generation (5G) network, a code division multiple access (CDMA) network, etc.), a local area network (LAN), a wide area network (WAN), a wireless LAN (WLAN), a private network, an ad-hoc network, an intranet, the Internet, an optical fiber-based network, an Ethernet network, a universal serial bus (USB) network, a cloud computing network, etc., and / or a combination of some or all of these or other types of networks.

[0063] The number and arrangement of systems and / or devices shown in Figure 1 are provided as an example. There may be additional, fewer, different, or different arrangements of systems and / or devices than those shown in Figure 1. Furthermore, two or more of the systems and / or devices shown in Figure 1 may be implemented within a single system or device, or a single system or device shown in Figure 1 may be implemented as multiple distributed systems or devices. Additionally or alternatively, a set of systems or devices (e.g., one or more systems, one or more devices) of environment 100 may perform one or more functions described as being performed by another set of systems or another set of devices of environment 100.

[0064] 2, which is a diagram of example components of a device 200. The device 200 may correspond to the AI ​​data management system 102, the data source 104, the destination system 106, and / or the AI ​​application system 108. In some non-limiting aspects or embodiments, the AI ​​data management system 102, the data source 104, the destination system 106, and / or the AI ​​application system 108 may include at least one device 200 and / or at least one component of the device 200. As shown in FIG. 2, the device 200 may include a bus 202, a processor 204, a memory 206, a storage component 208, an input component 210, an output component 212, and a communication component 214.

[0065] The bus 202 may include components that enable communication between the components of the device 200. In some non-limiting embodiments, the processor 204 may be implemented in hardware, software, or a combination of hardware and software. For example, the processor 204 may include a processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), etc.), a microprocessor, a digital signal processor (DSP), and / or any processing component that can be programmed to perform a function (e.g., a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), etc.). The memory 206 may include random access memory (RAM), read only memory (ROM), and / or another type of dynamic or static storage device (e.g., flash memory, magnetic memory, optical memory, etc.) that stores information and / or instructions for use by the processor 204.

[0066] The storage component 208 may store information and / or software related to the operation and use of the device 200. For example, the storage component 208 may include a hard disk (e.g., a magnetic disk, optical disk, magneto-optical disk, solid-state disk, etc.), a compact disk (CD), a digital versatile disk (DVD), a floppy disk, a cartridge, a magnetic tape, and / or another type of computer-readable medium along with a corresponding drive.

[0067] Input components 210 may include components that enable device 200 to receive information via user input (e.g., a touchscreen display, a keyboard, a keypad, a mouse, buttons, switches, a microphone, a camera, etc.), etc. Additionally or alternatively, input components 210 may include sensors for sensing information (e.g., a global positioning system (GPS) component, an accelerometer, a gyroscope, an actuator, etc.). Output components 212 may include components that provide output information from device 200 (e.g., a display, a speaker, one or more light emitting diodes (LEDs), etc.).

[0068] The communications component 214 may include transceiver-like components (e.g., a transceiver, a separate receiver and transmitter, etc.) that enable the device 200 to communicate with other devices via a wired connection, a wireless connection, or a combination of wired and wireless connections, etc. The communications component 214 may enable the device 200 to receive information from another device and / or provide information to another device. For example, the communications component 214 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi interface, a cellular network interface, etc.

[0069] The device 200 may perform one or more processes described herein. The device 200 may perform these processes based on the processor 204 executing software instructions stored by a computer-readable medium, such as the memory 206 and / or the storage component 208. A computer-readable medium (e.g., a non-transitory computer-readable medium) is defined herein as a non-transitory memory device. A non-transitory memory device includes a memory space located within a single physical storage device or a memory space spread across multiple physical storage devices.

[0070] Software instructions may be loaded into memory 206 and / or storage component 208 from another computer-readable medium or from another device via communication component 214. When executed, the software instructions stored in memory 206 and / or storage component 208 may cause processor 204 to perform one or more processes described herein. Additionally or alternatively, hardwired circuitry may be used in place of or in combination with software instructions to perform one or more processes described herein. Thus, the embodiments described herein are not limited to any specific combination of hardware circuitry and software.

[0071] The memory 206 and / or the storage component 208 may include a data store or one or more data structures (e.g., databases, etc.). The device 200 may be capable of retrieving information from, storing information, or retrieving information stored in a data store or one or more data structures in the memory 206 and / or the storage component 208.

[0072] The number and arrangement of components shown in Figure 2 are provided as an example. In some non-limiting embodiments, device 200 may include additional, fewer, different, or differently arranged components than those shown in Figure 2. Additionally or alternatively, a set of components (e.g., one or more components) of device 200 may perform one or more functions described herein as being performed by another set of components of device 200.

[0073] Reference is now made to Figure 3, which is a flow chart of a non-limiting embodiment of a process 300 for managing an automated healthcare data analysis application using AI. In some non-limiting embodiments, one or more of the portions of the process 300 may be performed (e.g., fully, partially, etc.) by the AI ​​data management system 102 (e.g., one or more devices of the AI ​​data management system 102). In some non-limiting embodiments, one or more of the portions of the process 300 may be performed (e.g., fully, partially, etc.) by another device or group of devices separate from or including the AI ​​data management system 102, the data source 104, the destination system 106, and / or the AI ​​application system 108.

[0074] As shown in FIG. 3, in portion 302, the process 300 includes receiving healthcare data from a data source. For example, the AI ​​data management system 102 may receive healthcare data from one or more data sources 104. In some non-limiting embodiments, the AI ​​data management system 102 may receive the healthcare data based on a device associated with the data source 104 performing a procedure. For example, the AI ​​data management system 102 may receive the healthcare data after a device associated with the data source 104 performs a procedure. In some non-limiting embodiments, the AI ​​data management system 102 may receive the healthcare data from a device associated with a hospital (e.g., a server operated by the hospital, such as an on-site server at the hospital or a server located remotely from the hospital, a hospital information system, etc.). In some non-limiting embodiments, the AI ​​data management system 102 may store the healthcare data (e.g., an application, a memory device, etc.) based on receiving the healthcare data.

[0075] In some non-limiting embodiments, the AI ​​data management system 102 may receive healthcare data and generate healthcare data associated with a classification of the automated healthcare data analysis application. For example, the AI ​​data management system 102 may receive healthcare data and determine certain parameters of the healthcare data associated with each automated healthcare data analysis application of the multiple automated healthcare data analysis applications. The AI ​​data management system 102 may generate healthcare data associated with a classification of the automated healthcare data analysis application based on the certain parameters of the healthcare data.

[0076] In some non-limiting embodiments, the AI ​​data management system 102 may receive healthcare data (e.g., from a hospital information system) according to a communication protocol for communicating data over a communication network. For example, the AI ​​data management system 102 may receive healthcare data according to a DICOM communication protocol, an HL7 standard communication protocol, etc.

[0077] In some non-limiting embodiments, the healthcare data may include data associated with electronic records (e.g., electronic patient records) from an EMR system, data associated with images generated by a medical imaging system, data associated with patient biometric measurements, data associated with fluid injection procedures performed by a fluid injection system, data associated with records from a pathology information system and / or laboratory information system. Additionally or alternatively, the healthcare data may include data associated with an identification of a patient, data associated with a patient procedure (e.g., data regarding procedures performed on a patient, such as a patient's examination procedure, a fluid injection procedure, a medical imaging procedure, radiation dose, etc.), data associated with devices involved in the patient procedure (e.g., data associated with a fluid injection system, data associated with a patient's devices, etc.), etc. In some non-limiting embodiments, the data associated with a patient procedure may include data associated with a fluid injection procedure, including data associated with contrast fluid provided during a fluid injection procedure, a gauge of a catheter used during a fluid injection procedure, a fluid injection protocol for a fluid injection procedure, a configuration of a fluid injection system, etc. Additionally or alternatively, the data associated with a patient procedure may include data associated with a medical imaging procedure, which may include data associated with an image (e.g., a radiological image), data associated with a radiation dose, etc.

[0078] In some non-limiting embodiments, the AI ​​data management system 102 may generate a machine learning model (e.g., an automated healthcare data analysis application predictive machine learning model) to provide a prediction of a classification of one of the multiple automated healthcare data analysis applications based on an input (e.g., a prediction including a score, such as a risk score).

[0079] In some non-limiting embodiments, the machine learning model may include a machine learning model designed to receive healthcare data as an input and provide a predicted classification of an automated healthcare data analysis application as an output. For example, the machine learning model may be designed to receive healthcare data (e.g., data associated with a patient procedure) and provide an output including a predicted classification of an automated healthcare data analysis application of a plurality of automated healthcare data analysis applications. The predicted classification of the automated healthcare data analysis application may include a classification of the automated healthcare data analysis application that may be capable of providing further analysis of the healthcare data. In some non-limiting embodiments, the AI ​​data management system 102 may store the machine learning model (e.g., for later use).

[0080] In some non-limiting embodiments, as described herein, the AI ​​data management system 102 may process healthcare data (e.g., historical healthcare data associated with an automated healthcare data analysis application, such as healthcare data including labels of a specified automated healthcare data analysis application for a particular parameter of a patient treatment) to obtain training data (e.g., a training dataset) for a machine learning model. For example, the AI ​​data management system 102 may process and modify the data into a format in which the data can be analyzed (e.g., by the AI ​​data management system 102) to generate a machine learning model. The modified data (e.g., data resulting from the modification) may be referred to as training data. In some non-limiting embodiments, the AI ​​data management system 102 may process the healthcare data to obtain training data based on receipt of the healthcare data. Additionally or alternatively, the AI ​​data management system 102 may process the healthcare data to obtain training data based on the AI ​​data management system 102 receiving an instruction from a user of the AI ​​data management system 102 (e.g., a user associated with a user device) that the AI ​​data management system 102 is to process the data, such as when the AI ​​data management system 102 receives an instruction to generate a machine learning model (e.g., for a time interval corresponding to the healthcare data, for a location corresponding to the healthcare data, etc.).

[0081] In some non-limiting embodiments, the AI ​​data management system 102 may process the healthcare data by determining healthcare data analytics application predictor variables based on the healthcare data. The healthcare data analytics application predictor variables may include metrics associated with the healthcare data analytics application that may be derived based on the healthcare data. The healthcare data analytics application predictor variables may be analyzed to generate a machine learning model. For example, the healthcare data analytics application predictor variables may include variables associated with a patient treatment (e.g., time of a patient treatment, a protocol used during a patient treatment, an amount of a substance used during a patient treatment, an outcome of a patient treatment, etc.), variables associated with aspects of an image (e.g., a radiology image), variables associated with patient demographics, variables associated with a patient condition, etc.

[0082] In some non-limiting embodiments, the AI ​​data management system 102 may analyze the training data to generate a machine learning model. For example, the AI ​​data management system 102 may analyze the training data using machine learning techniques to generate the machine learning model. In some non-limiting embodiments, generating the machine learning model (e.g., based on the training data obtained from historical healthcare data associated with the automated healthcare data analysis application) may be referred to as training the machine learning model. The machine learning techniques may include supervised and / or unsupervised techniques, such as, for example, decision trees, random forests, logistic regression, linear regression, gradient boosting, support vector machines, extra trees (e.g., an extension of random forests), Bayesian statistics, learning automata, hidden Markov modeling, linear classifiers, quadratic classifiers, association rule learning, and the like. In some non-limiting embodiments, the machine learning models may include models specific to particular characteristics, such as models specific to a particular location (e.g., a particular location of a hospital), particular patient demographics, particular systems used during patient treatment, and the like. Additionally or alternatively, the machine learning models may be specific to a particular entity providing healthcare services (e.g., healthcare delivery, such as a hospital, clinical facility, group of physicians, etc.). In some non-limiting embodiments, the AI ​​data management system 102 may generate one or more machine learning models for one or more entities, specific groups of entities, and / or one or more users of the one or more entities.

[0083] Additionally or alternatively, when analyzing the training data, the AI ​​data management system 102 may identify one or more variables (e.g., one or more independent variables) as predictor variables (e.g., features) that can be used to make predictions when analyzing the training data. In some non-limiting embodiments, the values ​​of the predictor variables may be inputs to a machine learning model. For example, the AI ​​data management system 102 may identify a subset (e.g., a suitable subset) of variables as predictor variables that can be used to accurately predict a classification of an automated healthcare data analysis application (e.g., from among a plurality of automated healthcare data analysis applications) for analyzing healthcare data. In some non-limiting embodiments, the predictor variables may include one or more of the healthcare data analysis application variables, as discussed above, that have a significant impact (e.g., a threshold-satisfying impact) on the predicted classification of the automated healthcare data analysis application for analyzing healthcare data determined by the AI ​​data management system 102.

[0084] In some non-limiting embodiments, the AI ​​data management system 102 may validate the machine learning model. For example, the AI ​​data management system 102 may validate the machine learning model after the AI ​​data management system 102 generates the machine learning model. In some non-limiting embodiments, the AI ​​data management system 102 may validate the machine learning model based on a portion of the training data used for validation. For example, the AI ​​data management system 102 may split the training data into a first portion and a second portion, and the first portion may be used to generate the machine learning model, as described above. In this example, the second portion of the training data (e.g., validation data) may be used to validate the machine learning model.

[0085] In some non-limiting embodiments, the AI ​​data management system 102 may validate the machine learning model by providing validation data associated with a user (e.g., healthcare data associated with an automated healthcare data analysis application) as input to the machine learning model and determining whether the machine learning model correctly or incorrectly makes a predicted classification of the automated healthcare data analysis application for analyzing the healthcare data based on the output of the machine learning model. In some non-limiting embodiments, the AI ​​data management system 102 may validate the machine learning model based on a validation threshold. For example, the AI ​​data management system 102 may be configured to validate the machine learning model when the classification of the automated healthcare data analysis application for analyzing the healthcare data (as identified by the validation data) is correctly predicted by the machine learning model (e.g., when the machine learning model correctly predicts 50% of the classifications of the automated healthcare data analysis application for analyzing the healthcare data, 70% of the classifications of the automated healthcare data analysis application, a threshold amount of classifications of the automated healthcare data analysis application, etc.).

[0086] In some non-limiting embodiments, if the AI ​​data management system 102 does not validate a machine learning model (e.g., if the percentage of correctly predicted classifications of the automated healthcare data analytics application does not meet a validation threshold), the AI ​​data management system 102 may generate one or more additional machine learning models.

[0087] In some non-limiting embodiments, once the machine learning model is validated, the AI ​​data management system 102 may further train the machine learning model and / or generate a new machine learning model based on receipt of new training data. The new training data may include additional healthcare data associated with a classification of the automated healthcare data analysis application. In some non-limiting embodiments, the new training data may include new healthcare data associated with multiple patient procedures (e.g., healthcare data associated with multiple patient procedures performed after a specified time). The AI ​​data management system 102 may use the machine learning model to predict a classification of the automated healthcare data analysis application and compare the output of the machine learning model to the new training data including healthcare data associated with the classification of the automated healthcare data analysis application. In such an example, the AI ​​data management system 102 may update one or more machine learning models based on the new training data.

[0088] In some non-limiting embodiments, the AI ​​data management system 102 may store the machine learning model. For example, the AI ​​data management system 102 may store the machine learning model in a data structure (e.g., a database, a linked list, a tree, etc.). The data structure may be located within the AI ​​data management system 102 or may be located in an external AI data management system 102 (e.g., separate from it).

[0089] As shown in FIG. 3, in portion 304, the process 300 includes determining a classification of the healthcare data. For example, the AI ​​data management system 102 may determine the classification of the healthcare data using a machine learning model. The machine learning model may be configured to provide an output, the output including a predicted classification of one of the automated healthcare data analysis applications based on an input to the machine learning model. In some non-limiting embodiments, the input may include the healthcare data. Additionally or alternatively, the AI ​​data management system 102 may activate a set of clinical workflows based on the predicted classification of the automated healthcare data analysis application.

[0090] In some non-limiting embodiments, the machine learning model may be configured to receive as input a data record associated with a patient (e.g., a data record including healthcare data). In some non-limiting embodiments, the data record may include at least one feature. In some non-limiting embodiments, the at least one feature may include at least one feature associated with an anatomical aspect of a body (e.g., a patient's body), at least one feature associated with a protocol of a device (e.g., a device of a fluid injection system), at least one feature associated with a characteristic of natural language processing, and / or at least one feature associated with a manual configuration of a device (e.g., a medical device, a device associated with the data source 104, etc.). In some non-limiting embodiments, the AI ​​data management system 102 may provide (e.g., generate, determine, etc.) one or more features. For example, the AI ​​data management system 102 may perform a feature extraction technique on the healthcare data (e.g., healthcare data included in the data record) to provide one or more features.

[0091] In some non-limiting embodiments, the machine learning model may be configured to determine whether the feature includes a category feature associated with an anatomical aspect of the body, a category feature associated with a protocol of the device, a category feature associated with a natural language processing characteristic, and / or a category feature associated with a manual configuration of the device. In some non-limiting embodiments, the machine learning model may determine a classification of the healthcare data (e.g., a classification associated with an automated healthcare data analysis application) based on determining whether the at least one feature includes a category feature associated with an anatomical aspect of the body, a category feature associated with a protocol of the device, a category feature associated with a natural language processing characteristic, or a category feature associated with a manual configuration of the device.

[0092] As shown in FIG. 3, in portion 306, the process 300 includes providing the healthcare data to an automated healthcare data analysis application based on the classification of the healthcare data. For example, the AI ​​data management system 102 may provide the healthcare data to an automated healthcare data analysis application (e.g., an AI-based healthcare data analysis application) based on the classification of the healthcare data. In some non-limiting embodiments, the AI ​​data management system 102 may provide the healthcare data to the AI ​​application system 108, and the AI ​​application system 108 may select one automated healthcare data analysis application of the multiple automated healthcare data analysis applications based on the classification of the healthcare data. In some non-limiting embodiments, the AI ​​application system 108 may send the healthcare data to the destination system 106 based on selecting the automated healthcare data analysis application of the multiple automated healthcare data analysis applications. In some non-limiting embodiments, the destination system 106 may be associated with the automated healthcare data analysis application selected by the AI ​​application system 108. In some non-limiting embodiments, the AI ​​application system 108 may send an output of the automated healthcare data analysis application to the destination system 106.

[0093] Reference is now made to Figure 4, which is a diagram of a non-limiting embodiment of the AI ​​data management system 102. In some non-limiting embodiments, the AI ​​data management system 102 may include multiple subsystems (e.g., software components, such as hardware components, modules, applications, extensions, units, etc., configured to run on one or more devices of the AI ​​data management system 102, or any combination thereof). In some non-limiting embodiments, the multiple subsystems of the AI ​​data management system 102 may be interconnected with each other via wired connections, wireless connections, or a combination of wired and wireless connections.

[0094] As shown in FIG. 4, the multiple subsystems may include a data capture subsystem 402, an image analysis subsystem 404, a matching subsystem 406, a guideline configuration subsystem 408, a customized configuration subsystem 410, a disease management configuration subsystem 412, and a prioritization subsystem 414. In some non-limiting embodiments, one or more of the multiple subsystems of the AI ​​data management system 102 may be hosted on a network device (e.g., a network edge device) closest to the facility interacting with the AI ​​data management system 102. In this manner, results from one or more subsystems of the AI ​​data management system 102 may be received in a shorter time compared to a situation in which one or more subsystems are hosted on a different network device. In some non-limiting embodiments, the AI ​​data management system 102 may include more or fewer subsystems than the multiple subsystems shown in FIG. 4. In some non-limiting embodiments, the AI ​​data management system 102 may include one or more subsystems configured to operate based on a manually provided configuration (e.g., a configuration provided by a user, such as a physician, technician, etc.).

[0095] In some non-limiting embodiments, the data capture subsystem 402 may be configured to receive healthcare data from one or more data sources (e.g., one or more data sources 104), and the data capture subsystem 402 may store, format, and / or perform additional functions on the healthcare data. In some non-limiting embodiments, the data capture subsystem 402 may identify a patient associated with the healthcare data and / or match the healthcare data to a patient record (e.g., based on patient name, patient identification number, etc.).

[0096] In some non-limiting embodiments, the image analysis subsystem 404 may be configured to provide anatomical intelligence regarding the healthcare data received by the data capture subsystem 402. For example, the image analysis subsystem 404 may detect a body part (e.g., a body region) of the patient, analyze the patient's images, and / or extract information from the patient's images. In some non-limiting embodiments, the image analysis subsystem 404 may provide output including an indication of one or more body parts and / or an indication of characteristics (e.g., quality) of the images. In some non-limiting embodiments, the image analysis subsystem 404 may determine characteristics of the images (e.g., type of image that identifies the body part from which the image was taken along with the modality of the image, such as CT, MRI, etc.). For example, the image analysis subsystem 404 may identify body parts depicted in the patient's images, determine whether the procedure involves the use of contrast (e.g., the procedure involves the use of contrast fluid or the procedure does not involve contrast fluid), determine information about the image (e.g., slice thickness, pixel size, radiation dose, voltage and / or amperage used, and other imaging parameters), extract text contained in the image (e.g., DICOM text), and determine the imaging protocol used to generate the image to provide characteristics of the image.

[0097] In some non-limiting embodiments, the matching subsystem 406 may be configured to receive an output from the image analysis subsystem 404 and match the output to one or more (e.g., a set) of automated healthcare data analysis applications applicable to the characteristics of the image. For example, the matching subsystem 406 may determine one or more automated healthcare data analysis applications of a plurality of automated healthcare data analysis applications to be used to analyze the output based on the characteristics of the image (e.g., the identity of the body part and the modality of the image). In some non-limiting embodiments, the matching subsystem 406 may provide an output including a list of one or more automated healthcare data analysis applications (e.g., potential automated healthcare data analysis applications that may be executed) and / or a plurality of input parameters to provide to the one or more automated healthcare data analysis applications (e.g., all automated healthcare data analysis applications included in the list of automated healthcare data analysis applications).

[0098] In some non-limiting embodiments, the guideline configuration subsystem 408 may be configured to compare the output of the matching subsystem 406 and identify and / or select one or more automated healthcare data analysis applications from among the multiple automated healthcare data analysis applications (e.g., the multiple automated healthcare data analysis applications identified by the matching subsystem 406 to be used to analyze healthcare data such as images). In some non-limiting embodiments, the guideline configuration subsystem 408 may refine the output of the matching subsystem 406 (e.g., remove, add, overwrite, etc., instructions for one or more automated healthcare data analysis applications) by comparing the output of the matching subsystem 406 to one or more guidelines (e.g., prescribed guidelines such as industry standard guidelines, regional guidelines specific to a particular geographic area, customer-specified guidelines, etc., which may be defined according to a specified level of patient care). In some non-limiting embodiments, the guidelines may be based on one or more automated healthcare data analysis applications associated with (e.g., available and / or accessible to) the facility (e.g., hospital). In some non-limiting embodiments, the matching subsystem 406 may provide a list of one or more automated healthcare data analysis applications (e.g., potential automated healthcare data analysis applications that may be executed in accordance with the guideline configuration subsystem 408) and / or an output including a number of input parameters to provide to the one or more automated healthcare data analysis applications (e.g., all automated healthcare data analysis applications included in the list of automated healthcare data analysis applications).

[0099] In some non-limiting embodiments, the customized configuration subsystem 410 may be configured to compare the output of the matching subsystem 406 and / or the guideline configuration subsystem 408 and identify and / or select one or more automated healthcare data analysis applications from a plurality of automated healthcare data analysis applications (e.g., a plurality of automated healthcare data analysis applications identified by the matching subsystem 406 and / or the guideline configuration subsystem 408 to be used to analyze healthcare data such as images). In some non-limiting embodiments, the customized configuration subsystem 410 may refine the output of the matching subsystem 406 and / or the guideline configuration subsystem 408 by comparing the output of the matching subsystem 406 and / or the guideline configuration subsystem 408 with one or more customized guidelines (e.g., individually specified guidelines). In some non-limiting embodiments, the customized guidelines may be based on one or more automated healthcare data analysis applications selected to be associated with the facility based on predefined parameters (e.g., facility-specific parameters, such as parameters associated with medical procedures available at the facility). In some non-limiting embodiments, the matching subsystem 406 may provide a list of one or more automated healthcare data analysis applications (e.g., potential automated healthcare data analysis applications that may be executed according to the customized configuration subsystem 410) and / or an output including a number of input parameters to provide to the one or more automated healthcare data analysis applications (e.g., all automated healthcare data analysis applications included in the list of automated healthcare data analysis applications).

[0100] In some non-limiting embodiments, the disease management configuration subsystem 412 may be configured to provide recommendations (e.g., additional automated healthcare data analysis applications in addition to or as an alternative to the output from the guideline configuration subsystem 408 and / or customized configuration subsystem 410) for a process of analyzing healthcare data based on one or more specified parameters (e.g., one or more specified parameters different from the parameters used in the guidelines of the guideline configuration subsystem 408 and / or customized configuration subsystem 410), such as results measuring the effectiveness of an automated healthcare data analysis application, disease tracking indications, etc. In some non-limiting embodiments, the disease management configuration subsystem 412 may provide output including information associated with the recommendation, such as a measurement of an outcome (e.g., a patient outcome based on a patient treatment or therapy) and / or a recommendation for an adjunct type treatment (e.g., medical screening).

[0101] In some non-limiting embodiments, the prioritization subsystem 414 may be configured to determine a priority of the automated healthcare data analysis applications (e.g., a plurality of automated healthcare data analysis applications determined to be applicable by the matching subsystem 406, the guideline configuration subsystem 408, the customized configuration subsystem 410, and / or the disease management configuration subsystem 412) to be used to analyze the healthcare data. In some non-limiting embodiments, the prioritization subsystem 414 may receive a list of automated healthcare data analysis applications, and the prioritization subsystem 414 may determine an order in which to execute each of the automated healthcare data analysis applications in the list. In some non-limiting embodiments, the prioritization subsystem 414 may determine an order in which to execute each of the automated healthcare data analysis applications based on parameters such as availability of the automated healthcare data analysis applications (e.g., whether the automated healthcare data analysis application, the amount of time required to execute the automated healthcare data analysis application, a previously (e.g., first) executed automated healthcare data analysis application, a metric associated with the severity of the patient, etc.).

[0102] In some non-limiting embodiments, the pre-processing subsystem 416 may be configured to determine a recommendation for a patient procedure (e.g., a scan) and / or a protocol for the patient procedure (e.g., a protocol including scan parameters such as slice thickness, type of contrast fluid, amount of contrast fluid, amount of time of the procedure, timing of different processes performed during the procedure, etc.) before the patient procedure is performed. In some non-limiting embodiments, the pre-processing subsystem 416 may determine the recommendation based on parameters such as the patient's disease monitoring procedure, the patient's health condition, previous treatments administered to the patient, information associated with one or more devices involved in the patient procedure, etc. In some non-limiting embodiments, the pre-processing subsystem 416 may provide a message (e.g., a report) including information regarding the recommendation to a device (e.g., a device associated with a hospital such as a fluid injection device in a hospital, a device associated with a medical professional such as a physician and / or technician, a device associated with a treatment facility, etc.).

[0103] In some non-limiting embodiments, the post-processing subsystem 418 may be configured to receive the output of one or more automated healthcare data analysis applications and provide information (e.g., predictions, recommendations, conclusions, etc.) regarding the one or more automated healthcare data analysis applications. For example, the post-processing subsystem 418 may provide information regarding the one or more automated healthcare data analysis applications to another device (e.g., a user device associated with a user). In some non-limiting embodiments, the post-processing subsystem 418 may provide a determination regarding parameters (e.g., patient demographics, patient condition, patient disease treatment, etc.) used by the one or more automated healthcare data analysis applications to provide an output. In some non-limiting embodiments, the post-processing subsystem 418 may provide information based on findings from a patient procedure such as a scan, healthcare data such as images from a medical imaging procedure, findings from a patient procedure such as protocol variances (e.g., protocol recommendations for those used in the protocol during the patient procedure), and the like. In some non-limiting embodiments, the post-processing subsystem 418 may provide recommendations regarding guidelines (e.g., new guidelines, guidelines to delete, guidelines to highlight, etc.) for the guideline configuration subsystem 408, the customized configuration subsystem 410, and / or the disease management configuration subsystem 412.

[0104] 5A-5C, which are diagrams of a non-limiting embodiment of an implementation 500 of a process (e.g., process 300) for managing an automated healthcare data analysis application using AI. As shown in FIG. 5A-5C, the implementation 500 includes an AI data management system 102, a data source 104, a destination system 106, a hospital cloud platform 508 including an AI application system 108, a communication network 112-1, and a communication network 112-2. In some non-limiting embodiments, the hospital cloud platform 508 may include a HIS operating on the cloud platform. In some non-limiting embodiments, each AI application system 108 of the AI ​​application systems 108 may be associated with an automated healthcare data analysis application. For example, each AI application system 108 of the AI ​​application systems 108 may be configured to execute an automated healthcare data analysis application based on healthcare data to provide an analysis of the healthcare data (e.g., a prediction of a result of the analysis). In some non-limiting embodiments, communications network 112-1 and / or communications network 112-2 may be the same as or similar to communications network 112. In some non-limiting embodiments, communications network 112-1 and / or communications network 112-2 may be a communications network associated with (e.g., operated by) a hospital and / or may be located at (e.g., internal to) a hospital or other treatment facility. In some non-limiting embodiments, communications network 112-1 and / or communications network 112-2 may be the same as communications network (e.g., the same communications network).

[0105] 5A, the AI ​​data management system 102 may receive healthcare data from one or more data sources. For example, the AI ​​data management system 102 may receive healthcare data from one or more devices or systems of the data sources 104. In some non-limiting embodiments, the AI ​​data management system 102 may also receive one or more data records from one or more data sources 104 that include healthcare data.

[0106] As shown by reference number 510 in FIG. 5B, the AI ​​data management system 102 may determine a classification of the healthcare data. For example, the AI ​​data management system 102 may determine a classification of the healthcare data using a machine learning model (e.g., an automated healthcare data analysis application predictive machine learning model). In some non-limiting embodiments, the AI ​​data management system 102 may provide the healthcare data as an input to the machine learning model, and the machine learning model may generate an output based on the input. The machine learning model may provide as an output a prediction of the classification of one of the automated healthcare data analysis applications.

[0107] As shown by reference number 515 in FIG. 5B, the AI ​​data management system 102 may provide the healthcare data to one or more AI application systems. For example, the AI ​​data management system 102 may provide the healthcare data to a hospital cloud platform 508 or to one or more AI application systems 108 of the hospital cloud platform 508. In some non-limiting embodiments, the AI ​​data management system 102 may provide the healthcare data to one or more AI application systems 108 based on the classification of the healthcare data. For example, the AI ​​data management system 102 may provide the healthcare data to an AI application system 108 associated with an automated healthcare data analysis application corresponding to the classification of the healthcare data. In this manner, the AI ​​data management system 102 may provide the healthcare data to an AI application system 108 suitably configured to perform an analysis of the healthcare data based on the automated healthcare data analysis application associated with the AI ​​application system 108. In some non-limiting embodiments, the AI ​​data management system 102 may provide the healthcare data to the hospital cloud platform 508, and the hospital cloud platform 508 may determine one or more AI application systems 108 to provide the healthcare data to based on the classification of the healthcare data.

[0108] As shown by reference number 520 in FIG. 5C, the hospital cloud platform 508 may provide the output of one or more AI application systems to one or more destination systems 106. For example, the hospital cloud platform 508 may provide the output of one or more AI application systems 108 to one or more destination systems 106 based on the one or more AI application systems 108 running an automated healthcare data analysis application on the healthcare data. In some non-limiting embodiments, the output may include an output of the automated healthcare data analysis application. In some non-limiting embodiments, the AI ​​data management system 102 may also cause the hospital cloud platform 508 to provide the output of one or more AI application systems 108 to one or more destination systems 106. For example, the AI ​​data management system 102 may control (e.g., via transmitted control signals) the hospital cloud platform 508 (e.g., one or more AI application systems 108 of the hospital cloud platform 508) to cause the hospital cloud platform 508 to provide the output of one or more AI application systems 108 to one or more destination systems 106.

[0109] In some non-limiting embodiments, one or more destination systems 106 may perform an action based on the output. For example, one or more destination systems 106 may display the output, generate a report based on the output, transmit the output to another device (e.g., another destination system 106), provide an alert based on the output, generate recommendations regarding a course of treatment based on the output, etc.

[0110] While the above systems, methods, and computer program products have been described in detail for purposes of illustration based on what are presently considered to be the most practical and preferred embodiments, it should be understood that such detail is for that purpose only, and the disclosure is not limited to the described embodiments, but on the contrary, is intended to cover modifications and equivalent arrangements within the spirit and scope of the appended claims. For example, it should be understood that the disclosure contemplates that, to the extent possible, at least one feature of any embodiment or aspect can be combined with at least one feature of any other embodiment or aspect. [Explanation of symbols]

[0111] 100 Environment 102 Artificial intelligence (AI) data management systems, external AI data management systems 104 Data Sources 106 Destination System 106-1~106-N Destination System 108 AI Application System 108-1~108-N AI application system 112 Communication Networks 200 devices 202 Bus 204 Processor 206 Memory 208 Memory Components 210 Input Component 212 Output Components 214 Communication Interface 300 processes 302 parts 304 parts 306 parts 402 Data Acquisition Subsystem 404 Image Analysis Subsystem 406 Matching Subsystem 408 Guideline Configuration Subsystem 410 Customized Configuration Subsystem 412 Disease Management Configuration Subsystem 414 Prioritization Subsystem 416 Pre-processing Subsystem 418 Aftertreatment Subsystem 500 Process implementation 505 Reference Number 1 508 Hospital Cloud Platform 510 Reference Number 515 Reference Number 1AI 520 Reference Number 1AI1

Claims

1. 1. A system for managing automated healthcare data analysis applications using artificial intelligence (AI), comprising: At least one processor, Receives healthcare data from a data source; determining a classification of the healthcare data using a machine learning model, the machine learning model configured to provide a predicted classification of one automated healthcare data analysis application of a plurality of automated healthcare data analysis applications based on an input; providing the healthcare data to the automated healthcare data analysis application based on the classification of the healthcare data At least one processor programmed or configured to A system comprising:

2. The at least one processor: Transmitting an output of the automated healthcare data analysis application to a destination system. The system of claim 1 , further programmed or configured to:

3. The destination system comprises: Picture Archiving and Communication Systems (PACS), Electronic Medical Record (EMR) systems, Data reporting systems, A communication device associated with the medical device; or User Devices Associated with a Patient The system of claim 2 , comprising:

4. The at least one processor: Training the machine learning model based on historical health care data from multiple data sources. The system of claim 1 , further programmed or configured to:

5. The machine learning model is configured to receive as input a data record, the data record including at least one feature, the at least one feature being: At least one feature associated with an anatomical aspect of the body; at least one feature associated with a protocol of the device; At least one feature associated with a natural language processing characteristic; At least one characteristic associated with the manual configuration of the device; or Any combination of them The system of claim 1 , comprising:

6. The machine learning model may further comprise: categorical features associated with anatomical aspects of the body; the device's protocols and associated category characteristics; categorical features associated with natural language processing properties; Categorical characteristics associated with the manual configuration of the device, or Any combination of them The system of claim 5 configured to determine whether the input signal includes

7. The data source is Electronic Medical Record (EMR) systems, Medical imaging systems, a communication device associated with the medical device; Fluid injection systems, Pathology Information System, Laboratory Information System, or User Devices Associated with a Patient The system of claim 1 , comprising:

8. 2. The system of claim 1, wherein the automated healthcare data analysis application comprises an AI-based healthcare data analysis application.

9. 1. A computer program product for managing an automated healthcare data analytics application using artificial intelligence (AI), the computer program product comprising at least one non-transitory computer-readable medium that, when executed by at least one processor, causes the at least one processor to: Receives healthcare data from a data source; determining a classification of the healthcare data using a machine learning model, the machine learning model configured to provide a predicted classification of one automated healthcare data analysis application of a plurality of automated healthcare data analysis applications based on an input; providing the healthcare data to the automated healthcare data analysis application based on the classification of the healthcare data. A computer program product comprising at least one non-transitory computer-readable medium containing one or more instructions.

10. The one or more instructions further include causing the at least one processor to: transmitting an output of the automated healthcare data analysis application to a destination system; 10. A computer program product as claimed in claim 9.

11. The destination system comprises: Picture Archiving and Communication Systems (PACS), Electronic Medical Record (EMR) systems, Data reporting systems, A communication device associated with the medical device; or User Devices Associated with a Patient 11. The computer program product of claim 10, comprising:

12. The one or more instructions further include causing the at least one processor to: training the machine learning model based on historical health care data from a plurality of data sources; 10. A computer program product as claimed in claim 9.

13. The machine learning model is configured to receive as input a data record, the data record including at least one feature, the at least one feature being: At least one feature associated with an anatomical aspect of the body; at least one feature associated with a protocol of the device; At least one feature associated with a natural language processing characteristic; At least one characteristic associated with the manual configuration of the device; or Any combination of them 10. The computer program product of claim 9, comprising:

14. The machine learning model may further comprise: categorical features associated with anatomical aspects of the body; the device's protocols and associated category characteristics; categorical features associated with natural language processing properties; Categorical characteristics associated with the manual configuration of the device, or Any combination of them 14. The computer program product of claim 13, configured to determine whether the

15. The data source is Electronic Medical Record (EMR) systems, Medical imaging systems, a communication device associated with the medical device; Fluid injection systems, Pathology Information System, Laboratory Information System, or User Devices Associated with a Patient 10. The computer program product of claim 9, comprising:

16. 10. The computer program product of claim 9, wherein the automated healthcare data analysis application comprises an artificial intelligence (AI) based healthcare data analysis application.

17. 1. A method for managing an automated healthcare data analysis application using artificial intelligence (AI), comprising: receiving healthcare data from a data source; determining a classification of the healthcare data using a machine learning model, the machine learning model configured to provide a predicted classification of one automated healthcare data analysis application of a plurality of automated healthcare data analysis applications based on an input; providing the healthcare data to the automated healthcare data analysis application based on the classification of the healthcare data; A method comprising:

18. Transmitting an output of the automated healthcare data analysis application to a destination system.

20. The method of claim 17, further comprising:

19. Training the machine learning model based on historical health care data from a plurality of data sources.

20. The method of claim 17, further comprising:

20. The machine learning model is configured to receive as input a data record, the data record including at least one feature, the at least one feature being: At least one feature associated with an anatomical aspect of the body; at least one feature associated with a protocol of the device; At least one feature associated with a natural language processing characteristic; At least one characteristic associated with the manual configuration of the device; or Any combination of them 20. The method of claim 17, comprising:

Images