A recommended method and apparatus for a ventricular assist device

Abstract

This invention provides a method and apparatus for recommending ventricular assist devices, relating to the field of medical device technology. The method includes: obtaining first data characterizing the real-time cardiac state of a target subject and second data characterizing the historical cardiac state; predicting the target ventricular assist device used by the target subject based on the first and second data; and recommending the target ventricular assist device to the target subject. Applying the solution provided in this embodiment to recommend ventricular assist devices can improve recommendation efficiency.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and in particular to a recommended method and apparatus for a ventricular assist device. Background Technology

[0002] Ventricular assist devices are used to promote cardiac recovery by providing hemodynamic support. For example, interventional left ventricular assist devices (LVAP) are temporary ventricular support devices suitable for persistent cardiogenic shock occurring within 48 hours after acute myocardial infarction, open-heart surgery, or myocardial disease. Using LVAP reduces ventricular workload and increases necessary circulatory support to facilitate cardiac recovery and early assessment of remaining myocardial function.

[0003] Currently, experienced physicians determine the recommended ventricular assist devices (VAMs) for patients from the existing pool of available VAMs. However, the large number of existing VAMs makes the recommendation process inefficient. Summary of the Invention

[0004] The purpose of this invention is to provide a method and apparatus for recommending ventricular assist devices, thereby improving recommendation efficiency. The specific technical solution is as follows:

[0005] In a first aspect, embodiments of the present invention provide a method for recommending ventricular assist devices, the method comprising:

[0006] Obtain first data representing the real-time state of the target object's heart, and second data representing the historical state of the heart;

[0007] Based on the first data and the second data, predict the target ventricular assist device used by the target object;

[0008] The target ventricular assist device is recommended to the target individual.

[0009] In one embodiment of the present invention, the above-mentioned prediction of the target ventricular assist device used by the target object based on the first data and the second data includes:

[0010] Based on the first data, a first device is determined from the candidate ventricular assist devices, and the first fit of the first device to the target object is determined;

[0011] Based on the second data, a second device is determined from the candidate ventricular assist devices, and a second fit of the second device to the target object is determined;

[0012] Based on the first degree of adaptation corresponding to the first device and the second degree of adaptation corresponding to the second device, the target ventricular assist device used by the target object is determined from the first device and the second device.

[0013] In one embodiment of the present invention, determining the target ventricular assist device used by the target object from the first device and the second device based on the first adaptation degree corresponding to the first device and the second adaptation degree corresponding to the second device includes:

[0014] Identify the third device that is duplicated between the first and second devices;

[0015] Based on the first and second fit of the third device, the target ventricular assist device used by the target object is determined from the third device.

[0016] In one embodiment of the present invention, the above-mentioned prediction of the target ventricular assist device used by the target object based on the first data and the second data includes:

[0017] Based on the first data and the second data, the third data is generated;

[0018] Based on the third data, the target ventricular assist device used by the target object is predicted.

[0019] In one embodiment of the present invention, the above-mentioned prediction of the target ventricular assist device used by the target object based on the third data includes:

[0020] Based on the attribute information of the target object, determine the target object class to which the target object belongs;

[0021] Based on fourth data characterizing the cardiac state of each object in the target object class and third data of the target object, a reference object of the target object is determined, and the ventricular assist device used by the reference object is determined as the target ventricular assist device used by the target object.

[0022] In one embodiment of the present invention, determining the reference object of the target object based on the fourth data of each object included in the target object class and the third data of the target object includes:

[0023] For each object contained in the target object class, calculate the similarity between the fourth data of that object and the third data of the target object;

[0024] Based on the calculated similarity, a reference object for the target object is determined.

[0025] In one embodiment of the present invention, the above-mentioned prediction of the target ventricular assist device used by the target object based on the third data includes:

[0026] The third data is input into the prediction model to obtain the target identifier of the ventricular assist device output by the prediction model, and the ventricular assist device corresponding to the target identifier is determined as the target ventricular assist device used by the target object.

[0027] The prediction model is a model obtained by training an initial neural network model using data representing the heart state of the sample object as training samples and the ventricular assist device used by the sample object as the training benchmark. This model is used to predict the fit of the ventricular assist device to the heart state of the object.

[0028] Secondly, embodiments of the present invention provide a recommended device for a ventricular assist device, the device comprising:

[0029] The data acquisition module is used to acquire first data representing the real-time state of the heart of the target object, and second data representing the historical state of the heart.

[0030] The device prediction module is used to predict the target ventricular assist device used by the target object based on the first data and the second data.

[0031] The device recommendation module is used to recommend the target ventricular assist device to the target object.

[0032] In one embodiment of the present invention, the above-mentioned device prediction module includes:

[0033] The first data determination submodule is used to determine a first device from the candidate ventricular assist devices based on the first data, and the first fit of the first device to the target object;

[0034] The second data determination submodule is used to determine a second device from the candidate ventricular assist devices and a second fit of the second device to the target object based on the second data.

[0035] The device determination submodule is used to determine the target ventricular assist device used by the target object from the first device and the second device based on the first adaptation degree corresponding to the first device and the second adaptation degree corresponding to the second device.

[0036] In one embodiment of the present invention, the above-mentioned device determination submodule is specifically used to determine a third device that is duplicated between the first device and the second device; and to determine the target ventricular assist device used by the target object from the third device based on the first fit and the second fit of the third device.

[0037] In one embodiment of the present invention, the above-mentioned device prediction module includes:

[0038] The third data determination submodule is used to generate third data based on the first data and the second data;

[0039] The device prediction submodule is used to predict the target ventricular assist device used by the target object based on the third data.

[0040] In one embodiment of the present invention, the above-mentioned device prediction submodule includes:

[0041] The object class determination unit is used to determine the target object class to which the target object belongs based on the attribute information of the target object;

[0042] The device determination unit is configured to determine a reference object of the target object based on fourth data characterizing the cardiac state of each object included in the target object class and third data of the target object, and to determine the ventricular assist device used by the reference object as the target ventricular assist device used by the target object.

[0043] In one embodiment of the present invention, the device determining unit is specifically configured to calculate the similarity between the fourth data of each object included in the target object class and the third data of the target object; and determine the reference object of the target object based on the calculated similarity.

[0044] In one embodiment of the present invention, the aforementioned device prediction submodule is specifically used to input the third data into the prediction model, obtain the target identifier of the ventricular assist device output by the prediction model, and determine the ventricular assist device corresponding to the target identifier as the target ventricular assist device used by the target object; wherein, the prediction model is: a model used to predict the fit of the ventricular assist device to the heart state of the object by training an initial neural network model with data representing the heart state of the sample object as training samples and the ventricular assist device used by the sample object as the training benchmark.

[0045] Thirdly, embodiments of the present invention provide an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0046] Memory, used to store computer programs;

[0047] When a processor executes a program stored in memory, it implements the steps of the method described in the first aspect above.

[0048] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method described in the first aspect above.

[0049] As can be seen from the above, when recommending ventricular assist devices using the solution provided in the embodiments of the present invention, since the electronic device predicts the ventricular assist device used by the target object based on the first data and the second data corresponding to the target object, and then recommends the target ventricular assist device to the target object, the recommendation efficiency is improved compared with manually determining the ventricular assist device in the prior art.

[0050] Furthermore, since the target ventricular assist device (VAM) is predicted based on the first and second data, and then recommended to the target individual, and because the first data reflects the target individual's current cardiac condition and the second data reflects their historical cardiac condition, the prediction of the target VAM considers both the current and historical cardiac conditions. This combination of factors ensures that the predicted VAM is more suitable for the target individual's cardiac condition, thereby improving the accuracy of the VAM recommendation.

[0051] Of course, implementing any product or method of the present invention does not necessarily require achieving all of the advantages described above at the same time. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other embodiments can be obtained based on these drawings.

[0053] Figure 1 A flowchart illustrating the recommended method for a first type of ventricular assist device provided in an embodiment of the present invention;

[0054] Figure 2 A flowchart illustrating the recommended method for a second type of ventricular assist device provided in an embodiment of the present invention;

[0055] Figure 3 A flowchart illustrating the recommended method for a third type of ventricular assist device provided in an embodiment of the present invention;

[0056] Figure 4 A flowchart illustrating the recommended method for a fourth type of ventricular assist device provided in an embodiment of the present invention;

[0057] Figure 5This is a schematic diagram of the structure of a recommended device for a ventricular assist device provided in an embodiment of the present invention;

[0058] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art based on this application are within the scope of protection of the present invention.

[0060] First, the execution subject of the embodiments of the present invention will be described.

[0061] The execution subject of this invention is an electronic device, which can be a server, cloud server, etc.

[0062] The following provides a detailed description of the recommended method for the ventricular assist device provided in the embodiments of the present invention.

[0063] See Figure 1 , Figure 1 This is a flowchart illustrating a recommended method for a first type of ventricular assist device provided in an embodiment of the present invention. The method includes the following steps S101-S103.

[0064] Step S101: Obtain first data representing the real-time state of the heart of the target object, and second data representing the historical state of the heart.

[0065] The aforementioned target group refers to the object to which a ventricular assist device is to be recommended, and the object can be a person, animal, etc.

[0066] Since the first data is used to characterize the real-time state of the target object's heart, it can be understood as real-time data, reflecting the current state of the target object's heart; since the second data is used to characterize the historical state of the target object's heart, it can be understood as historical data, reflecting the historical state of the target object's heart.

[0067] The aforementioned first data may be real-time parameter data of preset cardiac parameters of the target subject within a preset duration including the recommended time. The aforementioned recommended time is the current moment when a ventricular assist device needs to be recommended to the target subject, and the aforementioned preset duration can be 1 hour, 6 hours, 12 hours, 24 hours, etc. The aforementioned preset cardiac parameters may include: heart rate, mean arterial pressure, left ventricular pressure, left ventricular end-diastolic pressure, etc.

[0068] The second data mentioned above can be the parameter data of the target object's preset cardiac parameters before the preset time interval mentioned above. The preset time interval can be 24h, 48h, etc.

[0069] Specifically, medical diagnostic equipment can perform real-time diagnoses of the target individual's heart. Electronic devices can acquire the data diagnosed by the medical diagnostic equipment. For example, the medical diagnostic equipment can send the diagnosed data to the electronic device; alternatively, medical personnel can manually input the data diagnosed by the medical diagnostic equipment into the electronic device. The acquired data serves as the primary data characterizing the real-time state of the target individual's heart.

[0070] After obtaining cardiac state data for each diagnosis, this data can be stored. Based on this, second data representing the historical cardiac state of the target object can be retrieved from the stored data. Specifically, the second data representing the historical cardiac state of the target object can be retrieved from the recorded data based on the target object's identification information, such as the target object's name.

[0071] Step S102: Based on the first data and the second data, predict the target ventricular assist device used by the target object.

[0072] Since the first data reflects the current condition of the target's heart and the second data reflects the target's historical condition of the heart, and since the target ventricular assist device is predicted based on the first and second data, this process takes into account both the target's current condition and the target's historical condition of the heart. The target ventricular assist device predicted by combining the above two aspects is more consistent with the target's heart condition, thereby improving the accuracy of the prediction of the target ventricular assist device.

[0073] For details on how to predict the target ventricular assist device, please refer to the following sections. Figure 2 , Figure 3 The corresponding implementation examples will not be described in detail here.

[0074] Step S103: Recommend the target ventricular assist device to the target patient.

[0075] Specifically, the user interface of the electronic device can display identification information of the target ventricular assist device, such as its name and model. The identification information can also be broadcast via the microphone of the electronic device.

[0076] As can be seen from the above, when recommending ventricular assist devices using the solution provided in this embodiment, since the electronic device predicts the ventricular assist device used by the target object based on the first and second data corresponding to the target object, and then recommends the target ventricular assist device to the target object, the recommendation efficiency is improved compared with manually determining the ventricular assist device in the prior art.

[0077] Furthermore, since the target ventricular assist device is predicted based on the first and second data, and then the target ventricular assist device is recommended to the target, and since the first data reflects the target's current cardiac condition and the second data reflects the target's historical cardiac condition, the prediction of the target ventricular assist device takes into account both the target's current cardiac condition and the target's historical cardiac condition. Combining these two aspects makes the predicted target ventricular assist device more suitable for the target's cardiac condition, thereby improving the accuracy of the ventricular assist device recommendation.

[0078] In response to the above Figure 1 In step S102 of the illustrated embodiment, this embodiment of the invention provides two types of prediction methods: the first type of prediction method is to predict the target ventricular assist device by combining the first data and the second data; the second type of prediction method is to predict the target ventricular assist device based on the first data and the second data respectively. Specific prediction methods for these two types can be found below. Figures 2-4 Corresponding implementation examples.

[0079] See Figure 2 , Figure 2 This is a flowchart illustrating a recommended method for a second type of ventricular assist device provided in an embodiment of the present invention. The method includes the following steps S201-S204.

[0080] Step S201: Obtain first data representing the real-time state of the heart of the target object, and second data representing the historical state of the heart.

[0081] The above step S201 is the same as the aforementioned Figure 1 Step S101 in the illustrated embodiment is the same and will not be described again here.

[0082] Step S202: Generate third data based on the first data and the second data.

[0083] Since the third data is generated based on the first and second data, it can fully reflect the target object's heart condition.

[0084] The third data can be generated in the following two ways.

[0085] In the first implementation, for each preset cardiac parameter, the first data and the second data of that preset cardiac parameter are fused, and the fused data is used as the third data. The data fusion method can be Kalman filtering, maximum likelihood estimation, least squares, etc.

[0086] In the second embodiment, since the second data can be data obtained at various historical moments, one preset cardiac parameter item can correspond to multiple second data. Based on this, for each preset cardiac parameter item, a first range formed by each second data of the preset cardiac parameter item is determined. If the first data of the preset cardiac parameter item is within the first range, the first range is used as the third data of the preset cardiac parameter item. If the first data of the preset cardiac parameter item is not within the first range, a second range is determined based on the first data and the first range, and the second range is used as the third data of the preset cardiac parameter item.

[0087] Taking heart rate as a preset cardiac parameter, the second data of heart rate are: 68 bpm, 70 bpm, 80 bpm, 90 bpm, 100 bpm, and 130 bpm. The first range formed by each second data is [68, 130]. ​​If the first data of heart rate is 120 bpm, since 120 bpm is within the above first range, the first range [68, 130] is the third data of heart rate. If the first data of heart rate is 140 bpm, since 140 bpm is not within the above first range, the right boundary of the first range is updated to the first data, resulting in [68, 140] as the second range, and the second range [68, 140] is the third data of heart rate.

[0088] Step S203: Based on the third data, predict the target ventricular assist device used by the target object.

[0089] Since the third data is determined based on the first and second data, and can comprehensively reflect the target subject's cardiac state, the target ventricular assist device predicted based on the third data can better match the target subject's cardiac state, thereby improving the accuracy of the target ventricular assist device prediction.

[0090] In one implementation, deep learning can be used to predict the target ventricular assist device. Specifically, third data can be input into the prediction model to obtain the target identifier of the ventricular assist device output by the prediction model, and the ventricular assist device corresponding to the target identifier can be identified as the target ventricular assist device used by the target object.

[0091] The aforementioned prediction model is used to calculate the fit of each candidate ventricular assist device to the target patient's cardiac condition based on third-party data, and outputs the target identifier of the ventricular assist device with the highest fit.

[0092] The aforementioned prediction model uses data representing the cardiac state of the sample object as training samples and the ventricular assist device used by the sample object as the training benchmark. It is obtained by training an initial neural network model to predict the fit of the ventricular assist device to the cardiac state of the sample object. The initial neural network can be a CNN (Convolutional Neural Network) or an RNN (Recurrent Neural Network).

[0093] Since the prediction model is trained using data representing the heart state of the sample object as training samples and the ventricular assist device used by the sample object as training benchmark, the prediction model can accurately learn the features of determining the suitability of the ventricular assist device for the heart state of the sample object based on the heart state data. Therefore, based on the above features, the prediction model can accurately determine the target ventricular assist device used by the target object.

[0094] The prediction method for target ventricular assist devices can also be based on Figure 3 The corresponding implementation steps S303-S304 are carried out and will not be described in detail here.

[0095] Step S204: Recommend the target ventricular assist device to the target patient.

[0096] The above step S204 is the same as the aforementioned Figure 1 Step S103 in the illustrated embodiment is the same and will not be described again here.

[0097] Since the third data can comprehensively reflect the target subject's cardiac condition, the target ventricular assist device predicted based on the above third data can better match the target subject's cardiac condition, thereby improving the accuracy of ventricular assist device recommendations.

[0098] In step S203 above, when predicting the target ventricular assist device used by the target object based on the third data, in addition to using deep learning for prediction, it can also be done according to the following... Figure 3 The corresponding implementation steps S303-S304 are carried out.

[0099] See Figure 3 , Figure 3 This is a flowchart illustrating a recommended method for a third type of ventricular assist device provided in an embodiment of the present invention. The method includes the following steps S301-S305.

[0100] Step S301: Obtain first data representing the real-time state of the heart of the target object, and second data representing the historical state of the heart.

[0101] Step S302: Generate third data based on the first data and the second data.

[0102] The above steps S301-S302 are the same as those described above. Figure 2 Steps S201-S202 in the illustrated embodiment are the same and will not be described again here.

[0103] Step S303: Based on the attribute information of the target object, determine the target object class to which the target object belongs.

[0104] The target object class mentioned above refers to the group to which the target object belongs. The target object class contains multiple objects that are similar to the target object.

[0105] The attribute information of the target object mentioned above may include: age, gender, region, etc.

[0106] In one implementation, filtering conditions can be determined based on the attribute information of the target object. Based on the filtering conditions, objects that meet the filtering conditions can be identified from existing objects and used as the target object class to which the target object belongs.

[0107] For example, the target object's attribute information is: age 60 years old, gender male, and region A. Based on the above attribute information, the determined filtering conditions are: age 50-70 years old, gender male, and region A. From the existing objects, males aged 50-70 years old and from region A are identified as the target object class to which the target object belongs.

[0108] Step S304: Based on the fourth data representing the cardiac state of each object contained in the target object class and the third data of the target object, determine the reference object of the target object, and determine the ventricular assist device used by the reference object as the target ventricular assist device used by the target object.

[0109] In one implementation, for each object contained in the target object class, the similarity between the fourth data of that object and the third data of the target object can be calculated; based on the calculated similarity, a reference object of the target object can be determined.

[0110] When calculating similarity, the Euclidean distance, cosine similarity, or Manhattan distance between the fourth and third data can be used as the similarity between the fourth and third data.

[0111] After calculating the similarity, the object with the highest similarity can be determined as the reference object of the target object; alternatively, a preset number of objects with the highest similarity can be determined as the reference objects of the target object.

[0112] Step S305: Recommend the target ventricular assist device to the target patient.

[0113] The above step S305 is the same as the aforementioned Figure 2 Step S204 in the illustrated embodiment is the same and will not be described again here.

[0114] Since the reference object is determined based on the fourth data and the third data, the fourth data is the data representing the cardiac state of each object contained in the target object class to which the target object belongs, and the third data is the data representing the cardiac state of the target object. In this way, based on the third data and the fourth data, the parameter object of the target object can be accurately determined, thereby making the determined target ventricular assist device more consistent with the cardiac state of the target object.

[0115] In the foregoing Figure 1 In step S102 of the illustrated embodiment, when predicting the target ventricular assist device used by the target object based on the first data and the second data, in addition to using... Figure 2 , Figure 3 In addition to predicting the target ventricular assist device by combining the first and second data in the corresponding embodiments, the following methods can also be used. Figure 4 In the corresponding embodiment, steps S402-S404 are implemented.

[0116] Step S401: Obtain first data representing the real-time state of the heart of the target object, and second data representing the historical state of the heart.

[0117] The above step S401 is the same as the aforementioned Figure 1 Step S101 in the illustrated embodiment is the same and will not be described again here.

[0118] Step S402: Based on the first data, determine the first device from the candidate ventricular assist devices, and the first fit of the first device to the target object.

[0119] The aforementioned first fit degree indicates the degree to which the first device is adapted to the target object. The higher the first fit degree, the higher the degree of adaptation of the first device to the target object; the lower the first fit degree, the lower the degree of adaptation of the first device to the target object.

[0120] In one embodiment, the candidate ventricular assist device is pre-configured with a parameter data range for applicable preset cardiac parameter items. Based on this, if there is data in the first data that falls within the parameter data range corresponding to the candidate ventricular assist device, the candidate ventricular assist device is determined as the first device, and the proportion of the number of cardiac parameter items in the first data that fall within the aforementioned parameter data range is calculated in the total number of cardiac parameter items in the first data, and this proportion is used as the first fit. If the first data does not fall within the parameter data range corresponding to the candidate ventricular assist device, then the candidate ventricular assist device is not the first device.

[0121] For example, the first data is shown in Table 1 below.

[0122] Table 1

[0123] Heart rate Mean arterial pressure Left ventricular pressure Left ventricular end-diastolic pressure P1 P2 P3 P4

[0124] The parameter data ranges for the preset cardiac parameters applicable to the alternative ventricular assist device S1 are shown in Table 2 below.

[0125] Table 2

[0126] Heart rate Mean arterial pressure Left ventricular pressure Left ventricular end-diastolic pressure A1~A2 A3~A4 A5~A6 A7~A8

[0127] In this data set, the heart rate parameter P1 contained in the first data is within the heart rate parameter data range corresponding to device S1; the mean arterial pressure parameter P2 contained in the first data is within the mean arterial pressure parameter data range corresponding to device S1. Since there are parameters within the range corresponding to ventricular assist device S1 in the first data set, ventricular assist device S1 is designated as the first device. Furthermore, the number of parameter items in the first data set that fall within the range corresponding to ventricular assist device S1 is 2, and the total number of preset cardiac parameter items in the first data set is 4. The calculated percentage is 2 / 4 = 50%, which is used as the first fit.

[0128] Step S403: Based on the second data, determine a second device from the candidate ventricular assist devices, and the second fit of the second device to the target object.

[0129] The aforementioned second fit degree indicates the degree to which the second device is adapted to the target object. A higher second fit degree indicates a higher degree of adaptation of the second device to the target object, and a lower second fit degree indicates a lower degree of adaptation of the second device to the target object.

[0130] In one embodiment, the candidate ventricular assist device is pre-configured with a parameter data range for applicable preset cardiac parameter items. Based on this, if there is data in the second data that falls within the parameter data range corresponding to the candidate ventricular assist device, the candidate ventricular assist device is determined as the second device, and the proportion of the number of cardiac parameter items in the second data that fall within the aforementioned parameter data range is calculated as the proportion of the total number of cardiac parameter items in the second data, and this proportion is used as the second fit. If the second data does not fall within the parameter data range corresponding to the candidate ventricular assist device, then the candidate ventricular assist device is not the second device.

[0131] Step S404: Based on the first adaptation degree corresponding to the first device and the second adaptation degree corresponding to the second device, determine the target ventricular assist device used by the target object from the first device and the second device.

[0132] In one implementation, a third device that is duplicated between the first device and the second device can be identified, and the target ventricular assist device used by the target object can be determined from the third device based on the first and second fit of the third device.

[0133] Specifically, the average of the first and second fit of the third device can be calculated, and the third device with the highest average value can be used as the target ventricular assist device for the target object.

[0134] For example: the first device includes ventricular assist devices Sp1, Sp2, Sp3, and Sp4; the second device includes ventricular assist devices Sp3, Sp4, Sp5, and Sp6. Sp3 and Sp4 are third devices that overlap between the first and second devices. Sp3 has a first fit of 75% and a second fit of 50%, and the average of these two fits is 62.5%. Sp4 has a first fit of 80% and a second fit of 60%, and the average of these two fits is 70%. Since 70% > 62.5%, ventricular assist device Sp4 is identified as the target ventricular assist device used by the target patient.

[0135] Since the third device is a duplicate of the first and second devices, it can match both the current cardiac state and the historical cardiac state of the target subject. Therefore, the target ventricular assist device determined from the third device can be fully applied to the target subject, thereby improving the accuracy of the target ventricular assist device determination.

[0136] Step S405: Recommend the target ventricular assist device to the target patient.

[0137] The above step S405 is the same as the aforementioned Figure 1 Step S103 in the illustrated embodiment is the same and will not be described again here.

[0138] Since the first device and the second device suitable for the target object are determined by the first data and the second data respectively, and then the ventricular assist device used by the target object is determined from the first device and the second device, the ventricular assist device suitable for the target object can be comprehensively determined, thereby enabling a more accurate determination of the target ventricular assist device used by the target object.

[0139] Corresponding to the above-described method for recommending ventricular assist devices, this embodiment of the invention also provides a device for recommending ventricular assist devices.

[0140] See Figure 5 , Figure 5 This is a schematic diagram of a recommended device for a ventricular assist device provided in an embodiment of the present invention. The device includes the following modules 501-503.

[0141] The data acquisition module 501 is used to acquire first data representing the real-time state of the heart of the target object, and second data representing the historical state of the heart.

[0142] Device prediction module 502 is used to predict the target ventricular assist device used by the target object based on the first data and the second data;

[0143] The device recommendation module 503 is used to recommend the target ventricular assist device to the target object.

[0144] In one embodiment of the present invention, the device prediction module 502 includes:

[0145] The first data determination submodule is used to determine a first device from the candidate ventricular assist devices based on the first data, and the first fit of the first device to the target object;

[0146] The second data determination submodule is used to determine a second device from the candidate ventricular assist devices and a second fit of the second device to the target object based on the second data.

[0147] The device determination submodule is used to determine the target ventricular assist device used by the target object from the first device and the second device based on the first adaptation degree corresponding to the first device and the second adaptation degree corresponding to the second device.

[0148] In one embodiment of the present invention, the above-mentioned device determination submodule is specifically used to determine a third device that is duplicated between the first device and the second device; and to determine the target ventricular assist device used by the target object from the third device based on the first fit and the second fit of the third device.

[0149] In one embodiment of the present invention, the device prediction module 502 includes:

[0150] The third data determination submodule is used to generate third data based on the first data and the second data;

[0151] The device prediction submodule is used to predict the target ventricular assist device used by the target object based on the third data.

[0152] In one embodiment of the present invention, the above-mentioned device prediction submodule includes:

[0153] The object class determination unit is used to determine the target object class to which the target object belongs based on the attribute information of the target object;

[0154] The device determination unit is configured to determine a reference object of the target object based on fourth data characterizing the cardiac state of each object included in the target object class and third data of the target object, and to determine the ventricular assist device used by the reference object as the target ventricular assist device used by the target object.

[0155] In one embodiment of the present invention, the device determining unit is specifically configured to calculate the similarity between the fourth data of each object included in the target object class and the third data of the target object; and determine the reference object of the target object based on the calculated similarity.

[0156] In one embodiment of the present invention, the aforementioned device prediction submodule is specifically used to input the third data into the prediction model, obtain the target identifier of the ventricular assist device output by the prediction model, and determine the ventricular assist device corresponding to the target identifier as the target ventricular assist device used by the target object; wherein, the prediction model is: a model used to predict the fit of the ventricular assist device to the heart state of the object by training an initial neural network model with data representing the heart state of the sample object as training samples and the ventricular assist device used by the sample object as the training benchmark.

[0157] Corresponding to the recommended method for ventricular assist devices described above, embodiments of the present invention also provide an electronic device.

[0158] See Figure 6 , Figure 6 A schematic diagram of an electronic device provided in an embodiment of the present invention includes a processor 601, a communication interface 602, a memory 603, and a communication bus 604, wherein the processor 601, the communication interface 602, and the memory 603 communicate with each other through the communication bus 604.

[0159] Memory 603 is used to store computer programs;

[0160] The processor 601, when executing the program stored in the memory 603, implements the recommended method for the ventricular assist device provided in the embodiments of the present invention.

[0161] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0162] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0163] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0164] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0165] In another embodiment of the present invention, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor, implements the recommended method for ventricular assist devices provided in the embodiments of the present invention.

[0166] In another embodiment of the present invention, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute the recommended method for the ventricular assist device provided in the embodiments of the present invention.

[0167] As can be seen from the above, when recommending ventricular assist devices using the solution provided in this embodiment, since the electronic device predicts the ventricular assist device used by the target object based on the first and second data corresponding to the target object, and then recommends the target ventricular assist device to the target object, the recommendation efficiency is improved compared with manually determining the ventricular assist device in the prior art.

[0168] Furthermore, since the target ventricular assist device (VAM) is predicted based on the first and second data, and then recommended to the target individual, and because the first data reflects the target individual's current cardiac condition and the second data reflects their historical cardiac condition, the prediction of the target VAM considers both the current and historical cardiac conditions. This combination of factors ensures that the predicted VAM is more suitable for the target individual's cardiac condition, thereby improving the accuracy of the VAM recommendation.

[0169] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0170] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0171] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for apparatus, electronic devices, and computer-readable storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0172] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of protection of the present invention.

Claims

1. A method of recommending a ventricular assist device, the method comprising: The method comprises: obtaining first data representing real-time state of a heart of a target object, and second data representing historical state of the heart; predicting a target ventricular assist device to be used by the target object based on the first data and the second data; recommending the target ventricular assist device to the target object; the predicting the target ventricular assist device to be used by the target object based on the first data and the second data comprises: generating third data based on the first data and the second data; predicting the target ventricular assist device to be used by the target object based on the third data; the generating the third data based on the first data and the second data comprises: for each preset heart parameter item, determining a first range formed by the second data of the preset heart parameter item, if the first data of the preset heart parameter item is located in the first range, taking the first range as the third data of the preset heart parameter item; if the first data of the preset heart parameter item is not located in the first range, determining a second range based on the first data and the first range, and taking the second range as the third data of the preset heart parameter item.

2. The method of claim 1, wherein, the predicting the target ventricular assist device to be used by the target object based on the first data and the second data comprises: determining a first device from the alternative ventricular assist devices based on the first data, and a first adaptability of the first device to the target object; determining a second device from the alternative ventricular assist devices based on the second data, and a second adaptability of the second device to the target object; determining the target ventricular assist device to be used by the target object from the first device and the second device based on the first adaptability corresponding to the first device and the second adaptability corresponding to the second device.

3. The method of claim 2, wherein, the determining the target ventricular assist device to be used by the target object from the first device and the second device based on the first adaptability corresponding to the first device and the second adaptability corresponding to the second device comprises: determining a third device which is repeated in the first device and the second device; determining the target ventricular assist device to be used by the target object from the third device based on the first adaptability and the second adaptability of the third device.

4. The method of claim 1, wherein, the predicting the target ventricular assist device to be used by the target object based on the third data comprises: determining a target object class to which the target object belongs based on attribute information of the target object; determining a reference object of the target object based on fourth data representing heart state of each object included in the target object class and the third data of the target object, and determining a ventricular assist device used by the reference object as the target ventricular assist device to be used by the target object.

5. The method of claim 4, wherein, the determining the reference object of the target object based on the fourth data of each object included in the target object class and the third data of the target object comprises: calculating similarity between the fourth data of each object included in the target object class and the third data of the target object; determining the reference object of the target object based on the calculated similarity.

6. The method of claim 1, wherein, The third data is input into a prediction model to obtain a target identification of a ventricular assist device output by the prediction model, and a ventricular assist device corresponding to the target identification is determined as the target ventricular assist device used by the target object. The prediction model is obtained by training an initial neural network model using data representing a heart state of a sample object as a training sample and a ventricular assist device used by the sample object as a training benchmark. The apparatus comprises:

7. A recommendation device for a ventricular assist device, characterized in that a data obtaining module configured to obtain first data representing a real-time heart state of a target object and second data representing a historical heart state of the target object; a device predicting module configured to predict a target ventricular assist device used by the target object based on the first data and the second data; a device recommending module configured to recommend the target ventricular assist device to the target object; The device predicting module comprises: a third data determining submodule configured to generate third data based on the first data and the second data; a device predicting submodule configured to predict a target ventricular assist device used by the target object based on the third data; The third data determining submodule is specifically configured to, for each preset heart parameter item, determine a first range formed by the second data of the preset heart parameter item, and if the first data of the preset heart parameter item is located in the first range, take the first range as the third data of the preset heart parameter item; if the first data of the preset heart parameter item is not located in the first range, determine a second range based on the first data and the first range, and take the second range as the third data of the preset heart parameter item. The apparatus comprises a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus.

8. An electronic device, comprising: The memory is configured to store a computer program. The processor is configured to execute the program stored in the memory to implement the method steps in any one of claims 1-6. The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method steps in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method steps in any one of claims 1-6.

Images