Personalized intervention method for delirium in perioperative period of old orthopedic patient

Abstract

The invention relates to the field of medical health, in particular to a perioperative delirium personalized intervention method for old orthopedic patients. The method comprises the following steps: acquiring data of an old orthopedic patient and evaluating a delirium occurrence risk to obtain a delirium risk score; based on the old orthopedic patient data and the delirium risk score, evaluating the applicability of intervention measures, selecting the intervention measure with the highest applicability, and outputting an optimal intervention combination scheme; calculating an intervention effect expected gain of the optimal intervention combination scheme based on the delirium risk score and the applicability score of the intervention measure; data of the old orthopedic patients are obtained again, the delirium occurrence risk is evaluated, and the optimal intervention combination scheme is updated. The problems that traditional delirium risk assessment neglects individual differences of patients, which may cause inaccurate risk assessment and improper intervention measures are solved; the technical problems that a traditional intervention scheme often cannot accurately adjust mutual influence among measures and is difficult to flexibly adjust according to actual response of a patient are solved.

Description

Technical Field

[0001] The present invention relates to the field of medical health, and in particular to a personalized intervention method for perioperative delirium in elderly orthopedic patients. Background Art

[0002] Perioperative delirium refers to an acute, temporary disturbance of consciousness caused by a variety of physiological and psychological factors before and after surgery. It manifests as inattention, cognitive decline, and confusion. It is more common in elderly patients, particularly orthopedic patients. Due to factors such as aging, the complexity of surgery, and the effects of anesthesia, the elderly population is more susceptible to perioperative delirium. With the increasing prevalence of orthopedic surgery, especially hip and knee replacements, among elderly patients, with the aging population, perioperative delirium has become a significant clinical issue that needs to be addressed urgently.

[0003] Currently, in clinical practice, the intervention of perioperative delirium mainly relies on drug therapy and environmental adjustment, and adopts a "uniform standard" approach. Treatment plans are not formulated based on the patient's specific physiological, psychological, drug allergy history and other personalized characteristics. This may not effectively reduce the occurrence of delirium and may even aggravate the patient's symptoms. With the advancement of medical technology and a deeper understanding of the characteristics of elderly patients, personalized intervention methods for perioperative delirium will inevitably become an important part of the treatment of elderly orthopedic patients in the future, and will play a vital role in improving the quality of life and prognosis of elderly patients after surgery.

[0004] However, traditional perioperative delirium intervention methods have the following problems: lack of sufficient accuracy to effectively simulate complex changes in physiological and psychological states; neglect of the interrelationships between intervention measures; ignoring the persistence and attenuation of intervention effects; and lack of flexible adjustment mechanisms when facing changes in patient status. Summary of the Invention

[0005] The present invention provides a personalized intervention method for perioperative delirium in elderly orthopedic patients to address the technical problems that traditional delirium risk assessment ignores individual differences in patients and their physiological and psychological states that change over time, which may lead to inaccurate risk assessment and inappropriate intervention measures; there may be synergistic or conflicting effects between different intervention measures, and traditional intervention plans are often unable to accurately adjust the mutual influence between the measures, resulting in unsatisfactory treatment effects; as the treatment progresses, the intervention effect may gradually decline over time or become less than expected, and traditional treatment plans are difficult to flexibly adjust according to the patient's actual response.

[0006] The present invention provides a personalized intervention method for perioperative delirium in elderly orthopedic patients, which specifically includes the following technical solutions: A personalized intervention method for perioperative delirium in elderly orthopedic patients includes the following steps: S1. Obtain data on elderly orthopedic patients, assess their risk of delirium, and obtain a delirium risk score. S2. Based on the data of elderly orthopedic patients and the delirium risk score, evaluate the applicability of intervention measures and obtain the applicability score of the intervention measures; based on the applicability score of the intervention measures, select the intervention measure with the highest applicability and output the optimal intervention combination plan; S3. Calculate the expected gain of intervention effect of the optimal intervention combination based on the delirium risk score and the applicability score of the intervention measures; S4. Re-acquire the data of elderly orthopedic patients and assess the risk of delirium. Update the optimal intervention combination plan based on the difference between the actual intervention effect and the expected gain of the intervention effect.

[0007] Preferably, the S1 specifically includes: Based on the data of elderly orthopedic patients, a delirium risk assessment algorithm was introduced to evaluate the risk of delirium in elderly orthopedic patients.

[0008] Preferably, the S1 specifically includes: In the implementation of the delirium risk assessment algorithm, weight adjustment, periodic change terms and random disturbance factors are introduced to calculate the delirium risk score.

[0009] Preferably, the S2 specifically includes: Based on the data of elderly orthopedic patients and the delirium risk score, the sensitivity parameter of the intervention measure was introduced, and the applicability of the intervention measure was dynamically adjusted through an exponential function. Combined with the inhibition factor of the intervention measure based on the data of elderly orthopedic patients, the applicability score of the intervention measure was calculated.

[0010] Preferably, the S2 specifically includes: The applicability scores of the intervention measures are compared with the preset applicability score threshold to obtain a preliminary screening set of intervention measures; based on the preliminary screening set of intervention measures, an intervention relationship matrix is ​​constructed.

[0011] Preferably, the S2 specifically includes: Based on the initially screened set of intervention measures and the intervention relationship matrix, the objective function is constructed and solved, the intervention measures with the highest applicability are selected, and the optimal intervention combination plan is output.

[0012] Preferably, the S3 specifically includes: Based on the delirium risk score and the applicability score of the intervention measures, the effect attenuation coefficient and risk attenuation coefficient of the intervention measures were introduced to calculate the expected gain of the intervention effect.

[0013] Preferably, the S4 specifically includes: Based on the difference between the actual intervention effect and the expected gain of the intervention effect, the optimal intervention combination plan is continuously iterated and updated until the treatment goal is achieved.

[0014] The beneficial effects of the technical solution of the present invention are: 1. By integrating multi-dimensional data such as the patient's physiology, psychology, medical history, and medication use, combined with a delirium risk assessment algorithm, the patient's risk of delirium at different time points is dynamically assessed. By introducing periodic change items (such as circadian rhythm) and random disturbance factors, the risk assessment is made more consistent with the patient's actual physiological state and environmental changes, thereby improving the accuracy and reliability of the risk assessment.

[0015] 2. By introducing a calculation method for the applicability score of intervention measures, combined with the patient's delirium risk score, the sensitivity parameters of the intervention measures, and the inhibitory factors of the intervention measures in the data of elderly orthopedic patients, the set of intervention measures that best suits the patient's current condition is screened out. Further use of the intervention relationship matrix, considering the synergy or conflict between intervention measures, optimize the intervention combination plan, ensure that different intervention measures can work in coordination, and thus improve the treatment effect.

[0016] 3. By constructing an expected gain model for intervention effects, combining the effect attenuation coefficient and risk attenuation coefficient of intervention measures, the expected gain of intervention effects is calculated, and the effect changes of intervention measures over time are quantified, ensuring that the treatment plan can be dynamically adjusted so as to promptly reflect changes in patient risks, avoid weakening of effects in long-term treatment, and improve the overall treatment effect of patients.

[0017] 4. Use personalized intervention adjustment algorithms to automatically adjust the intervention combination plan based on the difference between the actual intervention effect and the expected gain. By controlling the amplitude of intervention adjustment, the side effects caused by excessive adjustment can be avoided. At the same time, the effect of intervention measures can be maximized to avoid unnecessary treatment interventions, thereby enhancing the flexibility and stability of the treatment process. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of the personalized intervention method for perioperative delirium in elderly orthopedic patients described in the present invention. DETAILED DESCRIPTION

[0019] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention pertains. A specific scheme of a personalized intervention method for perioperative delirium in elderly orthopedic patients provided by the present invention will be described in detail below with reference to the accompanying drawings.

[0021] Refer to the attached Figure 1 , which shows a flow chart of a personalized intervention method for perioperative delirium in elderly orthopedic patients provided by one embodiment of the present invention, the method comprising the following steps: S1. Obtain data on elderly orthopedic patients, assess their risk of delirium, and obtain a delirium risk score. Obtaining data on elderly orthopedic patients The data types of elderly orthopedic patients include but are not limited to basic physiological data, historical medical history, current medication usage, surgical information, and mental status score. The specific data items in each type include but are not limited to age and weight. Indicates time No. Class Data of elderly orthopedic patients, Indicates the number of types of data for elderly orthopedic patients, Indicates the The specific number of data items within a type; Based on data from elderly orthopedic patients, a delirium risk assessment algorithm is used to assess the delirium risk of elderly orthopedic patients at a specific time point, generating a delirium risk score. This algorithm introduces weight adjustment, periodic variation terms, and random perturbation factors to make delirium risk assessment realistic. It not only considers the static characteristics of individual patient data but also dynamically captures the impact of changes in elderly orthopedic patient data over time. The weight adjustment is to assign a basic weight to each elderly orthopedic patient's data. The basic weight is set based on relevant empirical values ​​or experiments in medical research to reflect the contribution of each data item to the risk of delirium. Because the human body's physiological and psychological changes exhibit obvious cyclical characteristics, such as circadian rhythms and biological clock regulation, in order to dynamically reflect the cyclical changes in the patient's condition, the delirium risk assessment algorithm, based on biological rhythm theory, introduces a cyclical change term. It uses a sine function to simulate the circadian cyclical changes in the patient's physiological data and psychological state to reflect the impact of natural rhythms on delirium risk. To simulate the inevitable random factors in real-world medical scenarios, such as environmental changes and measurement errors, the delirium risk assessment algorithm introduces a random perturbation factor. This perturbation factor is set between zero and a very small fixed interval to ensure a slight but reasonable impact on the overall delirium risk assessment. The delirium risk score is calculated as follows: ; in, Indicates time Delirium risk score; Indicates the sum operation of all data types and all specific data items; Indicates the Class The basic weight of the data of elderly orthopedic patients is used to measure the importance of different elderly orthopedic patients' data. It can be set according to the specific implementation scenario and is not limited here. The value range is ; Represents a periodic change term, which simulates the periodic changes of the patient's physiological data and psychological state (such as heart rate or hormone secretion with a circadian rhythm) through a sine function. It is used to dynamically adjust the delirium risk score to reflect the impact of natural rhythms on delirium risk; Indicates the Class The data cycle of elderly orthopedic patients is set according to the biological characteristics of specific data items (such as heart rate, hormone level or mental state). The common range may be 24 or its multiples, which is not limited here; represents the random perturbation factor used to Simulate the dynamic disturbance term of small environmental changes or measurement errors that are difficult to predict, so as to increase the robustness of risk assessment and prevent deviations caused by small changes in the outside world. The value range is ; By dynamically and individually quantifying the risk of delirium in elderly orthopedic patients, a clear reference basis is provided for intervention decisions; S2. Based on the data of elderly orthopedic patients and the delirium risk score, evaluate the applicability of intervention measures and obtain the applicability score of the intervention measures; based on the applicability score of the intervention measures, select the intervention measure with the highest applicability and output the optimal intervention combination plan; Based on data from elderly orthopedic patients and the delirium risk score, the applicability of all possible intervention measures was evaluated and the applicability score of the intervention measures was calculated; The calculation of the applicability score of the intervention depends on the patient's delirium risk level. Because different interventions respond differently to delirium risk, a sensitivity parameter for the intervention is introduced to reflect the sensitivity of a specific intervention to different delirium risks. Based on the current patient's delirium risk score and the sensitivity parameter of the intervention, the applicability of the intervention for high-risk patients is dynamically adjusted through an exponential function. The nonlinear design reflects the fact that high-risk patients may require stronger or more specific measures in clinical intervention. At the same time, because individual patient characteristics (such as advanced age or complex medical history) may reduce the applicability of the intervention, an inhibitory factor for the effect of geriatric orthopedic patient data on the applicability of the intervention is introduced to reflect the degree to which geriatric orthopedic patient data inhibits the applicability of the intervention. The formula for calculating the suitability score of an intervention measure is: ; in, Indicates time No. Applicability rating of each intervention; A nonlinear dynamic reflection term representing delirium risk, which amplifies or reduces the change in the patient's delirium risk through an exponential term to reflect the sensitivity of specific intervention measures to elderly orthopedic patients; Indicates the The sensitivity parameter of the intervention is used to reflect the The response intensity of each intervention measure to the patient's delirium risk can be set according to the specific implementation scenario and is not limited here. The value range is ; Indicates the reference value, used to ensure that the denominator is not 0; represents a double sum operation; Indicates the Class Data on elderly orthopedic patients The inhibitory factor of each intervention measure can be set according to the specific implementation scenario and is not limited here. The value range is ; The applicability score of the intervention measures is compared with the preset applicability score threshold to obtain the initial screening intervention measure set. The formula is as follows: ; in, Indicates time A collection of interventions for initial screening; Indicates time No. intervention measures; Indicates time No. Applicability rating of each intervention; It represents the applicability score threshold, which is used to screen whether the intervention measures are effective enough. It can be set according to the specific implementation scenario and is not limited here; Patients need to take different intervention measures to achieve better treatment effects, but there may be synergistic or conflicting relationships between different intervention measures. By introducing the intervention interaction matrix, it is used to describe the synergistic or conflicting relationships between intervention measures, such as the synergistic or conflicting relationships between drugs. Specifically, if two intervention measures can enhance each other's effects, they are considered to have a synergistic relationship. If two intervention measures offset each other or produce side effects, it is defined as a conflicting relationship. If there is no significant mutual relationship between two intervention measures, it is assumed to be a neutral relationship. The intervention relationship matrix is ​​constructed by analyzing the medical knowledge base, literature or background knowledge, and is expressed as follows: ; in, Indicates time The first intervention in the initial screening set interventions and The relationship between the intervention measures; Indicates time No. intervention measures; Based on the initially screened set of interventions and the intervention interrelationship matrix, an objective function is constructed: the first step is to calculate the sum of the applicability scores of each independent intervention in the initially screened set of interventions; the second step is to accumulate the scores brought by cooperation or conflict, so that any synergistic interventions will improve the overall score of the program, while conflicting interventions will weaken the total score of the program; the specific definition of the objective function is as follows: ; in, represents the objective function; represents the sum of the applicability scores of all initially screened interventions; Indicates synergistic or conflicting impacts among interventions; Indicates time No. Applicability rating of each intervention; To solve the objective function, a greedy algorithm is used to sort the intervention measures from high to low according to their applicability scores. Starting with the highest score, each intervention measure is tried to be added to the current combination one by one. At the same time, the conflict between the intervention measures in the current combination and the new intervention measure is considered. If the conflict exceeds a threshold preset based on expert experience, the new intervention measure is discarded. The greedy algorithm is a technical means well known to those skilled in the art and will not be described in detail here. Gradually select the intervention measures with the highest applicability and the least conflict, and output the optimal intervention combination plan; S3. Calculate the expected gain of intervention effect of the optimal intervention combination based on the delirium risk score and the applicability score of the intervention measures; Based on the delirium risk score and the applicability score of the intervention measures, an intervention effect expected gain model was constructed to calculate the expected intervention effect gain of the optimal intervention combination plan. This intervention effect expected gain model was constructed based on the actual needs of delirium risk assessment in elderly orthopedic patients and combined with the dynamic characteristics of medical intervention effects. It aims to quantify the expected effect of intervention measures on reducing delirium risk. To accurately reflect the actual effects, the intervention effect expected gain model is based on the applicability score of the intervention measures, reflecting the potential effect of each intervention measure on the patient's delirium risk. A higher applicability score means that the intervention measure is more suitable for the current patient condition. Considering that the effect of the intervention measure will gradually weaken over time (such as the effect of the drug decreases with metabolism), the effect attenuation coefficient of the intervention measure is introduced to simulate the nonlinear attenuation of the intervention effect in an exponential form, reflecting the persistence of the intervention measure and the rate of effect attenuation. At the same time, the risk attenuation coefficient is introduced to consider the relationship between the current delirium risk and the expected treatment effect, and adjust the impact of the risk level on the expected gain of the intervention effect, so that the patient's delirium risk will gradually decrease with the implementation of the intervention measure. The calculation formula for the expected gain of intervention effect is: ; in, Indicates that intervention measures continue The expected gain of intervention effect after the duration; Indicates time the optimal combination of interventions; Indicates the The effect attenuation coefficient of each intervention measure is used to reflect the persistence and effect reduction rate of the intervention measure. It can be set according to the specific implementation scenario and is not limited here. The value range is ; Indicates the length of time the intervention lasts; It represents the attenuation effect of delirium risk, indicating that as the delirium risk score increases, the overall intervention effect weakens. It is used to adjust the impact of high and low risk on the intervention effect and ensure that greater intervention efforts are applied to high-risk patients. It represents the risk attenuation coefficient, reflecting the sensitivity of risk level, and is used to adjust the impact of risk level on the overall expected gain. The value range is ; S4. Re-acquire data on elderly orthopedic patients and assess the risk of delirium. Update the optimal intervention combination plan based on the difference between the actual intervention effect and the expected gain of the intervention effect. Since the risk of perioperative delirium in elderly orthopedic patients changes dynamically due to individual differences, time changes and intervention effects, intervention measures need to be adjusted according to the difference between actual effects and expected effects to ensure the adaptability and effectiveness of the treatment plan. After a certain period of time, the data of elderly orthopedic patients are reacquired and the risk of delirium is assessed. The optimal intervention combination plan is updated based on the difference between the actual intervention effect and the expected gain of the intervention effect. In the embodiment of the present application, the optimal intervention combination plan can be updated by expert experience, or a personalized intervention adjustment algorithm can be introduced to automatically adjust the optimal intervention combination plan to ensure the stability of the intervention adjustment process. The personalized intervention adjustment algorithm introduces a sensitivity adjustment mechanism, which controls the magnitude of intervention adjustment through the sensitivity adjustment parameter of the intervention measure to obtain a dynamic adjustment value of the intervention measure; the sensitivity adjustment parameter of the intervention measure adjusts the intervention adjustment magnitude according to changes in the actual delirium risk score, thereby avoiding unnecessary treatment intervention due to over-adjustment; The formula for calculating the dynamic adjustment value of intervention measures is: ; in, Indicates time For the first Dynamic adjustment value of each intervention measure; Indicates the The proportion of intervention applicability of each intervention measure; Indicates time The optimal intervention combination The sum of the applicability scores of all interventions selected in ; Indicates time Time the amount of change in delirium risk score between patients; Used to reflect the difference between the actual intervention effect and the expected gain of the intervention effect. ; Indicates the The sensitivity adjustment parameter of each intervention measure is used to control the amplitude of intervention adjustment. It can be set according to the specific implementation scenario and is not limited here. The value range is ; It represents the absolute value of the difference in delirium risk score, which is used to quantify the change in actual delirium risk score and serve as the basis for adjusting sensitivity; like 0, indicating that the intervention effect is not as good as expected and the intervention needs to be strengthened; if 0, indicating that the intervention effect is too strong and the intervention may need to be adjusted or replaced; By continuously iterating and updating the optimal intervention combination plan, the treatment plan remains flexible throughout the entire treatment process until the treatment goal is achieved, ensuring that the treatment plan at each time point can maximize the patient's health benefits.

[0022] In summary, a personalized intervention method for perioperative delirium in elderly orthopedic patients was completed.

[0023] The order in which the embodiments of the invention are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0024] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0025] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A personalized intervention method for perioperative delirium in elderly orthopedic patients, characterized by: The following steps are involved: S1. Obtain data on elderly orthopedic patients, assess their risk of delirium, and obtain a delirium risk score. S2. Based on the data of elderly orthopedic patients and the delirium risk score, evaluate the applicability of intervention measures and obtain the applicability score of the intervention measures; based on the applicability score of the intervention measures, select the intervention measure with the highest applicability and output the optimal intervention combination plan; S3. Calculate the expected gain of intervention effect of the optimal intervention combination based on the delirium risk score and the applicability score of the intervention measures; S4. Re-acquire the data of elderly orthopedic patients and assess the risk of delirium. Update the optimal intervention combination plan based on the difference between the actual intervention effect and the expected gain of the intervention effect.

2. The personalized intervention method for perioperative delirium in elderly orthopedic patients according to claim 1, characterized in that: Said S1 specifically includes: Based on the data of elderly orthopedic patients, a delirium risk assessment algorithm was introduced to evaluate the risk of delirium in elderly orthopedic patients.

3. The personalized intervention method for perioperative delirium in elderly orthopedic patients according to claim 2, characterized in that: Said S1 specifically includes: In the implementation of the delirium risk assessment algorithm, weight adjustment, periodic change terms and random disturbance factors are introduced to calculate the delirium risk score.

4. The personalized intervention method for perioperative delirium in elderly orthopedic patients according to claim 1, characterized in that: Said S2 specifically includes: Based on the data of elderly orthopedic patients and the delirium risk score, the sensitivity parameter of the intervention measure was introduced, and the applicability of the intervention measure was dynamically adjusted through an exponential function. Combined with the inhibition factor of the intervention measure based on the data of elderly orthopedic patients, the applicability score of the intervention measure was calculated.

5. The personalized intervention method for perioperative delirium in elderly orthopedic patients according to claim 4, characterized in that: Said S2 specifically includes: The applicability scores of the intervention measures are compared with the preset applicability score threshold to obtain a preliminary screening set of intervention measures; based on the preliminary screening set of intervention measures, an intervention relationship matrix is ​​constructed.

6. The personalized intervention method for perioperative delirium in elderly orthopedic patients according to claim 5, characterized in that: Said S2 specifically includes: Based on the initially screened set of intervention measures and the intervention relationship matrix, the objective function is constructed and solved, the intervention measures with the highest applicability are selected, and the optimal intervention combination plan is output.

7. The personalized intervention method for perioperative delirium in elderly orthopedic patients according to claim 1, characterized in that: Said S3 specifically includes: Based on the delirium risk score and the applicability score of the intervention measures, the effect attenuation coefficient and risk attenuation coefficient of the intervention measures were introduced to calculate the expected gain of the intervention effect.

8. The personalized intervention method for perioperative delirium in elderly orthopedic patients according to claim 1, characterized in that: Said S4 specifically includes: Based on the difference between the actual intervention effect and the expected gain of the intervention effect, the optimal intervention combination plan is continuously iterated and updated until the treatment goal is achieved.

Images