A method and system for following up urology patients

Abstract

The embodiment of the specification provides a method for following up on a urology patient, comprising: a doctor client obtaining a medical label set by a doctor of a first account for a patient of a second account. According to the medical label, a plurality of follow-up templates corresponding to a plurality of combinations of diseases and treatment stages of urology are obtained from a plurality of follow-up templates of urology, wherein the plurality of diseases at least include cystitis, prostatitis and prostate cancer. A follow-up intelligent agent obtains a first follow-up template determined by the doctor according to the plurality of follow-up templates, and sends the first follow-up template to a patient client corresponding to the second account. The follow-up intelligent agent associates the first follow-up plan with the first account in response to a first message containing the first follow-up plan sent by the patient client.

Description

Technical Field

[0001] This specification relates to the field of computer technology, and more particularly to a method and system for follow-up of urology patients. Background Technology

[0002] In the clinical management of chronic diseases, follow-up is an indispensable and crucial step in assessing treatment effectiveness, monitoring disease progression, and improving patients' long-term quality of life. Follow-up refers to the systematic process by which healthcare professionals, after a patient completes primary treatment (e.g., surgery, radiotherapy, chemotherapy, or endocrine therapy), continuously track the patient's health status, disease-related indicators, and quality of life through regular, planned checkups, communication, and guidance. Effective follow-up can detect early signs of disease recurrence or metastasis, intervene promptly in treatment-related side effects, and provide patients with necessary psychological and rehabilitation support, thus extending one-time in-hospital treatment into comprehensive health management for the entire patient lifecycle.

[0003] Urinary system diseases encompass a wide range of types, including malignant tumors, chronic benign diseases, and congenital diseases. Due to the diverse characteristics of these diseases and the varied needs of diagnosis and treatment, systematic follow-up is of great importance to patients. Firstly, urinary system diseases typically have a long onset period and slow progression, with some patients remaining at low risk for extended periods. Active monitoring rather than radical treatment is more suitable for these patients, requiring physicians to conduct long-term and regular monitoring to promptly identify key inflection points in disease progression. Secondly, the main treatments for urinary system diseases (e.g., radical cancer resection, radiotherapy, endocrine therapy) may cause long-term or delayed side effects (e.g., urinary incontinence, osteoporosis, metabolic syndrome), necessitating continuous monitoring and intervention. Furthermore, the dynamic trends in prostate-specific antigen (PSA), complete blood count, and testosterone levels, which are highly correlated with urinary system diseases, are important indicators for monitoring disease progression and require regular testing and analysis. Therefore, establishing and implementing a standardized and continuous follow-up plan between doctors and patients has irreplaceable clinical value for urology patients to achieve early intervention of the disease, improve their quality of life, and reduce their psychological burden.

[0004] Currently, follow-up practices for urology patients primarily rely on a traditional offline model, which is entirely doctor-led and lacks a standardized, intelligent follow-up management system. During follow-up, doctors typically need to proactively contact patients via phone or text message to remind them to attend their in-person appointments. After completing various tests at the hospital, patients are required to keep paper copies of their test reports, which are then collected by the doctor during the in-person appointment. Simultaneously, doctors need to manually organize and analyze the scattered test data and patient complaints based on their clinical experience to assess the patient's disease progression.

[0005] However, in the traditional offline follow-up process, on the one hand, there is a lack of a systematic online data flow and integration mechanism, which makes it impossible to systematically integrate the various test data of urology patients; on the other hand, doctors need to invest a lot of manpower to promote the implementation of the follow-up plan, which is prone to conflict with daily diagnosis and treatment work, resulting in follow-up delays and affecting the follow-up effect.

[0006] Therefore, we hope to provide a solution that utilizes technology to build an automated and intelligent follow-up management system for urology patients. This system would automate the generation of follow-up plans and the collection of test data, thereby improving the efficiency and quality of follow-up care for urology patients, reducing the human resource investment required by doctors during the follow-up process, improving the patient's follow-up experience, and increasing patient compliance. Summary of the Invention

[0007] This specification describes one or more embodiments of a method and system for follow-up of urology patients, which can solve the above-mentioned technical problems and bring about the above-mentioned beneficial effects.

[0008] According to the first aspect, a method for follow-up of urology patients is provided, including:

[0009] The doctor's client obtains the medical tags set by the doctor of the first account for the patient of the second account. The medical tags indicate the combination of the patient's urological condition and the current stage of treatment.

[0010] Based on the medical tag, several follow-up templates are obtained from multiple follow-up templates in the urology department, wherein the multiple follow-up templates correspond to a combination of multiple urological diseases and multiple treatment stages; the matching degree between the multiple follow-up templates and the medical tag is higher than a preset threshold; the multiple diseases include at least: cystitis, prostatitis, and prostate cancer.

[0011] The follow-up agent obtains the first follow-up template determined by the doctor based on the plurality of follow-up templates, and sends the first follow-up template to the patient client corresponding to the second account; the first follow-up template includes multiple follow-up tasks, each follow-up task requires the patient to submit corresponding follow-up data, the follow-up data includes a description of symptoms related to urination, and test data corresponding to several test items, the test data including at least one of the following: prostate-specific antigen PSA, complete blood count, testosterone.

[0012] The follow-up agent responds to a first message containing a first follow-up plan sent by the patient client and associates the first follow-up plan with a first account; the first follow-up plan is generated by the patient client based on a first follow-up template and first-time information provided by the patient.

[0013] According to the second aspect, a system for follow-up of urology patients is provided, comprising:

[0014] The doctor client is configured to retrieve medical tags set by the doctor of the first account for the patient of the second account, wherein the medical tags indicate the combination of the patient's urological condition and the current stage of treatment.

[0015] The acquisition module is configured to acquire several follow-up templates from multiple follow-up templates in the urology department based on the medical tag, wherein the multiple follow-up templates correspond to a combination of multiple urological diseases and multiple treatment stages; the matching degree between the multiple follow-up templates and the medical tag is higher than a preset threshold; the multiple diseases include at least: cystitis, prostatitis, and prostate cancer.

[0016] The follow-up intelligent agent is configured to obtain a first follow-up template determined by the doctor based on the plurality of follow-up templates, and send the first follow-up template to the patient client corresponding to the second account; the first follow-up template includes multiple follow-up tasks, each follow-up task requires the patient to submit corresponding follow-up data, the follow-up data includes a description of urination-related symptoms, and test data corresponding to several test items, the test data including at least one of the following: prostate-specific antigen PSA, complete blood count, and testosterone.

[0017] The follow-up intelligent agent is further configured to associate the first follow-up plan with a first account in response to a first message containing the first follow-up plan sent by the patient client; the first follow-up plan is generated by the patient client based on the first follow-up template and the first time information provided by the patient.

[0018] According to a third aspect, a computer program product is provided, including a computer program / instructions that, when executed by a processor, implement the steps of the method described in the first aspect.

[0019] According to a fourth aspect, a computing device is provided, including a memory and a processor, characterized in that the memory stores executable code, and when the processor executes the executable code, it implements the method described in the first aspect.

[0020] In summary, the embodiments of this specification provide a method for follow-up of urology patients. This method enables the construction of an automated and intelligent follow-up management system for urology patients. Based on the medical tags set by the doctor for the patient, it intelligently recommends follow-up templates and generates personalized follow-up plans based on the patient's confirmation of the templates. This achieves automated generation of follow-up plans and automated collection of test data, thereby improving the efficiency and quality of follow-up for urology patients, reducing the doctor's manpower input during the follow-up process, improving the patient's follow-up experience, and increasing patient compliance. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0022] Figure 1 This is an implementation framework for a method for following up urology patients according to embodiments of this specification;

[0023] Figure 2 This is a flowchart illustrating a method for follow-up of urology patients according to embodiments of this specification.

[0024] Figure 3A This is an exemplary flowchart for establishing a doctor-patient relationship according to an embodiment of this specification;

[0025] Figure 3B This is an exemplary flowchart of setting a medical label according to an embodiment of this specification;

[0026] Figure 3C This is an illustrative scenario for confirming a follow-up template provided in the embodiments of this specification;

[0027] Figure 4A This is an illustrative scenario for a patient confirmation follow-up plan provided according to the embodiments of this specification;

[0028] Figure 4B This is an exemplary scenario for generating task prompts according to the embodiments provided in this specification;

[0029] Figure 4C This is an exemplary scenario for generating prompt information according to the embodiments provided in this specification;

[0030] Figure 5 This is a schematic diagram of a system for follow-up of urology patients according to an embodiment of this specification. Detailed Implementation

[0031] The solutions provided in the embodiments of this specification will now be described with reference to the accompanying drawings.

[0032] As mentioned earlier, although the need for standardized follow-up in clinical practice is increasingly urgent, the inherent defects of the offline follow-up model in relevant practices have become a bottleneck restricting the improvement of the quality of urology's full-course patient management. The fragmentation of data flow leads to delays and biases in doctors' assessments of patients' conditions; and the excessive consumption of doctors' human resources makes it difficult to implement follow-up plans for patients, affecting the quality of patients' prognosis.

[0033] In view of this, the inventors have proposed a method for follow-up of urology patients in the embodiments of this specification. Figure 1 The implementation architecture of this method is shown.

[0034] See Figure 1 Each doctor and patient holds an account (for clarity, the first account represents the doctor's account, and the second account represents the patient's account). The account refers to a registered identity identifier in the relevant terminal system using the methods described in this specification. In practical applications, this system can be deployed as a unified integrated platform or as interconnected doctor-side diagnosis and treatment systems (doctor clients) and patient-side health management systems (patient clients). In some application scenarios, doctors can handle diagnosis and treatment tasks from multiple departments. They can create multiple avatars in the doctor client, each corresponding to an independent account, to meet the doctor's follow-up management needs under multiple roles. It should also be noted that, normally, the doctor and patient are not the same entity, and they hold independent accounts (i.e., the first account and the second account are different); however, in some practices, such as self-diagnosis scenarios where the patient is also the attending physician, Figure 1 The accounts held by the doctor and patient shown may also be the same account. This embodiment of the specification does not specifically limit this.

[0035] Continue reading Figure 1 Taking the first follow-up template as an example, it can contain several follow-up tasks, each of which can be used to collect follow-up data submitted by the patient. Follow-up data may include descriptions of urination-related symptoms and corresponding test data for each of the several test items. As the patient performs follow-up tasks and submits relevant follow-up data, the symptom descriptions and the test data for each test item are filled in sequentially. In this implementation framework, a follow-up agent is also instantiated, which can be implemented, for example, based on a Large Language Model (LLM).

[0036] Figure 1 The implementation framework shown can be understood in two phases.

[0037] In the first phase, the initial follow-up template can be determined. (See also...) Figure 1 The doctor's client can obtain the medical tags set by the doctor for the patient (i.e., the second account), and based on these medical tags, retrieve several follow-up templates from a pool of urology follow-up templates. The method for obtaining the follow-up templates will be described in the following embodiments and will not be elaborated upon here. The doctor can select and determine the first follow-up template suitable for the patient from among the several follow-up templates. The follow-up agent can then send the first follow-up template to the patient's client corresponding to the patient's second account.

[0038] In the second phase, the first follow-up plan for each patient can be instantiated based on the first follow-up template. See [link / reference] Figure 1 The patient logs into the patient client using a second account, where they can view the first follow-up template selected by the doctor and provide the necessary time information (i.e., first time information) for the first follow-up template. This time information can be the date of the patient's first treatment, serving as the start date of the follow-up plan, or it can be a start date set by the patient according to their personal preferences, etc. Based on the first follow-up template and the first time information, the patient client instantiates and generates a first follow-up plan corresponding to the patient, and encapsulates the first follow-up plan as a first message, sending it to the follow-up agent. The follow-up agent can then associate the first follow-up plan with the first account, allowing the doctor using the first account to view the first follow-up plan in their doctor client.

[0039] The above, with reference to the accompanying diagram, briefly describes the implementation framework of a method for follow-up of urology patients. It is important to understand that... Figure 1 The number of follow-up tasks, the detection items included in the follow-up data, and the number of corresponding detection data in the follow-up template shown are only for illustrative purposes and are not intended to be limiting. In practical applications, they can be flexibly set according to needs.

[0040] Based on the above technical framework Figure 2 A flowchart illustrating a method for follow-up of urology patients according to embodiments of this specification is shown. It is understood that the methods disclosed in the embodiments of this specification can be executed by any device, apparatus, platform, or cluster of devices with computing and processing capabilities. See also... Figure 2In one embodiment, the method includes at least the following steps: S201: The doctor client obtains a medical tag set by the doctor of the first account for a patient of the second account, the medical tag indicating a combination of the patient's urological condition and the current stage of treatment. S203: Based on the medical tag, a plurality of follow-up templates are obtained from multiple urological follow-up templates. S205: The follow-up agent obtains a first follow-up template determined by the doctor based on the plurality of follow-up templates, and sends the first follow-up template to the patient client corresponding to the second account. S207: In response to a first message containing a first follow-up plan sent by the patient client, the follow-up agent associates the first follow-up plan with the first account; the first follow-up plan is generated by the patient client based on the first follow-up template and first-time information provided by the patient.

[0041] The following section will implement the framework based on the methods introduced above, and will further elaborate on... Figure 2 The various method steps in the illustrated embodiments are explained in detail.

[0042] First, in step S201, the doctor client obtains the medical tags set by the doctor of the first account for the patient of the second account. The medical tags indicate the combination of the patient's urological condition and the current stage of treatment.

[0043] During in-person consultations, patients can establish a doctor-patient relationship by having the doctor enter the patient's second account information into the doctor's client application or by sending an electronic invitation to the patient's second account. Once the patient becomes a managed patient under the doctor's name, the patient is associated with the doctor's first account in the system. In one specific practice, the patient can log in to the patient client using their second account and scan a QR code associated with the doctor's first account. The patient client will then display a dialog box confirming the establishment of the doctor-patient relationship. After the patient confirms, their second account will be added to the patient queue corresponding to the doctor's first account, becoming one of the patients the doctor is responsible for following up with. In other words, the second account is associated with the first account. After the doctor and patient successfully establish a doctor-patient relationship, the doctor can log in to the doctor's client using their first account to view the patient's basic information, medical history, and current follow-up status, and develop a personalized follow-up plan.

[0044] Figure 3AThe diagram illustrates an exemplary flowchart for establishing a doctor-patient relationship. The patient can log in to the patient client using their secondary account, scan a QR code associated with the doctor's primary account, and confirm joining the doctor's follow-up management. After patient confirmation, the doctor can log in to the doctor client using their primary account to view the patient's information (including but not limited to basic information, disease symptoms, and uploaded documents). The doctor can also confirm the medical team receiving the patient within the doctor client. When the doctor clicks the "Accept" button, the patient's secondary account is linked to the primary account.

[0045] In one embodiment, doctors can assign medical tags to patients based on their medical record data, which may include symptom descriptions and test results. For example, for a patient undergoing prostate cancer surgery, a doctor could assign a medical tag of "Prostate Cancer - Post-operative - PSA Monitoring"; for a patient diagnosed with bladder cancer but not yet having surgery, a doctor could assign a medical tag of "Bladder Cancer - Pre-operative - Adjuvant Therapy"; and for a patient with chronic kidney disease undergoing regular checkups, a doctor could assign a medical tag of "Chronic Kidney Disease - Stable Phase - Quarterly Checkups". Medical tags can summarize the patient's core diagnostic and treatment characteristics, providing a basis for matching subsequent follow-up templates.

[0046] In one implementation, the follow-up agent can generate several tags based on the patient's medical record data. The doctor's client obtains a first tag determined by the doctor based on the several tags, and associates the first tag as a medical tag with the second account.

[0047] Figure 3B An exemplary flowchart for setting medical tags is shown. The follow-up AI agent analyzes and determines several tags based on the patient's medical data. As shown in the attached diagram, the AI-recommended tags "Prostate Cancer - Preoperative - Adjuvant Therapy" and "Prostate Cancer - Postoperative - Quarterly Follow-up" are matched to the patient. Doctors can set medical tags for the patient themselves in their doctor's client, or select one from the tags recommended by the follow-up AI agent. After the doctor clicks the submit button, the medical tag is associated with a second account.

[0048] Next, in step S203, based on the medical label, several follow-up templates are obtained from multiple follow-up templates in the urology department. The urology department can preset multiple follow-up templates, corresponding to combinations of various urological conditions and multiple treatment stages. The various conditions include at least: cystitis, prostatitis, and prostate cancer; the multiple treatment stages include at least: pre-operative, post-operative, and recovery periods.

[0049] After obtaining the medical tag set by the doctor for the patient, the doctor's client can select several follow-up templates from the multiple follow-up templates based on the matching degree between the follow-up templates and the medical tag. The selected follow-up templates must have a matching degree higher than a preset matching degree threshold. This matching degree can be determined, for example, based on the semantic similarity calculation between the follow-up template and the medical tag, or based on keyword matching results. In short, the matching degree reflects the degree of association between the follow-up template and the medical tag, and its calculation methods are varied, which will not be listed one by one in this embodiment.

[0050] In a specific practice, the urology department can pre-set multiple follow-up templates. Specifically, urology staff can set up task chains in the doctor's client application. Each task item in the task chain includes a follow-up task and its corresponding task time offset (e.g., +3 days, every 7 days, etc.). It's easy to understand that the task time offset, together with the follow-up start time, determines the task execution time of the follow-up task. The doctor's client application can encapsulate the task chain and the time variable used to set the follow-up start time into a follow-up template. The time variable can be used to receive time information provided by the patient to instantiate a follow-up plan based on the follow-up template.

[0051] In a specific practice, the follow-up template may include a template summary, which outlines the purpose and applicable conditions of the follow-up template. The doctor's client can, based on the medical tags, perform a similarity-based search among multiple follow-up templates in the urology department, according to the template summary, to obtain several follow-up templates with a similarity higher than a preset matching threshold.

[0052] In step S205, the follow-up agent obtains the first follow-up template determined by the doctor based on the plurality of follow-up templates, and sends the first follow-up template to the patient client corresponding to the second account.

[0053] The follow-up agent can push several follow-up templates obtained in the aforementioned steps to the doctor's primary account. The doctor can view the specific content of these follow-up templates (e.g., follow-up tasks, test items) and select a first follow-up template for final confirmation. It should be understood that the doctor can also manually select the first follow-up template from the multiple follow-up templates pre-set by the urology department.

[0054] The doctor's client can send the first follow-up template confirmed by the doctor to the patient's client corresponding to the patient's second account. It is understood that if too many follow-up templates among the multiple templates have a matching degree higher than the matching degree threshold with the medical tag, the follow-up agent can select several of the top-ranked follow-up templates.

[0055] Figure 3C The illustration shows a schematic scenario for confirming a follow-up template. Doctors can view patient information on their client devices and select a follow-up template for the patient in a pop-up window. The follow-up agent can retrieve several follow-up templates matching the patient based on the medical tags set by the doctor, serving as AI recommendations. The doctor can choose a first follow-up template from a set of preset templates for urology, or from several templates recommended by the follow-up agent. Once the doctor has set the first follow-up template and confirmed it (by clicking the submit button), the first follow-up template can be sent to the patient client corresponding to the patient's second account.

[0056] As previously stated, the first follow-up template may include multiple follow-up tasks. Each follow-up task requires the patient to submit corresponding follow-up data. The follow-up data includes a description of urination-related symptoms and test data corresponding to several test items. Typically, the test data includes at least one of the following: prostate-specific antigen (PSA), complete blood count, and testosterone.

[0057] Next, in step S207, the follow-up agent responds to a first message containing a first follow-up plan sent by the patient client, and associates the first follow-up plan with a first account. The first follow-up plan is generated by the patient client based on a first follow-up template and first-time information provided by the patient.

[0058] It's important to understand that, from a data relationship perspective, the first follow-up template selected by the doctor belongs to the urology department, and is not associated with the doctor's primary account. After the patient completes the time settings for the first follow-up template, a corresponding first follow-up plan can be instantiated based on the template. This first follow-up plan needs to be associated with the doctor's primary account so that the doctor can view it after logging into the doctor's client using that account.

[0059] Based on the preceding introduction, it can be understood that the first follow-up plan may include several follow-up tasks arranged chronologically, such as "symptom assessment one month post-surgery," "PSA testing every three months," and "annual imaging follow-up." Each follow-up task can define specific data collection objectives to collect the follow-up data submitted by the patient in a structured manner. When a follow-up task is triggered, the patient can log in to the patient client using a second account and, guided by the follow-up agent, submit the data required for the follow-up task by filling out forms, uploading test reports, answering questionnaires, or authorizing the connection of smart medical devices.

[0060] Next, we will briefly introduce the generation process of the first follow-up plan with reference to the embodiments, and explain how the patient client responds based on the first follow-up plan.

[0061] After receiving the first follow-up template sent by the doctor's client, the patient's client can generate the first follow-up plan based on the first follow-up template and the first time information provided by the patient. In other words, based on the first time information provided by the patient, the static first follow-up template can be configured into a personalized first follow-up plan corresponding to the patient. Generally, the first time information provided by the patient refers to the date of the patient's first treatment, which can be used as the start date of the follow-up plan. In some scenarios, the first time information can also be the start date of the follow-up plan set by the patient according to personal preference. This embodiment of the specification does not limit this.

[0062] Figure 4A The illustration depicts a scenario where a patient confirms a follow-up plan. The patient logs into the patient client using a second account, can view the first follow-up template pushed to them by the doctor, and confirm the initial information within the patient client. The patient client can generate a first follow-up plan based on the first follow-up template and the initial information submitted by the patient. The patient can view the first follow-up plan within the patient client, such as... Figure 4A As shown, it includes multiple follow-up tasks, each of which includes its corresponding task execution time.

[0063] According to one implementation, after the patient's first follow-up plan is generated, the follow-up agent can remind the patient to perform the follow-up task based on the task execution time included in the follow-up task.

[0064] Specifically, the follow-up agent, for any first follow-up task in the first follow-up plan, can calculate a first time difference based on the current system time and the task execution time of the first follow-up task. The calculation of the first time difference typically uses the task execution time as a benchmark, subtracting the current system time from it to obtain a time interval (difference). If the result is positive, it indicates that the first follow-up task has not yet expired; if it is zero or negative, it indicates that the first follow-up task has expired or is overdue. For example, if the task execution time of the first follow-up task is set to January 28, 2026, and the current system time is January 23, 2026, then the first time difference is 5 days, indicating that the first follow-up task has not yet expired; if the current system time is January 31, 2026, then the first time difference is -3 days, indicating that the first follow-up task is overdue.

[0065] When the first time difference falls within a preset first time window, the follow-up agent can generate a task prompt corresponding to the first follow-up task under the second account. In specific applications, the first time window is usually set as a time period close to the task execution time. For example, it could be from the 3rd day before the task execution time to 3 days after the due date (i.e., the first time window is [-3, 3]). When the calculated first time difference falls within the numerical range defined by this first time window, it indicates that the first follow-up task is about to be executed or already needs to be executed. At this time, the follow-up agent can generate a task prompt corresponding to the first follow-up task under the patient's second account. The patient can log in to the patient client using the second account to view the task prompt. In practice, the task prompt can be displayed as a push notification, banner, or a highlighted item in a to-do list, and its content can include the name of the first follow-up task, the task execution time, etc.

[0066] Understandably, when the first time difference falls outside the first time window, the follow-up agent can cancel the task prompt corresponding to the first follow-up task. In specific applications, once the first follow-up task is completed, or the first time difference falls outside the numerical range defined by the first time window, it indicates that the first follow-up task has not entered the reminder period or has expired. The follow-up agent does not need to generate a task prompt, or it can cancel the previously generated task prompt corresponding to the first follow-up task from the patient's second account. The task prompt can be found in [reference needed]. Figure 4B As shown in the example, after a patient logs into the patient client using a second account, they can see task prompts for follow-up tasks that are about to be performed or are recently overdue.

[0067] As mentioned earlier, the first follow-up plan may include several follow-up tasks, and any follow-up task may include several test items. When performing a follow-up task, the patient can fill in the test data corresponding to each test item to form follow-up data.

[0068] In a specific practice, the follow-up task can be any of the following:

[0069] Follow-up and re-examination task: Instructing patients to have a follow-up visit with their doctor, usually conducted in person. After completing this follow-up task, patients can submit their test data and symptom descriptions as follow-up data through their client application; alternatively, they can authorize their client application to automatically retrieve relevant test data and symptom descriptions from the hospital's networked information system.

[0070] Task 1: Patients are instructed to complete a screening questionnaire online via a client application. This task uses a digital screening questionnaire to systematically collect information on patients' subjective symptom experiences, quality of life indicators, and psychological state.

[0071] Patient education task: Through the patient client, push and guide patients to learn specific disease knowledge, rehabilitation guidance or health education content.

[0072] Reminder and Care Task: Send patients reminders related to treatment adherence and healthy lifestyles through the patient client. Examples include daily medication reminders and recording daily water intake.

[0073] In a specific practice, the detection item can be any of the following:

[0074] Patient complaint: Subjective feelings and symptoms related to the disease as stated by the patient. This descriptive information can be recorded in the form of natural language text.

[0075] Biochemical tests: These are indicators obtained by collecting bodily fluid samples such as blood and urine from patients and analyzing them in a laboratory. The data are usually numerical or graded. Examples include prostate-specific antigen (PSA), complete blood count, testosterone, and urinalysis.

[0076] Imaging examinations: Descriptive conclusions or measurement data obtained after examining the patient's body parts using imaging equipment such as X-rays, ultrasound, computed tomography (CT), and magnetic resonance imaging (MR). The data can be in the form of text reports (e.g., new lesions or lesion metastasis), key values ​​(e.g., residual urine volume of 200 ml) or the image file itself.

[0077] Screening scales: These are rating scales consisting of a series of standardized questions used to systematically screen and assess a patient's specific functional status or quality of life. The output is typically one or more scores. Examples include the QoL scale for assessing quality of life and the IPSS scale for assessing prostate symptoms.

[0078] In a specific practice, the follow-up data provided by the patient can include any of the following: prostate-specific antigen (PSA), complete blood count, testosterone, residual urine volume, urinalysis, quality of life score (QoL), bone scan, prostate MR results, and PET-CT results.

[0079] In a specific practice, the follow-up intelligent agent can determine a patient's risk level based on the follow-up data provided by the patient. The follow-up intelligent agent can then translate the quantified risk level into specific, actionable clinical management instructions based on a preset risk response mechanism. Specifically, the follow-up intelligent agent can predefine a set of risk grading rules, with each risk level corresponding to a different clinical management strategy. Based on the patient's risk level, the follow-up intelligent agent can generate prompts under a first account and / or a second account.

[0080] In a specific practice, multiple risk levels can be preset based on expert experience. For example, two risk levels can be preset: Level 1 and Level 2; where Level 1 has a higher risk than Level 2.

[0081] When the risk level is Level 1, the follow-up agent can generate a first notification message under the first account. This first notification message is associated with the second account and is used to prompt the doctor to follow up with the patient. The doctor can log in to the doctor's client using the first account to view the first notification message and proactively monitor the patient. In some practices, the first notification message can also be generated simultaneously under the second account to prompt the patient to proactively contact the doctor for treatment.

[0082] When the risk level is Level 2, the follow-up agent can generate a second prompt message under the second account. This second prompt message is associated with the first account and is used to prompt the patient whether they need to perform a task (e.g., prompting the patient to have a follow-up appointment with the doctor). The patient can view the second prompt message by logging into the patient client using the second account.

[0083] Figure 4C As an example of the prompt message generation in the above embodiments, the follow-up agent can determine the risk level of the patient's condition based on the patient's risk level, and accordingly generate a prompt message under the patient's second account and / or the doctor's first account. The prompt message can be associated with the first or second account to facilitate communication between the patient or doctor.

[0084] In a specific practice, the follow-up agent can determine the risk level of a patient using an evaluation model. The evaluation model includes scoring rules corresponding to each of the several test items. The follow-up agent can first use the evaluation model to determine a score for any test item based on the test data, using the scoring rules corresponding to that test item. Then, the follow-up agent can perform semantic analysis on the symptom description to obtain a symptom score. Finally, the follow-up agent can determine the patient's risk level based on the symptom score and the scores of the several test items.

[0085] Specifically, any detection item The corresponding test item scores can be denoted as ,in Indicates the detection item The corresponding scoring rules, Indicates the detection item The corresponding detection data. The follow-up agent can obtain the scores for each detection item through the evaluation model. When designing the evaluation model, scoring rules adapted to the data type of the detection data can be defined for that detection item.

[0086] In one implementation, the test data for the first test item (hereinafter referred to as the first test item for ease of distinction) is numerical. The scoring rule for the first test item can be designed as a piecewise function. When determining the score of the first test item, the score can be determined by segmenting the test data of the first test item according to the domain of the piecewise function. Taking the routine urine test item as an example, the test data can be the white blood cell (WBC) index. The scoring rule for this test item can be defined as follows:

[0087]

[0088] The scoring rule defines a piecewise function with three domain segments. Based on the test data provided by the patient for the test item, the domain segment into which the patient falls can be determined, thereby obtaining the test item score corresponding to the test item.

[0089] According to one implementation method, the test data of the test item (hereinafter referred to as the second test item for ease of distinction) is of numerical type, and the scoring rule corresponding to the second test item can be designed as a piecewise function. When determining the score of the second test item, the test data of the second test item recorded by the patient in two follow-up tasks can be compared to obtain the comparison result. Then, based on the segmentation of the comparison result within the domain of the piecewise function, the score of the second test item is determined. Taking the PSA test item as an example, during the execution of the follow-up plan, it is necessary to monitor the increase in PSA. Therefore, the increase in PSA can be obtained by subtracting the PSA value provided by the patient in the previous follow-up task from the PSA value provided by the patient in the current follow-up task. The scoring rule for this test item can be defined as follows:

[0090]

[0091] This represents the increase in PSA. The domain of the piecewise function defined by this scoring rule includes three domain segments. Based on the increase in PSA provided by the patient for this test item, the domain segment into which the patient falls can be determined, thereby obtaining the test item score corresponding to that test item.

[0092] For data recorded in natural language text based on patient complaints, taking symptom descriptions as an example, the follow-up agent can perform semantic analysis on the symptom descriptions to obtain symptom scores. .

[0093] For example, with This refers to the symptom description provided by the patient, recorded in natural language. This represents n predefined symptom evaluation indicators, each symptom evaluation indicator Includes text description (For example, severe urinary frequency, slight difficulty urinating) and a corresponding score. . The text vectorization function can be implemented based on models such as BERT, mapping text into a high-dimensional semantic vector. This represents a vector similarity calculation function, which can be based on cosine similarity, for example. Thus, symptom description... Symptom score The calculation process can be represented as follows:

[0094] Calculate symptom description With each symptom evaluation index Text description Semantic similarity:

[0095]

[0096] By determining the index k corresponding to the text description with the highest semantic similarity, the correlation with the symptom description is established. Most relevant symptom assessment indicators :

[0097]

[0098] in, This indicates that the parameter index that maximizes the function value is returned.

[0099] Obtain symptom evaluation indicators corresponding score As a symptom description Corresponding symptom scores , shown as:

[0100]

[0101] Finally, after obtaining the patient's symptom score and the scores of the corresponding test items, the follow-up agent can determine the patient's overall risk score.

[0102] According to one implementation, the follow-up agent can determine the patient's risk score as the maximum value among the symptom score and several test item scores. , can be represented as:

[0103]

[0104] According to one implementation, the follow-up agent can perform a weighted summation of the symptom score and the scores of the plurality of test items to obtain the patient's risk score. , can be represented as:

[0105]

[0106] in, It is the weight of the symptom score. It is the weight of the score of the i-th detection item, and all weights satisfy normalization, i.e. The weights of the test items / symptom descriptions are positively correlated with their correlation with urological symptoms. In other words, the closer the correlation between a test item / symptom description and urological disease, the higher the predictive value of its test item / symptom score, and the greater its corresponding weight. For example, for prostate cancer patients, the weight of the PSA test item is usually higher; for patients receiving endocrine therapy, the weight of the test item test hormone is usually higher. The risk score obtained by weighted summation can more comprehensively reflect the overall progression of the patient's disease, avoiding the impact of accidental fluctuations in a single indicator on disease assessment.

[0107] Finally, the follow-up agent can determine the patient's risk level based on the risk score.

[0108] The foregoing description, based on one or more embodiments, details a method for follow-up of urology patients. Using the method provided in the embodiments of this specification, an automated and intelligent follow-up management system can be constructed for urology patients. Based on the medical tags set by the doctor for the patient, a follow-up template is intelligently recommended, and a personalized follow-up plan is generated based on the patient's confirmation of the template. This enables automated generation of follow-up plans and automated collection of test data, thereby improving the efficiency and quality of follow-up for urology patients, reducing the doctor's manpower input during the follow-up process, improving the patient's follow-up experience, and increasing patient compliance.

[0109] In this manual, the terms "first" in the first account, the first follow-up plan, etc., as well as the corresponding "second" and "third" (if any) in the text, are merely for the convenience of distinction and description, and do not have any limiting meaning.

[0110] The foregoing description describes specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than those shown in the embodiments, and the desired result may still be achieved. Furthermore, the processes depicted in the drawings do not necessarily need to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0111] Figure 5 This is a schematic diagram of a system for follow-up of urology patients according to an embodiment of this specification. The system 500 is deployed in a computing device, which can be implemented using any device, equipment, platform, device cluster, etc., with computing and processing capabilities. This system embodiment is similar to... Figure 2 Corresponding to the method embodiment shown, the system 500 includes:

[0112] Doctor client 501 is configured to obtain medical tags set by the doctor of the first account for the patient of the second account, wherein the medical tags indicate the combination of the patient's urological condition and the current stage of treatment.

[0113] The acquisition module 502 is configured to acquire several follow-up templates from multiple follow-up templates in the urology department based on the medical tag, wherein the multiple follow-up templates correspond to a combination of multiple diseases and multiple treatment stages in the urology department; the matching degree between the multiple follow-up templates and the medical tag is higher than a preset threshold; the multiple diseases include at least: cystitis, prostatitis, and prostate cancer.

[0114] The follow-up intelligent agent 503 is configured to obtain a first follow-up template determined by the doctor based on the plurality of follow-up templates, and send the first follow-up template to the patient client corresponding to the second account; the first follow-up template includes multiple follow-up tasks, each follow-up task requires the patient to submit corresponding follow-up data, the follow-up data includes a description of symptoms related to urination, and test data corresponding to several test items, the test data including at least one of the following: prostate-specific antigen PSA, complete blood count, and testosterone.

[0115] The follow-up intelligent agent 503 is further configured to associate the first follow-up plan with the first account in response to a first message containing the first follow-up plan sent by the patient client; the first follow-up plan is generated by the patient client based on the first follow-up template and the first time information provided by the patient.

[0116] According to another embodiment, this specification also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the foregoing combinations. Figure 2 The steps of the method are described.

[0117] According to yet another embodiment, this specification also provides a computing device including a memory and a processor, characterized in that the memory stores executable code, and when the processor executes the executable code, it implements the foregoing combination. Figure 2 The steps of the method are described.

[0118] Those skilled in the art will recognize that the functions described in the embodiments of the present invention in one or more of the above examples can be implemented using hardware, software, firmware, or any combination thereof. When implemented in software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium.

[0119] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the embodiments of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made based on the technical solutions of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for follow-up of urology patients, comprising: The doctor's client obtains the medical tags set by the doctor of the first account for the patient of the second account. The medical tags indicate the combination of the patient's urological condition and the current stage of treatment. Based on the medical label, several follow-up templates are obtained from multiple follow-up templates in the urology department, wherein the multiple follow-up templates correspond to a combination of multiple urological diseases and multiple stages of diagnosis and treatment; The degree of matching between the several follow-up templates and the medical tags is higher than a preset threshold; The aforementioned conditions include at least: cystitis, prostatitis, and prostate cancer; The follow-up agent obtains the first follow-up template determined by the doctor based on the plurality of follow-up templates, and sends the first follow-up template to the patient client corresponding to the second account; the first follow-up template includes multiple follow-up tasks, each follow-up task requires the patient to submit corresponding follow-up data, the follow-up data includes a description of symptoms related to urination, and test data corresponding to several test items, the test data including at least one of the following: prostate-specific antigen PSA, complete blood count, testosterone; The follow-up agent responds to a first message containing a first follow-up plan sent by the patient client and associates the first follow-up plan with a first account; the first follow-up plan is generated by the patient client based on a first follow-up template and first-time information provided by the patient.

2. The method according to claim 1, wherein, The medical label is set up in the following way: The patient adds the second account to the patient queue corresponding to the first account by scanning the doctor's QR code; the doctor's QR code is associated with the first account. The doctor uses the first account through a doctor's client to set medical tags for the second account based on the patient's medical record data; the medical record data includes symptom descriptions and test results.

3. The method according to claim 2, wherein, Based on the patient's medical record data, medical tags are set for the second account, including: The follow-up intelligent agent generates several tags based on the patient's medical records; The doctor's client obtains a first tag determined by the doctor based on the several tags, and associates the first tag as a medical tag with the second account.

4. The method according to claim 1, wherein, Any of the multiple follow-up templates can be preset in the following way: Obtain the task chain, wherein each task item in the task chain includes a follow-up task and its corresponding task time offset, wherein the task time offset is used to determine the task execution time of the follow-up task together with the follow-up start time. The task chain and the time variable used to set the follow-up start time are encapsulated into a follow-up template.

5. The method according to claim 1, wherein, The follow-up template includes a template summary; based on the medical label, several follow-up templates are obtained from multiple follow-up templates in the urology department, including: Based on the medical tag, a similarity-based search is performed on the multiple follow-up templates to obtain several follow-up templates with a similarity higher than a preset similarity threshold.

6. The method according to claim 1, wherein, The follow-up task includes a task execution time; the method further includes: The follow-up agent calculates a first time difference for any first follow-up task in the first follow-up plan, based on the current system time and the task execution time of the first follow-up task. When the first time difference falls within the preset first time window, the follow-up agent generates a task prompt corresponding to the first follow-up task under the second account.

7. The method according to claim 1, further comprising: The follow-up agent determines the risk level based on the follow-up data; When the risk level is Level 1, the follow-up agent generates a first notification message under the first account; The first notification message is associated with the second account and is used to prompt the doctor to follow up with the patient. When the risk level is level two, the follow-up agent generates a second prompt message under the second account; The second notification is associated with the first account and is used to prompt the patient whether they need to perform a task; wherein, the risk level of the first level is higher than that of the second level.

8. The method according to claim 7, wherein, The follow-up agent determines the risk level based on the follow-up data, including: The follow-up agent uses an evaluation model to determine the score of any detection item based on the detection data of that item. The follow-up agent performs semantic analysis on the symptom descriptions to obtain symptom scores; The follow-up agent determines the patient's risk level based on the symptom score and the scores of several test items corresponding to the test items.

9. The method according to claim 1, wherein, The test items are any one of the following: patient complaints, biochemical tests, imaging tests, and screening scales.

10. The method according to claim 1, wherein, The test data also includes one or more of the following: residual urine volume, urinalysis, quality of life score (QoL), bone scan, prostate MR results, and PET-CT results.

11. The method according to claim 1, wherein, The follow-up task can be any one of the following: re-examination and follow-up visit, filling out a questionnaire, patient education, or care and reminder.

12. A system for follow-up of urology patients, comprising: The doctor client is configured to obtain medical tags set by the doctor of the first account for the patient of the second account, wherein the medical tags indicate the combination of the patient's urological condition and the current stage of diagnosis and treatment. The acquisition module is configured to acquire several follow-up templates from multiple follow-up templates in the urology department based on the medical tag, wherein the multiple follow-up templates correspond to a combination of multiple diseases and multiple treatment stages in the urology department; The degree of matching between the several follow-up templates and the medical tags is higher than a preset threshold; The aforementioned conditions include at least: cystitis, prostatitis, and prostate cancer; The follow-up intelligent agent is configured to obtain a first follow-up template determined by the doctor based on the plurality of follow-up templates, and send the first follow-up template to the patient client corresponding to the second account; the first follow-up template includes multiple follow-up tasks, each follow-up task requires the patient to submit corresponding follow-up data, the follow-up data includes a description of symptoms related to urination, and test data corresponding to several test items, the test data including at least one of the following: prostate-specific antigen PSA, complete blood count, testosterone; The follow-up intelligent agent is further configured to associate the first follow-up plan with a first account in response to a first message containing the first follow-up plan sent by the patient client; the first follow-up plan is generated by the patient client based on the first follow-up template and the first time information provided by the patient.

13. A computer program product comprising a computer program / instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1-11.

14. A computing device, comprising a memory and a processor, characterized in that, The memory stores executable code, and when the processor executes the executable code, it implements the method of any one of claims 1-11.

Images