System, computer-implemented method, and computer-readable storage medium

Abstract

Described herein is an improved mechanical thrombus removal system that uses artificial intelligence to more effectively capture, push, segment, and / or aspirate thrombus regardless of the thrombus' age, size (length, diameter, etc.), hardness, or location. The improved mechanical thrombus removal system described herein can include a catheter, one or more sensors connected to the catheter, and a control unit connected to the catheter and the sensor that uses artificial intelligence to capture, push, segment, and / or aspirate thrombus.

Description

[Technical field]

[0001] This application claims the benefit of priority to U.S. Provisional Patent Application No. 63 / 328,192, entitled "Artificial Intelligence-Based Control of Catheter Operation," filed April 6, 2022, and U.S. Provisional Patent Application No. 63 / 448,949, entitled "Artificial Intelligence-Based Control of Catheter Operation," filed February 28, 2023, both of which are incorporated by reference in their entireties. This application is also related to U.S. Patent Application No. 17 / 658,244, entitled "Aspiration Catheter," filed April 6, 2022, and which is incorporated by reference in its entirety. All applications which specify a foreign or domestic priority claim in an Application Data Sheet filed with this application are incorporated by reference into this application under 37 C.FR § 1.57. [Background technology]

[0002] The present disclosure relates to the field of medical methods and devices, and more particularly to catheters operated by motors controlled in part using artificial intelligence.

[0003] Thromboembolism is a disease caused by the formation of blood clots. In the venous system, thromboembolism has two distinct peripheral manifestations: deep vein thrombosis (DVT) and pulmonary embolism (PE). Venous thromboembolism is a leading cause of death and disability worldwide and in the United States, it is the third most common vascular disease after myocardial infarction and stroke. Researchers estimate that approximately 1 million people suffer from venous thromboembolism each year in the United States, with 600,000 hospitalizations. As a result, approximately 60,000 to 180,000 deaths occur within 30 days of onset each year in the United States, and direct medical costs associated with venous thromboembolism are estimated to exceed $10 billion annually.

[0004] Thrombi and their effects are, by their nature, heterogeneous and unpredictable. Thrombi come in many forms. Depending on the properties of the vasculature and the morphology of the thrombus, by the time a thromboembolism is diagnosed, the underlying thrombus may be large and hard due to aging. As a result, methods designed to remove new, soft thrombi are ineffective and inefficient at removing the larger, older thrombi commonly associated with venous thromboembolism. Current products are cumbersome and often compromised in deliverability by rigid catheters and complex mechanical components. Summary of the Invention

[0005] The systems, methods and devices described herein each have multiple aspects, no single one of which determines its desirable attributes, and without limiting the scope of the disclosure, some non-limiting features will be discussed briefly. [Means for solving the problem]

[0006] One aspect of the present disclosure provides a system including a catheter including an outer sheath and an inner sheath. The system further includes one or more sensors coupled to the catheter. The system further includes a control unit coupled to the catheter and the one or more sensors. The control unit includes a motor configured to move the inner sheath relative to the outer sheath. The control unit further includes a processor configured with computer executable instructions, which when executed by the processor, cause the processor to obtain sensor data from at least one of the one or more sensors, determine power consumption by the motor when moving the inner sheath relative to the outer sheath, apply the sensor data and an indication of the power consumption of the motor as inputs to a trained artificial intelligence model, cause the trained artificial intelligence model to output an amplitude and a frequency due to the application of the sensor data and the indication of the power consumption of the motor as inputs to the trained artificial intelligence model, and adjust operation of the motor to oscillate the inner sheath between a retracted position and an extended position at the frequency and a distance corresponding to the amplitude.

[0007] The system of the preceding paragraph may combine the following features: The computer executable instructions, when executed by the processor, further cause the processor to apply the sensor data, an indication of the power consumption of the motor, and the type of the motor as inputs to the trained artificial intelligence model. The catheter further comprises a valve at a distal end of the catheter configured to be inserted into a venous system. The computer executable instructions, when executed by the processor, further cause the processor to apply the sensor data, the indication of the power consumption of the motor, and the type of the valve included in the catheter as inputs to a trained artificial intelligence model. The valve is closed when the inner sheath is in an extended position and the valve is open when the inner sheath is in an extended position, and the trained artificial intelligence model is associated with at least one of the type of the valve or the type of the motor. The one or more sensors include at least one of a flow sensor, a contact sensor, a temperature sensor, a pressure sensor, or a camera. At least a portion of the one or more sensors are connected to a distal end of a catheter configured to be inserted into a venous system. At least a portion of the one or more sensors are coupled to a proximal end of the catheter and configured to aspirate one or more thrombus fragments during operation of the catheter. The system also includes a catheter operation learning system configured with second computer-executable instructions that, when executed, cause the catheter operation learning system to train an artificial intelligence model using the training data to form a trained artificial intelligence model and load the trained artificial intelligence model into a storage medium of a control unit.

[0008] Another aspect of the disclosure provides a computer-implemented method for actuating an inner sheath of a catheter, the computer-implemented method including obtaining sensor data from at least one sensor coupled to the catheter, determining power consumption of a motor configured to move the inner sheath relative to the outer sheath of the catheter while moving the inner sheath relative to the outer sheath, applying the sensor data and an indication of the power consumption of the motor as inputs to a trained artificial intelligence model, causing the trained artificial intelligence model to output an amplitude and a frequency, and adjusting operation of the motor to oscillate the inner sheath between a retracted position and an extended position at the frequency and a distance corresponding to the amplitude.

[0009] The computer-implemented method of the preceding paragraph may combine the following features: Applying the sensor data and the indication of the power consumption of the motor as inputs to the trained artificial intelligence model further comprises applying the sensor data, the indication of the power consumption of the motor, and a type of the motor as inputs to the trained artificial intelligence model. The catheter further comprises a valve at a distal end of the catheter configured for insertion into a venous system. Applying the sensor data and the indication of the power consumption of the motor as inputs to the trained artificial intelligence model further comprises applying the sensor data, the indication of the power consumption of the motor, and a type of the valve included in the catheter as inputs to the trained artificial intelligence model. The valve is closed when the inner sheath is in an extended position, and the valve is open when the inner sheath is in an extended position. The trained artificial intelligence model is also associated with at least one of the type of the valve or the type of the motor.

[0010] Another aspect of the present disclosure provides a non-volatile computer-readable storage medium including computer-executable instructions for actuating an inner sheath of a catheter, the computer-executable instructions, when executed by a computer system, causing the computer system to obtain sensor data from at least one sensor coupled to the catheter, determine power consumption by a motor configured to move the inner sheath relative to the outer sheath of the catheter while moving the inner sheath relative to the outer sheath, apply the sensor data and an indication of the power consumption of the motor as inputs to a trained artificial intelligence model, apply the sensor data and an indication of the power consumption of the motor as inputs to the trained artificial intelligence model to output an amplitude and frequency, and adjust operation of the motor to cause the inner sheath to oscillate between a retracted position and an extended position at the frequency and a distance corresponding to the amplitude.

[0011] The non-volatile computer-readable storage medium of the preceding paragraph may be combined with the following features: the computer-executable instructions, when executed, cause the computer system to apply the sensor data, the indication of the power consumption of the motor, and the type of the motor as inputs to the trained artificial intelligence model, the catheter further comprising a valve at a distal end of the catheter configured for insertion into a venous system, and the computer-executable instructions, when executed, cause the computer system to further apply the sensor data, the indication of the power consumption of the motor, and the type of valve included in the catheter as inputs to the trained artificial intelligence model. [Brief description of the drawings]

[0012] Throughout the drawings, reference numbers may be reused to indicate correspondence between referenced elements. The drawings are provided to illustrate example embodiments described herein and are not intended to limit the scope of the present disclosure.

[0013] [Figure 1] FIG. 1 is a block diagram of an exemplary operating environment of a mechanical thrombectomy system in which a catheter control unit uses artificial intelligence to operate a catheter.

[0014] [Diagram 2] FIG. 2 is a flow diagram illustrating operations performed by components of the operating environment of FIG. 1 to determine the amplitude and frequency at which to actuate the inner sheath of a catheter.

[0015] [Figure 3A] 1 shows examples of catheters in various positions. [Figure 3B] 1 shows examples of catheters in various positions.

[0016] [Figure 4A] 1 shows an example of a catheter used in a procedure to aspirate a thrombus. [Figure 4B] 1 shows an example of a catheter used in a procedure to aspirate a thrombus. [Figure 4C] 1 shows an example of a catheter used in a procedure to aspirate a thrombus. [Figure 4D] 1 shows an example of a catheter used in a procedure to aspirate a thrombus.

[0017] [Diagram 5] FIG. 11 is a flow diagram illustrating an inner sheath actuation routine, as illustratively implemented in one embodiment of the catheter control unit. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] As discussed above, methods designed to remove new, soft clots are ineffective at removing the larger, older clots commonly associated with venous thromboembolism. Current products are cumbersome and often have poor deliverability due to rigid catheters and complex mechanical components. Furthermore, while anticoagulants can reduce the risk of future clots, their use to remove clots requires lengthy procedures, typically lasting 12-24 hours. Yet, anticoagulants often fail to break down or remove existing clots, potentially significantly increasing a patient's risk of bleeding.

[0019] Many therapies have been developed for the treatment of thromboembolism, ranging from open surgery to minimally invasive catheter-based therapies, but these therapies have limitations when used to treat thromboembolism. For example, mechanical thrombectomy systems are one of the therapies that have been developed. However, typical mechanical thrombectomy systems are not configured to adequately address the shapes, quantities, and compositions of common thrombi in thromboembolism due to poor deliverability. In particular, typical mechanical thrombectomy systems are generally too large in size, which reduces delivery capability and makes the catheter system stiff, resulting in excessive clogging and excessive blood removal. In addition, typical mechanical thrombectomy systems are generally designed to remove soft, new thrombi, and problems arise when attempting to remove more extensive, hard, old thrombi. In addition, typical mechanical thrombectomy systems have difficulty removing thrombi from the vessel wall.

[0020] To overcome the technical deficiencies of conventional mechanical thrombus removal systems, physicians often remove the catheter multiple times to move and aspirate the thrombus from the patient's venous system. Still, it is difficult for many humans to completely aspirate the thrombus using conventional mechanical thrombus removal systems. For example, conventional mechanical thrombus removal systems may include a component inserted into the patient's venous system that is activated to aspirate the thrombus. However, aspirating the thrombus may require the component to be activated five to six times per second or more. Given the unique characteristics of the structure of the patient's venous system, the composition of the patient's blood, the thrombus to be aspirated, etc., it is impossible for most humans to activate such components that many times per second, let alone determine how many times per second is sufficient to aspirate the thrombus. Therefore, procedures using conventional mechanical thrombus removal systems may result in poor thrombus aspiration results and significantly longer procedure times.

[0021] Accordingly, described herein is an improved mechanical thrombus removal system that can use artificial intelligence to more effectively capture, push, split, and / or aspirate thrombus while reducing the risk of bleeding during surgery, regardless of age, thrombus size (e.g., length, diameter, etc.), hardness, or location. For example, an improved mechanical thrombus removal system described herein can include a catheter, one or more sensors connected to the catheter, and a control unit connected to the catheter and the sensor that uses artificial intelligence to capture, push, split, and / or aspirate thrombus.

[0022] The catheter may include an outer sheath, a valve, and an inner sheath. The outer sheath and the inner sheath have a cylindrical shape at least partially across the length of the catheter, and the diameter of the inner sheath is smaller than the diameter of the outer sheath. The distal end of the catheter is inserted into a venous system, and the proximal end of the catheter is connected to a collection container that stores thrombus fragments aspirated from the venous system. The valve may be disposed at the distal end of the catheter. The inner sheath may be axially movable between a closed or retracted position, a flushing position, and / or an open position. In the retracted position, the inner sheath is located inside the outer sheath, and the valve is closed to prevent objects outside the distal end of the catheter from entering the inner sheath. In the flushing position, the inner sheath is located inside the outer sheath, and an end of the inner sheath distal to the catheter is closer to the valve than when the inner sheath is in the retracted position, and the valve is closed to prevent objects outside the distal end of the catheter from entering the inner sheath. In the open position, at least a portion of the end of the inner sheath distal to the catheter is disposed outside the outer sheath and the valve may be open.

[0023] The control unit includes a motor and a computing system. The motor is mechanically connected to at least the inner sheath and / or the outer sheath and can actuate the inner sheath and / or the outer sheath, such as by moving the inner sheath relative to the outer sheath and between a retracted position, a flushing position, and / or an open position. In particular, the motor can move the inner sheath between a retracted position and an open position when the catheter is used to capture, push, divide, and / or aspirate thrombus. The motor can move the inner sheath between a retracted position, a flushing position, and / or an open position when a flushing operation is performed to flush thrombus fragments through the inner sheath into the collection container and / or to wash the inner sheath.

[0024] The computing system can use artificial intelligence to determine appropriate positions for the inner sheath, such as the distance or amplitude to move the inner sheath to reach a flushed or open position, and the frequency at which the inner sheath moves between the retracted and flushed positions and / or between the retracted and open positions. For example, the sensors can include one or more flow sensors (e.g., a sensor that detects the rate at which blood, clots, and other matter is drawn into the inner sheath at the distal end of the catheter), one or more temperature sensors (e.g., a thermistor that can be used to measure the temperature at the distal end of the catheter, which ultimately uses the measured temperature to calculate the rate at which matter is flowing into the distal end of the catheter, which in turn uses the calculated rate to calculate the fluid pressure at the distal end of the catheter), one or more pressure sensors (e.g., a sensor that measures the fluid pressure at the distal end of the catheter), one or more cameras (e.g., an infrared camera), one or more sensors (e.g., a tachometer ... The catheter may include a catheter-based device (e.g., a flow sensor that can determine the length and / or distance between the thrombus pieces as they are aspirated into a collection container based on changes in the flow rate of material through the inner sheath, a camera that can take one or more images of the thrombus pieces after they exit the venous system and are aspirated through the inner sheath toward a collection container, etc. The sensor may communicate with the computing system (e.g., via a wired or wireless connection) directly and / or indirectly via the motor to provide one or more measurements to the computing system. Similarly, the motor may communicate with the computing system (e.g., via a wired or wireless connection) to provide one or more operating parameters (e.g., current motor power consumption, motor resistance, etc.).The computing system can periodically apply the received sensor measurements, the received motor operating parameters, an indication of the type of valve (e.g., duckbill, umbrella, flapper, etc.) at the distal end of the catheter, and / or an indication of the type of motor (e.g., direct current (DC) motor, alternating current (AC) motor, direct drive motor, linear motor, rotary motor, stepper motor, brushless motor, brushed motor, air cooled motor, liquid cooled motor, single phase motor, two phase motor, three phase motor, etc.) present in the control unit as inputs to an artificial intelligence model (e.g., a machine learning model, a neural network, etc.) that has been trained to output an amplitude that defines a distance that the inner sheath moves from a retracted position to either a cleaning position or an open position, and a frequency at which the inner sheath oscillates between the retracted position and the cleaning position or the open position. In response to the inputs provided to the trained artificial intelligence model, the trained artificial intelligence model can output an amplitude (e.g., in millimeters, e.g., 0.00 mm, 0.05 mm, 1 mm, 2 mm, 3 mm, etc.) and a frequency (e.g., in Hz, e.g., 0 Hz, 4 Hz, 5 Hz, 6 Hz, etc.). The computing system then sends a signal to the motor to instruct the motor to adjust its operation so that the inner sheath oscillates between the retracted position and the cleaning or open position at or near the output frequency (e.g., within 0.01%, 0.1%, 1% of the output frequency) where the distance the inner sheath travels to get from the retracted position to the cleaning or open position matches the output amplitude or nearly matches the output amplitude (e.g., within 0.01%, 0.1%, 1% of the output amplitude).

[0025] The computing system may apply the inputs to the trained artificial intelligence model one or more times during a procedure. For example, the computing system may automatically apply the inputs to the trained artificial intelligence model every millisecond, every second, every 10 seconds, etc., such as at the beginning of a procedure, in response to a request from a physician, or in response to a motor's power consumption exceeding a threshold. Thus, the computing system may adjust the operation of the motor one or more times during a single procedure.

[0026] The control unit or remote computing system may perform initial training of the artificial intelligence model and / or retraining or updating of a trained artificial intelligence model. For example, the control unit or remote computing system may train or retrain the artificial intelligence model using training data including individual data groups labeled with amplitude and frequency values. Each data group may include one or more sensor measurements (e.g., any of the sensor measurements described herein), one or more motor operating parameters (e.g., any of the motor operating parameters described herein), an indication of the type of valve present at the distal end of the catheter when the sensor measurements were obtained, and an indication of the type of motor used to actuate the inner sheath of the catheter. The amplitude numerical label applied to the data group may represent an amplitude that defines a flushing or opening position that provided the highest level of capture, expulsion, division, and / or aspiration of thrombus and / or the highest level of flushing of the inner sheath, taking into account the sensor measurements, motor operating parameters, valve types, and motor types that form the data group. Similarly, the frequency numerical label applied to a data group may represent the frequency of vibration of the inner sheath that resulted in the greatest level of capture, pushing, dividing, and / or aspirating of thrombus, and / or the greatest level of cleaning of the inner sheath, taking into account the sensor measurements, motor operating parameters, valve type, and motor type forming the data group.

[0027] The control unit or remote computing system can train or retrain the artificial intelligence model asynchronously with the use of the improved mechanical thrombectomy system described herein. For example, the control unit or remote computing system can train or retrain the artificial intelligence model before the individual units of the improved mechanical thrombectomy system described herein are used for the first time in a procedure, so that the trained artificial intelligence model is stored in the computing system of the individual units and is available for the procedure of the first use of the individual units. In other words, the computing system of the individual units can be pre-loaded with the trained artificial intelligence model or updated to include the trained artificial intelligence model before the first use. Alternatively or additionally, the control unit or remote computing system can train or retrain the artificial intelligence model while the individual units of the improved mechanical thrombectomy system described herein are used for the first time in a procedure or at a time after the individual units are used for the first time in a procedure. In other words, the computing system of the individual units can receive the trained or retrained artificial intelligence model during or after the individual units are used for the first time (this can be applied, for example, in a situation where the control unit of the improved mechanical thrombectomy system is reusable). When the remote computing system performs learning or re-learning in any scenario, the remote computing system may send the trained artificial intelligence model to the individual unit's computing system via a network and store it, or the remote computing system may export the trained artificial intelligence model to a physical storage medium (e.g., a hard disk, a flash memory, a solid state drive, etc.), or connect the physical storage medium to the individual unit's computing system and transfer the trained artificial intelligence model to the individual unit's computing system and store it.

[0028] Although this disclosure describes a control unit or remote computing system training a single artificial intelligence model for use in determining the movement of the catheter inner sheath, this is not intended to be limiting. The control unit or remote computing system may train multiple artificial intelligence models, each of which may generate outputs specific to a valve type or motor type. For example, the control unit or remote computing may train one artificial intelligence model to output amplitude and another artificial intelligence model to output frequency. In this example, the training data used for training may include the aforementioned data groups, but the training data used to train the artificial intelligence model that outputs amplitude may include data groups labeled with amplitude values, and the training data used to train the artificial intelligence model that outputs frequency may include data groups labeled with frequency values. In another example, the control unit or remote computing system may train multiple artificial intelligence models, each associated with a particular type of valve. In this example, the training data used to perform the training may include a data group that includes data collected from a mechanical thrombectomy system with a particular type of valve (thus, the data group may not include valve type data, and / or the control unit or remote computing system may exclude valve type data when the training is performed). In another example, the control unit or remote computing system may train multiple artificial intelligence models, each associated with a particular type of motor. In this example, the training data used to perform the training may include a data group that includes data collected from a mechanical thrombectomy system with a particular type of motor (and thus the data group may not include motor type data and / or the control unit or remote computing system may exclude motor type data when training is performed).

[0029] The control unit or remote computing system may train any combination of the artificial intelligence models described herein with training data adjusted in accordance with the description herein (e.g., training a first artificial intelligence model that is specialized for the first type of valve and outputs an amplitude, training a second artificial intelligence model that is specialized for the first type of valve and outputs a frequency, training a third artificial intelligence model that is specialized for the second type of valve and outputs an amplitude, training a fourth artificial intelligence model that is specialized for the second type of valve and outputs a frequency, etc., or training a first artificial intelligence model specialized for the first type of valve and the first type of motor, training a second artificial intelligence model specialized for the first type of valve and the second type of motor, training a third artificial intelligence model specialized for the second type of valve and the first type of motor, etc. The control unit 100 may learn a first artificial intelligence model that is specialized for a first type of valve and a first type of motor and outputs an amplitude, a second artificial intelligence model that is specialized for a first type of valve and a first type of motor and outputs a frequency, a third artificial intelligence model that is specialized for a first type of valve and a second type of motor and outputs an amplitude, a fourth artificial intelligence model that is specialized for a first type of valve and a second type of motor and outputs a frequency, a first artificial intelligence model that is specialized for a first type of valve and outputs an amplitude, a second artificial intelligence model that is specialized for a first type of valve and outputs a frequency, a third artificial intelligence model that is specialized for a second type of valve and outputs an amplitude and a frequency, etc. The type of artificial intelligence model loaded or transmitted to an individual unit of the improved mechanical thrombus removal system described herein may match the characteristics of the individual unit (e.g., if an individual unit includes a first type of valve and a second type of motor, the individual unit may be loaded and / or receive an artificial intelligence model trained specifically for the first type of valve and / or the second type of motor).

[0030] By using artificial intelligence, the improved mechanical thrombectomy system described herein can determine the appropriate number of times per second to actuate the inner sheath or how far to actuate the inner sheath to effectively capture, push, split, and / or aspirate the thrombus. As discussed above, this determination may depend on the unique characteristics of the patient's venous system structure, the composition of the patient's blood, the thrombus to be aspirated, etc., and / or is often impossible for a human to make this determination by judgment, since a human does not have the ability to observe or identify these unique characteristics during a procedure. In fact, even if a human knew how many times per second to actuate the inner sheath, the number would usually be high enough (e.g., 4 times per second, 5 times per second, 6 times per second, etc.) that a human would not be able to physically actuate the inner sheath this many times per second. Although the motor may actuate the inner sheath at an appropriate number of times per second and / or a desired distance, variations in the structure of the patient's venous system, the composition of the patient's blood, the size of the aspirated clot, the time since formation, and / or the composition, etc., may make it difficult for even the motor to maintain the amplitude and / or frequency. However, the trained artificial intelligence model may take into account some or all of these characteristics when outputting the amplitude and frequency. In some cases, the amplitude and / or frequency output by the artificial intelligence model may be lower or higher than the actual amplitude and / or frequency at which the clot can be best captured, pushed out, split, and / or aspirated. Specifically, if the motor is instructed to actuate the inner sheath at the actual amplitude and / or actual frequency, the motor may not be able to do so given the resistance caused by the structure of the patient's venous system, the composition of the patient's blood, the size of the aspirated clot, the time since formation, and / or the composition, etc. However, the amplitude and / or frequency output by the trained artificial intelligence model may be the level of the actual amplitude and / or actual frequency at which the motor actuates the inner sheath. Thus, the use of artificial intelligence may improve the functionality of the motor.

[0031] The foregoing aspects and many of the attendant advantages of the present disclosure will become better understood and appreciated by reference to the following detailed description, when taken in conjunction with the accompanying drawings, in which:

[0032] <Example of an artificial intelligence-based mechanical thrombus removal system environment> 1 is a block diagram illustrating an example operating environment 100 of a mechanical thrombectomy system in which a catheter control unit 120 uses artificial intelligence to actuate a catheter 150. Operating environment 100 includes one or more sensors 155 and / or a display system 160 in communication with catheter control unit 120, and a catheter actuation learning system 170 that can communicate with catheter control unit 120 via network 110.

[0033] Catheter control unit 120 can include a computing system 130 and a motor 140. Computing system 130 can be configured to determine the amplitude and / or frequency at which an inner sheath of catheter 150 moves during a procedure. Computing system 130 can be a single computing device or can include multiple different computing devices. Each of the components of computing system 130 can be implemented in application specific hardware (e.g., one or more application specific integrated circuits (ASICs)) that does not require software, or in a combination of hardware and software (e.g., a single board microcontroller, a multi-board microcontroller, etc., including one or more microprocessors, memory (e.g., flash memory), one or more input / output (I / O) pins, one or more transceivers, one or more printed circuit expansion boards, and / or hardware-like that is programmed to use firmware or software). In some embodiments, computing system 130 can include additional or reduced components from FIG. 1.

[0034] The motor 140 may be connected to the computing system 130 via a wired or wireless connection. The motor 140 may be configured to transmit operating parameters to the computing system 130 via a wired or wireless connection, including current motor power consumption, motor resistance, and the like. The motor 140 may also be connected to at least an inner sheath of the catheter 150. The motor 140 may be configured to actuate the inner and / or outer sheaths, such as by moving the inner sheath relative to the outer sheath and between a retracted, flushing, and / or open position. The motor 140 may move the inner sheath between the retracted, flushing, and / or open position and / or maintain the inner sheath in the retracted or flushing position when a flushing operation is performed to flush thrombus debris through the inner sheath into a collection container connected to the catheter control unit 120 and / or when a flushing operation is performed to wash the inner sheath. The motor 140 may further be connected to a power source (eg, a battery, an AC power source, a DC power source, etc.) that provides power to facilitate operation of the motor.

[0035] The catheter 150 may include an outer sheath, a valve, and an inner sheath. The outer sheath and the inner sheath have a cylindrical shape that at least partially traverses the length of the catheter 150, and the diameter of the inner sheath is smaller than the diameter of the outer sheath. The distal end of the catheter 150 is inserted into the venous system, and the proximal end of the catheter is connected to a collection container that stores thrombus fragments aspirated from the venous system. A valve may be provided at the distal end of the catheter 150. The inner sheath can be axially moved between a closed or retracted position, a flushing position, and / or an open position. When in the retracted position, the inner sheath is located inside the outer sheath and the valve is closed, which can prevent objects outside the distal end of the catheter 150 from entering the inner sheath. When in the flushing position, the inner sheath is located inside the outer sheath and the end of the inner sheath at the distal end of the catheter 150 is closer to the valve than when the inner sheath is in the retracted position, and the valve is closed, which can prevent objects outside the distal end of the catheter 150 from entering the inner sheath. The inner sheath may be in a flushing position to clear any debris from the inner sheath. As described in more detail below, an irrigation fluid (e.g., saline) may be injected between the inner and outer sheaths of the catheter 150 and directed toward the distal end of the catheter 150. If a valve at the distal end of the catheter 150 is closed, some or all of the saline may be prevented from exiting the catheter 150, and the saline may also be aspirated through the inner sheath by a vacuum that draws objects from the distal end of the catheter 150 to the proximal end of the catheter 150 within the inner sheath. Aspirating saline through the inner sheath from the distal end to the proximal end of the catheter 150 helps flush and remove blood clot debris and other debris that may be lodged in the inner sheath. Based on the measurements of the sensor 155, the trained artificial intelligence model may determine that the inner sheath is sufficiently blocked and output an amplitude to activate the inner sheath to a flushing position (rather than an open position). When in the open position, at least a portion of the end of the inner sheath at the distal end of the catheter 150 is disposed outside the outer sheath, allowing the valve to be open.

[0036] The one or more sensors 155 may include one or more flow sensors (e.g., a sensor that detects the rate at which blood, clots, and / or other matter is drawn into an inner sheath at the distal end of the catheter 150) located inside the catheter 150, outside the catheter 150, in a collection container, etc., one or more contact sensors (e.g., a sensor that measures the contact pressure between the clot and the inner sheath), one or more temperature sensors (e.g., a thermistor that can be used to measure the temperature at the distal end of the catheter 150 and ultimately use the measured temperature to calculate the velocity of matter entering the distal end of the catheter 150 and / or use the calculated velocity to calculate the fluid pressure at the distal end of the catheter 150), and one or more pressure sensors (e.g., a sensor that measures the fluid pressure at the distal end of the catheter 150). , one or more cameras (e.g., a camera, such as an infrared camera or other infrared optical sensor, that may be inserted into the venous system and capture one or more images of the thrombus within the venous system, optionally positioned at the distal end of the catheter 150), one or more sensors that measure the length of the thrombus fragments and / or the distance between the thrombus fragments as they are aspirated into a collection container (e.g., a flow sensor that may determine the length and / or distance between the thrombus fragments based on changes in the flow rate of material through the inner sheath, a camera that may capture one or more images of the thrombus fragments after they exit the venous system and are aspirated through the inner sheath toward a collection container), one or more sensors that measure impedance (e.g., a sensor that measures impedance at the distal end of the catheter 150), etc. Some or all of the sensors 155 may be connected to the distal end of the catheter 150 (e.g., connected to the outer sheath of the catheter 150, connected between the inner and outer sheaths of the catheter 150, or connected within the inner sheath of the catheter 150). Other sensors 155 may be at or near the proximal end of catheter 150 or connected to catheter control unit 120 near the proximal end of catheter 150 (e.g., one or more sensors that measure the length of the thrombus pieces as they are aspirated into a collection receptacle and / or the distance between the thrombus pieces as they are aspirated into a collection receptacle).Regardless of the location of the sensor 155, the sensor 155 can communicate with the computing system directly and / or indirectly via the motor 140 (e.g., via a wired or wireless connection) to provide one or more sensor 155 measurements to the computing system 130.

[0037] Computing system 130 may include various modules, components, data stores, etc. for providing the artificial intelligence functionality described herein. For example, computing system 130 may include an artificial intelligence based inner sheath actuation controller 132, an artificial intelligence based saline controller 133, an image processor 134, and an inner sheath model data store 136.

[0038] The artificial intelligence based inner sheath actuation controller 132 can use one or more trained artificial intelligence models to determine the amplitude and / or frequency at which the inner sheath of the catheter 150 moves during a procedure. For example, the artificial intelligence based inner sheath actuation controller 132 can obtain sensor 155 measurements from the sensor 155 and / or motor 140 operating parameters from the motor 140. The artificial intelligence based inner sheath actuation controller 132 can also obtain the trained artificial intelligence model from the inner sheath model data store 136. The trained artificial intelligence model has been trained to output an amplitude that defines the distance the inner sheath moves from the retracted position to either the cleaning position or the open position, and a frequency at which the inner sheath oscillates between the retracted position and the cleaning position or the open position. The artificial intelligence based inner sheath actuation controller 132 can periodically apply received sensor 155 measurements, expected sensor 155 measurements (e.g., expected flow rate through the inner sheath), received motor 140 operating parameters, an indication of the type of valve at the distal end of the catheter 150 (e.g., duckbill, umbrella, flapper, etc.), and / or an indication of the type of motor 140 present in the catheter control unit 120 (e.g., DC motor, AC motor, direct drive motor, linear motor, rotary motor, stepper motor, brushless motor, brushed motor, air cooled motor, liquid cooled motor, single phase motor, two phase motor, three phase motor, etc.) as inputs to a trained artificial intelligence model. In response to the artificial intelligence based inner sheath actuation controller 132 providing input to the trained artificial intelligence model, the trained artificial intelligence model can output amplitude (e.g., in millimeters, such as 0.00 mm, 0.05 mm, 1 mm, 2 mm, 3 mm, etc.) and / or frequency (e.g., in Hz, such as 0 Hz, 4 Hz, 5 Hz, 6 Hz, etc.).

[0039] As described herein, the trained artificial intelligence model may be a general model applicable to catheters 150 with any type of valve and / or catheter control units 120 with any type of motor 140. Alternatively, the trained artificial intelligence model may be specific to a type of valve and / or a type of motor 140. If the trained artificial intelligence model is specific to a particular type of valve, the artificial intelligence-based inner sheath actuation controller 132 may not provide an indication of the type of valve as an input to the trained artificial intelligence model. Similarly, if the trained artificial intelligence model is specific to a type of motor 140, the artificial intelligence-based inner sheath actuation controller 132 may not provide information indicating the type of motor 140 as an input to the trained artificial intelligence model. Additionally, the artificial intelligence-based inner sheath actuation controller 132 may obtain and use multiple trained artificial intelligence models (e.g., one for amplitude and one for frequency, each model receiving the same inputs) to generate a desired output.

[0040] Optionally, image processor 134 can process some or all of the measurements of sensor 155 in a manner described below. Artificial intelligence based inner sheath actuation controller 132 can provide processed measurements of sensor 155, rather than raw measurements of sensor 155, as input to a trained artificial intelligence model.

[0041] Once the trained AI model outputs the amplitude and frequency, the AI-based inner sheath actuation controller 132 sends a signal to the motor 140 to instruct the motor 140 to adjust its operation (e.g., actuation of the inner sheath) to oscillate between the retracted position and the cleaning or open position at or near the output frequency (e.g., within a percentage error of the output frequency, the percentage error being 0.01%, 0.1%, 1%, etc.). In this case, the distance traveled by the inner sheath from the retracted position to the cleaning or open position matches or approximately matches the output amplitude (e.g., within a percentage error of the output amplitude, the percentage error being 0.01%, 0.1%, 1%, etc.). If the output amplitude is at least equal to or greater than the distance between the distal end of the inner sheath in the retracted position and the distal end of the outer sheath. On the other hand, if the output amplitude is less than the distance between the distal end of the inner sheath in the retracted position and the distal end of the outer sheath, the inner sheath may be moved to the cleaning position. In some cases, the output amplitude may be a value (e.g., 0.00 mm, 0.01 mm, 0.02 mm, etc.) such that the inner sheath remains in the retracted position, moves slowly (e.g., at a low output frequency such as 0 Hz, 0.5 Hz, 0.8 Hz, 1 Hz, etc.) from the retracted position to a position between the retracted position and the cleaning position, remains in the cleaning position, and / or moves slowly (e.g., at a low output frequency such as 0 Hz, 0.5 Hz, 0.8 Hz, 1 Hz, etc.) from the cleaning position to a position between the retracted position and the cleaning position. The trained artificial intelligence model may be determined, for example, by the measured blood loss through the inner sheath (e.g., determined by the flow rate measured by the flow sensor 155, where a higher flow rate indicates increased blood loss), by the impedance measured by the impedance sensor 155, where a higher impedance indicates increased cell volume and therefore increased blood loss, or by the output from an infrared optical sensor 155, which can detect increased blood loss due to increased blood flow.) is greater than a threshold amount and / or if the flow rate through the inner sheath changes from an expected flow rate through the inner sheath (e.g., changes to a flow rate value higher than the expected flow rate value).

[0042] The artificial intelligence based inner sheath actuation controller 132 can apply inputs to the trained artificial intelligence model one or more times during a procedure. For example, the artificial intelligence based inner sheath actuation controller 132 can automatically apply inputs to the trained artificial intelligence model in response to a request from a physician, when the power consumption of the motor 140 exceeds a threshold, at the beginning of a procedure, etc. Thus, the artificial intelligence based inner sheath actuation controller 132 can adjust the operation of the motor 140 one or more times during a single procedure.

[0043] The artificial intelligence based saline controller 133 can use the trained saline artificial intelligence model to drive a component (e.g., a saline pump) that controls the pressure or rate of saline flow through the inner sheath. As described herein, saline is injected between the inner and outer sheaths of the catheter 150 and pumped toward the distal end of the catheter 150. If a valve at the distal end of the catheter 150 is closed, some or all of the saline can be prevented from exiting the catheter 150, and saline can also be pulled through the inner sheath by a vacuum that draws objects from the distal end of the catheter 150 to the proximal end of the catheter 150 within the inner sheath. Pulling saline through the inner sheath from the distal end of the catheter 150 to the proximal end of the catheter 150 helps flush and remove blood clot debris and other debris that may be lodged in the inner sheath. In some cases, flow sensor 155 (e.g., a flow sensor that detects the rate at which blood, clots, and / or other objects are drawn into the inner sheath at the distal end of catheter 150) may indicate that the flow rate of objects being drawn into the inner sheath at the distal end of catheter 150 is below a threshold flow rate value. If the flow rate is below the threshold flow rate value, it may indicate that the inner sheath is still clogged with one or more objects and / or that the clog is being cleared at a slower rate than expected. Adjusting the saline flow rate (e.g., increasing the saline flow rate, decreasing the saline flow rate, etc.) may improve by flushing or cleaning the inner sheath. AI-based saline controller 133 obtains the trained saline AI model and determines the flow rate of the saline fluid based on one or more flow measurements obtained from flow sensor 155, a current saline pressure or flow value (e.g., from flow sensor 155 that measures the saline flow rate, or from a component that controls the saline flow rate (e.g., a saline pump internal or external to catheter control unit 120).), one or more operating parameters of the component controlling the saline pressure or flow rate, an indication of the type of valve present at the distal end of the catheter 150 when the flow sensor 155 reading was taken, and / or an indication of the type of component used to control the saline pressure or flow rate (e.g., the type of saline pump) can be applied as inputs to the trained saline artificial intelligence model. As a result, the trained saline artificial intelligence model can output the saline pressure or flow rate, or an indication of an adjustment to be made to the current saline pressure or flow rate. The artificial intelligence-based saline controller 133 then sends a signal to the component controlling the saline flow rate (e.g., the saline pump) instructing the component to adjust the saline pressure or flow rate output by the trained saline artificial intelligence model (e.g., if the model has output a new saline pressure or flow rate value) or an amount indicated by the output of the trained saline artificial intelligence model (e.g., if the model has output an indication that an adjustment should be made).

[0044] The artificial intelligence based saline controller 133 can apply inputs to the trained saline artificial intelligence model one or more times during a procedure. For example, the artificial intelligence based saline controller 133 can automatically apply inputs to the trained saline artificial intelligence model every millisecond, every second, every 10 seconds, etc., in response to a request from a physician, when the flow rate through the inner sheath falls below a threshold, at the start of a procedure, etc. Thus, the artificial intelligence based saline controller 133 can adjust the pressure or flow rate of the saline flow one or more times during a single procedure.

[0045] Image processor 134 can be configured to process one or more images taken by a sensor 155, such as a camera connected to the distal end of catheter 150 and / or a camera positioned to capture the length of thrombus pieces aspirated towards a collection receptacle and / or the distance between thrombus pieces aspirated into a collection receptacle. For example, a camera connected to the distal end of catheter 150 can take one or more images of the boundary of a blood vessel and / or the boundary of a thrombus within a blood vessel. Image processor 134 can use image processing techniques (e.g., performing edge detection, identifying temperature differences (e.g., in the case of infrared images), etc.) to determine, for example, the size of the thrombus. The image processor 134 may cause the display system 160 to display one or more captured images indicative of the determined thrombus size, provide the determined thrombus size to the artificial intelligence based inner sheath actuation controller 132 for use as input to the trained artificial intelligence model, and / or illuminate an indicator light on the catheter control unit 120 or catheter 150 if the image processor 134 determines that the determined thrombus size is below a threshold value (the indicator light being lit may inform the physician that a sufficient amount of thrombus has been aspirated and that the catheter 150 can be removed).

[0046] In another example, a camera positioned to capture the length of and / or distance between the thrombus pieces aspirated toward the collection container can take a corresponding image and provide the image to the image processor 134. The image processor 134 can use image processing techniques (e.g., performing edge detection based on color differences between the thrombus pieces aspirated toward the collection container and other material within the inner sheath) to estimate the size of one or more thrombus pieces and / or the distance between the thrombus pieces as they are aspirated toward the collection container. The image processor 134 can provide the determined length of and / or distance between the thrombus pieces to the artificial intelligence based inner sheath actuation controller 132 for use as input to a trained artificial intelligence model.

[0047] The inner sheath model datastore 136 may store one or more trained artificial intelligence models (e.g., machine learning models, neural networks, etc.) each trained to output an amplitude and / or frequency. As described herein, the trained artificial intelligence models stored in the inner sheath model datastore 136 may be a general artificial intelligence model applicable to all types of catheters 150, an artificial intelligence model specific to the type of valve at the distal end of the catheter 150, and / or an artificial intelligence model specific to the type of motor 140 present in the catheter control unit 120. Optionally, the inner sheath model datastore 136 may also store one or more trained artificial intelligence models (e.g., machine learning models, neural networks, etc.) each trained to output a new saline pressure or flow rate or an adjustment to an existing saline pressure or flow rate. The inner sheath model datastore 136 is shown as being internal to the computing system 130, but is not limited thereto. For example, while not shown, the inner sheath model datastore 136 may be located external to the computing system 130.

[0048] Display system 160 may include one or more displays (e.g., an organic light emitting diode (OLED) display, a light emitting diode (LED) display, a liquid crystal display (LCD), a cell phone screen, a tablet screen, a laptop screen, a workstation screen, etc.) configured to display information obtained from catheter control unit 120, catheter 150, and / or sensor 155 (e.g., images captured by a camera at the distal end of catheter 150, etc.). Display system 160 may be located at the bedside during a procedure, for example. Display system 160 may be in wired or wireless communication with catheter control unit 120, catheter 150, and / or sensor 155.

[0049] Catheter operation learning system 170 may be a single computing device or may include multiple individual computing devices, such as computer servers, that are logically or physically grouped together to collectively operate as a server system. Each component of catheter operation learning system 170 may be implemented in application-specific hardware that does not require software (e.g., a server computing device with one or more ASICs) or as a combination of hardware and software. Additionally, the modules and components of catheter operation learning system 170 may be combined on a server computing device or separated into individual or groups on multiple server computing devices. In some embodiments, catheter operation learning system 170 may include more or fewer components than those shown in FIG. 1.

[0050] In some embodiments, the functionality and services provided by catheter operation learning system 170 may be implemented as web services available over network 110. In further embodiments, catheter operation learning system 170 is provided by one or more virtual machines implemented in a hosted computing environment. A hosted computing environment may include one or more computing resources that are rapidly provisioned and released, which may include computing, network, and / or storage devices. A hosted computing environment may also be referred to as a cloud computing environment.

[0051] Catheter operation learning system 170 may include various modules, components, data stores, etc. to provide the model learning functionality described herein. For example, catheter operation learning system 170 may include inner sheath model trainer 172, saline model trainer 173, and learning data store 174.

[0052] The inner sheath model trainer 172 can perform initial training of an artificial intelligence model and / or retraining or updating a trained artificial intelligence model. For example, the inner sheath model trainer 172 can train or retrain an artificial intelligence model using training data obtained from a training data store 174 that includes individual data groups labeled with amplitude and frequency values. Each data group can include one or more sensor 155 measurements (e.g., any of the sensor 155 measurements described herein, where the measurements can be actual and / or predicted values), one or more motor 140 operating parameters (e.g., any of the motor 140 operating parameters described herein), an indication of the type of valve present at the distal end of the catheter 150 when the sensor 155 measurements were obtained, and an indication of the type of motor 140 used to actuate the inner sheath of the catheter 150. An amplitude value label applied to a data group may represent an amplitude that defines a wash or open position that provided the best level of clot capture, push, split and / or aspiration, and / or the best level of cleaning of the inner sheath based on the sensor 155 measurements, motor 140 operating parameters, valve type and motor 140 type that form the data group. Similarly, a frequency value label applied to a data group may represent an inner sheath vibration frequency that provided the best level of clot capture, push, split and / or aspiration, and / or the best level of cleaning of the inner sheath based on the sensor 155 measurements, motor 140 operating parameters, valve type and motor 140 type that form the data group.

[0053] The inner sheath model trainer 172 may train or retrain the artificial intelligence model asynchronously with the use of the catheter control unit 120 and / or catheter 150. For example, the inner sheath model trainer 172 may train and / or retrain the artificial intelligence model before the individual units of the catheter control unit 120 and / or catheter 150 are used in a procedure for the first time, and the trained artificial intelligence model is stored in the computing system 130 of the individual units and available when the individual units are used in a procedure for the first time. In other words, the computing system 130 of the individual units may be pre-loaded with the trained artificial intelligence model or may be updated to include the trained artificial intelligence model before the first use. Alternatively or additionally, the inner sheath model trainer 172 may train and / or retrain the artificial intelligence model while the individual units of the catheter control unit 120 and / or catheter 150 are used in a procedure for the first time, or at a time after the individual units are used in a procedure for the first time. In other words, the individual unit's computing system 130 can receive the trained or retrained artificial intelligence model during or after the individual unit is initially used (this can be applied, for example, in situations where the catheter control unit 120 is reusable). The inner sheath model trainer 172 can transmit the trained artificial intelligence model to the individual unit's computing system 130 via the network 110 for storage, the inner sheath model trainer 172 can export the trained artificial intelligence model to a physical storage medium (e.g., a hard disk, a flash memory, a solid state drive, etc.), the physical storage medium can be connected to the individual unit's computing system 130, the trained artificial intelligence model can be transferred to the individual unit's computing system 130 for storage, etc.

[0054] The saline model trainer 173 can perform initial training of the saline artificial intelligence model and / or retraining or updating of a trained saline artificial intelligence model. For example, the saline model trainer 173 can train or retrain the artificial intelligence model using training data obtained from a training data store 174 that includes individual data groups labeled to indicate whether the inner sheath is clogged or not. Each data group can include one or more sensor 155 measurements (e.g., measurements of any of the sensors 155 described herein, which may be actual or predicted values), one or more operating parameters of a component that controls the saline pressure or flow rate (e.g., a saline pump), an indication of the type of valve present at the distal end of the catheter 150 when the sensor 155 measurements were obtained, and / or an indication of the type of component used to control the saline pressure or flow rate (e.g., the type of saline pump).

[0055] The saline model trainer 173 can train or retrain the saline artificial intelligence model asynchronously with the use of the catheter control unit 120 and / or catheter 150. For example, the saline model trainer 173 can train and / or retrain the saline artificial intelligence model before the individual units of the catheter control unit 120 and / or catheter 150 are used in a procedure for the first time, and the trained saline artificial intelligence model is stored in the computing system 130 of the individual units and available when the individual units are used in a procedure for the first time. In other words, the computing system 130 of the individual units may be pre-loaded with the trained saline artificial intelligence model or may be updated to include the trained saline artificial intelligence model before the first use. Alternatively or additionally, the saline model trainer 173 can train or retrain the saline artificial intelligence model while the individual units of the catheter control unit 120 and / or catheter 150 are used in a procedure for the first time, or at a time after the individual units are used in a procedure for the first time. In other words, the individual unit's computing system 130 can receive the trained or retrained saline artificial intelligence model during or after the individual unit is initially used (this can be applied, for example, in situations where the catheter control unit 120 is reusable). The saline model trainer 173 can transmit the trained saline artificial intelligence model to the individual unit's computing system 130 via the network 110 for storage, the saline model trainer 173 can export the trained saline artificial intelligence model to a physical storage medium (e.g., a hard disk, a flash memory, a solid state drive, etc.), connect the physical storage medium to the individual unit's computing system 130, transfer the trained saline artificial intelligence model to the individual unit's computing system 130 for storage, etc.

[0056] Training data store 174 can store training data used to train one or more artificial intelligence models and / or one or more saline artificial intelligence models. For example, training data may include sensor 155 measurements taken during bench testing by individual units, such as catheter control unit 120 and / or catheter 150, and / or operating parameters of motor 140, etc. Alternatively or additionally, training data can include sensor 155 measurements (e.g., measurements from a flow sensor measuring the flow rate through an inner sheath, measurements from a flow sensor measuring the flow rate of saline, etc.) and / or operating parameters of components that control the pressure or flow rate of saline (e.g., operating parameters of a saline pump). Alternatively or additionally, training data can include sensor 155 measurements (e.g., measurements from a flow sensor measuring the flow rate through an inner sheath, measurements from a flow sensor measuring the flow rate of saline, etc.) and / or operating parameters of components that control the pressure or flow rate of saline (e.g., operating parameters of a saline pump). Training data store 174 is shown as being internal to catheter operation training system 170, but is not limited thereto. For example, although not shown, the learning data store 174 can be located external to the catheter operation learning system 170 .

[0057] Catheter operation learning system 170 is described herein, without limitation, as performing learning of an artificial intelligence model. Some or all of the functionality described herein as being performed by catheter operation learning system 170 may be performed by computing system 130.

[0058] <Example of a block diagram for determining catheter operation> FIG. 2 is a flow diagram illustrating operations performed by components of the operating environment 100 of FIG. 1 to determine the amplitude and frequency at which to actuate the inner sheath of the catheter 150. As shown in FIG. 2, one or more of the sensors 155A-C and / or other sensors 155 transmit sensor data to the artificial intelligence-based inner sheath actuation controller 132 at (1). The sensor data can include any of the sensor 155 measurements described herein. The sensors 155A-C and / or other sensors 155 can transmit sensor data via a wired or wireless connection that optionally passes through the motor 140. Before, during, and / or after the sensors 155A-C and / or other sensors 155 transmit sensor data, the motor 140 can transmit power consumption data to the artificial intelligence-based inner sheath actuation controller 132. Optionally, the motor 140 can transmit other operating parameters, such as the resistance of the motor 140, to the artificial intelligence-based inner sheath actuation controller 132.

[0059] The artificial intelligence-based inner sheath actuation controller 132 can retrieve the trained artificial intelligence model from the inner sheath model data store 136 (3). As described herein, the trained artificial intelligence model can be a general model trained to output amplitude and / or frequency for any type of motor 140 and catheter 150 with any type of valve present in the catheter control unit 120. Alternatively, the trained artificial intelligence model can be specific to the type of valve present in the catheter 150 to be actuated and / or the type of motor 140 present in the catheter control unit 120 connected to the catheter 150 to be actuated. In some embodiments, the artificial intelligence-based inner sheath actuation controller 132 can retrieve multiple trained artificial intelligence models. For example, one trained artificial intelligence model may be trained to output amplitude and another trained artificial intelligence model may be trained to output frequency.

[0060] The artificial intelligence based inner sheath actuation controller 132 can apply the sensor data and / or power consumption data as inputs to the trained artificial intelligence model at (4). In further embodiments, the artificial intelligence based inner sheath actuation controller 132 can also apply an indication of the type of valve present in the catheter 150 and / or the type of motor 140 present in the catheter control unit 120 as inputs to the trained artificial intelligence model. Based on providing one or more inputs to the trained artificial intelligence model and causing the trained artificial intelligence model to generate an output, the artificial intelligence based inner sheath actuation controller 132 can determine the amplitude and frequency at (5). The artificial intelligence based inner sheath actuation controller 132 can send an indication of the amplitude and frequency to the motor 140 at (6).

[0061] The motor 140 can adjust its operation upon receiving instructions from the artificial intelligence based inner sheath actuation controller 132. For example, the motor 140 can adjust its operation such that the inner sheath oscillates from a retracted position to an extended position (e.g., a flushing position or an open position) corresponding to the amplitude and frequency indicated in (7).

[0062] Some or all of the operations disclosed with respect to Figure 2 may be repeated one or more times in a particular sequence. Additionally, although the operations disclosed with respect to Figure 2 are described in a particular order, this is not intended to be limiting and one or more of these operations may be performed in a different order.

[0063] <Example of catheter> 3A-3B show examples of the catheter 150 in various positions. For example, FIG. 3A shows the catheter 150 in a closed or retracted position. As shown in FIG. 3A, the catheter 150 includes an outer sheath 302 (also referred to herein as an outer support catheter), an inner sheath 304 (also referred to herein as an inner suction catheter), a valve 306, and an inlet 310 through which saline can be injected toward a distal end 320 of the catheter 150. As shown, the inner suction catheter 304 extends through the outer support catheter 302. The inner sheath 304 can be considered to be in a closed or retracted position because the valve 306 is closed and the inner sheath 304 cannot move further toward the proximal end 322 of the catheter 150.

[0064] As described herein, saline injected into the inlet 310 may pass through an inlet disposed between the outer sheath 302 and the inner sheath 304 toward the distal end 320 of the catheter 150. Because the inner sheath 304 is in a closed or retracted position and the valve 306 is closed, a vacuum force within the inner sheath 304 during operation of the catheter 150 may draw saline from the distal end 320 of the catheter 150, through the inner sheath toward the proximal end 322 of the catheter 150.

[0065] The inner suction catheter 304 defines an aspiration lumen 308. The inner suction catheter 304 may be operably connected to a suction source. The suction source may cause the inner suction catheter 304 to aspirate the thrombus C through the suction lumen 308.

[0066] The inner suction catheter 304 can include a polymeric material with a reinforcing braid or coil. The outer diameter of the inner suction catheter 304 is at least about 1.0 mm and / or is not greater than about 12.0 mm, e.g., between 2.0 mm and 10.0 mm, and can be not greater than 5.0 mm, not greater than 4.0 mm, or not greater than 3.0 mm. The wall thickness of the inner suction catheter 304 can be not greater than about 0.5 mm, not greater than about 0.4 mm, not greater than about 0.3 mm, not greater than about 0.2 mm, or not greater than about 0.1 mm.

[0067] 3A, the aspiration lumen 308 may have a constant diameter. A distal segment of the inner aspiration catheter 304 may include a first material and a proximal segment of the aspiration catheter may include a second material having different properties than the first material, e.g., a different stiffness.

[0068] In other embodiments, the aspiration lumen 308 may have a varying diameter, with a distal segment of the lumen 308 having a smaller diameter than a proximal portion of the lumen 308. The inner aspiration catheter 304 may include a distal segment connected to a proximal segment. The distal and proximal segments may include the same or different materials. For example, the proximal segment may be stiffer than the distal segment. The distal segment may have a first inner diameter and the proximal segment may have a second inner diameter that is greater than the first inner diameter. The distal segment may extend within the proximal segment, with an outer surface of the distal segment connected to an inner surface of the proximal segment. The outer diameter of the proximal segment may be smaller than the inner diameter of the valve housing 312. The transition between the distal and proximal segments may form a stop joint that prevents the inner aspiration catheter 304 from moving a certain distance beyond the distal end of the outer support catheter 302. For example, the aspiration catheter may only extend 5 cm or less (3 cm or less, 2 cm or less, 1 cm or less, 0.5 cm or less, or 0.1 cm or less) from the distal end of the outer support catheter 302. However, if there is residual thrombus in the small distal vessels, the aspiration tube can be manually or slowly extended a greater distance from the support tube in a "search" mode to capture this residual thrombus and quickly pull it back into the support tube to complete the procedure.

[0069] The outer support catheter 302 can include an elongate tubular body that can include a polymeric material with a reinforcing braid or coil. One or more radiopaque markers can be disposed along the elongate tubular body.

[0070] The inner diameter of the outer support catheter 302 can be greater than the outer diameter of the inner suction catheter 304, thereby providing a space 314 for fluid flow between the two catheters. The outer diameter of the outer support catheter 302 can be at least about 1.0 mm and / or about 12.0 mm or less, such as 2.0 mm to 10.0 mm, or 3.0 mm to 5.0 mm. The inner diameter of the outer support catheter 302 can be at least 0.1 mm greater than the outer diameter of the inner suction catheter 304, such as at least about 0.1 mm greater than the outer diameter of the inner suction catheter 304, and / or not more than about 1.0 mm relative to the outer diameter of the inner suction catheter 304, such as about 0.25 mm to about 0.75 mm greater than the outer diameter of the inner suction catheter 304. The wall thickness of the outer support catheter 302 can be about 0.5 mm or less, about 0.4 mm or less, about 0.3 mm or less, about 0.2 mm or less, or about 0.1 mm or less.

[0071] The outer support catheter 302 can include a valve 306 at or near the distal end 316 of the elongate tubular body. For example, the valve 306 can be located within 15 cm (within 10 cm, within 5 cm, within 1 cm, within 0.5 cm, or within 0.1 cm) of the distal end 316 of the elongate tubular body. The valve 306 can be located within the lumen of the outer support catheter 302 or can be located external to the outer support catheter 302.

[0072] As shown, the valve 306 can be secured to the elongate tubular body by a valve housing 312. The valve housing 312 can protect the vessel wall from the valve 306. The valve 306 is disposed within the valve housing 312, which extends distally and / or proximally of the valve 306. The valve 306 can be secured within the valve housing 312 mechanically or chemically.

[0073] The valve housing 312 may be secured to the distal end 316 of the elongate tubular body by, for example, welding or gluing. The valve housing 312 may also be secured to the exterior surface of the elongate tubular body. The valve housing 312 may be made of plastic or metal.

[0074] The inner diameter of the valve housing 312 may be greater than the inner diameter of the elongated tubular body. However, in other embodiments, the valve housing 312 may extend into the elongated tubular body. The diameter of the opening at the distal end 318 may be equal to or less than the inner diameter of the distal end 316 of the elongated tubular body. The distal end 318 of the valve housing 312 may form the distal end of the outer support catheter 302. The distal end 318 of the valve housing 312 may be tapered. The tapered distal end 318 may function as a break shoulder to break or split the thrombus. This helps split tougher thrombus.

[0075] When assembled, the distal end 316 of the elongate tubular body abuts the proximal side of the valve 306, maintaining the position of the valve 306 within the valve housing 312. The distal end 316 of the elongate tubular body is spaced from the proximal face of the valve 306 to allow irrigation fluid to enter the inner suction catheter 304.

[0076] The valve housing 312 is optional. The valve 306 can be mounted directly to or within the elongated tubular body. For example, a metal ring can be placed within the valve 306 and welded to a reinforcing structure within the elongated tubular body.

[0077] The valve 306 may be a one-way valve. As shown, the valve 306 is a duckbill valve, but may include any of the valve functions described above. The valve 306 may be any valve with an open end that is sufficiently rigid to divide a clot. The valve 306 may be any valve that allows the inner suction catheter 304 to be advanced and retracted through the valve 306. The valve 306 may be a slit valve or a valve with overlapping pieces, the ends of which may have a structure suitable for segmenting the valve. The inner diameter of the valve 306 may be smaller than the inner diameter of the outer support catheter 302 and larger than the outer diameter of the inner suction catheter 304.

[0078] The catheter 150 may include a manifold 324 at the proximal end of the outer support catheter 302. The manifold 324 may include an inlet 310 for connection to an irrigation source. The manifold 324 allows irrigation fluid to flow to the space 314 between the outer support catheter 302 and the inner suction catheter 304. The manifold 324 also includes a passageway 326 through which the inner suction catheter 304 connects to a suction source.

[0079] The passageway 326 may include a seal member 328 to prevent the fluid flushing solution from exiting the space outside the inner suction catheter 304. The seal member 328 may have less than 360 degrees of contact with the inner suction catheter 304. For example, the seal member 328 may include one or more bulges or protrusions for connecting with the inner suction catheter 304, such as two bulges, three bulges, or four bulges. The separated contact points reduce friction between the inner suction catheter 304 and the seal member 328, allowing for the use of lower torque motors.

[0080] The inner suction catheter 304 can be moved within the lumen of the support catheter either manually or automatically. If automatic, the catheter 150 may include a drive unit 330. The drive unit 330 may include a motor for driving the inner suction catheter 304 relative to the outer support catheter 302. The drive unit 330 may include or be operably connected to a controller configured to cause the motor to advance and retract the inner suction catheter 304. The drive unit 330 may include a battery power source. The drive unit 330 may be a handheld component that is separately attachable to the inner suction catheter 304. For example, the same drive unit 330 may be used with a disposable catheter assembly.

[0081] 3B, on the other hand, illustrates the catheter 150 in an open position. As shown in FIG 3B, the inner sheath 304 extends toward the distal end 320 of the catheter 150 and protrudes from the outer sheath 302. Also, the valve 306 is open.

[0082] 4A-4D show an example of a catheter 150 used in a procedure to aspirate a thrombus 430. As shown in FIG. 4A, the catheter 150 is in an open position with the inner sheath 304 extending toward the thrombus 430 to capture it. As shown in FIG. 4B, the catheter 150 is in a retracted position with the inner sheath 304 moving backward from the distal end 320 of the catheter 150. The thrombus 430 is now pushed into the inner sheath by suction. The thrombus 430 may continue to move within the inner sheath 304 toward the proximal end 322 of the catheter for collection in a collection vessel. The amplitude with which the inner sheath 304 extends to reach the open position and the frequency with which the inner sheath 304 oscillates between the open and retracted positions may be determined by a trained artificial intelligence model.

[0083] As shown in FIG. 4C, the catheter 150 is in a retracted or flushed position. For example, the inner sheath 304 may be disposed inside the outer sheath 302 such that the valve 306 is closed while the thrombus fragments 432 and 434 (e.g., thrombus fragments split from the thrombus 430) are present within the inner sheath 304. The amplitude at which the inner sheath 304 extends to reach the flushed position and the frequency at which the inner sheath 304 oscillates between the flushed and retracted positions may be determined by a trained artificial intelligence model. Although the suction force may pull the thrombus fragments 432 and 434 toward the proximal end 322 of the catheter 150, the suction force alone may be insufficient to pull the thrombus fragments 432 and 434 at a desired rate and / or to prevent clogging of the inner sheath 304. However, saline injected into the inlet 310 may flow to the distal end 320 of the catheter and be pulled by the suction force. The saline may help prevent clogging of the inner sheath 304, as the force generated by the saline pushing out the thrombus pieces 432 and 434, combined with the suction force, may be sufficient to draw the thrombus pieces 432 and 434 toward the proximal end 322 of the catheter 150 at least at a desired rate.

[0084] As shown in FIG. 4D, fluid flows between the outer surface of the inner suction catheter 304 and the inner surface of the outer support catheter 302. When the irrigation fluid reaches the valve 306, it enters the distal end of the inner suction catheter 304 and pushes the softened thrombus segments proximally through the inner suction catheter 304 as the suction force aspirates the thrombus segments. The added propellant accelerates the suction and prevents clogging. The application of water pressure doubles the suction force to at least about 1 bar and / or up to about 2 bar. The added propellant accelerates the suction and prevents clogging. Positive pressure can also be applied using other methods, such as using a pump.

[0085] If the inner suction catheter 304 becomes clogged, it can be pulled back proximal to the valve 306 without being completely withdrawn from the body. This improves the suction of irrigation fluid. The flow of irrigation fluid clears the clog in the inner suction catheter 304. In some methods, the irrigation flow rate may be activated only if a non-continuous flow (clog) is detected, or the irrigation flow rate may be increased if a non-continuous flow is detected. In this process, the inner suction catheter 304 may remain stationary or may move forward and backward while remaining behind the distal valve 306.

[0086] <Example of inner sheath operation routine> 5 is a flow diagram illustrating an exemplary inner sheath operation routine 500, illustratively implemented by a catheter control unit, according to one embodiment. As an example, the catheter control unit 120 of FIG. 1 can be configured to execute the inner sheath operation routine 500. The inner sheath operation routine 500 begins at block 502.

[0087] In block 504, sensor data is acquired. For example, the sensor data may include any of the measurements of the sensors 155 described herein. The sensor data may be data acquired by one or more sensors 155 while the catheter 150 is in use during a procedure.

[0088] At block 506, an amount of power consumed by the motor when moving the inner sheath of the catheter relative to the outer sheath of the catheter is determined. For example, the motor 140 can provide an indication of the amount of power consumed. As another example, the motor 140 can provide a motor resistance, and the amount of power consumed can be derived from the motor resistance.

[0089] In block 508, the sensor data and the indication of motor power consumption are applied as inputs to a trained artificial intelligence model, which may then output amplitude and frequency. Optionally, other data may also be provided to the trained artificial intelligence model, such as the type of valve present in the catheter 150 being used in the procedure and the type of motor 140 present in the catheter control unit 120 connected to the catheter 150 being used in the procedure.

[0090] At block 510, the operation of the motor is adjusted to oscillate the inner sheath between the retracted and extended positions at a frequency output by the trained artificial intelligence model and a distance corresponding to the amplitude output by the trained artificial intelligence model. As described herein, the amplitude may be 0 mm or the frequency may be 0 Hz, in which case the inner sheath will not oscillate until the trained artificial intelligence model is rerun and produces a different output, if applicable.

[0091] Blocks 504, 506, 508, and / or 510 may be repeated zero or more times during a single procedure. After the operation of the motors has been coordinated, the inner sheath actuation routine 500 proceeds to block 512 and ends.

[0092] <Additional embodiments> Network 110 may include any wired network, wireless network, or combination thereof. For example, network 110 may be a personal area network, a local area network, a wide area network, a wireless broadcast network (such as radio or television), a cable network, a satellite network, a cellular network, or combination thereof. As a further example, network 110 may be a publicly accessible network in a linked network that may be operated by various separate parties, such as the Internet. In some embodiments, network 110 may be a private or semi-private network, such as a corporate or university intranet. Network 110 may include one or more wireless networks, such as a Global System for Mobile Communications (GSM) network, a Code Division Multiple Access (CDMA) network, a Long Term Evolution (LTE) network, or other types of wireless networks. Network 110 may use protocols and components for communicating over the Internet or other types of networks mentioned above. For example, protocols used in network 110 may include Hypertext Transfer Protocol (HTTP), HTTP Secure (HTTPS), Message Queue Telemetry Transport (MQTT), Constrained Application Protocol (CoAP), and the like. The protocols and components for communicating over the Internet or any other type of communication network mentioned above are well known to those skilled in the art and will not be described in detail herein.

[0093] <Terminology> All of the methods and tasks described herein are performed by a computer system and are fully automated. The computer system may include multiple individual computers or computing devices (e.g., physical servers, workstations, storage arrays, cloud computing resources, etc.) that communicate and interoperate over a network to perform the described functions. Each such computing device may typically include a processor (or multiple processors) that executes program instructions or modules stored in memory or other non-volatile computer-readable storage media or devices (e.g., solid-state storage devices, disk drives, etc.). Various functions disclosed herein may be embodied in such program instructions or implemented in the computer system's application-specific circuitry (e.g., ASIC or FPGA). When a computer system includes multiple computing devices, these devices can be, but are not necessarily, co-located. Results of the disclosed methods and tasks may be written and persistently stored in physical storage devices, such as solid-state memory chips or magnetic disks. In some embodiments, the computer system may be a cloud-based computing system whose processing resources are shared by multiple separate entities or other users.

[0094] Depending on the embodiment, certain operations, events, or functions of any of the processes or algorithms described herein may be performed in a different order, added, connected, or omitted entirely (e.g., not all operations or events described are required for execution of an algorithm.) Furthermore, in certain embodiments, operations or events may be performed simultaneously rather than sequentially, for example, via multithreading, interrupt processing, multiple processors or processor cores, or other parallel architectures.

[0095] The various exemplary logic blocks, modules, routines, and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware (e.g., ASIC or FPGA devices), computer software running on computer hardware, or a combination of both. Furthermore, the various exemplary logic blocks and modules described in connection with the embodiments disclosed herein can be implemented or performed by machines such as processor devices, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. The processor device can be a microprocessor, but alternatively the processor device can also be a controller, a microcontroller, or logic circuitry implementing a state machine, combinations thereof, and the like. The processor device may include electrical circuitry configured to process computer-executable instructions. In another embodiment, the processor device includes an FPGA or other programmable device that performs logical operations without processing computer-executable instructions. A processor device may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in combination with a DSP core, or other similar configurations. Although described herein primarily with respect to digital technology, a processor device may also include primarily analog components. For example, some or all of the rendering techniques described herein may be implemented with analog circuitry or mixed analog and digital circuitry.The computing environment can include any type of computer system, including, but not limited to, computer systems based on microprocessors, mainframe computers, digital signal processors, portable computing devices, device controllers, computational engines within appliances, and the like.

[0096] Elements of the methods, processes, routines or algorithms described in connection with the embodiments disclosed herein may be embodied directly in hardware, in software modules executed by a processor device, or in a combination of the two. The software modules may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of non-volatile computer readable storage medium. An exemplary storage medium may be coupled to the processor device such that the processor device can read information from, and write information to, the storage medium. Alternatively, the storage medium may be integrated into the processor device. The processor device and the storage medium may be stored in an ASIC. Alternatively, the processor device and the storage medium may reside as separate components in a user terminal.

[0097] Conditional language used herein, such as "can," "may," "could," "may," "for example," and the like, is generally intended to convey that certain features, elements, or steps are included in certain embodiments and not included in other embodiments, unless otherwise specified or understood within the context in which it is used. Thus, such conditional language does not generally imply that features, elements, or steps are in any way required for one or more embodiments, nor does it imply that one or more embodiments necessarily include logic for determining whether those features, elements, or steps are included or performed in a particular embodiment, with or without other input or prompts. Terms such as "including," "comprising," "having," and the like, are synonymous and are used in an inclusive and open-ended manner and do not exclude additional elements, features, acts, operations, etc. Additionally, the term "or" is used in an inclusive rather than exclusive sense, so that, for example, when used to connect a list of elements, the term "or" may mean one, some, or all of the elements in the list.

[0098] Disjunctive phrases such as "at least one of X, Y, Z" are understood to be generally used to indicate that an item, term, etc. may be either X, Y, Z, or any combination thereof (e.g., X, Y, or Z) from the context, unless otherwise indicated. Thus, such disjunctive language is generally not intended or imply that at least one of X, at least one of Y, and at least one of Z each must be present in a particular embodiment.

[0099] Although the above detailed description has shown, described and pointed out novel features applicable to various embodiments, it will be understood that various omissions, substitutions and changes may be made in the form and details of the illustrated devices or algorithms without departing from the spirit of the disclosure. As will be appreciated, certain embodiments described herein may be implemented in a manner that does not provide all of the features and advantages described herein, since some features can be used or practiced separately from other features. The scope of the specific embodiments disclosed herein is indicated by the appended claims, rather than the foregoing description. All changes that come within the meaning and range of equivalence of the claims are intended to be embraced within their scope.

Claims

1. It is a system, A catheter including an outer sheath and an inner sheath, One or more sensors connected to the catheter, The catheter and the control unit connected to one or more sensors are included. The control unit is A motor unit configured to move the inner sheath relative to the outer sheath, Includes a processor capable of executing computer executable instructions, When the aforementioned computer executable instruction is executed by the processor, the processor will: Sensor data is acquired from at least one of the one or more sensors mentioned above. The aforementioned sensor data is applied as input to a trained artificial intelligence model. By applying the aforementioned sensor data as input to the trained artificial intelligence model, the trained artificial intelligence model is made to output amplitude and frequency. The operation of the motor unit is adjusted to cause the inner sheath to vibrate between the retracted position and the extended position at the frequency and by a distance corresponding to the amplitude. system.

2. The system according to claim 1, A system in which, when the computer executable instruction is executed by the processor, the processor further causes the processor to apply the sensor data, the display of the power consumption of the motor unit, and the type of the motor unit as input to the trained artificial intelligence model.

3. The system according to claim 1, The catheter is configured to be inserted into a venous system, and the system further comprises a valve at the distal end of the catheter.

4. The system according to claim 3, A system in which, when the computer executable instruction is executed by the processor, the processor further causes the processor to apply the sensor data, the display of the power consumption of the motor unit, and the type of valve contained in the catheter as input to the trained artificial intelligence model.

5. The system according to claim 3, A system in which the valve is closed when the inner sheath is in the extended position.

6. The system according to claim 3, A system in which the valve is open when the inner sheath is in the extended position.

7. The system according to claim 3, A system in which the trained artificial intelligence model is associated with at least one of the types of valves or the types of motor units.

8. The system according to claim 1, The system includes at least one of the following sensors: a flow sensor, a contact sensor, a temperature sensor, a pressure sensor, or a camera.

9. The system according to claim 1, A system in which at least some of the one or more sensors are connected to the distal end of a catheter configured to be inserted into a venous system.

10. The system according to claim 1, A system in which at least a portion of the one or more sensors are connected to the proximal end of the catheter and configured to aspirate one or more thrombus fragments during the operation of the catheter.

11. The system according to claim 1, The system further includes a catheter operation learning system composed of a second computer-executable instruction, A system that, when the second computer executable instruction is executed, causes the catheter operation learning system to train an artificial intelligence model using the training data, to form the trained artificial intelligence model, and to load the trained artificial intelligence model into the storage medium of the control unit.

12. A computer-implemented method for activating the inner sheath of a catheter, To acquire sensor data from at least one sensor connected to the catheter, The method involves applying the aforementioned sensor data as input to a trained artificial intelligence model, thereby causing the trained artificial intelligence model to output amplitude and frequency. The motor unit adjusts its operation to cause the inner sheath to vibrate between the retracted position and the extended position at the frequency and by a distance corresponding to the amplitude, Computer implementation method.

13. A computer implementation method according to claim 12, A computer implementation method in which applying the sensor data and the display of the power consumption of the motor unit as input to the trained artificial intelligence model further includes applying the sensor data, the display of the power consumption of the motor unit, and the type of the motor unit as input to the trained artificial intelligence model.

14. A computer implementation method according to claim 12, A computer-implemented method wherein the catheter is configured to be inserted into a venous system, and further comprises a valve at the distal end of the catheter.

15. A computer implementation method according to claim 14, A computer implementation method that further includes applying the sensor data and the display of the power consumption of the motor unit as input to the trained artificial intelligence model, the sensor data, the display of the power consumption of the motor unit, and the type of valve contained in the catheter as input to the trained artificial intelligence model.

16. A computer implementation method according to claim 14, A computer implementation method in which the valve is closed when the inner sheath is in the extended position, and the valve is open when the inner sheath is in the extended position.

17. A computer implementation method according to claim 14, A computer implementation method wherein the trained artificial intelligence model is associated with at least one of the types of valves or the types of motor units.

18. A non-volatile computer-readable storage medium containing computer-executable instructions for operating the inner sheath of a catheter, When the aforementioned computer executable instruction is executed by the computer system, the computer system will: Sensor data is acquired from at least one sensor connected to the catheter. The aforementioned sensor data is applied as input to a trained artificial intelligence model. By applying the display of the sensor data as input to the trained artificial intelligence model, the trained artificial intelligence model is made to output amplitude and frequency. The operation of the motor unit is adjusted so that the inner sheath vibrates between the retracted position and the extended position by a distance corresponding to the amplitude at the frequency. Computer-readable storage medium.

19. A computer-readable storage medium according to claim 18, A computer-readable storage medium, when the computer-executable instruction is executed, causes the computer system to apply the sensor data, the display of the power consumption by the motor unit, and the type of the motor unit as input to the trained artificial intelligence model.

20. A computer-readable storage medium according to claim 18, The catheter is configured to be inserted into the venous system and further includes a valve at its distal end. A computer-readable storage medium that, when the aforementioned computer-executable instruction is executed, causes the computer system to further apply the sensor data, the display of the power consumption by the motor unit, and the type of valve contained in the catheter as input to the trained artificial intelligence model.

Images