Hepatobiliary surgery patient nursing auxiliary system based on artificial intelligence

Abstract

The invention discloses a hepatobiliary surgery patient nursing auxiliary system based on artificial intelligence. The system comprises a data acquisition module, a data expansion model building module, a nursing auxiliary model building module and a patient nursing module. The invention relates to the technical field of patient nursing assistance, in particular to a hepatobiliary surgery patient nursing assistance system based on artificial intelligence. According to the scheme, a core framework comprising a generator and a discriminator is constructed, a chaos vector generation mechanism and a weight updating strategy are introduced, the fidelity and diversity of generated data are improved, and the accuracy and reliability of the system are improved. Real data distribution is simulated more effectively, so that the quality and scale of a data set are expanded; a model framework comprising a resetting unit, an updating unit, an integration unit, a candidate state unit and a state updating unit is innovatively designed, and an improved loss function is introduced, so that the modeling capability of the model on time sequence data is improved, the capturing capability on a long-term dependency relationship is enhanced, and the prediction precision and stability of the nursing assistance model are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of patient care assistance, and specifically refers to a patient care assistance system for hepatobiliary surgery based on artificial intelligence. Background Art

[0002] The patient care assistance system for hepatobiliary surgery based on artificial intelligence is an innovative intelligent medical solution that uses artificial intelligence algorithms and big data analysis technology to deeply mine and analyze multi-dimensional data of patients, realizing accurate prediction of patients' care needs and personalized intervention. The system can monitor the patient's status in real time, predict potential complications, and send out early warning information in a timely manner, providing scientific care decision-making support for medical staff.

[0003] Traditional methods for generating patient care data in hepatobiliary surgery have problems such as low-quality generated data, insufficient diversity, and difficulty in effectively simulating the real data distribution; traditional patient care assistance models for hepatobiliary surgery have problems such as insufficient ability to model time series data, difficulty in capturing long-term dependence relationships, and relatively low model prediction accuracy. Summary of the Invention

[0004] In view of the above situation, to overcome the defects of the prior art, the present invention provides a patient care assistance system for hepatobiliary surgery based on artificial intelligence. Aiming at the problems of traditional methods for generating patient care data in hepatobiliary surgery, such as low-quality generated data, insufficient diversity, and difficulty in effectively simulating the real data distribution, this solution improves the fidelity and diversity of the generated data and more effectively simulates the real data distribution by constructing a core architecture including a generator and a discriminator, introducing a chaotic vector generation mechanism, and optimizing the loss function and weight update strategy, thereby expanding the quality and scale of the data set; aiming at the problems of traditional patient care assistance models for hepatobiliary surgery, such as insufficient ability to model time series data, difficulty in capturing long-term dependence relationships, and relatively low model prediction accuracy, this solution improves the model's ability to model time series data and enhances the ability to capture long-term dependence relationships by innovatively designing a model framework including a reset unit, an update unit, an integration unit, a candidate state unit, and a state update unit, and introducing an improved loss function, thereby improving the prediction accuracy and stability of the care assistance model.

[0005] The technical solution adopted by the present invention is as follows: The patient care assistance system for hepatobiliary surgery based on artificial intelligence provided by the present invention includes a data acquisition module, a data expansion model construction module, a care assistance model construction module, and a patient care module;

[0006] The data acquisition module collects the physical data, disease data, vital sign data, and complication data of historical hepatobiliary surgery patients;

[0007] The module for constructing a data expansion model expands the dataset by generating a core architecture, generating a chaotic vector, evaluating the generator loss, evaluating the discriminator loss, and updating the weights;

[0008] The module for constructing a nursing assistance model constructs a nursing assistance model by designing a basic framework, a reset unit, an update unit, an integration unit, a candidate state unit, a state update unit, and a loss function;

[0009] The patient care module uses the nursing assistance model to predict the complication data of the patient. When the model predicts that the patient will have a complication, a prompt message is sent.

[0010] Furthermore, the data acquisition module acquires the physical data, disease data, vital sign data, laboratory examination data, and patient status data of historical hepatobiliary surgery patients; the physical data includes the patient's age, gender, height, and weight; the disease data refers to the type and stage of the hepatobiliary disease the patient has; the vital sign data includes the patient's body temperature, blood pressure, and heart rate; the laboratory examination data includes liver function and blood routine data; the complication data refers to whether the patient has postoperative bleeding, infection, bile fistula, and liver failure.

[0011] Furthermore, the module for constructing a data expansion model specifically includes the following:

[0012] Generate a core architecture. The model includes a generator and a discriminator. The generator includes an input layer, a hidden layer, and a generation layer. The input layer receives the chaotic vector. The hidden layer is activated by a rectified linear unit function, and a skip connection is introduced in the hidden layer. The generation layer is activated by a hyperbolic tangent function. The generator generates data similar to the real data by learning the mapping from the chaotic vector to the real data distribution; the discriminator is a classifier that outputs a probability value indicating the probability that the input data is real data;

[0013] Generate a chaotic vector, expressed as follows:

[0014] ;

[0015] where i represents the dimension index of the data vector, represents the value of the chaotic vector in the i-th dimension, represents the sigmoid function, represents the value of the random noise vector in the i-th dimension;

[0016] Evaluate the generator loss, expressed as follows:

[0017] ;

[0018] where, represents the loss value of the generator, Denotes the expectation of the chaotic vector . Denotes that z is sampled from the prior distribution . Denotes the generator Denotes the discriminator Denotes the discrimination probability of the discriminator for the fake samples generated by the generator . , and Denotes the loss weight of the generator Denotes the expectation of the real samples . Denotes Sampled from the real data distribution . Denotes the encoder Denotes that the encoder encodes the real samples into chaotic vectors Denotes the samples reconstructed by the generator according to the chaotic vectors obtained by the encoder . Denotes taking the square of the L2 norm Denotes the gradient of the generator with respect to the input chaotic vector;

[0019] Evaluating the discriminator loss is expressed as follows:

[0020] ;

[0021] where Denotes the loss value of the discriminator Denotes the discrimination probability of the discriminator for the real samples x Denotes the loss weight of the discriminator Denotes the samples reconstructed by the generator according to the chaotic vector z;

[0022] Weight update is expressed as follows:

[0023] ;

[0024] where it denotes the number of weight update times Denotes the model weights at the -th weight update Denotes the model weights at the -th weight update and Denotes the learning rate of the model weights Denotes the increment of the model weights Denotes the total number of data samples Denotes the index of the data samples Denotes at the The discrimination probability of the discriminator for the q-th data sample during the secondary weight update represents the discrimination probability of the discriminator for the q-th generated data sample ;

[0025] Expand the dataset, use the generator to generate simulation data, and add the simulation data to the original dataset to expand the original dataset.

[0026] Furthermore, the module for constructing the nursing assistance model specifically includes the following content:

[0027] Design the basic framework. The model includes a reset unit, an update unit, an integration unit, a candidate state unit, and a state update unit. Set the complication data as the label data of the model;

[0028] Design the reset unit to control the influence of the previous hidden state on the current state, introduce the weighted sum of historical hidden states, and dynamically adjust the importance of historical information;

[0029] Design the update unit to control the fusion of the current input and the previous hidden state, and generate a new intermediate state by adjusting the fusion ratio of the current input and historical information;

[0030] Design the integration unit to capture the non-linear features in the input data using the hyperbolic tangent function;

[0031] Design the candidate state unit to combine the output of the reset unit and the output of the integration unit to generate the final candidate state;

[0032] Design the state update unit. The state update unit controls the fusion ratio of the previous hidden state and the candidate state through the output of the update unit, and introduces a scale transformation matrix to adjust the amplitude of state update;

[0033] Design the loss function, which is expressed as follows:

[0034] ;

[0035] where represents the loss value of the nursing assistance model, c represents the data index for training the nursing assistance model, represents the total number of data for training the nursing assistance model, represents the true label value of the c-th data, represents the model prediction value of the c-th data, represents the logarithmic function, T represents the total number of time steps, represents the hidden state at the k-th time step, represents the hidden state at the (k - 1)-th time step, and represent the loss weights. represents the model prediction value of the c-th data at the -th time step, represents the model prediction value of the c-th data at the k-th time step, represents the model prediction value of the c-th data at the -th time step.

[0036] Furthermore, the patient care module collects the physical data, disease data, vital sign data, and laboratory examination data of the patient in real time, and uses the nursing assistance model to predict the complication data of the patient. When the model predicts that the patient will have a complication, a prompt message is sent to prompt the medical staff to prepare for the complication response.

[0037] The beneficial effects achieved by the present invention using the above solution are as follows:

[0038] (1) Aiming at the problems of low quality, insufficient diversity, and difficulty in effectively simulating the real data distribution in the traditional method for generating patient care data in hepatobiliary surgery, this solution improves the fidelity and diversity of the generated data, more effectively simulates the real data distribution, and thus expands the quality and scale of the data set by constructing a core architecture including a generator and a discriminator, introducing a chaotic vector generation mechanism, and optimizing the loss function and weight update strategy.

[0039] (2) Aiming at the problems of insufficient ability to model time series data, difficulty in capturing long-term dependence relationships, and low model prediction accuracy in the traditional nursing assistance model for hepatobiliary surgery patients, this solution improves the model's ability to model time series data and enhances the ability to capture long-term dependence relationships by innovatively designing a model framework including a reset unit, an update unit, an integration unit, a candidate state unit, and a state update unit, and introducing an improved loss function, thereby improving the prediction accuracy and stability of the nursing assistance model. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a schematic diagram of an artificial intelligence-based nursing assistance system for hepatobiliary surgery patients provided by the present invention;

[0041] Figure 2 is a schematic diagram of constructing a data expansion model module;

[0042] Figure 3 is a schematic diagram of constructing a nursing assistance model module.

[0043] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0044] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0045] In the description of the present invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc. indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention.

[0046] Embodiment 1, refer to Figure 1 , the artificial intelligence-based nursing assistance system for hepatobiliary surgery patients provided by the present invention includes a data acquisition module, a data expansion model construction module, a nursing assistance model construction module, and a patient care module;

[0047] The data acquisition module acquires the physical data, disease data, vital sign data, and complication data of historical hepatobiliary surgery patients, and sends the data to the data expansion model construction module;

[0048] The data expansion model construction module expands the data set by generating a core architecture, generating chaotic vectors, evaluating the generator loss, evaluating the discriminator loss, and updating weights, and sends the data to the nursing assistance model construction module;

[0049] The nursing assistance model construction module constructs a nursing assistance model by designing a basic framework, a reset unit, an update unit, an integration unit, a candidate state unit, a state update unit, and a loss function, and sends the data to the patient care module;

[0050] The patient care module uses the nursing assistance model to predict the complication data of the patient. When the model predicts that the patient will have a complication, a prompt message is sent.

[0051] Embodiment 2, refer to Figure 1, This embodiment is based on the above embodiment. The data acquisition module acquires the physical constitution data, disease data, vital sign data, laboratory examination data, and patient status data of historical hepatobiliary surgery patients. The physical constitution data includes the patient's age, gender, height, and weight. The disease data refers to the type and stage of the hepatobiliary disease the patient has. The vital sign data includes the patient's body temperature, blood pressure, and heart rate. The laboratory examination data includes liver function and blood routine data. The complication data refers to whether the patient has postoperative bleeding, infection, bile leakage, and liver failure.

[0052] Embodiment Three, refer to Figure 1 and Figure 2 , This embodiment is based on the above embodiment. The module for constructing a data expansion model specifically includes the following content:

[0053] Generate the core architecture. The model includes a generator and a discriminator. The generator includes an input layer, a hidden layer, and a generation layer. The input layer receives the chaotic vector. The hidden layer is activated by the rectified linear unit function, and skip connections are introduced in the hidden layer. The generation layer is activated by the hyperbolic tangent function. The generator generates data similar to the real data by learning the mapping from the chaotic vector to the real data distribution. The discriminator is a classifier that outputs a probability value indicating the probability that the input data is real data.

[0054] Generate the chaotic vector. A random noise vector and the golden ratio are introduced, which is expressed as follows:

[0055] ;

[0056] where i represents the dimension index of the data vector, represents the value of the chaotic vector in the i-th dimension, represents the sigmoid function, represents the value of the random noise vector in the i-th dimension;

[0057] Evaluate the generator loss. Reconstruction loss and gradient regularization are innovatively introduced to encourage the generator to be able to reconstruct real samples based on the chaotic vector obtained by the encoder, which is expressed as follows:

[0058] ;

[0059] where, represents the loss value of the generator, represents the expectation of the chaotic vector , represents that z is sampled from the prior distribution , represents the generator, represents the discriminator, represents the probability that the discriminator assigns to the fake sample The discrimination probability, , and represent the loss weights of the generator, represents the expectation of the real sample . represents sampling from the real data distribution , represents the encoder, means that the encoder encodes the real sample into a chaotic vector, represents that the generator reconstructs a sample according to the chaotic vector obtained by the encoder . represents taking the square of the L2 norm, represents the gradient of the generator with respect to the input chaotic vector;

[0060] Evaluate the discriminator loss, and evaluate the discriminator loss by combining the real sample loss, the generated sample loss, and the gradient regularization, which is expressed as follows:

[0061] ;

[0062] where represents the loss value of the discriminator, represents the discrimination probability of the discriminator for the real sample x, represents the loss weight of the discriminator, represents the sample reconstructed by the generator according to the chaotic vector z;

[0063] Weight update, introduce the discrimination probabilities of the discriminator for real samples and generated samples to design the weight increment, so as to update the weights of the model, which is expressed as follows:

[0064] ;

[0065] where it represents the number of weight update times, represents the model weights at the -th weight update, represents the model weights at the -th weight update, and represent the learning rate of the model weights, represents the weight increment of the model, represents the total number of data samples, represents the index of the data sample, represents the discrimination probability of the discriminator for the q-th data sample at the -th weight update, represents the discrimination probability of the discriminator for the q-th generated data sample .

[0066] Expand the dataset, use a generator to generate simulation data, and add the simulation data to the original dataset to expand the original dataset.

[0067] By performing the above operations, aiming at the problems of low quality, insufficient diversity of the generated data and difficulty in effectively simulating the real data distribution in the traditional method for generating hepatobiliary surgery patient care data, this solution improves the fidelity and diversity of the generated data and more effectively simulates the real data distribution by constructing a core architecture including a generator and a discriminator, introducing a chaotic vector generation mechanism, and optimizing the loss function and weight update strategy, thereby improving the quality and scale of the dataset.

[0068] Example 4, refer to Figure 1 and Figure 3 , based on the above example, the module for constructing the nursing assistance model specifically includes the following content:

[0069] Design the basic framework. The model includes a reset unit, an update unit, an integration unit, a candidate state unit, and a state update unit, and set the complication data as the label data of the model;

[0070] Design the reset unit to control the influence of the previous hidden state on the current state, introduce the weighted sum of the historical hidden states, and dynamically adjust the importance of the historical information, which is expressed as follows:

[0071] ;

[0072] Among them, t represents the index of the time step, represents the output value of the reset unit at the t-th time step, represents the weight of the reset unit, represents the input value of the reset unit, represents the weight from the previous hidden state to the reset unit, represents the hidden state at the (t - 1)-th time step, k represents the index of the time step, represents the state weight of the reset unit at the k-th time step, represents the hidden state at the k-th time step;

[0073] Design the update unit to control the fusion of the current input and the previous hidden state, and generate a new intermediate state by adjusting the fusion ratio of the current input and the historical information, which is expressed as follows:

[0074] ;

[0075] Among them, represents the output value of the update unit at the t-th time step, represents the weight of the update unit, represents the input value of the update unit, represents the weight from the previous hidden state to the update unit, represents the state weight of the update unit at the k-th time step, represents the state adjustment bias of the update unit;

[0076] Design an integration unit that uses the hyperbolic tangent function to capture the non-linear features in the input data, which is expressed as follows:

[0077] ;

[0078] where, represents the output value of the integration unit, represents the hyperbolic tangent function, represents the weight of the integration unit, represents the input of the integration unit, represents the weight from the previous hidden state to the integration unit, represents the state weight of the integration unit at the k-th time step;

[0079] Design a candidate state unit that combines the output of the reset unit and the output of the integration unit to generate the final candidate state, which is expressed as follows:

[0080] ;

[0081] where, represents the output value of the candidate state unit at the t-th time step, represents the element-wise multiplication symbol, represents the weight of the candidate state unit, represents the input value of the candidate state unit, represents the state weight of the integration unit at the t-th time step;

[0082] Design a state update unit. The state update unit controls the fusion ratio of the previous hidden state and the candidate state through the output of the update unit and introduces a scaling transformation matrix to adjust the amplitude of the state update, which is expressed as follows:

[0083] ;

[0084] where, represents the hidden state at the t-th time step, represents the scaling transformation matrix at the t-th time step;

[0085] Design a loss function that introduces a smoothness constraint on the hidden state and the predicted value, which is expressed as follows:

[0086] ;

[0087] Among them, represents the loss value of the nursing assistance model, c represents the data index for training the nursing assistance model, represents the total number of data for training the nursing assistance model, represents the true label value of the c-th data, represents the model prediction value of the c-th data, represents the logarithmic function, T represents the total number of time steps, and represent the loss weights, represents at the -th time step, the model prediction value of the c-th data, represents at the k-th time step, the model prediction value of the c-th data, represents at the -th time step, the model prediction value of the c-th data.

[0088] By performing the above operations, for the problems of the traditional hepatobiliary surgery patient care assistance model, such as insufficient ability to model time series data, difficulty in capturing long-term dependencies, and relatively low model prediction accuracy, this solution improves the model's ability to model time series data and enhances the ability to capture long-term dependencies by innovatively designing a model framework including a reset unit, an update unit, an integration unit, a candidate state unit, and a state update unit, and introducing an improved loss function, thereby improving the prediction accuracy and stability of the nursing assistance model.

[0089] Example 5, refer to Figure 1 , based on the above example, the patient care module collects the patient's physical data, disease data, vital sign data, and laboratory test data in real time, and uses the nursing assistance model to predict the patient's complication data. When the model predicts that the patient will have a complication, a prompt message is sent to prompt the medical staff to prepare for complication response.

[0090] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprises", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0091] Although embodiments of the present invention have been shown and described, those of ordinary skill in the art will appreciate that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the invention.

[0092] The above describes the present invention and its embodiments. Such a description is not restrictive. What is shown in the drawings is only one of the embodiments of the present invention, and the actual structure is not limited thereto. In general, if those of ordinary skill in the art are inspired by it and, without departing from the gist of the present invention, creatively design structural modes and embodiments similar to the technical solution, they shall fall within the protection scope of the present invention.

Claims

1. An artificial intelligence-based nursing assistance system for hepatobiliary surgery patients, characterized in that: It includes a data acquisition module, a data expansion model construction module, a nursing assistance model construction module, and a patient care module; The data acquisition module acquires the physical data, disease data, vital sign data, and complication data of historical hepatobiliary surgery patients; The data expansion model construction module expands the data set by generating a core architecture, generating chaotic vectors, evaluating the generator loss, evaluating the discriminator loss, and updating the weights; Generate the core architecture. The model includes a generator and a discriminator. The generator includes an input layer, a hidden layer, and a generation layer. The input layer receives chaotic vectors. The hidden layer is activated by a rectified linear unit function, and skip connections are introduced in the hidden layer. The generation layer is activated by a hyperbolic tangent function. The generator generates data similar to the real data by learning the mapping from chaotic vectors to the real data distribution. The discriminator is a classifier that outputs a probability value indicating the probability that the input data is real data; Generate chaotic vectors, which are expressed as follows: ； where \(i\) represents the dimension index of the data vector, represents the value of the chaotic vector in the \(i\)-th dimension, represents the sigmoid function, represents the value of the random noise vector in the \(i\)-th dimension; The nursing assistance model construction module constructs a nursing assistance model by designing a basic framework, a reset unit, an update unit, an integration unit, a candidate state unit, a state update unit, and a loss function; The patient care module uses the nursing assistance model to predict the complication data of the patient. When the model predicts that the patient will have complications, a prompt message is sent.

2. The artificial intelligence-based hepatobiliary surgery patient care assistance system according to claim 1, wherein: The data expansion model construction module specifically includes the following contents: Generate the core architecture; Generate chaotic vectors; Evaluate the generator loss, which is expressed as follows: ； Among them, represents the loss value of the generator, represents the expectation of the chaotic vector ; represents that z is sampled from the prior distribution ; represents the generator, represents the discriminator, represents the discrimination probability of the discriminator for the fake sample generated by the generator; , and represent the loss weights of the generator, represents the expectation of the real sample ; represents sampled from the real data distribution ; represents the encoder, represents that the encoder encodes the real sample into a chaotic vector, represents the sample reconstructed by the generator according to the chaotic vector obtained by the encoder, represents taking the square of the L2 norm, represents the gradient of the generator with respect to the input chaotic vector; Evaluate the discriminator loss, which is expressed as follows: ； Among them, represents the loss value of the discriminator, represents the discrimination probability of the discriminator for the real sample x, represents the loss weight of the discriminator, represents the sample reconstructed by the generator according to the chaotic vector z; Update the weights, which are expressed as follows: ； where \(it\) represents the number of weight updates, represents the model weights at the th weight update, represents the and represents the learning rate of the model weights, represents the increment of the model weights, represents the total number of data samples, represents the index of the data sample, represents the discrimination probability of the discriminator for the \(q\)th data sample at the th weight update, represents the discrimination probability of the discriminator for the \(q\)th generated data sample ; Expand the data set. Use the generator to generate simulation data and add the simulation data to the original data set to expand the original data set.

3. The hepatobiliary surgery patient care assistance system based on artificial intelligence according to claim 1, wherein: The nursing assistance model construction module specifically includes the following contents: Design the basic framework. The model includes a reset unit, an update unit, an integration unit, a candidate state unit, and a state update unit. The complication data is set as the label data of the model; Design the reset unit to control the influence of the previous hidden state on the current state, introduce the weighted sum of historical hidden states, and dynamically adjust the importance of historical information; Design the update unit to control the fusion of the current input and the previous hidden state, and generate a new intermediate state by adjusting the fusion ratio of the current input and historical information; Design the integration unit to use the hyperbolic tangent function to capture the non-linear features in the input data; Design the candidate state unit to combine the output of the reset unit and the output of the integration unit to generate the final candidate state; Design the state update unit. The state update unit controls the fusion ratio of the previous hidden state and the candidate state through the output of the update unit, and introduces a scale transformation matrix to adjust the amplitude of state update; Design the loss function, which is expressed as follows: ； Among them, represents the loss value of the nursing assistance model, c represents the data index for training the nursing assistance model, represents the total number of data for training the nursing assistance model, represents the true label value of the c-th data, represents the model prediction value of the c-th data, represents the logarithmic function, T represents the total number of time steps, represents the hidden state at the k-th time step, represents the hidden state at the (k - 1)-th time step, and represent the loss weight, represents at the -th time step, the model prediction value of the c-th data, represents at the k-th time step, the model prediction value of the c-th data, represents at the -th time step, the model prediction value of the c-th data.

4. The hepatobiliary surgery patient care assistance system based on artificial intelligence according to claim 1, wherein: The data acquisition module collects the physical data, disease data, vital sign data, laboratory examination data, and patient status data of historical hepatobiliary surgery patients; the physical data includes the patient's age, gender, height, and weight; the disease data refers to the type and stage of hepatobiliary diseases suffered by the patient; the vital sign data includes the patient's body temperature, blood pressure, and heart rate; the laboratory examination data includes liver function and blood routine data; the complication data refers to whether the patient has postoperative bleeding, infection, bile fistula, and liver failure.

5. The hepatobiliary surgery patient care assistance system based on artificial intelligence according to claim 1, characterized in that: The patient care module predicts the complication data of the patient by collecting the physical data, disease data, vital sign data, and laboratory examination data of the patient in real time, and uses a nursing assistance model. When the model predicts that the patient will have complications, a prompt message is sent to prompt medical staff to prepare for complication response.

Images