Evaluation system based on multi-dimensional smoking cessation management model and computing device

Abstract

The invention discloses an evaluation system based on a multi-dimensional smoking cessation management model and a computing device. The evaluation system comprises a smoking cessation data set construction module which integrates personal basic information, smoking habits, motivation and lung function data to form a smoking cessation data set; and the smoking cessation treatment scheme generation module automatically generates a personalized smoking cessation scheme according to the tobacco dependence degree. And the doctor-patient interaction and information pushing module promotes information circulation and regularly pushes medicine taking reminding. The smoking cessation behavior monitoring module regularly collects smoking cessation behavior data of a patient, a smoking cessation scheme most suitable for the current state is matched based on a similarity algorithm through the smoking cessation scheme matching module, and manual auditing is conducted through the scheme auditing and confirming module. And the information pushing module is used for pushing schemes, knowledge, questionnaires and early warning information as required. And the smoking cessation behavior construction and trend analysis module summarizes behavior indexes in stages. The influence factor analysis and personalized guidance module deeply analyzes smoking cessation behavior influence factors, customized smoking cessation suggestions are provided for patients, and the success rate of smoking cessation is increased.

Description

Technical Field

[0001] The present invention relates to the technical field of medical and health informatization, and particularly relates to an evaluation system and a computing device based on a multi-dimensional smoking cessation management model. Background Art

[0002] Tobacco dependence is a chronic and highly recurrent disease, and smoking is one of the main risk factors for disability-adjusted life years. Controlling smoking is the most important and feasible measure for population disease prevention and human health care. The "Healthy China Initiative (2019-2030)" clearly requires the gradual establishment and improvement of a smoking cessation service system and the strengthening of tobacco control work in professional institutions at all levels. At present, medical staff have widely carried out smoking cessation counseling and education and provided various smoking cessation methods during the diagnosis and treatment of patients. However, due to multiple factors, the smoking cessation work still needs to be further improved.

[0003] However, although medical staff have widely carried out smoking cessation counseling and education and provided various smoking cessation methods during the diagnosis and treatment of patients, there are still many deficiencies in the current smoking cessation work. Traditional smoking cessation methods mostly rely on smoking cessation products or drugs, such as nicotine replacement therapy, antidepressant drugs, etc. Although they can help patients reduce the amount of smoking or quit smoking temporarily to a certain extent, they lack a perfect smoking cessation management link, resulting in a generally low success rate of smoking cessation and easy relapse. Existing smoking cessation methods often ignore the individual differences and complexities during the smoking cessation process. The degree of tobacco dependence, smoking motivation, health status, and environmental factors of each patient are different. Therefore, a single smoking cessation product or drug is difficult to meet the needs of all patients. In addition, due to the lack of effective smoking cessation management and monitoring mechanisms, patients are prone to lose motivation and confidence during the smoking cessation process, ultimately leading to the failure of smoking cessation.

[0004] To solve the above problems, the present invention discloses an evaluation system and a computing device based on a multi-dimensional smoking cessation management model to achieve comprehensive monitoring and personalized management of the patient's smoking cessation process, provide customized smoking cessation advice for patients, and further assist patients in successfully quitting smoking. Summary of the Invention

[0005] In view of the above problems, the present invention provides an evaluation system and a computing device based on a multi-dimensional smoking cessation management model.

[0006] According to one aspect of the present invention, there is provided an evaluation system based on a multi-dimensional smoking cessation management model, including:

[0007] A smoking cessation data set construction module, configured to collect and integrate demographic information, smoking status, smoking motivation, smoking cessation attempt history, health status, and pulmonary function examination results to form a smoking cessation data set;

[0008] A smoking cessation treatment plan generation module, which is used to automatically analyze and generate a personalized smoking cessation treatment plan according to the scoring results of the severity of tobacco dependence;

[0009] A doctor-patient interaction and information push module, which is used to realize information interaction between doctors and patients through a server and a client; generate and push the smoking cessation drug taking time information according to the patient's smoking cessation date, and ensure that the patient is sent a medication reminder regularly and at a fixed point during the medication period to improve medication compliance;

[0010] A smoking cessation behavior monitoring module, which is used to regularly push a smoking cessation diary questionnaire or telephone follow-up to the patient according to a preset path, and collect and analyze the patient's smoking cessation behavior data;

[0011] A smoking cessation plan matching module, which is used to match a personalized smoking cessation plan for the patient's current smoking cessation status from a smoking cessation treatment plan library according to a similarity algorithm;

[0012] A plan review and confirmation module, which is used to manually review and confirm the personalized smoking cessation plan for the patient's current smoking cessation status;

[0013] An information push module, which is used to push the reviewed smoking cessation plan, relevant knowledge, questionnaire and warning information to the patient according to the set nodes to assist the patient in implementing the smoking cessation plan;

[0014] A smoking cessation behavior construction and trend analysis module, which is used to summarize the smoking cessation behavior indicators, smoking craving and withdrawal symptom evaluations in stages during the patient's smoking cessation process to construct a smoking cessation behavior data set; and, conduct a visual analysis of the patient's smoking cessation behavior trend to help the patient and the doctor understand the smoking cessation progress;

[0015] An influencing factor analysis and personalized guidance module, which is used to analyze the influencing results of each factor on the patient's smoking cessation behavior according to the smoking cessation behavior influencing factor data set; generate a personalized smoking cessation guidance plan for the patient according to the influencing results, and provide personalized smoking cessation suggestions for the patient.

[0016] In an optional manner, the automatically analyzing and generating a personalized smoking cessation treatment plan according to the scoring results of the severity of tobacco dependence further includes:

[0017] Scoring the patient's tobacco dependence degree according to the smoking cessation data set and the tobacco dependence scale to obtain a scoring result;

[0018] Generating a personalized smoking cessation treatment plan for the patient according to the scoring result;

[0019] Among them, for patients with mild tobacco dependence, a dry quitting treatment plan is recommended, and at the same time, psychological support and behavioral therapy auxiliary means of non-drug treatment are provided;

[0020] For patients with moderate to severe tobacco dependence, a comprehensive smoking cessation method combining drug treatment and psychotherapy is recommended. Among them, the treatment drugs include nicotine patches, nicotine chewing gum, and bupropion hydrochloride, and the psychotherapy includes cognitive behavioral therapy and motivational interviewing methods.

[0021] In an alternative approach, the personalized smoking cessation plan that matches the patient's current smoking cessation status from the smoking cessation treatment plan library further includes:

[0022] Obtain the patient feature vector based on the patient's smoking cessation history information, where the smoking cessation history information includes age, gender, smoking years, daily smoking amount, number of attempts to quit smoking, and smoking cessation results;

[0023] Extract the features of each treatment plan in the smoking cessation treatment plan library to obtain the treatment plan feature vector, where the treatment plan includes treatment means, applicable age range, gender preference, and smoking years;

[0024] Calculate the similarity between the patient feature vector and each smoking cessation treatment plan feature vector, and select multiple smoking cessation treatment plans as candidate plans based on the similarity;

[0025] Select the personalized smoking cessation plan for the patient's current smoking cessation status from the candidate plans according to the patient's personal preferences and the accessibility of the treatment plan.

[0026] In an alternative approach, the smoking behavior influencing factor dataset includes physical factors, psychological factors, sociodemographic factors, smoking behavior factors, smoking behavior factors, and environmental factors;

[0027] Among them, physical factors include whether suffering from smoking-related diseases and smoking addiction;

[0028] Psychological factors include the patient's internal driving force for quitting smoking, the patient's understanding of the harms of smoking and the benefits of quitting smoking, the patient's confidence in being able to successfully quit smoking, the impact of anxiety and depression on smoking cessation behavior, and personality traits; among them, the patient's internal driving force for quitting smoking includes health concerns, economic concerns, family pressure, social recognition and image, self-improvement and growth, improvement of quality of life, spiritual and psychological needs, and personal beliefs and values; personality traits include impulsivity and self-discipline;

[0029] Sociodemographic factors include gender, age, education level, and economic status;

[0030] Smoking behavior factors include smoking years, daily smoking amount, and smoking pattern;

[0031] Environmental factors include family, work environment, and social pressure.

[0032] In an alternative approach, further analyzing the impact of each factor on the patient's smoking cessation behavior based on the smoking cessation behavior influencing factor dataset includes:

[0033] Analyzing the combined impact of multiple smoking cessation behavior influencing factors on the smoking cessation success rate through a multiple linear regression model;

[0034] Based on the combined impact of multiple smoking cessation behavior influencing factors on the smoking cessation success rate, evaluating the smoking cessation success probability of the patient through a Cox proportional hazards model.

[0035] In an alternative approach, further analyzing the combined impact of multiple smoking cessation behavior influencing factors on the smoking cessation success rate through a multiple linear regression model includes:

[0036] Constructing a multiple linear regression model based on multiple smoking cessation behavior influencing factors and the smoking cessation success rate;

[0037] Estimating the regression coefficients according to the least squares method, calculating the standardized regression coefficients of each smoking cessation behavior influencing factor, and evaluating the relative contribution of each smoking cessation behavior influencing factor to the smoking cessation success rate.

[0038] In an alternative approach, the multiple linear regression model is:

[0039]

[0040] where y is the smoking cessation success rate; β0, β i , β ii , β iii are the regression coefficients respectively; X i is the i-th smoking cessation behavior influencing factor; ∈ is the error term.

[0041] In an alternative approach, further evaluating the smoking cessation success probability of the patient through a Cox proportional hazards model includes:

[0042] Constructing a Cox proportional hazards model based on the multiple linear regression model, and the Cox proportional hazards model is:

[0043] h(t|X) = h0(t)exp(y)

[0044] where h(t|X) is the smoking cessation failure hazard rate given the influencing factor X at time t; h0(t) is the baseline hazard rate function;

[0045] Estimating the regression coefficients of the multiple linear regression model through the maximum partial likelihood estimation method;

[0046] Calculating the smoking cessation success probability of the patient according to the estimated regression coefficients.

[0047] In an alternative manner, the estimation formula for the baseline hazard rate function h0(t) is:

[0048]

[0049] where d t is the number of smoking relapse occurrences within time t; n is the number of individuals still under observation within time t; X ti is the covariate vector of the i-th individual within time t; is the mean value of X ti ; β i is the regression coefficient.

[0050] According to another aspect of the present invention, there is provided a computing device, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus;

[0051] The memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform operations corresponding to the above-mentioned autonomous driving path optimization control method that fuses environment perception and prediction.

[0052] The solution provided by the present invention includes: a smoking cessation dataset construction module, which is used to collect and integrate demographic information, smoking status, smoking motivation, smoking cessation attempt history, health status, and pulmonary function test results to form a smoking cessation dataset; a smoking cessation treatment plan generation module, which is used to automatically analyze and generate a personalized smoking cessation treatment plan according to the results of the tobacco dependence severity score; a doctor-patient interaction and information push module, which is used to realize information interaction between doctors and patients through a server and a client; generate and push information on the smoking cessation medication taking time according to the patient's smoking cessation date, and ensure that medication reminders are sent to the patient regularly and at fixed points during the medication period to improve medication compliance; a smoking cessation behavior monitoring module, which is used to regularly push a smoking cessation diary questionnaire or conduct a telephone follow-up to the patient according to a preset path, and collect and analyze the patient's smoking cessation behavior data; a smoking cessation plan matching module, which is used to match a personalized smoking cessation plan for the patient's current smoking cessation status from a smoking cessation treatment plan library according to a similarity algorithm; a plan review and confirmation module, which is used to manually review and confirm the personalized smoking cessation plan for the patient's current smoking cessation status; an information push module, which is used to push the reviewed smoking cessation plan, relevant knowledge, questionnaires, and warning information to the patient according to set nodes to assist the patient in implementing the smoking cessation plan; a smoking cessation behavior construction and trend analysis module, which is used to summarize smoking cessation behavior indicators, smoking craving, and withdrawal symptom evaluations in stages during the patient's smoking cessation process to construct a smoking cessation behavior dataset; and conduct a visual analysis of the patient's smoking cessation behavior trend to help the patient and the doctor understand the smoking cessation progress; an influencing factor analysis and personalized guidance module, which is used to analyze the influence results of various factors on the patient's smoking cessation behavior according to a smoking cessation behavior influencing factor dataset; generate a personalized smoking cessation guidance plan for the patient according to the influence results, and provide personalized smoking cessation suggestions for the patient. By integrating multi-dimensional data such as the patient's personal information, smoking status, and health status, the present invention automatically generates a personalized smoking cessation treatment plan, and through doctor-patient interaction, information push, etc., improves the patient's medication compliance and smoking cessation success rate. At the same time, by deeply analyzing the influencing factors of smoking cessation behavior, it provides tailor-made smoking cessation suggestions for the patient, further improving the patient's smoking cessation success rate.

[0053] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present invention more obvious and understandable, the following specifically enumerates the specific implementation manners of the present invention. Brief Description of the Drawings

[0054] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0055] Figure 1 Shows a schematic framework diagram of an evaluation device based on a multi-dimensional smoking cessation management model according to an embodiment of the present invention;

[0056] Figure 2 Shows a schematic structural diagram of a computing device according to an embodiment of the present invention. Detailed implementation manners

[0057] Hereinafter, exemplary embodiments of the present invention will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present invention can be more thoroughly understood and the scope of the present invention can be fully conveyed to those skilled in the art.

[0058] Figure 1 Shows a schematic framework diagram of an evaluation device based on a multi-dimensional smoking cessation management model according to an embodiment of the present invention. Specifically, as Figure 1 shown, it includes:

[0059] A smoking cessation data set construction module, configured to collect and integrate demographic information, smoking status, smoking motivation, smoking cessation attempt history, health status, and pulmonary function examination results to form a smoking cessation data set. Specifically, through online questionnaires, offline physical examinations, pulmonary function tests, etc., multi-dimensional data of patients are collected, and the collected data is integrated and cleaned using a database management system or data analysis software to form a structured smoking cessation data set. For example, for male patient A who is 45 years old and has a 20-year smoking history, with a daily smoking volume of about 20 cigarettes. He had previously tried to quit smoking but failed. He went to the hospital for medical treatment due to symptoms such as coughing and shortness of breath and received a pulmonary function examination. The smoking cessation data set construction module collects and integrates the following data:

[0060] Demographic information: Age 45, gender male, occupation programmer.

[0061] Smoking status: Smoking duration 20 years, daily smoking volume 20 cigarettes.

[0062] Smoking motivation: Stress relief.

[0063] Smoking cessation attempt history: Has tried to quit smoking but failed.

[0064] Health status: Recently had symptoms such as coughing and shortness of breath.

[0065] Pulmonary function examination results: Include vital capacity, FEV1 / FVC ratio, etc.

[0066] The smoking cessation treatment plan generation module is used to automatically analyze and generate a personalized smoking cessation treatment plan based on the tobacco dependence severity score result. Automatically analyzing and generating a personalized smoking cessation treatment plan according to the patient's tobacco dependence severity score result can fully consider the individual differences of patients and improve the pertinence of the smoking cessation plan. For example, male patient A has a high tobacco dependence severity score and is accompanied by mild anxiety and depressive symptoms. The smoking cessation treatment plan generation module generates the following personalized smoking cessation treatment plan:

[0067] It is recommended that the patient use nicotine replacement therapy (such as nicotine patches, nicotine gum, etc.) to relieve withdrawal symptoms. At the same time, prescribe some anti-anxiety and anti-depressant drugs for adjuvant treatment according to the patient's specific situation.

[0068] Recommend cognitive behavioral therapy, mindfulness therapy, etc. to help the patient adjust the mindset and enhance the determination and confidence to quit smoking.

[0069] Formulate a specific behavior intervention plan to help the patient gradually get rid of the dependence on tobacco and improve the success rate of smoking cessation.

[0070] The doctor-patient interaction and information push module is used to realize the information interaction between doctors and patients through the server and the client; generate and push the smoking cessation drug taking time information according to the patient's smoking cessation date, and ensure that the patient is sent a medication reminder regularly and at a fixed point during the medication period to improve medication compliance. Through the real-time communication between the server and the client, the instant information interaction between doctors and patients is realized. The patient can receive the doctor's guidance and advice without going to the hospital in person, which improves the convenience of communication. By regularly sending medication reminders to patients, the medication compliance of patients can be significantly improved. The patient can take the medicine on time and in the right amount, so as to more effectively control the withdrawal symptoms and improve the success rate of smoking cessation. For example, when the push time is reached, the server sends a medication reminder message to the patient through the push channel selected by the patient (such as text message or APP push). The reminder message contains information such as the patient's name, drug name, taking time and dosage, etc., to ensure that the patient can take the medicine on time.

[0071] The smoking cessation behavior monitoring module is used to regularly push a smoking cessation diary questionnaire or conduct a telephone follow-up with the patient according to a preset path, and collect and analyze the patient's smoking cessation behavior data. Among them, the questionnaire content includes the patient's smoking cessation days, changes in smoking amount, experience of withdrawal symptoms, etc. After the patient fills out the questionnaire, it is stored in the database. After preprocessing and analysis, it is found that the patient's smoking cessation days have increased in the past week, but the smoking amount still fluctuates, and mild withdrawal symptoms have occurred. Regularly pushing a smoking cessation diary questionnaire or conducting a telephone follow-up with the patient according to a preset path to monitor the patient's smoking cessation behavior in real time and collect relevant data helps the doctor to timely understand the patient's smoking cessation progress and problems encountered, so as to adjust the smoking cessation plan.

[0072] The smoking cessation plan matching module is used to match a personalized smoking cessation plan for the patient's current smoking cessation status from the smoking cessation treatment plan library according to a similarity algorithm. Based on the patient's current smoking cessation status, the most suitable personalized smoking cessation plan is accurately matched from the vast smoking cessation treatment plan library by using the similarity algorithm, fully considering the individual differences of the patient and the dynamic changes in the smoking cessation process, further improving the pertinence of the smoking cessation plan.

[0073] The plan review and confirmation module is used to conduct manual review and confirmation of the personalized smoking cessation plan for the patient's current smoking cessation status. Manual review allows for personalized adjustment of the smoking cessation plan. Each patient's smoking cessation process is unique and may encounter different problems and challenges. Through manual review, the plan can be fine-tuned according to the specific situation of the patient to ensure better meeting the actual needs of the patient. The manual review and confirmation process makes the patient feel more humanized care and professionalism. When the patient knows that the smoking cessation plan is formulated by professional doctors or reviewers after careful consideration, they are more likely to trust the plan and thus execute the smoking cessation plan more actively. In addition, it provides additional safety guarantees for the patient and reduces the risks that may arise due to an inappropriate plan.

[0074] The information push module is used to push the reviewed smoking cessation plan, relevant knowledge, questionnaires, and warning information to the patient according to the set nodes to assist the patient in implementing the smoking cessation plan. For example, after the patient sets a smoking cessation date, the system pushes a customized smoking cessation plan according to their personal situation and smoking cessation goals. The plan includes a smoking cessation schedule, drug use suggestions, diet adjustments, etc., to help the patient gradually reduce the amount of smoking and ultimately quit smoking. According to the patient's smoking cessation progress and interests, popular science articles and videos on the hazards of tobacco, benefits of smoking cessation, and smoking cessation techniques are pushed, which helps to enhance the patient's motivation and confidence in smoking cessation and at the same time provides practical smoking cessation methods and suggestions. At key nodes in the smoking cessation process, questionnaires are pushed to collect the patient's real-time data and feedback. The questionnaires include changes in the amount of smoking, feelings of withdrawal symptoms, psychological state assessment, etc., which helps the system understand the patient's smoking cessation progress and difficulties, so as to provide more accurate support and guidance. When the system detects that the patient may face the risk of relapse, warning information is pushed in a timely manner. The warning information includes encouraging words, coping suggestions, or prompts to contact professionals to help the patient overcome the temptation of relapse.

[0075] The smoking cessation behavior construction and trend analysis module is used to summarize smoking cessation behavior indicators, smoking craving, and withdrawal symptom evaluations in stages during the patient's smoking cessation process to construct a smoking cessation behavior dataset; and, conduct visual analysis on the patient's smoking cessation behavior trend to help patients and doctors understand the progress of smoking cessation. Automatically summarize the patient's smoking cessation behavior data and conduct preliminary analysis according to preset time nodes or smoking cessation stages to help patients and doctors understand the progress of smoking cessation. By comparing data from different stages, the difficulties in the patient's smoking cessation process can be identified. Present the patient's smoking cessation behavior trend in an intuitive way through line charts, bar charts, pie charts, etc. Doctors can quickly identify the patient's smoking cessation pattern, fluctuations, and potential risk points through visual analysis, so as to formulate more precise smoking cessation strategies.

[0076] The influencing factor analysis and personalized guidance module is used to analyze the influencing results of various factors on the patient's smoking cessation behavior according to the smoking cessation behavior influencing factor dataset; generate a personalized smoking cessation guidance plan for the patient according to the influencing results, and provide personalized smoking cessation suggestions for the patient.

[0077] In an optional manner, the automatically analyzing and generating a personalized smoking cessation treatment plan according to the tobacco dependence severity score result further includes:

[0078] Score the patient's tobacco dependence degree according to the smoking cessation dataset and the tobacco dependence scale to obtain a score result;

[0079] Generate a personalized smoking cessation treatment plan for the patient according to the score result;

[0080] Among them, for patients with mild tobacco dependence, a dry quitting treatment plan is recommended, and at the same time, psychological support and behavioral therapy auxiliary means of non-drug treatment are provided;

[0081] For patients with moderate to severe tobacco dependence, a comprehensive smoking cessation method combining drug treatment and psychological treatment is recommended. Among them, the treatment drugs include nicotine patches, nicotine chewing gum, and bupropion hydrochloride, and the psychological treatment includes cognitive behavioral therapy and motivational interviewing methods.

[0082] In this embodiment, through the smoking cessation dataset and the tobacco dependence scale, the patient's tobacco dependence degree can be comprehensively and objectively evaluated.

[0083] In an optional manner, the matching of a personalized smoking cessation plan for the patient's current smoking cessation status from the smoking cessation treatment plan library according to the similarity algorithm further includes:

[0084] Obtain the patient feature vector according to the patient's smoking cessation history information, and the smoking cessation history information includes age, gender, smoking years, daily smoking amount, number of attempts to quit smoking, and smoking cessation results;

[0085] Extract the features of each treatment plan in the smoking cessation treatment plan library to obtain a treatment plan feature vector, where the treatment plan includes treatment means, applicable age range, gender preference, and smoking years;

[0086] Calculate the similarity between the patient feature vector and each smoking cessation treatment plan feature vector, and select multiple smoking cessation treatment plans as candidate plans according to the similarity;

[0087] According to the patient's personal preferences and the accessibility of the treatment plan, select a personalized smoking cessation plan for the patient's current smoking cessation status from the candidate plans.

[0088] In this embodiment, by analyzing the smoking cessation history information of the patient to construct a patient feature vector and calculating the similarity with the treatment plan feature vector in the smoking cessation treatment plan library, a treatment plan that best matches the patient's current smoking cessation status can be accurately matched. For example, Zhang's feature vector: [40, male, 20, 20, 3, poor], the feature vector of the treatment plan: [30 - 50, male, 15 - 25, nicotine patch + bupropion hydrochloride]; Use the similarity algorithm to calculate the similarity between Zhang's feature vector and each treatment plan feature vector, and the similarity scores are: Plan A: 0.9, Plan B: 0.85, Plan C: 0.75. According to the similarity scores, select Plan A and Plan B as candidate plans. Zhang said that he has a higher preference for Plan A (nicotine patch + bupropion hydrochloride), and the accessibility of this plan is better.

[0089] In an optional manner, the smoking cessation behavior influencing factor data set includes physical factors, psychological factors, sociodemographic factors, smoking behavior factors, smoking behavior factors, and environmental factors;

[0090] Among them, physical factors include whether there are smoking-related diseases and smoking addiction;

[0091] Psychological factors include the patient's internal driving force for smoking cessation, the patient's understanding of the harms of smoking and the benefits of smoking cessation, the patient's confidence in being able to successfully quit smoking, the impact of anxiety and depression on smoking cessation behavior, and personality traits; among them, the patient's internal driving force for smoking cessation includes health concerns, economic concerns, family pressure, social recognition and image, self-improvement and growth, improvement of quality of life, spiritual and psychological needs, and personal beliefs and values; personality traits include impulsivity and self-discipline;

[0092] Sociodemographic factors include gender, age, education level, and economic status;

[0093] Smoking behavior factors include smoking years, daily smoking amount, and smoking pattern;

[0094] Environmental factors include family, work environment, and social pressure.

[0095] In this embodiment, the effectiveness of smoking cessation intervention measures is objectively evaluated through quantitative indicators (such as the amount of smoking, anxiety level, self-efficacy, etc.). By collecting longitudinal data (such as tracking the long-term situation of participants after quitting smoking), the long-term influencing factors of smoking cessation behavior can be studied more deeply.

[0096] Specifically, a structured questionnaire is used in the questionnaire survey to collect data on the physical condition, mental state, sociodemographic information, smoking behavior, and environmental factors of the participants. The biological index detection includes measuring biological indexes related to smoking, such as blood lipids, blood pressure, lung function, etc., to objectively evaluate the physical condition. The collected data is sorted out to establish a dataset of influencing factors for smoking cessation behavior. The data in the dataset is mined to discover the key factors and rules affecting smoking cessation behavior. According to the analysis results and the specific situation of the patient, a personalized smoking cessation plan is formulated. The smoking cessation plan includes content such as smoking cessation goals, smoking cessation methods, smoking cessation schedule, and monitoring indicators. The dataset of influencing factors for the smoking cessation behavior of Patient A is shown in Table 1:

[0097] Table 1

[0098]

[0099]

[0100] Based on the dataset of this patient, the following personalized smoking cessation plan can be formulated:

[0101] Goal setting: Achieve complete smoking cessation within 6 months. Smoking cessation method: Use nicotine replacement therapy (such as nicotine patches) to relieve withdrawal symptoms, and at the same time combine psychological counseling and behavioral therapy to improve the confidence in smoking cessation. Schedule: The first month is the smoking cessation preparation stage, including understanding smoking cessation knowledge, formulating a smoking cessation plan, etc.; the second to third months are the smoking cessation implementation stage, gradually reducing the amount of smoking until complete smoking cessation; the fourth to sixth months are the consolidation stage to prevent relapse. Monitoring indicators: Include the daily smoking amount, changes in anxiety and depression emotions, improvement of physical condition, etc. Monitor and evaluate the progress of the patient's smoking cessation. If it is found that the patient shows a tendency to relapse or has large mood swings, adjust the smoking cessation plan in a timely manner and increase intervention measures such as psychological support and behavioral therapy.

[0102] In an alternative manner, the further analysis of the influence of each factor on the patient's smoking cessation behavior based on the dataset of influencing factors for smoking cessation behavior includes:

[0103] Analyze the combined influence of multiple influencing factors for smoking cessation behavior on the smoking cessation success rate through a multiple linear regression model;

[0104] Evaluate the smoking cessation success probability of the patient through a Cox proportional hazards model based on the combined influence of multiple influencing factors for smoking cessation behavior on the smoking cessation success rate.

[0105] In this embodiment, the multiple linear regression model simultaneously considers multiple influencing factors of smoking cessation behavior, such as age, gender, number of cigarettes smoked per day, carbon monoxide (CO) concentration, etc., so as to more comprehensively evaluate the combined influence of these factors on the smoking cessation success rate, and can predict the smoking cessation success rate under different combinations of factors. The Cox proportional hazards model considers the influence of time factors on the smoking cessation success rate and evaluates the probability of smoking cessation success of patients in different time periods.

[0106] Specifically, the smoking cessation success rate is selected as the dependent variable, and multiple influencing factors of smoking cessation behavior are used as independent variables for multiple linear regression analysis to obtain the regression equation and coefficients. According to the regression equation and coefficients, the combined influence of each factor on the smoking cessation success rate is evaluated. The smoking cessation success (or failure) is selected as the event endpoint, and multiple influencing factors of smoking cessation behavior are used as covariates for Cox proportional hazards regression analysis to obtain the hazard ratio (HR) and 95% confidence interval. According to the HR and confidence interval, the influence degree of each factor on the smoking cessation success risk is evaluated. According to the results of the multiple linear regression model and the Cox proportional hazards model, the influence of each factor on the smoking cessation success rate and risk is explained.

[0107] For example, through the analysis of the multiple linear regression model, it is found that age, number of cigarettes smoked per day, and CO concentration have a significant impact on the smoking cessation success rate. That is, the higher the age, the more cigarettes smoked per day, and the higher the CO concentration of the patient, the lower the smoking cessation success rate. Using the Cox proportional hazards model to further evaluate the influence of these factors on the smoking cessation success risk, for every 10-year increase in age, the smoking cessation success risk is reduced by about 20%; for every 10-cigarette increase in the number of cigarettes smoked per day, the smoking cessation success risk is increased by about 30%; for every 1-unit increase in the CO concentration, the smoking cessation success risk is increased by about 15%. For patients with older age, more cigarettes smoked per day, and higher CO concentration, it is recommended to use smoking cessation drugs, receive psychological counseling, etc. to improve the smoking cessation success rate.

[0108] In an alternative way, the further step of analyzing the combined influence of multiple influencing factors of smoking cessation behavior on the smoking cessation success rate by the multiple linear regression model includes:

[0109] Construct a multiple linear regression model based on multiple influencing factors of smoking cessation behavior and the smoking cessation success rate;

[0110] Estimate the regression coefficients according to the least squares method, calculate the standardized regression coefficients of each influencing factor of smoking cessation behavior, and evaluate the relative contribution of each influencing factor of smoking cessation behavior to the smoking cessation success rate.

[0111] In this embodiment, the number of days of smoking cessation is used as an indicator of the success rate of smoking cessation, and age, gender (converted into a binary variable), the number of cigarettes smoked per day, and the adjusted CO concentration are used as independent variables. A multiple linear regression model is established, the regression coefficients are estimated according to the least squares method, and the standardized regression coefficients of various influencing factors of smoking cessation behavior are calculated to evaluate the relative contributions of various influencing factors of smoking cessation behavior to the success rate of smoking cessation.

[0112] In an alternative approach, the multiple linear regression model is:

[0113]

[0114] where y is the success rate of smoking cessation; β0, β i , β ii , β iii are regression coefficients respectively; X i is the i-th influencing factor of smoking cessation behavior; ∈ is the error term.

[0115] In this embodiment, adding a logarithmic term to the multiple linear regression model can handle skewed distribution of predictor variables, help stabilize the variance, and can more comprehensively evaluate the effects of various factors on the success rate of smoking cessation, including direct effects and indirect effects.

[0116] In an alternative approach, the further steps of evaluating the success probability of a patient's smoking cessation by the Cox proportional hazards model include:

[0117] Construct a Cox proportional hazards model based on the multiple linear regression model, and the Cox proportional hazards model is:

[0118] h(t|X) = h0(t)exp(y)

[0119] where h(t|X) is the risk rate of smoking cessation failure given the influencing factor X at time t; h0(t) is the baseline risk rate function;

[0120] Estimate the regression coefficients of the multiple linear regression model by the maximum partial likelihood estimation method;

[0121] Calculate the success probability of the patient's smoking cessation according to the estimated regression coefficients.

[0122] In this embodiment, the Cox model takes into account the influence of time factors on the success probability of smoking cessation, that is, at different time points, the same influencing factor has different effects on the success probability of smoking cessation, and can estimate the relative risk (HR) of each influencing factor, that is, the degree of influence of a certain influencing factor on the risk of smoking cessation failure of the patient.

[0123] For example, the Cox proportional hazards model is h(t|X) = h0(t)exp(β1 age + β2 gender + β3 smoking history).

[0124] The regression coefficients β1, β2, and β3 are estimated using the maximum partial likelihood estimation method. Suppose it is calculated that β1 = -0.02 (for every 1-year increase in age, the risk of smoking cessation failure decreases by 2%), β2 = 0.5 (for males compared to females, the risk of smoking cessation failure increases by 50%), and β3 = 0.3 (for every 1-year increase in smoking history, the risk of smoking cessation failure increases by 3%).

[0125] For a 40-year-old male patient with a 10-year smoking history, the risk rate of smoking cessation failure in the intervention group is h(t|X) = h0(t)exp(-0.02×40 + 0.5 + 0.3×10). The baseline risk rate function h0(t) is estimated from the sample data, and then the risk rate of smoking cessation failure for this patient at different time points can be calculated. Furthermore, the probability of successful smoking cessation for this patient can be calculated, such as P(success) = 1 - h(t|X).

[0126] In an alternative approach, the estimation formula for the baseline risk rate function h0(t) is:

[0127]

[0128] where d t is the number of smoking cessation relapses that occurred within time t; n is the number of individuals still under observation within time t; X ti is the covariate vector of the i-th individual within time t; is the mean of X ti ; and β i is the regression coefficient.

[0129] In this embodiment, by considering the covariate vector of each individual, the estimation of the baseline risk rate is more personalized and can more accurately reflect the risk of smoking cessation failure for different individuals at specific time points. By continuously updating the number of smoking cessation relapses that occurred within time t and the number of individuals still under observation, the baseline risk rate can be dynamically adjusted. For example, assume that on the 30th day, 10 smokers had smoking cessation relapses, i.e., d t = 10. At this time, the number of individuals still under observation n = 100 (assuming no loss to follow-up or withdrawal). Calculate the covariate vector X ti for each individual and its mean Substitute the above data into the formula to calculate the baseline risk rate h0(30) on the 30th day.

[0130] The solution provided by the present invention includes: a smoking cessation dataset construction module for collecting and integrating demographic information, smoking status, smoking motivation, smoking cessation attempt history, health status, and pulmonary function test results to form a smoking cessation dataset; a smoking cessation treatment plan generation module for automatically analyzing and generating a personalized smoking cessation treatment plan based on the tobacco dependence severity score; a doctor-patient interaction and information push module for realizing information interaction between doctors and patients through a server and a client; generating and pushing information on the smoking cessation drug taking time according to the patient's smoking cessation date, ensuring that medication reminders are sent to the patient regularly and at fixed points during the medication period to improve medication compliance; a smoking cessation behavior monitoring module for regularly pushing a smoking cessation diary questionnaire or conducting a telephone follow-up with the patient according to a preset path, collecting and analyzing the patient's smoking cessation behavior data; a smoking cessation plan matching module for matching a personalized smoking cessation plan for the patient's current smoking cessation status from a smoking cessation treatment plan library according to a similarity algorithm; a plan review and confirmation module for manually reviewing and confirming the personalized smoking cessation plan for the patient's current smoking cessation status; an information push module for pushing the reviewed smoking cessation plan, relevant knowledge, questionnaires, and warning information to the patient according to set nodes to assist the patient in implementing the smoking cessation plan; a smoking cessation behavior construction and trend analysis module for summarizing smoking cessation behavior indicators, smoking craving, and withdrawal symptom evaluations in stages during the patient's smoking cessation process to construct a smoking cessation behavior dataset; and visually analyzing the patient's smoking cessation behavior trend to help the patient and the doctor understand the smoking cessation progress; an influencing factor analysis and personalized guidance module for analyzing the influence results of each factor on the patient's smoking cessation behavior according to a smoking cessation behavior influencing factor dataset; generating a personalized smoking cessation guidance plan for the patient according to the influence results and providing personalized smoking cessation suggestions for the patient. By integrating multi-dimensional data such as the patient's personal information, smoking status, and health status, the present invention automatically generates a personalized smoking cessation treatment plan, and improves the patient's medication compliance and smoking cessation success rate through doctor-patient interaction, information push, etc. At the same time, by deeply analyzing the influencing factors of smoking cessation behavior, customized smoking cessation suggestions are provided for the patient, further improving the patient's smoking cessation success rate.

[0131] Figure 2 FIG. shows the structural schematic diagram of an embodiment of a computing device according to the present invention. The specific implementation of the computing device in the specific embodiment of the present invention is not limited.

[0132] As Figure 2 shown, the computing device may include: a processor 202, a communications interface 204, a memory 206, and a communication bus 208.

[0133] Among them: The processor 202, the communication interface 204, and the memory 206 communicate with each other through the communication bus 208. The communication interface 204 is used to communicate with network elements of other devices such as clients or other servers. The processor 202 is used to execute the program 210, and specifically can execute the relevant steps in the above-mentioned evaluation system embodiments based on the multi-dimensional smoking cessation management model.

[0134] Specifically, the program 210 may include program code, and the program code includes computer operation instructions.

[0135] The processor 202 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. One or more processors included in the computing device may be of the same type of processor, such as one or more CPUs; or may be of different types of processors, such as one or more CPUs and one or more ASICs.

[0136] The memory 206 is used to store the program 210. The memory 206 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0137] The solution provided by the present invention includes: a smoking cessation dataset construction module, which is used to collect and integrate demographic information, smoking status, smoking motivation, smoking cessation attempt history, health status, and pulmonary function test results to form a smoking cessation dataset; a smoking cessation treatment plan generation module, which is used to automatically analyze and generate a personalized smoking cessation treatment plan according to the results of the tobacco dependence severity score; a doctor-patient interaction and information push module, which is used to realize information interaction between doctors and patients through a server and a client; generate and push information on the smoking cessation medication taking time according to the patient's smoking cessation date, and ensure that medication reminders are sent to the patient regularly and at fixed points during the medication period to improve medication compliance; a smoking cessation behavior monitoring module, which is used to regularly push a smoking cessation diary questionnaire or conduct a telephone follow-up on the patient according to a preset path, and collect and analyze the patient's smoking cessation behavior data; a smoking cessation plan matching module, which is used to match a personalized smoking cessation plan for the patient's current smoking cessation status from a smoking cessation treatment plan library according to a similarity algorithm; a plan review and confirmation module, which is used to manually review and confirm the personalized smoking cessation plan for the patient's current smoking cessation status; an information push module, which is used to push the reviewed smoking cessation plan, relevant knowledge, questionnaires, and warning information to the patient according to set nodes to assist the patient in implementing the smoking cessation plan; a smoking cessation behavior construction and trend analysis module, which is used to summarize smoking cessation behavior indicators, smoking craving, and withdrawal symptom evaluations in stages during the patient's smoking cessation process to construct a smoking cessation behavior dataset; and visually analyze the patient's smoking cessation behavior trend to help the patient and the doctor understand the smoking cessation progress; an influencing factor analysis and personalized guidance module, which is used to analyze the influence results of various factors on the patient's smoking cessation behavior according to a smoking cessation behavior influencing factor dataset; generate a personalized smoking cessation guidance plan for the patient according to the influence results, and provide personalized smoking cessation suggestions for the patient. By integrating multi-dimensional data such as the patient's personal information, smoking status, and health status, the present invention automatically generates a personalized smoking cessation treatment plan, and improves the patient's medication compliance and smoking cessation success rate through doctor-patient interaction, information push, etc. At the same time, by deeply analyzing the influencing factors of smoking cessation behavior, tailored smoking cessation suggestions are provided for the patient, further improving the patient's smoking cessation success rate.

[0138] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and arranged in one or more devices different from that of the embodiment. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be adopted to combine all the features disclosed in this specification (including the accompanying claims, abstract and drawings), and all the processes or units of any method or device so disclosed. Unless otherwise explicitly stated, each feature disclosed in this specification (including the accompanying claims, abstract and drawings) can be replaced by an alternative feature that provides the same, equivalent or similar purpose. In addition, those skilled in the art can understand that although some of the embodiments herein include certain features included in other embodiments rather than other features, the combination of the features of different embodiments means that it is within the scope of the present invention and forms different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination. The present invention can be implemented by means of hardware including several different elements and by means of a properly programmed computer. In the unit claims listing several devices, several of these devices can be embodied by the same hardware item. The steps in the above embodiments, unless otherwise specified, should not be construed as a limitation on the execution order.

Claims

1. An evaluation system based on a multi-dimensional smoking cessation management model, characterized in that, Including: A smoking cessation dataset construction module, which is used to collect and integrate demographic information, smoking status, smoking motivation, smoking cessation attempt history, health status, and pulmonary function test results to form a smoking cessation dataset; A smoking cessation treatment plan generation module, which is used to automatically analyze and generate a personalized smoking cessation treatment plan according to the tobacco dependence severity score results; A doctor-patient interaction and information push module, which is used to realize information interaction between doctors and patients through a server and a client; generate and push smoking cessation drug taking time information according to the patient's smoking cessation date, and ensure that medication reminders are sent to the patient regularly and at fixed points during the medication period to improve medication compliance; A smoking cessation behavior monitoring module, which is used to regularly push a smoking cessation diary questionnaire or telephone follow-up to the patient according to a preset path, and collect and analyze the patient's smoking cessation behavior data; A smoking cessation plan matching module, which is used to match a personalized smoking cessation plan for the patient's current smoking cessation status from a smoking cessation treatment plan library according to a similarity algorithm; A plan review and confirmation module, which is used to manually review and confirm the personalized smoking cessation plan for the patient's current smoking cessation status; An information push module, which is used to push the reviewed smoking cessation plan, relevant knowledge, questionnaires, and warning information to the patient according to the set nodes to assist the patient in implementing the smoking cessation plan; A smoking cessation behavior construction and trend analysis module, which is used to summarize smoking cessation behavior indicators, smoking craving, and withdrawal symptom evaluations in stages during the patient's smoking cessation process to construct a smoking cessation behavior dataset; and, perform visual analysis on the patient's smoking cessation behavior trend to help the patient and doctor understand the smoking cessation progress; An influencing factor analysis and personalized guidance module, which is used to analyze the influence results of each factor on the patient's smoking cessation behavior according to the smoking cessation behavior influencing factor dataset; generate a personalized smoking cessation guidance plan for the patient and provide personalized smoking cessation suggestions for the patient.

2. The evaluation system based on the multi-dimensional smoking cessation management model according to claim 1, characterized in that, The automatically analyzing and generating a personalized smoking cessation treatment plan according to the tobacco dependence severity score results further includes: Scoring the patient's tobacco dependence degree according to the smoking cessation dataset and the tobacco dependence scale to obtain a scoring result; Generating a personalized smoking cessation treatment plan for the patient according to the scoring result; Among them, for patients with mild tobacco dependence, a dry quitting treatment plan is recommended, and at the same time, psychological support and behavioral therapy auxiliary means of non-drug treatment are provided; For patients with moderate to severe tobacco dependence, a comprehensive smoking cessation method combining drug treatment and psychological treatment is recommended. Among them, the treatment drugs include nicotine patches, nicotine chewing gum, and bupropion hydrochloride, and the psychological treatment includes cognitive behavioral therapy and motivational interviewing methods.

3. The evaluation system based on the multi-dimensional smoking cessation management model according to claim 1, characterized in that, The matching of a personalized smoking cessation plan for the patient's current smoking cessation status from the smoking cessation treatment plan library according to the similarity algorithm further includes: Obtaining a patient feature vector according to the patient's smoking cessation history information, where the smoking cessation history information includes age, gender, smoking years, daily smoking amount, number of attempts to quit smoking, and smoking cessation results; Extracting the features of each treatment plan in the smoking cessation treatment plan library to obtain a treatment plan feature vector, where the treatment plan includes treatment means, applicable age range, gender preference, and smoking years; Calculate the similarity between the patient feature vector and the feature vectors of each smoking cessation treatment plan, and select multiple smoking cessation treatment plans as candidate plans according to the similarity; According to the patient's personal preferences and the accessibility of the treatment plans, select a personalized smoking cessation plan for the patient's current smoking cessation status from the candidate plans.

4. The evaluation system based on the multi-dimensional smoking cessation management model according to claim 1, characterized in that The smoking behavior influencing factor dataset includes physical factors, psychological factors, sociodemographic factors, smoking behavior factors, and environmental factors; Among them, physical factors include whether suffering from smoking-related diseases and smoking addiction; Psychological factors include the patient's internal driving force for smoking cessation, the patient's understanding of the harms of smoking and the benefits of smoking cessation, the patient's confidence in being able to successfully quit smoking, the impact of anxiety and depression on smoking cessation behavior, and personality traits; among them, the patient's internal driving force for smoking cessation includes health concerns, economic concerns, family pressure, social recognition and image, self-improvement and growth, improvement of quality of life, spiritual and psychological needs, and personal beliefs and values; personality traits include impulsivity and self-discipline; Sociodemographic factors include gender, age, education level, and economic status; Smoking behavior factors include smoking years, daily smoking amount, and smoking pattern; Environmental factors include family, work environment, and social pressure.

5. The evaluation system based on the multi-dimensional smoking cessation management model according to claim 4, wherein The further analysis of the impact of each factor on the patient's smoking cessation behavior based on the smoking behavior influencing factor dataset includes: Analyze the combined impact of multiple smoking behavior influencing factors on the smoking cessation success rate through a multiple linear regression model; According to the combined impact of multiple smoking behavior influencing factors on the smoking cessation success rate, evaluate the patient's smoking cessation success probability through a Cox proportional hazards model.

6. The evaluation system based on the multi-dimensional smoking cessation management model according to claim 5, wherein The further analysis of the combined impact of multiple smoking behavior influencing factors on the smoking cessation success rate through a multiple linear regression model includes: Construct a multiple linear regression model according to multiple smoking behavior influencing factors and the smoking cessation success rate; Estimate the regression coefficients according to the least squares method, calculate the standardized regression coefficients of each smoking behavior influencing factor, and evaluate the relative contribution of each smoking behavior influencing factor to the smoking cessation success rate.

7. The evaluation system based on the multi-dimensional smoking cessation management model according to claim 6, characterized in that, The multiple linear regression model is: Among them, y is the smoking cessation success rate; β0, β i , β ii , β iii are regression coefficients; X i is the i-th influencing factor of smoking cessation behavior; ∈ is the error term.

8. The evaluation system based on the multi-dimensional smoking cessation management model according to claim 7, wherein, The further evaluation of the patient's smoking cessation success probability through a Cox proportional hazards model includes: Construct a Cox proportional hazards model according to the multiple linear regression model, and the Cox proportional hazards model is: h(t|X) = h0(t)exp(y) Where, h(t|X) is the smoking cessation failure risk rate at time t given the influencing factor X; h0(t) is the baseline risk rate function; Estimate the regression coefficients of the multiple linear regression model through the maximum partial likelihood estimation method; Calculate the patient's smoking cessation success probability according to the estimated regression coefficients.

9. The evaluation system based on the multi-dimensional smoking cessation management model according to claim 8, characterized in that The estimation formula for the baseline risk rate function h0(t) is: where d t is the number of smoking relapse during time t; n is the number of individuals still under observation during time t; X ti is the covariate vector of the i-th individual during time t; is the mean of X ti ; β i is the regression coefficient.

10. A computing device, comprising: A processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface complete communication with each other through the communication bus; The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the operations corresponding to the above-mentioned evaluation system based on the multi-dimensional smoking cessation management model.

Images