System and method for suggesting catheter parameters
By using machine learning models in the vasculature evaluation device to determine catheter parameters from vascular image data, the problems of catheter placement risks and training difficulty caused by the complexity of existing vascular imaging devices are solved, and the rapid and accurate determination of catheter parameters is achieved. Reduces operational complexity.
Patent Information
- Application Number
- CN202410929063.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-07-12
- Filing Date
- 2024-07-11
- Publication Date
- 2025-01-14
AI Technical Summary
Existing vascular imaging equipment is complex, which causes clinicians to need a lot of training before placing the catheter, increasing the risk of operation and learning difficulty, especially for undertrained doctors.
A vasculature evaluation device, including an imaging detector and console, uses machine learning models to determine recommended catheter parameters, including size, length and model, from vascular image data, and provides suggestions through the display to simplify catheter placement process.
The system reduces the complexity of the operation of angiography equipment, allowing less-trained physicians to quickly and accurately determine catheter parameters, reducing risks in patients and during catheter placement.
Smart Images
Figure CN119313603A_ABST
Abstract
Description
[0001] priority
[0002] This application claims the benefit of priority to U.S. patent application No. 18 / 221,318, filed on July 12, 2023, which is incorporated by reference in its entirety into this application. Technical Field
[0003] The present application relates to the field of medical devices, and more particularly to systems and methods for suggesting catheter parameters. Background Art
[0004] Placing a catheter within a blood vessel typically includes determining the catheter size and length that best matches the patient's vascular parameters prior to the catheter placement event. Typically, vascular parameters are detected using vascular imaging equipment used to assist in the placement of the catheter. The complexity of such vascular imaging equipment requires extensive training for clinicians in operating the vascular imaging equipment when placing the catheter to minimize the risk to the patient. Due to the complex nature of the vascular imaging equipment, a similar significant level of training may be required to detect vascular parameters, even though the risk of detecting vascular parameters to the patient is negligible compared to the risks associated with catheter placement. Therefore, there is a need for a system configured to detect vascular parameters that can be operated by a clinician with less training than that required for the clinician to place the catheter.
[0005] Disclosed herein are devices, systems, and methods that address the aforementioned problems. Summary of the invention
[0006] According to some embodiments, a vascular system assessment device is disclosed herein, comprising: an imaging detector configured to acquire raw image data of a patient's blood vessel; and a device module having a console coupled to the imaging detector. The console comprises a processor and a memory having logic stored thereon, the logic performing operations when executed by the processor, the operations comprising: (i) receiving raw image data from the imaging detector; (ii) determining blood vessel data from the raw image data; (iii) applying a trained machine learning (ML) model to the blood vessel data to determine recommended catheter parameters related to insertion of a catheter within the blood vessel; and (iv) depicting the recommended catheter parameters on a display of the device module.
[0007] In some embodiments, the vessel data includes a diameter of the vessel and a depth of the vessel relative to the skin surface, and in some embodiments, the suggested catheter parameters include a catheter size and a catheter length.
[0008] In some embodiments, the imaging probe is an ultrasound probe.In some embodiments, the head of the ultrasound probe includes a plurality of transducers, wherein all transducers are arranged in a single linear array.
[0009] In some embodiments, the imaging detector is configured to obtain raw image data via A-mode ultrasound imaging technology combined with near infrared (NIR) imaging technology.
[0010] In some embodiments, the operations further include determining an image of the blood vessel from the raw image data, and depicting the image on a display.
[0011] In some embodiments, the suggested catheter parameters include a suggested catheter model, and in such embodiments, the operations include selecting the suggested catheter model from a list of catheter models stored in memory.
[0012] In some embodiments, the operations further include transmitting the suggested catheter parameters to an electronic medical record (EMR) system for inclusion in the patient's EMR.
[0013] In some embodiments, the operations also include receiving a trained ML model from an external computing system and storing the trained ML model in a memory.
[0014] In some embodiments, the imaging detector, device module, and display are combined into a single unit.
[0015] According to some embodiments, a vascular system assessment system is also disclosed herein, comprising a plurality of vascular system assessment devices according to any one of the above-mentioned vascular system assessment devices and a computing system connected to these vascular system assessment devices. The computing system includes a memory having ML logic stored thereon, and the ML logic performs ML operations when executed by a processor of the computing system, and these ML operations include executing an ML algorithm on a historical catheter placement data set to define a trained ML model. The historical catheter placement data set includes a vascular data set received from the vascular system assessment device and an actual catheter parameter data set corresponding to the vascular data set individually.
[0016] In some embodiments, the computing system is communicatively coupled to the EMR system, and the ML operations include receiving the actual catheter parameter data set from the EMR system.
[0017] In some embodiments, each blood vessel data set includes the diameter of the corresponding patient's blood vessel and the depth of the blood vessel relative to the skin surface of the corresponding patient, and in some embodiments, each actual catheter parameter data set includes the catheter size and catheter length of the catheter inserted into the corresponding patient's blood vessel. In some embodiments, each actual catheter parameter data set includes a catheter model.
[0018] According to some embodiments, the present invention also discloses a system method for determining recommended catheter parameters, which includes: (i) receiving multiple vascular data sets from multiple vascular system assessment devices; (ii) receiving multiple actual catheter parameter data sets from an electronic medical record (EMR) system, wherein each catheter parameter data set corresponds to a vascular data set; (iii) performing a machine learning (ML) algorithm on the vascular data set and the actual catheter parameter data set to train an ML model that relates the vascular data set to the actual catheter parameter data set; (iv) acquiring raw image data of the blood vessel from an instant patient using one of the vascular system assessment devices; (v) determining instant vascular data from the raw image data; (vi) applying the (ML) model to the instant vascular data to determine recommended catheter parameters for a catheter to be inserted into the blood vessel; and (vii) depicting the recommended catheter parameters on a display of one of the vascular system assessment devices.
[0019] In some embodiments of the system method, the vessel data includes a diameter of the vessel and a depth of the vessel relative to the skin surface, and the suggested catheter parameters include a catheter size and a catheter length.
[0020] In some embodiments of the system method, each vasculature assessment device includes an ultrasound probe configured to acquire raw image data, and in some embodiments, the ultrasound probe is configured to acquire the raw image data using A-mode ultrasound imaging.
[0021] These and other features of the concepts provided herein will become more readily apparent to those skilled in the art in view of the accompanying drawings and the following description, which describe in more detail specific embodiments of such concepts. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] Figure 1A A vasculature assessment device configured to determine recommended catheter parameters for a catheter to be inserted into the vasculature is shown according to some embodiments.
[0023] Figure 1B According to some embodiments Figure 1A Bottom view of the imaging module of the device.
[0024] Figure 2 According to some embodiments, Figure 1A A block diagram of the console of a device.
[0025] Figure 3 Shown is a cross-sectional side view of a blood vessel of a patient with a catheter inserted therein, according to some embodiments.
[0026] Figure 4is shown according to some embodiments configured to define Figure 1A A vascular system assessment system based on a trained machine learning model of a device.
[0027] Figure 5 A block diagram of a system method for determining suggested catheter parameters for a catheter to be inserted into a patient's vasculature is shown, according to some embodiments. DETAILED DESCRIPTION
[0028] Before disclosing some specific embodiments in more detail, it should be understood that the specific embodiments disclosed herein do not limit the scope of the concepts provided herein. It should also be understood that the specific embodiments disclosed herein may have features that can be easily separated from the specific embodiments, and these features may be optionally combined with or replace the features of any of the many other embodiments disclosed herein.
[0029] About the terms used herein, it should also be understood that these terms are for the purpose of describing some specific embodiments, and these terms do not limit the scope of the concepts provided herein. Ordinal numbers (e.g., first, second, third, etc.) are generally used to distinguish or identify different features or steps in a set of features or steps, and do not provide sequence or numerical restrictions. For example, "first", "second" and "third" features or steps do not necessarily appear in this order, and the specific embodiments including such features or steps are not necessarily limited to these three features or steps. For convenience, labels such as "left", "right", "top", "bottom", "front", "back" etc. are used, and these labels are not intended to imply, for example, any specific fixed position, orientation or direction. On the contrary, such labels are used to reflect, for example, relative position, orientation or direction. "A kind of", "one" and "the" in the singular form include plural references, unless the context clearly stipulates otherwise. For example, "systemic reaction" as used herein can include a combination of systemic reactions of a type or multiple types of systemic reactions.
[0030] The phrases "connected to," "coupled to," and "in communication with" refer to any form of interaction between two or more entities, including but not limited to physical, mechanical, electrical, magnetic, electromagnetic, fluid, wireless, and thermal interactions. Two components may be coupled to each other even if they are not in direct contact or communication with each other. For example, two components may be coupled to each other through an intermediate component.
[0031] The term "logic" may refer to hardware, firmware, or software configured to perform one or more functions. As hardware, the term "logic" may refer to or include circuits having data processing and / or storage functions. Examples of such circuits may include, but are not limited to or constrained to, hardware processors (e.g., microprocessors, one or more processor cores, digital signal processors, programmable gate arrays, microcontrollers, application specific integrated circuits "ASICs", etc.), semiconductor memories, or combinational components.
[0032] Additionally or alternatively, the term "logic" may refer to or include software, such as one or more processes, one or more instances, an application programming interface (API), a subroutine, a function, an applet, a servlet, a routine, a source code, an object code, a shared library / dynamic link library (dll), or even one or more instructions. The software may be stored in any type of suitable non-transitory storage medium or transient storage medium (e.g., an electrical, optical, acoustic, or other form of propagating signal, such as a carrier wave, an infrared signal, or a digital signal). Examples of non-transitory storage media may include, but are not limited to or limited to: programmable circuits; non-persistent storage devices, such as volatile memory (e.g., any type of random access memory "RAM"); or persistent memory, such as non-volatile memory (e.g., read-only memory "ROM", power-powered RAM, flash memory, phase change memory, etc.), a solid-state drive, a hard drive, an optical drive, or a portable memory device. As firmware, the logic may be stored in a persistent storage device.
[0033] Unless defined otherwise, all technical and scientific terms used herein have the same meanings as commonly understood by one of ordinary skill in the art.
[0034] The terms "proximal" and "distal" refer to the opposite ends of a medical device, including the devices disclosed herein. As used herein, the proximal portion of a medical device is the portion closest to a practitioner during use, while the distal portion is the portion at the opposite end. For example, the proximal end of a catheter is defined as the end closest to a practitioner during use of the catheter. The distal end is the end opposite the proximal end along the longitudinal direction of the catheter.
[0035] Any method disclosed herein includes one or more steps or actions for performing the described method. These method steps and / or actions can be interchangeable with each other. In other words, unless the proper operation of the embodiment requires a specific order of steps or actions, the order and / or use of specific steps and / or actions can be modified. In addition, a subroutine or only a portion of the method described herein can be a separate method within the scope of the disclosed text. In other words, some methods can include only a portion of the steps described in the more detailed method. In addition, all embodiments disclosed herein are combinable and / or interchangeable, unless otherwise stated, or such combination or interchange will be contrary to the operability of any embodiment.
[0036] Figure 1A A vascular system assessment device (device) 100 configured to determine suggested parameters for a vascular access catheter to be inserted into a patient's blood vessel according to some embodiments is shown. The device 100 is configured to assist a clinician in identifying and / or preparing a catheter to be used to access a blood vessel without requiring extensive training in the use of an imaging system. In some cases, a first minimally trained clinician may utilize the device 100 to determine catheter parameters, e.g., size, length, and / or model, for a catheter to be inserted into a blood vessel, and a second clinician may utilize a second imaging system (which requires more extensive training) to provide guidance and / or placement assistance during insertion of the catheter.
[0037] The device 100 typically includes an imaging detector 150 that is operatively connected (e.g., via a wired or wireless connection) to the device module 110. The imaging detector 150 is configured to obtain / acquire raw image data of a blood vessel 55 of the patient 50. The logic of the console 115 or the device 100 determines vascular data from the raw image data, such as a depth 121 of the blood vessel relative to the patient's skin surface and a diameter 123 of the blood vessel 55. The logic further determines recommended catheter parameters from the vascular data, such as a catheter size or specification 126, a length 127, and / or a catheter model 128, as described in more detail below. The device 100 notifies the clinician of the catheter parameters so that the clinician can identify, obtain, and / or prepare a catheter for insertion. In some cases, preparing the catheter includes trimming the catheter to a desired length.
[0038] The imaging detector 150 includes an imaging module 152 configured to obtain raw image data. The imaging module 152 may include any suitable imaging technology capable of obtaining the image 125. In the illustrated embodiment, the imaging module 152 includes ultrasound technology. In other embodiments, the imaging module 152 may include imaging technology other than ultrasound. The imaging detector 150 may include control buttons 154 that enable a clinician to operate the device 100 from the imaging detector 150. As also shown, the logic may determine an image 125 of a target area of the patient (including a vascular image 120 of the blood vessel 55) from the raw image data and cause the image 125 to be depicted on the display 112.
[0039] Figure 1B 1 is a bottom end view of one embodiment of an imaging module 152 that utilizes ultrasound technology to obtain an image 125. In the illustrated embodiment, the imaging module 152 includes a plurality of ultrasound transducers 153 arranged in a linear array consistent with A-mode ultrasound imaging. A-mode (i.e., one-dimensional) ultrasound technology provides a cost advantage over other two-dimensional ultrasound technologies. In some embodiments, the imaging module 152 may include a near infrared (NIR) imaging module 156 so that the imaging detector 150 can utilize A-mode ultrasound imaging in combination with NIR imaging to obtain raw image data.
[0040] Figure 2 1 shows a block diagram of a console 115 according to some embodiments. The console 115 is generally configured to manage the operation of the device 100. The console 115 includes, for example, a processor 210 and a memory 220 (e.g., a non-transitory computer readable medium) having logic modules stored thereon, such as imaging logic 221, vascular logic 222, and catheter parameter logic 223. Machine learning logic 225 and one or more trained machine learning models 224 may also be stored in the memory 220. In the following, with respect to at least Figures 4 to 5 10. The execution of and processing by the machine learning logic 225 and one or more trained machine learning models 224 are discussed in detail below. The console 115 may include a wireless module 250 to facilitate wireless communication with an external computing device (or system) 260 and / or an electronic medical record (EMR) system 270, as further described below. The console 115 may be fully incorporated into the imaging detector 150 or the device module 110. Similarly, the console 115 may be partially incorporated into both the imaging detector 150 and the device module 110. In some embodiments, although not shown, the imaging detector 150 and the device module 110 may be combined into a single handheld unit. For example, the console 115 and the display 112 may be integrated into the imaging detector 150.
[0041] The console 115 may, for example, include an interface module 240 configured to define an operational connection with the imaging module 152, such as converting analog signals into digital data. The console 115 is powered via a power source 230. In some embodiments, the power source 230 may include an internal battery (e.g., a rechargeable battery) capable of providing sufficient power to operate the device 100 for a defined operating duration. For example, other power sources are also contemplated and therefore included herein, such as an external facility power source.
[0042] The imaging logic 221 is configured to acquire raw image data (e.g., manage the operation of the imaging module 152). The imaging logic 221 may also determine the image 125 from the raw image data. The vascular logic 222 is configured to determine vascular data of the blood vessel 55 from the raw image data. The vascular data may include any parameters associated with the blood vessel 55 that may help identify a catheter or catheter parameters suitable for insertion into the blood vessel 55. The vascular data may include the location and / or shape of the blood vessel 55. Regarding the location, the vascular data may include the depth 212 of the blood vessel 55 relative to the skin surface. In some cases, the depth 212 may be related to the length of the catheter. Regarding the shape of the blood vessel 55, the vascular data may include the diameter 123 of the blood vessel 55. In some cases, the blood vessel 55 may not be circular (i.e., may include an elliptical or flat shape). Therefore, the diameter 123 may be the minimum diameter of the blood vessel 55. The diameter 123 may be related to the size / specification (i.e., diameter) of the catheter to be inserted into the blood vessel 55.
[0043] Figure 3 A cross-sectional side view of a catheter 310 inserted into a blood vessel 55 is shown. The blood vessel 55 is shown having a diameter 123 and disposed at a depth 121 from the skin surface 52. The catheter 310 is inserted through the patient's tissue into the blood vessel 55. A proximal portion of the catheter 310 having a length 311 extends between the skin surface 52 and the blood vessel 55 at an insertion angle 317. A distal portion of the catheter 310 having a length 312 extends along the blood vessel 55. Thus, the length of the catheter 310 may include the sum of the lengths 311, 312.
[0044] The catheter parameter logic 223 is configured to determine the recommended catheter parameters based on the vascular data. In the illustrated embodiment, the catheter parameter logic 223 utilizes a trained machine learning (ML) model 224 to determine the recommended catheter parameters. More specifically, the catheter parameter logic 223 can apply the trained ML model 224 to the vascular data to determine the recommended catheter parameters. According to the illustrated embodiment, the catheter parameter logic 223 can apply the trained ML model 224 to the vascular data to determine one or more of the catheter size (specification), catheter length, or catheter model from at least the depth 121 of the vessel and the diameter 123 of the vessel.
[0045] The catheter parameter logic 223 may cause the catheter size (gauge) 126, catheter length 127, and / or catheter model 128 to be depicted on the display 112. The catheter parameter logic 223 may also transmit the catheter size (gauge) 126, catheter length 127, and / or catheter model 128 to the EMR system 270 for inclusion in the EMR of the patient 50.
[0046] Figure 4 A vascular system assessment system (system) 400 is shown according to some embodiments. The system 400 is generally configured to define a trained ML model 224, i.e., train the ML model 224. The system 400 generally includes a plurality of devices 100 coupled to a computing device 260. According to one embodiment, the computing device 260 can be, for example, an external computing device, such as a network server. In some embodiments, the computing device 260 can be incorporated into the EMR system 270. In other embodiments, the computing device 260 can be incorporated into one or more of the devices 100.
[0047] The computing device 260 includes a database 407 and a machine learning (ML) logic 409 stored on a non-transitory computer readable medium. The ML logic 409 is configured to obtain a historical catheter placement data set to form a training data set 408 stored in the database 407. The ML logic 409 is further configured to apply an ML algorithm 410 to the training data set 408 to define a trained ML model 224, wherein the ML logic 409 may include or be configured to execute a plurality of ML algorithms 410 (e.g., prediction algorithms such as linear regression, logistic regression, classification and regression trees, naive Bayes, K nearest neighbors, etc.). The historical catheter placement data set includes a vascular data set and an actual catheter parameter data set that corresponds to the vascular data set individually (i.e., according to a one-to-one relationship). More specifically, for a single catheter placement event, each vascular data set corresponds to an actual catheter parameter data set.
[0048] The vascular data set for the catheter placement event includes the depth of the vessel and the diameter of the vessel. The actual catheter parameter data set includes the parameters (e.g., size, length, and / or model) of the catheter actually placed in the patient as part of the catheter placement event. In some cases, the parameters of the catheter can be recorded in the patient's EMR.
[0049] The computing device 260 may be coupled to the EMR system 270, and the ML logic 409 may obtain the actual catheter parameter data set from the EMR system 270. The trained ML model 224 may be stored in a memory of the computing device 260. The ML logic 409 may transmit or transfer the trained ML model 224 to the device 100 for storage in the memory 220.
[0050] Figure 5 is a block diagram of a system method 500 for determining suggested catheter parameters according to some embodiments, the system method including all or any subset of the following actions, steps, or processes. Figure 5 Each box shown in represents an operation of method 500 performed by a vasculature assessment system and / or vasculature assessment device disclosed herein, and is generally a result of executing one or more logic modules disclosed herein and deploying a specific machine or device such as vasculature assessment device 100 and vasculature assessment system 400. Method 500 may include receiving multiple vascular data sets from multiple vascular assessment devices (box 510). The vascular data set may include a diameter of a vessel and a depth of the vessel relative to a skin surface, as determined from raw image data acquired from a patient via one of the vascular assessment devices. The vascular assessment device may include an ultrasound probe configured to acquire raw image data, and in some embodiments, the ultrasound probe is configured to acquire the raw image data using A-mode ultrasound imaging.
[0051] The method of method 500 may also include receiving a plurality of actual catheter parameter data sets (block 520), the plurality of actual catheter parameter data sets may be obtained from an electronic medical record (EMR) system, wherein each catheter parameter data set corresponds to a vascular data set. The method of method 500 may also include executing a machine learning (ML) algorithm on the vascular data set and the actual catheter parameter data set, wherein the vascular data set and the actual catheter parameter data set define a training data set for the ML model (block 530), and wherein a result of executing the machine learning (ML) algorithm is a trained ML model that relates the vascular data set to the actual catheter parameter data set.
[0052] The method of method 500 may also include acquiring raw image data of a blood vessel from a live patient using one of the vascular system assessment devices (block 540). The method of method 500 may also include determining live blood vessel data from the raw image data (block 550). The method of method 500 may also include applying a trained (ML) model to the live blood vessel data to determine suggested catheter parameters (block 560), wherein the suggested catheter parameters are related to the catheter to be inserted into the blood vessel. The suggested catheter parameters may include catheter size and catheter length. The method of method 500 may also include depicting the suggested catheter parameters on a display of one of the vascular system assessment devices (block 570).
[0053] Although some specific embodiments have been disclosed herein, and although these specific embodiments have been disclosed in considerable detail, these specific embodiments are not intended to limit the scope of the concepts provided herein. Additional adaptations and / or modifications may be envisioned by those of ordinary skill in the art, and in broader aspects, these adaptations and / or modifications are also encompassed. Therefore, changes may be made to the specific embodiments disclosed herein without departing from the scope of the concepts provided herein.
Claims
1. A vascular system assessment device, comprising: an imaging detector configured to acquire raw image data of a blood vessel of a patient; and An apparatus module having a console coupled to the imaging detector, the console comprising a processor and a memory having logic stored thereon, the logic, when executed by the processor, performing operations comprising: receiving the raw image data from the imaging detector; determining blood vessel data from the raw image data; applying the trained machine learning model to the blood vessel data to obtain recommended catheter parameters related to insertion of a catheter within the blood vessel; and The suggested catheter parameters are depicted on a display of the equipment module. 2 . The vascular system assessment device according to claim 1 , wherein the blood vessel data comprises a diameter of the blood vessel and a depth of the blood vessel relative to a skin surface.
3. A vasculature assessment device according to claim 1 or 2, wherein the recommended catheter parameters include catheter size and catheter length.
4. The vasculature assessment apparatus according to any one of the preceding claims, wherein the imaging probe is an ultrasound probe.
5. A vasculature assessment apparatus according to any one of the preceding claims, wherein: The head of the ultrasound probe includes a plurality of transducers, and All of the transducers are arranged in a single linear array.
6. The vascular system assessment device according to any one of the preceding claims, wherein the imaging detector is configured to obtain the raw image data via A-mode ultrasound imaging technology combined with near infrared imaging technology.
7. The vasculature assessment apparatus of any preceding claim, wherein the operations further comprise: determining an image of the blood vessel from the raw image data; as well as The image is depicted on the display.
8. The vasculature assessment apparatus of any one of the preceding claims, wherein the suggested catheter parameters include a catheter model, the operation comprising selecting the catheter model from a list of catheter models stored in the memory.
9. The vasculature assessment device of any of the preceding claims, wherein the operations further comprise transmitting the suggested catheter parameters to an electronic medical record system for inclusion in the patient's electronic medical record.
10. The vascular system assessment device of any of the preceding claims, wherein the operation further comprises receiving the trained machine learning model from an external computing system and storing the trained machine learning model in the memory.
11. The vasculature assessment device according to any one of the preceding claims, wherein the imaging detector, the device module and the display are combined into a single unit.
12. A vascular system assessment system comprising: A plurality of vascular system assessment devices, each vascular system assessment device comprising: an imaging detector configured to acquire raw image data of a blood vessel of a patient; and An apparatus module having a console coupled to the imaging detector, the console comprising a processor and a memory having logic stored thereon, the logic, when executed by the processor, performing operations comprising: receiving the raw image data from the imaging detector; determining blood vessel data from the raw image data; applying the trained machine learning model to the blood vessel data to determine recommended catheter parameters associated with a catheter to be inserted into the blood vessel; and depicting the suggested catheter parameters on a display of the equipment module; and a computing system coupled to the vasculature assessment device, the computing system comprising a memory having machine learning logic stored thereon, the machine learning logic, when executed by a processor, performing a machine learning operation comprising executing a machine learning algorithm on a historical catheter placement dataset to define the trained machine learning model, wherein the historical catheter placement dataset comprises: a vascular dataset received from the vasculature assessment device; and Actual catheter parameter dataset, Each actual catheter parameter data set corresponds to a blood vessel data set in a one-to-one relationship.
13. The vasculature assessment system of claim 12, wherein the computing system is communicatively coupled to an electronic medical record system, the machine learning operation comprising receiving the actual catheter parameter data set from the electronic medical record system.
14. The vascular system assessment system according to claim 12 or 13, wherein each blood vessel data set comprises a diameter of a blood vessel of a corresponding patient and a depth of the blood vessel relative to a skin surface of the corresponding patient. 15 . The vasculature assessment system of claim 14 , wherein each actual catheter parameter data set comprises a catheter size and a catheter length of a catheter inserted into the blood vessel of the corresponding patient.
16. The vasculature assessment system of claim 15, wherein each actual catheter parameter data set further includes a catheter model.
17. A system method for determining recommended catheter parameters, comprising: receiving a plurality of vascular data sets from a plurality of vasculature assessment devices; receiving a plurality of actual catheter parameter data sets from an electronic medical record system, each catheter parameter data set corresponding to a vascular data set; executing a machine learning algorithm on the blood vessel dataset and the actual catheter parameter dataset to train a machine learning model that relates the blood vessel dataset to the actual catheter parameter dataset; Using one of the vascular system assessment devices, acquiring raw image data of blood vessels from a live patient; determining instantaneous blood vessel data from the raw image data; applying the machine learning model to the real-time vascular data to determine recommended catheter parameters for a catheter to be inserted into the blood vessel; as well as The suggested catheter parameters are depicted on a display of the one of the vasculature assessment devices.
18. The system method according to claim 17, wherein: The blood vessel data includes the diameter of the blood vessel and the depth of the blood vessel relative to the skin surface, and The recommended catheter parameters include catheter size and catheter length.
19. The system method of claim 17 or 18, wherein each vasculature assessment device comprises an ultrasound probe configured to acquire the raw image data.
20. The system method according to any one of claims 17 to 19, wherein the ultrasound probe is configured to acquire the raw image data using A-mode ultrasound imaging.