Intelligent hip replacement intraoperative nursing method and system

Abstract

The invention relates to the technical field of computer assistance, in particular to an intelligent hip replacement intraoperative nursing method and system, and the method comprises the following steps: integrating preoperative evaluation data of a patient, including blood pressure, heart rate and bone mineral density, carrying out data synchronization with a dynamic Bayesian network model, and carrying out the construction of a time sequence. According to the method, data synchronization and time sequence construction are carried out through the dynamic Bayesian network model, the real-time monitoring capability of hip replacement is improved, the real-time data flow in the operation is matched by calibrating network parameters and structures in real time, a medical team can directly carry out more accurate evaluation and prediction on the operation risk, and in addition, the method has the advantages that the real-time monitoring capability of hip replacement is improved. According to the system and the method, the operation process is continuously monitored and timely adjusted through continuous analysis of key risk indexes in the operation and real-time updating of risk states, and by optimizing the operation path and dynamically adjusting operation tools, the operation safety is improved, and meanwhile the rehabilitation process and life quality of a patient are optimized.

Description

Technical Field

[0001] The present invention relates to the field of computer - assisted technology, and particularly to an intelligent intraoperative nursing method and system for hip replacement surgery. Background Art

[0002] The field of computer - assisted technology encompasses a variety of advanced technological applications in medicine and surgery, with a particular focus on improving the accuracy and efficiency of surgeries through the assistance of computer systems. This field mainly utilizes software and hardware tools, such as three - dimensional imaging and simulation technology, robotics, real - time data processing, and visualization technology, to help doctors make more accurate decisions during complex surgical procedures. Computer - assisted orthopedic surgery (CAOS) enables doctors to meticulously plan the surgical process before the operation, predict potential challenges and outcomes through surgical simulations, thereby reducing intraoperative uncertainties and risks. Additionally, this technology can provide real - time feedback and adjustment guidance during the surgery, further enhancing the safety and success rate of the surgery.

[0003] Among them, an intelligent intraoperative nursing method for hip replacement surgery refers to the use of computer - assisted technology in hip replacement surgery to monitor and guide the entire surgical process, ensuring the accuracy and safety of the surgery. The main purpose of this technology is to help doctors place hip replacement implants more precisely through high - precision monitoring and instant feedback, reduce intraoperative and postoperative complications, and improve the rehabilitation effect and quality of life of patients. Through computer assistance, doctors can conduct detailed surgical planning before the operation and ensure that every link of the surgical steps conforms to the pre - designed plan through real - time imaging and data analysis during the operation.

[0004] Although existing computer - assisted surgical technologies have improved the accuracy and efficiency of surgeries, they have obvious limitations in real - time data processing and adaptive adjustment. Traditional methods mainly rely on detailed preoperative planning and simulation, but have limited ability to respond to rapid physiological changes and emergencies during the actual surgery. In complex operations such as hip replacement surgery, preoperative simulations may not comprehensively foresee all potential challenges. Once unexpected situations occur, the lack of sufficient real - time data support may lead to slow adjustment of surgical strategies, increasing the surgical risk. In addition, traditional technologies lack a real - time feedback mechanism, and doctors' decision - making processes rely too much on empirical judgment, which is not precise enough. This may lead to unsatisfactory surgical outcomes and longer rehabilitation times in high - risk surgeries. These deficiencies may result in an increase in postoperative complications and limited improvement in the rehabilitation effect and quality of life in actual operations. Summary of the Invention

[0005] The objective of the present invention is to address the drawbacks existing in the prior art and propose an intelligent intraoperative nursing method and system for hip replacement surgery.

[0006] To achieve the above object, the present invention adopts the following technical solutions: An intelligent intraoperative nursing method for hip replacement surgery, comprising the following steps:

[0007] S1: Integrate the preoperative assessment data of the patient, including blood pressure, heart rate, and bone density, synchronize the data with the dynamic Bayesian network model, construct a time series, update the data every minute to monitor the physiological changes of the patient, and integrate them into the initial risk state result;

[0008] S2: Utilize the initial risk state result to calibrate the dynamic network parameters in real time, adjust the network structure to match the real-time data during the surgery, update the probability model, and obtain the risk prediction after parameter adjustment;

[0009] S3: Analyze the key risk indicators during the surgery shown by the risk prediction after parameter adjustment, continue to evaluate the physiological response and surgical conditions of the patient through the real-time updated surgical data, refresh the risk assessment every minute, reflect the current surgical state, and generate the real-time risk update result;

[0010] S4: According to the real-time risk update result, adjust the surgical plan and the position of the surgical tools, optimize the surgical path, adjust the layout of the surgical tools, match the current physiological state of the patient, and generate the intraoperative response adjustment result.

[0011] As a further solution of the present invention, the specific steps for obtaining the initial risk state result are as follows:

[0012] S111: Collect the preoperative data of the patient, including blood pressure, heart rate, and bone density, and use the formula:

[0013]

[0014] Calculate the weighted average of each data to obtain the health index;

[0015] Among them, H represents the health index, w BP represents the blood pressure weight, w HR represents the heart rate weight, w BMD represents the bone density weight;

[0016] S112: Input the health index into the dynamic Bayesian network, and refer to the time dependence, using the formula:

[0017]

[0018] Generate the updated network state;

[0019] Among them, S represents the network state, λ represents the influence coefficient of the current health data, S prev represents the network state at the previous time point, and κ represents the parameter for adjusting the data sensitivity;

[0020] S113: Based on the updated network status, perform time series analysis using the formula:

[0021]

[0022] Obtain a time series model;

[0023] where T represents the time series model, α t represents the time decay coefficient, β t represents the deviation adjustment coefficient at each time point, S avg represents the average value of S;

[0024] S114: Use the time series model to evaluate the patient's risk status using the formula:

[0025]

[0026] Obtain the initial risk status result;

[0027] where R represents the initial risk status, max(T) represents the maximum value of the time series, and min(T) represents the minimum value of the time series.

[0028] As a further solution of the present invention, the obtaining steps of the risk prediction after parameter adjustment are specifically as follows:

[0029] S211: Use the initial risk status result to dynamically adjust the network parameters, and add a new parameter to represent the influence degree of the real-time data stream on the parameters, using the formula:

[0030]

[0031] Calculate and generate the updated network parameters;

[0032] where w i represents the weight of multiple parameters, P i represents the original network parameters, n represents the number of parameters, θ represents the influence of real-time data, and δ i represents the difference between the real-time data and the preset parameters, and P new represents the updated network parameters;

[0033] S212: Based on the updated network parameters, adjust the network structure to match the real-time data stream, using the formula:

[0034]

[0035] Update the network structure to obtain a new network structure;

[0036] where S new represents the new network structure, vj Denote the structural adjustment coefficient as S j Denote the original structural parameters, m represents the total number of structural components, γ represents the sensitivity of structural adjustment, and ∈ j Denote the deviation between the structural parameters and the actual data;

[0037] S213: Based on the new network structure, update the probability model using the formula:

[0038] M updated = η·(α·P new + β·S new )

[0039] Obtain the updated probability model;

[0040] where M updated represents the updated probability model, α and β are the influence coefficients of the network parameters and structural parameters respectively, and η represents the adjustment factor of the model complexity;

[0041] S214: According to the updated probability model, conduct risk prediction using the formula:

[0042]

[0043] Obtain the risk prediction after parameter adjustment;

[0044] where R final represents the risk prediction after parameter adjustment, and λ represents the risk perception coefficient.

[0045] As a further solution of the present invention, the specific steps for obtaining the real-time risk update result are as follows:

[0046] S311: Conduct a difference analysis between the risk prediction after parameter adjustment and the real-time surgical data, calculate the deviation degree of each risk index using the formula:

[0047]

[0048] Generate the risk deviation degree result ΔR;

[0049] where D realtime,i represents the i-th real-time surgical data, w i represents the clinical importance weight of the risk factor, k represents the total number of risk factors, and ΔR represents the risk deviation degree result;

[0050] S312: Evaluate the patient's physiological response using the risk deviation degree result, using the formula:

[0051]

[0052] Refer to the dynamic factor τ of the reference time, update the risk assessment in real time, and obtain the risk assessment results per minute;

[0053] Among them, R eval represents the risk assessment result per minute, and ΔR i represents the deviation degree of the i-th risk factor;

[0054] S313: Perform time weighting on the risk assessment results per minute, use the exponential decay model to reflect the real-time changes in the surgical state, and adopt the formula:

[0055]

[0056] Integrate into the real-time risk update result;

[0057] Among them, R update represents the real-time risk update result, R eval,t represents the risk assessment result at the t-th minute, and θ t represents the attenuation coefficient at the t-th minute, and T represents the total assessment duration.

[0058] As a further solution of the present invention, the specific steps for obtaining the intraoperative response adjustment result are as follows:

[0059] S411: Starting from the real-time risk update result, deeply evaluate the suitability of the surgical plan, and adopt the dynamic response formula:

[0060]

[0061] Introduce the adjustment factor γ to enhance the adaptability of the model and generate the surgical plan suitability index;

[0062] Among them, μ represents the preset risk threshold, σ represents the standard deviation of risk fluctuations, and A suitability represents the surgical plan suitability index;

[0063] S412: According to the surgical plan suitability index, adjust the position of the surgical tool to optimize the surgical path, and adopt the formula:

[0064] P adjustment =α·(tanh(β·(A suitability -0.5)+δ))

[0065] Calculate and generate the surgical tool position adjustment coefficient;

[0066] Among them, P adjustment represents the surgical tool position adjustment coefficient, α and β represent the adjustment sensitivity parameters, and δ represents the fine-tuning parameter for position adjustment;

[0067] S413: Adjust the surgical tool layout in combination with the surgical tool position adjustment coefficient to match the patient's current physiological state, using the formula:

[0068]

[0069] Generate the intraoperative response adjustment result;

[0070] where L layout represents the intraoperative response adjustment result, κ represents the layout baseline adjustment constant, and ξ, η represent the stability adjustment factors.

[0071] An intelligent intraoperative nursing system for hip replacement surgery, the intelligent intraoperative nursing system for hip replacement surgery is used to execute the above-mentioned intelligent intraoperative nursing method for hip replacement surgery, and the system includes:

[0072] The preoperative assessment integration module obtains the preoperative data of the patient including blood pressure, heart rate, and bone density, integrates multiple data into the dynamic Bayesian network model, synchronizes the data and constructs a time series, updates the data every minute for physiological change monitoring, and generates the initial assessment data result;

[0073] The initial risk status module performs time series analysis on blood pressure, heart rate, and bone density based on the initial assessment data result, synchronizes the dynamic Bayesian network data, integrates the data to form a time series, monitors and updates the physiological data every minute, and generates the initial risk status result;

[0074] The parameter calibration module uses the initial risk status result to analyze the changes in blood pressure and heart rate data during the operation in real time, calibrates and adjusts the dynamic network parameters, matches the real-time operation data, combines the current data to update the probability model, and establishes the calibrated risk prediction;

[0075] The real-time risk assessment module analyzes the calibrated risk prediction, evaluates the patient's physiological response and surgical conditions in real time according to the key risk indicators during the operation, updates the data every minute for risk assessment, and integrates multiple data to generate the real-time risk assessment result;

[0076] The intraoperative response adjustment module adjusts the surgical plan and tool position based on the real-time risk assessment result, optimizes the surgical path and tool layout according to the real-time physiological state, matches the patient's current physiological conditions, and generates the intraoperative response adjustment result.

[0077] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0078] In the present invention, by integrating the preoperative assessment data of patients and constructing data synchronization and time series through a dynamic Bayesian network model, the real-time monitoring ability of hip replacement surgery is improved. By calibrating the network parameters and structure in real time to match the real-time data stream during the operation, the medical team can directly evaluate and predict the surgical risks more accurately. In addition, through the continuous analysis of key risk indicators during the operation and the real-time update of the risk status, continuous monitoring and timely adjustment of the operation process are achieved, effectively reducing the risks of intraoperative and postoperative complications. By optimizing the surgical path and dynamically adjusting the surgical tools, not only the surgical safety is improved, but also the rehabilitation process and quality of life of the patient are optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 It is a schematic diagram of the work flow of the present invention;

[0080] Figure 2 It is a flow chart of the steps for obtaining the initial risk status result of the present invention;

[0081] Figure 3 It is a flow chart of the steps for obtaining the risk prediction after parameter adjustment of the present invention;

[0082] Figure 4 It is a flow chart of the steps for obtaining the real-time risk update result of the present invention;

[0083] Figure 5 It is a flow chart of the steps for obtaining the intraoperative response adjustment result of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0084] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0085] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is 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 therefore should not be construed as limiting the present invention. In addition, in the description of the present invention, the meaning of "a plurality" is two or more unless otherwise specifically defined.

[0086] Embodiment 1

[0087] Please refer to Figure 1, the present invention provides a technical solution: an intelligent intraoperative nursing method for hip replacement surgery, comprising the following steps:

[0088] S1: Integrate the preoperative assessment data of the patient, including blood pressure, heart rate, and bone density, synchronize the data with the dynamic Bayesian network model, construct a time series, update the data every minute to monitor the physiological changes of the patient, and integrate them into the initial risk status result;

[0089] S2: Utilize the initial risk status result to calibrate the dynamic network parameters in real time, adjust the network structure to match the real-time data during the surgery, update the probability model, and obtain the risk prediction after parameter adjustment;

[0090] S3: Analyze the key risk indicators during the surgery shown by the risk prediction after parameter adjustment, continue to evaluate the physiological response and surgical conditions of the patient through the real-time updated surgical data, refresh the risk assessment every minute, reflect the current surgical status, and generate the real-time risk update result;

[0091] S4: According to the real-time risk update result, adjust the surgical plan and the position of the surgical tools, optimize the surgical path, adjust the layout of the surgical tools, match the current physiological state of the patient, and generate the intraoperative response adjustment result.

[0092] The initial risk status result includes blood pressure index, heart rate index, and bone density score. The risk prediction after parameter adjustment includes risk level prediction, patient stability prediction, and intraoperative complexity expectation. The real-time risk update result is specifically physiological parameter update, risk level adjustment, and real-time assessment of surgical conditions. The intraoperative response adjustment result includes surgical tool positioning, surgical path planning, and physiological state adaptability.

[0093] Please refer to Figure 2 , the specific steps for obtaining the initial risk status result are as follows:

[0094] S111: Collect the preoperative data of the patient, including blood pressure, heart rate, and bone density, and use the formula:

[0095]

[0096] Calculate the weighted average of each data to obtain the health index;

[0097] where H represents the health index, w BP represents the blood pressure weight, w HR represents the heart rate weight, w BMD represents the bone density weight;

[0098] S112: Input the health index into the dynamic Bayesian network, and refer to the time dependence, using the formula:

[0099]

[0100] Generate the updated network status;

[0101] where S represents the network status, λ represents the influence coefficient of the current health data, S prev represents the network status at the previous time point, and κ represents the parameter for adjusting data sensitivity;

[0102] S113: Based on the updated network status, perform time series analysis using the formula:

[0103]

[0104] Obtain the time series model;

[0105] where T represents the time series model, α t represents the time decay coefficient, β t represents the deviation adjustment coefficient at each time point, and S avg represents the average value of S;

[0106] S114: Use the time series model to evaluate the patient's risk status using the formula:

[0107]

[0108] Obtain the initial risk status result;

[0109] where R represents the initial risk status, max(T) represents the maximum value of the time series, and min(T) represents the minimum value of the time series.

[0110] Detailed Explanation and Numerical Example of the Formula in Step 1

[0111] Formula

[0112]

[0113] where

[0114] BP: Blood pressure value, within 100 - 120 mmHg (normal range).

[0115] HR: Heart rate, within 60 - 100 beats per minute (normal resting heart rate for adults).

[0116] BMD: Bone mineral density, generally 0.8 - 1.2 g / cm 2 (normal bone mineral density for adults).

[0117] w BP 、w HR 、w BMD : Weights of blood pressure, heart rate, and bone mineral density respectively, assumed to be 1.

[0118] Calculation Example

[0119] Assumptions:

[0120] BP = 115 mmHg

[0121] HR = 75 beats per minute

[0122] BMD = 1.0 g / cm 2

[0123] w BP = w HR = w BMD = 1

[0124] Calculation Process:

[0125] Calculate the weighted sum of squares:

[0126]

[0127] Sum = 13225 + 5625 + 1 = 18851

[0128] Calculate the average weight:

[0129] w BP + w HR + w BMD = 1 + 1 + 1 = 3

[0130] Calculate the health index H:

[0131]

[0132] Result Analysis

[0133] The obtained health index H = 45.8 represents the score referring to blood pressure, heart rate, and bone mineral density, and this score is used to evaluate the patient's health status.

[0134] Detailed Explanation of the Formula and Calculation Example in Step 2

[0135] Formula

[0136]

[0137] Where

[0138] λ: Influence coefficient of the current health data, assumed to be 0.6 (indicating that new data accounts for a larger proportion).

[0139] κ: Parameter for adjusting data sensitivity, assumed to be 0.1 (a small change can significantly affect the result).

[0140] S prev : Network state at the previous time point, assumed to be 40 (the state value calculated last time).

[0141] Calculation example

[0142] Assumptions:

[0143] H = 45.8 (obtained from step 1)

[0144] λ = 0.6

[0145] κ = 0.1

[0146] S prev = 40

[0147] Calculation process:

[0148] Calculate the weighted average of the new and old data:

[0149] λ·H+(1 - λ)·S prev = 0.6·45.8 + 0.4·40 = 27.48 + 16 = 43.48

[0150] Calculate the adjustment factor:

[0151] 1 + κ·|H - S prev | = 1 + 0.1·|45.8 - 40| = 1 + 0.58 = 1.58

[0152] Calculate the new network state S:

[0153]

[0154] Result analysis

[0155] The updated network state S = 27.52 represents the network state score after considering the current data and the influence of the previous state, and this score reflects the patient's immediate health status.

[0156] Detailed explanation of the formula and calculation example in step 3

[0157] Formula

[0158]

[0159] Where

[0160] α t : Time decay coefficient, which decreases as time goes by, assumed to be linearly decaying, from 1.0 to 0.1.

[0161] β t : Deviation adjustment coefficient at each time point, assumed to be 0.05, indicating a low sensitivity to deviations.

[0162] S(t): Network state at time point t.

[0163] S avg: The average value of the network state, assuming the average of all S(t).

[0164] Calculation example

[0165] Assumption:

[0166] n = 3, there are 3 time points, and the states are S(1) = 27.52, S(2) = 26, S(3) = 28 (obtained from step 2 or similar calculations)

[0167] α t = [1.0, 0.7, 0.4]

[0168]

[0169] Calculation process:

[0170] Calculate for each time point:

[0171] Time 1:

[0172] Time2:

[0173] Time3:

[0174] Calculate the total time series model T:

[0175] T = 27.06 + 17.19 + 10.75 = 55.00

[0176] Result analysis

[0177] The time series model T = 55.00 represents the cumulative time series value after considering the reference time decay and state deviation. This value is used to analyze the patient's health trend.

[0178] Detailed explanation of the formula in step 4 and calculation example

[0179] Formula

[0180]

[0181] Where

[0182] max(T) and min(T): The maximum and minimum values of T.

[0183] Calculation example

[0184] Assumption:

[0185] From the time series data in step 3: T(1) = 27.06, T(2) = 17.19, T(3) = 10.75

[0186] Calculation process:

[0187] Calculate max(T) and min(T):

[0188] max(T) = 27.06

[0189] min(T) = 10.75

[0190] Calculate the initial risk state R:

[0191]

[0192] Result analysis

[0193] The initial risk state R = 24.83 represents the square root of the difference between the maximum and minimum state values according to the time series, and is used to evaluate the volatility of the patient's health risk.

[0194] Please refer to Figure 3 , and the specific steps for obtaining the risk prediction after parameter adjustment are as follows:

[0195] S211: Utilize the initial risk state result to dynamically adjust the network parameters, add new parameters to represent the influence degree of the real-time data stream on the parameters, and adopt the formula:

[0196]

[0197] Calculate and generate the updated network parameters;

[0198] Among them, w i represents the weight of multiple parameters, P i represents the original network parameters, n represents the number of parameters, θ represents the influence of real-time data, and δ i represents the difference between the real-time data and the preset parameters, and P new represents the updated network parameters;

[0199] S212: Based on the updated network parameters, adjust the network structure to match the real-time data stream, and adopt the formula:

[0200]

[0201] Update the network structure to obtain a new network structure;

[0202] Among them, S new represents the new network structure, v j represents the structure adjustment coefficient, S j represents the original structure parameters, m represents the total number of structure components, γ represents the sensitivity of structure adjustment, and ∈ j represents the deviation between the structure parameters and the actual data;

[0203] S213: Update the probability model based on the new network structure using the formula:

[0204] M updated = η·(α·P new + β·S new )

[0205] to obtain the updated probability model;

[0206] where M updated represents the updated probability model, α and β are the influence coefficients of network parameters and structure parameters respectively, and η represents the adjustment factor of model complexity;

[0207] S214: Perform risk prediction according to the updated probability model using the formula:

[0208]

[0209] to obtain the risk prediction after parameter adjustment;

[0210] where R final represents the risk prediction after parameter adjustment, and λ represents the risk perception coefficient.

[0211] Formula derivation of Step 1

[0212] Formula:

[0213]

[0214] Parameter details and derivation:

[0215] R: Initial risk state result, assumed to be 0.5.

[0216] w i : Parameter weight, assuming all weights are equal, each being 1.

[0217] P i : Original network parameters, assuming there are 3 parameters in the network, which are 0.6, 0.4, and 0.8 respectively.

[0218] θ: Influence of real-time data, assumed to be 0.2.

[0219] δ i : Difference between real-time data and preset parameters, assuming the difference values are 0.1, -0.2, and 0.05 respectively.

[0220] n: Number of parameters, which is 3 here.

[0221] Derivation process:

[0222]

[0223] Pnew = 0.763

[0224] This P new value represents the average of the updated network parameters and is used to reflect the average risk level of the entire network state.

[0225] Formula derivation of Step 2

[0226] Formula:

[0227]

[0228] Detailed parameter explanation and derivation:

[0229] v j : Structure adjustment coefficient, assumed to be 1 for all.

[0230] S j : Original structure parameter, assumed to have two structure parameters 0.9 and 0.7.

[0231] m: Total number of structure components, which is 2 here.

[0232] γ: Sensitivity of structure adjustment, assumed to be 0.3.

[0233] ∈ j : Deviation between structure parameter and actual data, assumed values are 0.2 and -0.1 respectively.

[0234] Derivation process:

[0235]

[0236] S new = 0.815

[0237] This S new value represents the average of the network structure after being adjusted by real-time data.

[0238] Formula derivation of Step 3

[0239] Formula:

[0240] M updated = η·(α·P new + β·S new )

[0241] Detailed parameter explanation and derivation:

[0242] η: Adjustment factor for model complexity, assumed to be 1.

[0243] α, β: Influence coefficients, assumed to be 1 for both.

[0244] P new 、S newObtained from the previous steps, which are 0.763 and 0.815 respectively. Derivation process:

[0245] M updated = 1·(1·0.763 + 1·0.815)

[0246] M updated = 1.578

[0247] Formula derivation of Step 4

[0248] Formula:

[0249]

[0250] Detailed parameter explanation and derivation:

[0251] λ: Risk perception coefficient, assumed to be 0.5.

[0252] M updated Obtained from the previous steps, which is 1.578.

[0253] Derivation process:

[0254] Derivation process:

[0255]

[0256] R final = 1 - e -0.5·1.256

[0257] R final = 1 - e -0.628

[0258] R final = 1 - 0.533

[0259] R final = 0.467

[0260] This R final value represents the risk prediction value. The closer it is to 1, the higher the risk; conversely, the lower the risk.

[0261] Please refer to Figure 4 for the specific steps to obtain the real-time risk update result:

[0262] S311: Conduct a difference analysis on the risk prediction after parameter adjustment and the real-time surgical data, calculate the deviation degree of each risk index, using the formula:

[0263]

[0264] Generate the risk deviation degree result ΔR;

[0265] where D realtime,iRepresents the i-th real-time surgical data, w i Represents the clinical importance weight of the risk factor, k represents the total number of risk factors, and ΔR represents the risk deviation result;

[0266] S312: Evaluate the patient's physiological response using the risk deviation result, using the formula:

[0267]

[0268] With reference to the time dynamic factor τ, update the risk assessment in real time to obtain the risk assessment result per minute;

[0269] Among them, R eval Represents the risk assessment result per minute, and ΔR i Represents the deviation degree of the i-th risk factor;

[0270] S313: Perform time weighting on the risk assessment result per minute, and use the exponential decay model to reflect the real-time change of the surgical state, using the formula:

[0271]

[0272] Integrate into the real-time risk update result;

[0273] Among them, R update Represents the real-time risk update result, R eval,t Represents the risk assessment result at the t-th minute, and θ t Represents the decay coefficient at the t-th minute, and T represents the total evaluation duration.

[0274] Step 1: Risk deviation calculation

[0275] Formula:

[0276]

[0277] Among them:

[0278] ΔR: Risk deviation result

[0279] w i : Importance weight of the i-th risk factor

[0280] R final : Adjusted total risk prediction

[0281] D realtime,i : The i-th real-time surgical data

[0282] k: Total number of risk factors

[0283] Calculation process and example:

[0284] Suppose there is the following data:

[0285] R final = 0.8 (Adjusted Total Risk Prediction)

[0286] Real-time surgical data (D realtime ): [0.7, 0.6, 0.9], corresponding risk factor weights (w): [0.5, 0.3, 0.2]

[0287] Total number of risk factors (k = 3)

[0288] Calculation steps:

[0289] Calculate the squared deviation of each risk factor: (R final - D realtime,i ) 2

[0290] (0.8 - 0.7) 2 = 0.01

[0291] (0.8 - 0.6) 2 = 0.04

[0292] (0.8 - 0.9) 2 = 0.01

[0293] Calculate the weighted deviation: w i ·(R final - D realtime,i ) 2

[0294] 0.5 × 0.01 = 0.005

[0295] 0.3 × 0.04 = 0.012

[0296] 0.2 × 0.01 = 0.002

[0297] Sum and take the square root:

[0298] Result analysis:

[0299] ΔR = 0.138 represents the deviation between the current risk prediction and the real-time data, referring to the importance of the differential risk factors.

[0300] Step 2: Risk assessment update per minute

[0301] Formula:

[0302]

[0303] Where:

[0304] R eval : Risk assessment result per minute

[0305] τ: Time dynamic adjustment factor

[0306] ΔR i : Deviation degree of the i-th risk factor

[0307] Calculation process and example:

[0308] Assume τ = 1 and continue to use the above deviation degree result:

[0309] Calculation steps:

[0310] Apply the logical function to transform the deviation degree impact:

[0311]

[0312] Calculate the average risk assessment: Result analysis:

[0313] R eval = 0.666 indicates the average risk assessment result after referring to the deviation degree at the current moment.

[0314] Step 3: Real-time risk update result

[0315] Formula:

[0316]

[0317] Among them:

[0318] R update : Real-time risk update result

[0319] θ t : Time decay coefficient

[0320] T: Total evaluation duration

[0321] Calculation process and example:

[0322] Suppose there is 5 minutes of data, the θ coefficient is [0.5, 0.4, 0.3, 0.2, 0.1], and R eval value is [0.6, 0.65, 0.7, 0.75, 0.8]

[0323] Calculation steps:

[0324] Apply the time decay model:

[0325] 0.5 × 0.6 = 0.3

[0326] 0.4 × 0.65 = 0.26

[0327] 0.3 × 0.7 = 0.21

[0328] 0.2 × 0.75 = 0.15

[0329] 0.1 × 0.8 = 0.08

[0330] Sum: R update = 0.3 + 0.26 + 0.21 + 0.15 + 0.08 = 1.0

[0331] Result analysis:

[0332] R update = 1.0 represents the risk assessment per minute within 5 minutes, adjusted for the time decay effect, providing a risk update value.

[0333] Please refer to Figure 5 , the steps to obtain the intraoperative response adjustment result are specifically as follows:

[0334] S411: Starting from the real-time risk update result, deeply evaluate the suitability of the surgical plan, using the dynamic response formula:

[0335]

[0336] Introduce the adjustment factor γ to enhance the adaptability of the model and generate the surgical plan suitability index;

[0337] Among them, μ represents the preset risk threshold, σ represents the standard deviation of risk fluctuations, and A suitability represents the surgical plan suitability index;

[0338] S412: According to the surgical plan suitability index, adjust the position of the surgical tool to optimize the surgical path, using the formula:

[0339] P adjustment = α · (tanh(β · (A suitability - 0.5) + δ))

[0340] Calculate and generate the surgical tool position adjustment coefficient;

[0341] Among them, P adjustment represents the surgical tool position adjustment coefficient, α and β represent the adjustment sensitivity parameters, and δ represents the fine-tuning parameter for position adjustment;

[0342] S413: Combine the surgical tool position adjustment coefficient to adjust the surgical tool layout to match the patient's current physiological state, using the formula:

[0343]

[0344] Generate the intraoperative response adjustment result;

[0345] Among them, L layoutIndicates the intraoperative response adjustment result, κ represents the layout baseline adjustment constant, and ξ, η represent the stability adjustment factors.

[0346] Step 1: Calculation of the surgical plan suitability index

[0347] Formula:

[0348]

[0349] Detailed parameter explanations and derivation process:

[0350] R update : Real-time risk update result, assuming the calculated value is 0.6 at a certain moment.

[0351] μ: Preset risk threshold, set according to historical data, assumed to be 0.5 here.

[0352] σ: Standard deviation of risk fluctuation, indicating the measurement uncertainty or the magnitude of risk fluctuation, assumed to be 0.1.

[0353] γ: Adaptability adjustment factor, improving the sensitivity of the model to sudden changes, assumed to be 0.05.

[0354] Calculation process:

[0355] Calculate the standardized difference between the risk deviation and the threshold:

[0356] Add the standardized difference to the adaptability adjustment factor: 1.0 + 0.05 = 1.05

[0357] Apply the sigmoid function to calculate the suitability index:

[0358] Result description:

[0359] The calculated surgical plan suitability index is approximately 0.74, indicating that the current surgical plan is relatively suitable compared to the real-time risk and has a high suitability.

[0360] Step 2: Calculation of the surgical tool position adjustment coefficient

[0361] Formula:

[0362] P adjustment = α·(tanh(β·(A suitability - 0.5)+δ))

[0363] Detailed parameter explanations and derivation process:

[0364] A suitability： The suitability index obtained from Step 1, approximately 0.74.

[0365] α: Adjust the sensitivity parameter, which affects the magnitude of the adjustment coefficient, assumed to be 2.0.

[0366] β: Used to adjust the intensity of the influence on the suitability index, assumed to be 5.0.

[0367] δ: Fine-tuning parameter to increase flexibility, assumed to be 0.1.

[0368] Calculation process:

[0369] Calculate the adjusted input of the suitability index: β·(A suitability -0.5)+δ = 5.0·(0.74 - 0.5)+0.1 = 1.3

[0370] Calculate the result of the tanh function: tanh(1.3) ≈ 0.865

[0371] Calculate the adjustment coefficient: P adjustment = 2.0·0.865 = 1.73

[0372] Result description:

[0373] The calculated adjustment coefficient for the surgical tool position is 1.73, which means that according to the current suitability index, the surgical tool position needs to be significantly adjusted to match the surgical conditions.

[0374] Step 3: Calculate the result of intraoperative response adjustment

[0375] Formula:

[0376]

[0377] Detailed parameter explanation and derivation process:

[0378] P adjustment： The adjustment coefficient for the surgical tool position obtained from Step 2 is 1.73.

[0379] κ: Layout baseline adjustment constant to increase adjustment flexibility, assumed to be 0.2.

[0380] ξ, η: Stability adjustment factors to ensure the smoothness of adjustment, assumed ξ = 0.3, η = 0.1. Calculation process:

[0381] Calculate the layout adjustment factor:

[0382] Calculate the result of intraoperative response adjustment: L layout = 1.73·1.5 = 2.595

[0383] Result description:

[0384] The calculated intraoperative response adjustment result is 2.595, indicating that according to the adjustment of the surgical tool position and the changes in surgical conditions, the surgical layout needs to be adjusted accordingly to maximize the matching of the patient's physiological state and optimize the surgical path.

[0385] An intelligent intraoperative nursing system for hip replacement surgery. The intelligent intraoperative nursing system for hip replacement surgery is used to execute the above-mentioned intelligent intraoperative nursing method for hip replacement surgery. The system includes:

[0386] The preoperative assessment integration module obtains the preoperative data of the patient including blood pressure, heart rate, and bone density, integrates multiple data into a dynamic Bayesian network model, synchronizes the data and constructs a time series, updates the data every minute for physiological change monitoring, and generates the initial assessment data result;

[0387] The initial risk status module performs time series analysis on blood pressure, heart rate, and bone density based on the initial assessment data result, synchronizes the dynamic Bayesian network data, integrates the data to form a time series, monitors and updates the physiological data every minute, and generates the initial risk status result;

[0388] The parameter calibration module uses the initial risk status result to analyze the changes in blood pressure and heart rate data during the operation in real time, calibrates and adjusts the dynamic network parameters, matches the real-time surgical data, combines the current data to update the probability model, and establishes the calibrated risk prediction;

[0389] The real-time risk assessment module analyzes the calibrated risk prediction, evaluates the patient's physiological response and surgical conditions in real time according to the key risk indicators during the operation, updates the data every minute for risk assessment, and integrates multiple data to generate the real-time risk assessment result;

[0390] The intraoperative response adjustment module adjusts the surgical plan and tool position based on the real-time risk assessment result, optimizes the surgical path and tool layout according to the real-time physiological state, matches the patient's current physiological conditions, and generates the intraoperative response adjustment result.

[0391] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent method for intraoperative care of hip replacement, characterized in that: The following steps are involved: Integrate the patient's preoperative assessment data, including blood pressure, heart rate, and bone density, synchronize the data with the dynamic Bayesian network model, construct a time series, update the data every minute to monitor the patient's physiological changes, and integrate them into the initial risk status results; Using the initial risk status results, calibrating dynamic network parameters in real time, adjusting the network structure to match the real-time data during the surgery, updating the probability model, and obtaining risk prediction after parameter adjustment; Analyze the key risk indicators during surgery shown in the risk prediction after the parameter adjustment, continue to evaluate the patient's physiological response and surgical conditions through real-time updated surgical data, refresh the risk assessment every minute to reflect the current surgical status, and generate real-time risk update results; According to the real-time risk update results, the surgical plan and the position of surgical tools are adjusted, the surgical path is optimized, the layout of surgical tools is adjusted to match the patient's current physiological state, and the intraoperative response adjustment results are generated.

2. The intelligent intraoperative care method for hip replacement according to claim 1 is characterized in that: The steps for obtaining the initial risk status result are specifically as follows: Collect the patient's preoperative data including blood pressure, heart rate, and bone density, using the formula: Calculate the weighted average of each data to get the health index; Among them, H represents the health index, w BP represents the blood pressure weight, w HR represents the heart rate weight, w BMD represents bone density weight; The health indicators are input into the dynamic Bayesian network, and the formula is adopted with reference to the time dependency: Generate updated network status; Among them, S represents the network status, λ represents the influence coefficient of the current health data, and S prev represents the network state at the previous time point, κ represents the parameter that adjusts data sensitivity; Based on the updated network status, time series analysis is performed using the formula: Get the time series model; Among them, T represents the time series model, α t represents the time decay coefficient, β t represents the deviation adjustment coefficient at each time point, S avg represents the average value of S; The time series model is used to assess the patient risk status using the formula: Get the initial risk status result; Among them, R represents the initial risk state, max(T) represents the maximum value of the time series, and min(T) represents the minimum value of the time series.

3. The intelligent intraoperative care method for hip replacement according to claim 2 is characterized in that: The steps for obtaining the risk prediction after the parameter adjustment are specifically as follows: Using the initial risk status results, the network parameters are dynamically adjusted, and new parameters are added to represent the degree of influence of real-time data flow on the parameters, using the formula: Calculate and generate updated network parameters; Among them, w i Represents the weight of multiple parameters, P i represents the original network parameters, n represents the number of parameters, θ represents the impact of real-time data, and δ i Represents the difference between real-time data and preset parameters, P new Represents the updated network parameters; Based on the updated network parameters, the network structure is adjusted to match the real-time data flow, using the formula: Update the network structure to obtain a new network structure; Among them, S new represents the new network structure, v j represents the structural adjustment coefficient, S j represents the original structural parameters, m represents the total number of structural components, γ represents the sensitivity of structural adjustment, ∈ j Represents the deviation of structural parameters from actual data; Based on the new network structure, the probability model is updated using the formula: M updated =η·(α·P new +β·S new ) Get the updated probability model; Among them, M updated represents the updated probability model, α and β are the influence coefficients of network parameters and structural parameters respectively, and η represents the adjustment factor of model complexity; According to the updated probability model, risk prediction is performed using the formula: Get the risk prediction after parameter adjustment; Among them, R final represents the risk prediction after parameter adjustment, and λ represents the risk perception coefficient.

4. The intelligent intraoperative care method for hip replacement according to claim 3 is characterized in that: The steps for obtaining the real-time risk update result are specifically as follows: The risk prediction after the parameter adjustment is analyzed with the real-time surgical data, and the deviation of each risk indicator is calculated using the formula: Generate risk deviation result ΔR; Among them, D realtime,i represents the i-th real-time surgical data, w i represents the clinical importance weight of the risk factor, k represents the total number of risk factors, and ΔR represents the risk deviation result; The risk deviation result is used to evaluate the patient's physiological response using the formula: With reference to the time dynamic factor τ, the risk assessment is updated in real time to obtain the risk assessment results every minute; Among them, R eval Represents the risk assessment result per minute, ΔR i Represents the deviation of the ith risk factor; The risk assessment results per minute are time-weighted, and an exponential decay model is used to reflect the real-time changes in the surgical status, using the formula: Integrate into real-time risk update results; Among them, R update represents the real-time risk update result, R eval,t represents the risk assessment result at minute t, θ t represents the decay coefficient at the tth minute, and T represents the total evaluation time.

5. The intelligent intraoperative care method for hip replacement according to claim 4 is characterized in that: The steps for obtaining the intraoperative response adjustment result are specifically as follows: Based on the real-time risk update results, the suitability of the surgical plan is deeply evaluated using a dynamic response formula: The adjustment factor γ is introduced to enhance the adaptability of the model and generate the surgical plan suitability index; Among them, μ represents the preset risk threshold, σ represents the standard deviation of risk fluctuation, and A suitability It represents the surgical plan suitability index; According to the surgical plan suitability index, the surgical tool position is adjusted to optimize the surgical path, using the formula: P adjustment =α·(tanh(β·(A suitability -0.5)+d)) Calculate and generate surgical tool position adjustment coefficients; Among them, P adjustment represents the surgical tool position adjustment coefficient, α and β represent adjustment sensitivity parameters, and δ represents the fine-tuning parameter of position adjustment; Combined with the surgical tool position adjustment coefficient, the surgical tool layout is adjusted to match the patient's current physiological state, using the formula: Generate intraoperative response adjustment results; Among them, L layout represents the intraoperative response adjustment result, κ represents the layout baseline adjustment constant, and ξ and η represent stability adjustment factors.

6. An intelligent intraoperative care system for hip replacement, characterized in that: According to the intelligent intraoperative care method for hip replacement according to any one of claims 1 to 5, the system comprises: The preoperative evaluation integration module obtains the patient's preoperative data including blood pressure, heart rate, and bone density, integrates multiple data into the dynamic Bayesian network model, synchronizes the data and constructs a time series, updates the data every minute to monitor physiological changes, and generates initial evaluation data results; The initial risk status module performs time series analysis on blood pressure, heart rate, and bone density based on the initial assessment data results, synchronizes dynamic Bayesian network data, integrates data to form a time series, monitors and updates physiological data every minute, and generates initial risk status results; The parameter calibration module uses the initial risk status results to analyze the changes in blood pressure and heart rate data during surgery in real time, calibrate and adjust dynamic network parameters, match real-time surgery data, update the probability model in combination with current data, and establish a calibrated risk prediction; The real-time risk assessment module analyzes the calibrated risk prediction, evaluates the patient's physiological response and surgical conditions in real time based on key risk indicators during surgery, updates data every minute for risk assessment, and integrates multiple data to generate real-time risk assessment results; The intraoperative response adjustment module adjusts the surgical plan and tool position based on the real-time risk assessment results, optimizes the surgical path and tool layout according to the real-time physiological status, matches the patient's current physiological condition, and generates intraoperative response adjustment results.

Images