Patient Monitoring Devices

Abstract

According to one aspect, a computer-implemented method is provided for execution by a patient monitoring device, the method comprising determining a health parameter of a subject using a patient monitoring model, the method further comprising determining a search query for querying a database of medical images using one or more outputs of the patient monitor model to retrieve matching medical images related to the determined health parameter.

Description

[Technical field]

[0001] The disclosure herein relates to patient monitoring devices and computer-implemented methods performed by patient monitoring devices. [Background technology]

[0002] The disclosure herein relates to monitoring patients in clinical environments such as hospitals, clinics, nursing homes, or any other medical facilities. In such facilities, patients are often monitored automatically. For example, vital signs such as heart rate, blood pressure, and SpO2 rate, among others, are monitored using sensors attached to the patient.

[0003] Furthermore, clinical decision support tools are becoming more and more common in hospital environments. Such tools (or models) exchange data with databases, such as electronic medical records (EMRs) or patient monitoring databases, during a patient's hospital stay and generate predictions from monitored vital signs. The predictions may relate, for example, to deterioration events and may be used to sound alarms on the patient monitor. Patient monitors, such as bedside monitors, remote health monitors (for remotely monitoring patients), and central stations (where data from multiple patient monitoring systems is displayed), are often the primary vital signs visualization dashboard for critical care teams. Summary of the Invention [Problem to be solved by the invention]

[0004] In a clinical environment, care is often centered around workflows, such as the ultrasound workflow associated with acquiring, processing, and storing ultrasound images acquired during an ultrasound examination. Ultrasound workflows are well defined in cardiology and radiology and often revolve around modality worklists and DICOM (Digital Imaging and Communications in Medicine) studies with multiple images.

[0005] There are also separate workflows associated with patient monitoring in a critical care environment, for example those related to acquiring, storing and processing vital sign measurements.

[0006] These workflows are implemented to standardize care and ensure that a continuum of quality care is met for different patients. The workflows also ensure rigorous record keeping.

[0007] A drawback of workflows is that they are difficult to combine, which leads to information not being optimally stored or retrieved. The aim of the present disclosure is to remedy the above mentioned problems. [Means for solving the problem]

[0008] Thus, according to a first aspect, there is provided a computer-implemented method performed by a patient monitoring device, comprising determining a health parameter of a subject using a patient monitoring model, and using one or more outputs of the patient monitoring model to determine a search query for querying a database of medical images to retrieve matching medical images related to the determined health parameter.

[0009] According to a second aspect, there is an apparatus having a memory having instruction data representing a set of instructions, and a processor in communication with the memory and configured to execute the set of instructions, which when executed by the processor causes the processor to determine a health parameter of a subject using a patient monitoring model, and to determine a search query for querying a database of medical images to retrieve matching medical images related to the determined health parameter using one or more outputs of the patient monitoring model.

[0010] According to a third aspect there is provided a patient monitoring device comprising the apparatus of the second aspect, the patient monitoring device further comprising a display, the processor further configured to retrieve a matching medical image from a database of medical images and transmit instructions to the display for the display to make the matching medical image available for rendering on the display.

[0011] According to a fourth aspect there is a computer program product having a computer readable medium having computer readable code embodied therein which, when executed by a suitable computer or processor, configures said computer or processor to perform the method of the first aspect.

[0012] Thus, a method and apparatus are provided for selecting a medical image sequence for automatic display on a patient monitoring display. As mentioned above, the disclosure herein is made in response to the challenge of combining ultrasound and patient monitoring workflows in a critical care environment. The disclosure herein provides a novel approach to the challenge whereby the patient monitor can "pull" relevant ultrasound data from a server. The advantage of this approach is that it allows relevant images to be acquired / "pulled" by the patient monitor in response to a prediction or calculation made by a clinical decision support tool, providing images that are relevant to the prediction / calculation made by the clinical decision support tool to assist the clinician in interpreting the results.

[0013] These and other aspects will be apparent from and elucidated with reference to the embodiments described hereinafter. [Brief description of the drawings]

[0014] Exemplary embodiments will now be described, by way of example only, with reference to the following drawings, in which: [Figure 1] FIG. 1 illustrates an apparatus according to some embodiments of the present disclosure. [Diagram 2] FIG. 2 illustrates a patient monitoring device according to some embodiments herein. [Diagram 3] FIG. 3 illustrates a method according to some embodiments of the present disclosure. [Figure 4] FIG. 4 illustrates an example system according to some embodiments of the present disclosure. [Diagram 5] FIG. 5 shows an example signal flow between the components illustrated in FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] As mentioned above, the disclosure herein is inspired by the cross value stream initiative in ultrasound and patient monitoring. The inventors of the present application recognized that there is a challenge in combining ultrasound workflows and patient monitoring workflows in a critical care environment. Ultrasound workflows are well defined, for example in cardiology and radiology, with modality worklists and DICOM studies with multiple images. Measurements generate separate entities called structured reports, similar to computed tomography (CT) / magnetic resonance (MR). Data are stored in the institution's DICOM storage entity or in a picture archiving and communication system (PACS) archive. In the critical care environment, these workflows will be gradually adopted as more caregivers become adept at taking vital signs, and as new technologies improve the repeatability and continuity of vital signs obtained from echo. Dedicated storage of image data in critical care currently tends to be episodic and is often not stored permanently, but when stored, the storage is often in a prerequisite separate DICOM storage entity.

[0016] Patient monitoring information, on the other hand, is stored in a variety of locations, including at the bedside and in a central clearinghouse, and tends to be stored using industry standard formats, such as the Health Level Seven (HL7) format, which is a set of international standards for transferring clinical and administrative data between software applications used by healthcare providers.

[0017] For example, patient monitors, such as bedside monitors, remote health monitors, and central stations, tend to be the de facto vital signs visualization dashboard for care teams (e.g., critical care teams) in hospitals. As described in more detail below, the disclosure herein relates to improved patient monitors, remote health monitors, and / or central stations that can display medical images related to the current condition of the patient being monitored. Thus, the disclosure herein enables "Monitoring Pull," e.g., the ability of the patient monitor to filter and display relevant image data for monitoring insights.

[0018] Briefly, the present invention enables a patient monitoring system to filter and retrieve ultrasound images and measurements that are clinically relevant to the output of a clinical decision support tool. In essence, the clinical decision support tool, as described above, exchanges data with a patient clearinghouse during a patient's stay and generates predictions, such as predictions of deterioration events. The output of the clinical decision support tool is used to determine a list of DICOM query parameters that will be used to acquire images related to the predicted deterioration events. In some embodiments, this list of parameters is generated as part of the output of the tool, or can be done separately by a predefined look-up table, or a user-configurable look-up table.

[0019] Thus, a mechanism is provided to "pull" relevant images associated with the output of the clinical decision tool to the patient monitor.

[0020] 1, in some embodiments there is an apparatus 100 according to some embodiments herein. Typically the apparatus forms part of a computing device or system, such as, for example, a laptop, desktop computer, or other computing device. In some embodiments, the apparatus 100 may form part of a distributed computing arrangement or cloud.

[0021] The apparatus includes a memory 104 having instruction data representing a sequence of instructions, and a processor 102 (e.g., a processing circuit or logic circuit) in communication with the memory and configured to execute the sequence of instructions. In general, the sequence of instructions, when executed by the processor, causes the processor to perform any of the embodiments of a method 300 as described below.

[0022] An embodiment of the apparatus 100 may be for use in monitoring a patient, for example in a clinical environment such as a hospital. More specifically, the set of instructions, when executed by a processor, cause the processor to determine a health parameter of a subject using a patient monitoring model, and to determine a search query for querying a database of medical images to retrieve matching medical images related to the determined health parameter using one or more outputs of the patient monitoring model.

[0023] The processor 102 may have one or more processors, processing units, multi-core processors, or modules configured or programmed to control the device 100 in the manner described herein. In certain implementations, the processor 102 may have multiple software and / or hardware modules, each configured or intended to perform an individual step or steps of the methods described herein. The processor 102 may have one or more processors, processing units, multi-core processors, and / or modules configured or programmed to control the device 100 as described herein. In some implementations, for example, the processor 102 may have multiple (e.g., interoperated) processors, processing units, multi-core processors, and / or modules configured for distributed processing. It will be understood by those skilled in the art that such processors, processing units, multi-core processors, and / or modules may be located in different locations and may perform different steps of the methods described herein and / or different portions of a single step.

[0024] The memory 104 is configured to store program code executed by the processor 102 to perform the methods described herein. Alternatively or additionally, one or more memories 104 may be external to the apparatus 100 (i.e., separate or remote from the apparatus). For example, one or more memories 104 may be part of another device. The memory 104 is used to store the determined health parameters, the search queries, the matching medical images, and / or any other information or data received, calculated, or determined by the processor 102 of the apparatus 100 or from any interface, memory, or device external to the apparatus 100. The processor 102 may be configured to control the memory 104 to store the determined health parameters, the search queries, the matching medical images, and / or any other information or data.

[0025] In some embodiments, memory 104 may have multiple sub-memories, each capable of storing a portion of instruction data, for example at least one sub-memory may store instruction data representing at least one instruction of a sequence of instructions, while at least one other sub-memory may store instruction data representing at least one other instruction of the sequence of instructions.

[0026] It is understood that Fig. 1 shows only the components required to illustrate this aspect of the disclosure, and that in an actual embodiment, device 100 may have components in addition to those shown. For example, device 100 may have a battery or other power source for powering device 100, or a means for connecting device 100 to a mains power source. Device 100 may further have a communication interface, for example, for communicating wirelessly with other computing devices.

[0027] The apparatus 100 may be included in a patient monitor, such as the patient monitor 200 illustrated in Fig. 2. The patient monitor 200 has a display 202. In this example, the processor 102 is further adapted to obtain a matching medical image from a database of medical images and transmit instructions to the display to enable the display to use the matching medical image for rendering on the display.

[0028] The display 202 may comprise, for example, a computer screen, such as a liquid crystal display (LCD), or any other type of display. The patient monitor may further comprise other components, such as a stand 204 and / or a user input device, such as a keyboard, a mouse, one or more buttons, or any other input device that allows a user to interact with the device, for example, to cause a corresponding image to be displayed on the display.

[0029] Additionally, the patient monitoring device 200 may include one or more sensors, for example, to obtain vital signs or other information about the patient being monitored. Examples of sensors include, but are not limited to, an SpO2 monitor, a heart rate monitor, and a blood pressure monitor.

[0030] 3, there is a computer-implemented method 300 performed by a patient monitoring device. An embodiment of the method 300 may be performed by an apparatus such as, for example, the apparatus 100 described above.

[0031] Briefly, in a first step 302, the method 300 comprises determining a health parameter of a subject using a patient monitoring model. In a second step 304, the method 300 comprises determining a search query for querying a database of medical images to retrieve matching medical images related to the determined health parameter using one or more outputs of the patient monitoring model.

[0032] As used herein, a patient monitoring device (or patient monitor) may be, for example, a bedside monitor or a central station, such as, for example, a central computer unit for receiving and displaying information for monitoring multiple patients. In other embodiments, a patient monitoring device may be, for example, a remote monitoring device, such as, for example, a remote health monitor. An example of a remote health monitor is a tele-ICU monitor.

[0033] As described above, in step 302, a patient monitoring model is used to determine a health parameter of the subject.

[0034] As used herein, a patient monitoring model is a clinical decision tool, a clinical decision support algorithm, or any other model or process used to process monitored information from a patient.

[0035] The patient monitoring model can, for example, take one or more vital signs as input and output a health parameter that can, for example, be determined, e.g., calculated or predicted, by the patient monitoring model. The patient monitor model can determine the health parameter in any manner, for example, using a lookup table, a set of thresholds, or if / then statements, if / then formulas, or using machine learning, or in any other manner.

[0036] In some embodiments, the health parameter is a score. The score is thus derived from patient data available to the patient monitoring device. For example, the score is any metric used to determine whether a patient's condition is improving, worsening, or stable. The score may be linked to a particular structure, parameter, measurement time, or parameter value. Examples of scores include, but are not limited to, a hemodynamic stability index score, a hypotension prediction index score, an acute heart failure prediction index, a score linked to a patient monitoring alarm, or a patient monitoring trend.

[0037] Examples of patient monitoring modes include, but are not limited to, a model for determining a hemodynamic stability index score, a hypotension prediction index score, or an acute heart failure prediction index.

[0038] One of the main needs of ultrasound in critical care is to aid in the long-term management of the patient's cardiovascular physiology to improve hemodynamics. An example of this is the patient-specific cardiac Frank-Starling relation, which describes the relationship between cardiac preload and output. Ultrasound is a reliable non-invasive tool to measure this in real time, beat by beat.

[0039] However, one skilled in the art will appreciate that these are merely examples, and that the method 300 applies equally to any patient monitoring model.

[0040] In step 304, the method includes using one or more outputs of the patient monitoring model to determine a search query for querying a database of medical images to retrieve matching medical images related to the determined health parameter.

[0041] Although some of the examples herein describe ultrasound (US) images, the medical images in the database of medical images may be of any imaging modality. Exemplary medical images include, but are not limited to, computed tomography (CT) images (e.g., from a CT scan), such as a C-arm CT image, a spectral CT image, or a phase contrast CT image, an X-ray image (e.g., from an X-ray scan), a magnetic resonance (MR) image (e.g., from an MR scan), an ultrasound (US) image (e.g., from an ultrasound scan), a fluoroscopy image, a nuclear medicine image, or any other medical image.

[0042] The medical images may be stored in a format that includes meta-information (e.g., metadata), such as in the form of an image header, although those skilled in the art will appreciate that this is merely an example and that metadata may be stored in other ways, such as using strings, images, event hyperlinks, coding objects, and / or macros linked to applications.

[0043] In some embodiments, the medical images may be in DICOM format, which is described in the article by Dandu Ravi Varma entitled "Managing DICOM images: Tips and tricks for the radiologist" (Indian J Radio Imaging. 2012 Jan-Mar; 22(1): 4-13). DICOM metadata may be read and / or searched using various tools and encoding languages. For example, in MathWorks, metadata from the DICOM file "Filename.dcm" may be read using the following command: metadata=dicominfo('Filename.dcm'). However, it is understood that this is merely an example and that medical images may be stored in other formats, such as the Flexible Image Transport System (FITS) format, or any other format with searchable meta information.

[0044] In some embodiments, the medical images may be stored in an institution's DICOM storage entity or a picture archiving and communication system (PACS) archive. Thus, the database of medical images may be a DICOM database, a PACS database, or any other database that contains medical images. The database of medical images may be referred to as an electronic medical record (EMR) database, or a patient monitor database. The database of medical images may be stored or hosted locally, for example forming part of a hospital network. Alternatively, the patient database of medical images may be made available via the cloud.

[0045] These medical images may be associated with an accompanying structured report that has measurements and / or annotations (e.g., calculated values) of features in the associated medical images. The structured report may be generated in a standardized manner, for example, as part of an ultrasound workflow.

[0046] In step 302, one or more outputs of the patient monitoring model are used to determine a search query for querying a database of medical images to retrieve matching medical images related to the determined health parameter, where the matching medical images satisfy the search query.

[0047] In some examples, at least one of the one or more outputs of the patient monitoring model is formatted in a manner for direct use as a DICOM search query, for example, the patient monitoring model is configured to output a search query.

[0048] Using the mitral valve as an example, the query can include the word "mitral valve" or can additionally (or alternatively) specify a particular image view that indirectly guarantees visualization of the mitral valve (e.g., "apical four-chamber (A4C) view"). Additional options can be filtered by ultrasound (US) acquisition parameters, such as depth, focal region, mode (B-mode / color / PW), etc. For example, an A4C view acquired at a depth of 18 cm (vs., 8 cm) is more likely to include visualization of the mitral valve in its entirety.

[0049] The format of the DICOM query can be found in the online document "DICOM PS3.3 2022b - Information Object Definitions," a DICOM® Publication (2022) by the DICOM Standards Committee. For example, section: DICOM PS3.17 2022b - Explanatory Information: "N.3.5 Left Ventricle Output" relates to the DICOM standard for left ventricular performance.

[0050] The following code demonstrates a python example of querying a DICOM study using a DICOM tag (PatientName) using the DICOM Web standard. In this example, the "params" are output by the Patient Monitoring model for use in the query. ===================================================================== def dicomweb_search_studies(project_id, location, dataset_id, dicom_store_id): ““Handles the GET requests specified in the DICOMweb standard. See https: / / github.com / GoogleCloudPlatform / python-docs-samples / tree / main / healthcare / api-client / vl / dicom before running the sample.””” # Imports Python's built-in “os” module import os # Imports the google.auth.transport.requests transport from google.auth.transport import requests # Imports a module to allow authentication using a service account from google.oauth2 import service_account # Gets credentials from the environment. credentials = service_account.Credentials.from_service_account_file( os.environ[“GOOGLE_APPLICATION_CREDENTIALS”] ) scoped_credentials = credentials. with_scopes( [https: / / www.googleapis.com / auth / cloud-platform] ) # Creates a requests Session object with the credentials. session = requests.AuthorizedSession(scoped_credentials) # URL to the Cloud Healthcare API endpoint and version base_url = https: / / healthcare.googleapis.com / vl # TODO(developer): Uncomment these lines and replace with your values. # project_id = ‘my-project’# replace with your GCP project ID # location = ‘us-central1’# replace with the parent dataset’s location # dataset_id = ‘my-dataset’ # replace with the parent dataset’s ID # dicom_store_id = ‘my-dicom-store’ # replace with the DICOM store ID url = “{} / projects / {} / locations / {}”.format(base_url, project_id, location) dicomweb path = “{} / datasets / {} / dicomStores / {} / dicomWeb / studies”,format(url, dataset id, dicom store id ) # Refine your search by appending DICOM tags to the # request in the form of query parameters. This sample # searches for studies containing a patient's name. params = {“PatientName”:“Sally Zhang”} response = session.get(dicomweb_path, params=params) response.raise_for_status() print(“Studies found: response is {}”.format(response)) # Uncomment the following lines to process the response as JSON. # patients = response json() # print(‘Patients found matching query:’) # print(json.dumps(patients, indent=2)) # return patients ===================================================================

[0051] In some embodiments, at least one of the one or more outputs of the patient monitoring model is formatted as a string or image, and the string or image is used in a search query.

[0052] In other examples, one or more outputs of the patient monitoring model are converted into a search query using a lookup table, a machine learning (ML) model, a mapping procedure, a mathematical function, or any other method of converting an output into a DICOM search query. It is understood that the lookup tables and mapping functions can be pre-configured by a human engineer who can specify appropriate DICOM queries for various situations. Similarly, an ML model (e.g., a neural network) or the like is trained using training data having training examples, each of the training examples having i) an example output of the patient monitoring model, and ii) a ground truth DICOM query to be made for the example output.

[0053] In this manner, the output of the patient monitoring model is formatted into a query for a database to search and retrieve medical images related to the health parameter.

[0054] Following step 304, the method 300 may further comprise retrieving a matching medical image from a database of medical images and sending instructions to the display making the matching medical image available for rendering on the display. The matching medical image may be rendered automatically or upon request by a user of the patient monitor.

[0055] In some embodiments, step 304 may occur in response to certain criteria being met, for example in response to a trigger.

[0056] For example, step 304 may be performed in response to the determined health parameter triggering an alert on a patient monitoring device. In such an example, when the health parameter (or its value) causes an alert, the patient monitor may automatically query a database of medical images to obtain medical images related to the alert. These images may then be displayed on the patient monitor to assist a clinician in determining whether treatment is required.

[0057] In another example, step 304 may be triggered by a health parameter threshold that is separate from the threshold for issuing a warning on a patient monitor. For example, a first threshold may be used to trigger the action of step 304 and a second threshold may be used to sound an alarm.

[0058] In some embodiments, step 304 may be performed in response to the determined health parameter indicating a deterioration of the patient. For example, if the health parameter (or its value) is compared to a certain criterion and the criterion indicates that the patient is (likely to be) deteriorating, this may trigger the operation of step 304. Thus, if the patient is starting to deteriorate, the patient monitor may pull medical images related to the particular deterioration state, thus providing all relevant information to the clinician on the patient monitor.

[0059] In this way, information generated by an imaging workflow (e.g., a US workflow) may be combined with a patient monitoring workflow to provide clinicians with the most relevant information about the patient and help them make the most informed decisions about the patient's treatment.

[0060] In another embodiment, more than one query can be formatted. For example, the patient monitoring model can query a database of medical images as part of step 202 (e.g., as part of the step of using the patient monitoring model to determine a health parameter of the subject). For example, the method 300 can include a step of generating a first output to generate a first search query, the result of which is used by the patient monitoring model to generate a health parameter displayed to the user (which in this embodiment can be considered a second, updated or final output). As a result of the second output, a second query for searching can also be generated according to step 304. In this manner, an initial output of the patient monitoring model can be used to query a database of medical images to obtain information for use in determining the final health parameter.

[0061] Reference is now made to Figure 4, which illustrates how the patient monitor 200 interfaces with other elements in a hospital system to perform the above-described method 300 according to some embodiments of the present specification. In this embodiment, the medical images are US (ultrasound) images stored in DICOM image format. However, it is understood that these are merely examples and that the examples of Figure 4 apply equally to other imaging modalities and other patient monitoring models.

[0062] The embodiment of FIG. 4 shows the following elements: One or more ultrasound imaging systems 402 The ultrasound imaging system proceeds through its standard DICOM workflow, which includes study creation based on patient-specific information, series and image acquisition 404, and transfer of primary images and secondary structured reports. Database of medical images in DICOM storage server format 406 A DICOM Storage Server is a DICOM Storage Repository configured by any institution that supports Service Class Providers (SCPs) and Service Class Users (SCUs). A patient monitoring device 200 (e.g., a bedside monitor) A device for visualizing integrated data Patient monitoring model 408 (also referred to herein as a patient monitoring clinical decision support tool) 4, the patient monitoring model is a Hemodynamic Stability Index (HSI) computational model. As described above, the patient monitoring model performs methods for combining patient data to determine health parameters 410 (e.g., to provide a prediction and / or score regarding the patient's health) and generate searchable strings 412 that can be used to query the DICOM space. DICOM SCP and Controller Unit A unit that manages the flow of searchable strings and performs SCP queries. In step 414, matching images from the query may be transmitted to and displayed on the patient monitor 200. Thus, in this manner, the patient monitoring system can filter and extract ultrasound images and measurements that are clinically relevant to the output of the patient monitoring model (e.g., algorithm).

[0063] Reference is now made to Figure 5, which illustrates an embodiment of the present disclosure, in which the medical images are US images in DICOM format and the patient monitoring model is for determining an HSI score, however, it is understood that these are merely examples and that the examples of Figure 5 apply equally to other imaging modalities and other patient monitoring models.

[0064] Step 502: The US Acquisition System 402 stores the images / measurements in the DICOM Server 406. The ultrasound system is used according to the standard DICOM workflow to generate studies, series and images. An image processing process and / or an expert reviewer generates measurements from these images to generate one or more observations that are encapsulated in a structured report. For a typical cardiac surgery patient in the ICU, three different ultrasound systems operated by different users generate six separate ultrasound exams with a total of 80 cine loops containing 1600 image frames. Since this is a cardiac valve surgery patient, the automated image analysis algorithms measure parameters such as aortic velocity time integral (VTI) and the expert reviewer evaluates parameters such as mitral regurgitation volume (SR Code Semantics (0008,0104) Aortic Regurgitation Volume (PISA)) using SR Finding Sites such as "Left Ventricular Outflow Tract" (Code Value T-32650). These measurements are directly linked to the SOP Instance UID for secondary capture annotations generated by the algorithm. Numerous other measurements are made from the ultrasound data such as the right pulmonary artery diameter (code values ​​18021-6) on the right pulmonary artery (finding location code value 44200).

[0065] Step 504: The patient monitoring server 512 and the HSI patient monitoring model 408 interact to generate predictions. The ultrasound system exports these studies and their associated reports for long-term archiving to a dedicated DICOM storage server, such as the institution's PACS. All six studies of the exam described above can be exported and stored.

[0066] Step 506: The HSI patient monitoring model 408 exchanges data with the patient clearinghouse 512 during the patient's hospital stay and generates a prediction (e.g., by step 302 above) that the patient's blood pressure will decrease sharply within the next 15 minutes. The HSI patient monitoring model 408 recognizes that this event, in conjunction with the presence of surgery and an increase in heart rate, is likely related to the patient's mitral valve function. Thus, the HSI patient monitoring model transmits (at step 508) a list of DICOM query parameters along with its deterioration prediction. As described above, this list of parameters may be generated as part of the output of the HSI patient monitoring model, or may be done separately by a predefined lookup table or a user configurable lookup table (e.g., by step 304 above).

[0067] Step 508: The patient monitoring controller uses the parameters to query the DICOM server, which returns a list of measurements and five image sequences (SOP Instances). When measurements are made, image phase tags are included so that specific parts of the cardiac cycle can be highlighted.

[0068] Step 510: The patient monitoring controller formats this list of image pointers to the bedside monitor 200, which renders the images according to the data extracted from the DICOM server.

[0069] In the above embodiment, the HSI is given as an example for a predictive score derived from patient data. As mentioned above, this is just one example, and the system of FIG. 5 can operate with another score, for example, the hypotension prediction index (HPI) developed by Edwards. See the article by Davies SJ, Vistisen ST, Jian Z et al., entitled "Ability of an arterial waveform analysis derived hypotension prediction index to predict future hypotensive events in surgical patients." Anesth Analg 2020;130:352-9. See also Hatib F, Jian Z, Buddi S et al., “Machine-learning algorithm to predict hypotension based on high-fidelity arterial pressure waveform analysis” Anesthesiology 2018;129:663-74 and Wijnberge M, Geerts BF, Hol L et al., “Effect of a machine learning derived early warning system for intraoperative hypotension vs standard care on depth and duration of intraoperative hypotension during elective noncardiac surgery” JAMA 2020;323:1052-60.Another example of a score that may be used is the Acute Heart Failure Prediction Index, as described, for example, in the article by Claire Zhao et al., entitled “Predicting Disposition Decision, Mortality, and Readmission for Acute Heart Failure Patients in Emergency Department Using Vital Sign, Laboratory, Echocardiographic, and Other Clinical Data”, Circulation November 6, 2018 Vol 138, Issue Suppl_l.

[0070] Referring now to other embodiments, there is provided a computer program product having a computer readable medium having computer readable code embodied therein, the computer readable code being configured, upon execution of instructions by a suitable computer or processor, to cause the computer or processor to perform the methods described herein.

[0071] It will therefore be understood that the present disclosure also applies to computer programs adapted to carry out the embodiments, in particular computer programs on or in a carrier, which may be in the form of source code, object code, code intermediate sources and object code, for example in partially compiled form, or in any other form suitable for use in the implementation of the methods according to the embodiments described herein.

[0072] It will also be appreciated that such programs can have many different architectural designs. For example, program code implementing the functionality of the method or system may be subdivided into one or more subroutines. Many different ways of distributing the functionality among these subroutines will be apparent to those skilled in the art. These subroutines may be stored in an executable file to form a self-contained program. Such an executable file may comprise computer executable instructions, such as processor instructions and / or interpreter instructions (e.g. Java interpreter instructions). Alternatively, one or more or all of the subroutines may be stored in at least one external library file and linked statically or dynamically, e.g. at run-time, with a main program. This main program includes at least one call to at least one of the subroutines. The subroutines may have function calls to each other.

[0073] The carrier of a computer program may be any entity or device capable of carrying a program. For example, the carrier may comprise a data storage device, for example a ROM, such as a CD-ROM or a semiconductor ROM, or a magnetic recording medium, for example a hard disk. Furthermore, the carrier may be a transmissible carrier, for example an electrical or optical signal, which may be conveyed via an electrical or optical cable or by radio or other means. When the program is embodied in such a signal, the carrier may be constituted by such a cable or other device or means. Alternatively, the carrier may be an integrated circuit in which the program is embedded, the integrated circuit being adapted to perform or used for the performance of the relevant method.

[0074] Variations to the disclosed embodiments can be understood and implemented by those skilled in the art in implementing the principles and techniques described herein, from a study of the drawings, the disclosure and the appended claims. In the claims, the word "comprises" does not exclude other elements or steps, nor does it exclude a plurality of them, even if a plurality is not stated. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain means are recited in mutually different dependent claims does not indicate that a combination of these means cannot be used to advantage. A computer program may be stored or distributed on a suitable medium, such as an optical storage medium or a solid-state medium, supplied together with or as part of other hardware, but may also be distributed in other forms, such as, for example, via the Internet or other wired or wireless telecommunication systems. Any reference signs in the claims should not be interpreted as limiting the scope thereof.

Claims

1. 1. A computer-implemented method performed by a patient monitoring device, the method comprising: determining a health parameter of the subject using the patient monitoring model; and determining a search query for querying a database of medical images to retrieve matching medical images related to the determined health parameter using one or more outputs of the patient monitoring model; 13. A computer-implemented method comprising:

2. determining the search query using one or more outputs of the patient monitoring model, the determined health parameter triggering an alert in the patient monitoring device; and / or the determined health parameter being indicative of a deterioration of the patient. The method of claim 1 , wherein the method is performed in response to

3. The medical images in the database of medical images are associated with an associated structured report, the structured report having measurements and / or annotations of features in the associated medical image; and The method of claim 1 or 2, wherein the search query is formatted to search for the measurements and / or annotations.

4. The method of claim 1 , wherein at least one of the one or more outputs of the patient monitoring model is formatted as a string or an image, and the string or image is used in the search query.

5. 4. The method of claim 1, wherein at least one of the one or more outputs of the patient monitoring model is formatted in a manner for direct use as a DICOM search query.

6. 6. The method of claim 1, wherein determining the search query using one or more outputs of the patient monitoring model comprises converting the one or more outputs of the patient monitoring model into the search query using a lookup table, a machine learning model, or a mapping procedure.

7. The method according to any one of claims 1 to 6, wherein the determined health parameter is a score derived from patient data available to the patient monitoring device.

8. The score is: Hemodynamic Stability Index score, Hypotension Prediction Index Score, Acute Heart Failure Prediction Index, or Scores linked to patient monitoring alerts or patient monitoring trends The method according to any one of claims 1 to 7, wherein

9. The method of claim 1 , wherein the medical image comprises meta-information.

10. The method according to any one of claims 1 to 9, wherein the medical images are in DICOM image format.

11. retrieving the matching medical images from the database of medical images; and sending instructions to a display to make the matching medical images available for rendering on the display; The method of any one of claims 1 to 10, further comprising:

12. a memory having instruction data representing a sequence of instructions; A processor in communication with the memory and configured to execute the set of instructions. The set of instructions, when executed by the processor, causes the processor to: determining a health parameter of a subject using the patient monitoring model; determining a search query for querying a database of medical images to retrieve matching medical images related to the determined health parameter using one or more outputs of the patient monitoring model; Device.

13. 13. A patient monitoring device having the apparatus of claim 12, further comprising a display; The processor, retrieving the matching medical images from the database of medical images; and sending instructions to the display for making the matching medical image available to the display for rendering on the display; To do more of that, Patient monitoring devices.

14. The patient monitoring device of claim 13 , wherein the processor is further configured to perform a method according to any one of claims 2 to 10.

15. A computer program product having a computer readable medium having computer readable code embodied therein, the computer readable code being configured, upon execution of instructions by a suitable computer or processor, to cause the computer or processor to perform a method according to any one of claims 1 to 11.

Images