One-stop self-management method and system based on NMOSD

Abstract

The invention discloses an NMOSD-based one-stop self-management method and system, and a computing device, and the method comprises the steps: obtaining a patient data set which comprises the personal information, clinical features, iconography performance, laboratory indexes and medication records of a patient; according to the patient data set and the recurrence risk factors, obtaining a recurrence risk index and a corresponding risk level of the patient; according to the recurrence risk index, the corresponding risk grade and the NMOSD treatment guide, determining a personalized drug treatment and follow-up visit plan of the patient; and displaying the personalized drug treatment and follow-up visit plan in a visual mode. According to the method, the risk rule set is added to the C4.5 decision tree, and the feature values of the patient data set are preferentially sorted according to the Gini impurity reduction and the risk rule set, so that the accuracy and efficiency of patient self-risk assessment are improved, and the self-management level of the patient is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical auxiliary diagnosis, and in particular to a one-stop self-management method and system based on NMOSD, and a computing device. Background Art

[0002] NMOSD, or neuromyelitis optica spectrum disorder, is a rare, highly relapsing, and highly disabling autoimmune disease of the central nervous system. Many factors are associated with the relapse of NMOSD patients. Currently, there are few social resources, and medical staff, patients, and caregivers lack understanding of treatment, nursing, and self-management. There is also little corresponding research, and there is a lack of corresponding self-management systems and models.

[0003] To solve the above problems, the present invention proposes a one-stop self-management method based on NMOSD to improve the accuracy and efficiency of patients' self-risk assessment, thereby improving the level of patients' self-management. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] The present invention provides a one-stop self-management method and system for NMOSD, and a computing device for improving the self-risk assessment and self-management level of patients.

[0006] (II) Technical solution

[0007] According to one aspect of the present invention, a one-stop self-management method based on NMOSD is provided, comprising:

[0008] Obtain patient data sets, which include patients' personal information, clinical characteristics, imaging manifestations, laboratory indicators, and medication records;

[0009] Obtaining a recurrence risk index and a corresponding risk level of the patient according to the patient data set and the recurrence risk factors;

[0010] Determine the patient's personalized medication and follow-up plan based on the recurrence risk index and corresponding risk level and NMOSD treatment guidelines;

[0011] The personalized drug treatment and follow-up plan are presented in a visual manner.

[0012] In an optional manner, the personal information includes age, gender, length of spinal cord involvement, AQP4 antibody status, serum IL-6 level and number of previous relapses; the clinical characteristics include symptom description, past medical history and family medical history; the imaging manifestations include MRI and CT scan results; the laboratory indicators include AQP4 antibody test results and serum IL-6 level; the medication records include current medication and past medication information.

[0013] In an optional manner, obtaining the patient's recurrence risk index and the corresponding risk level according to the patient data set and the recurrence risk factors further includes:

[0014] Adding the risk rule set to the C4.5 decision tree, wherein when selecting a split node, the feature values ​​of the patient data set are prioritized according to the reduction of Gini impurity and the risk rule set; if a rule directly determines the risk level, the corresponding leaf node is no longer split;

[0015] At the leaf node, the recurrence risk index and the corresponding risk level are calculated according to the characteristic values ​​accumulated on the path and the rule influence results of the risk rule set.

[0016] In an optional manner, the calculation formula of the Gini impurity is:

[0017]

[0018] Where D is the set of all samples contained in the current node; f i is the segmentation data set; t is the segmentation point; D left According to f i The data set that is located in the left subset after being divided by the split point t; D right According to f i The data set that is located in the right subset after being divided by the split point t; |D left | is the left subset D left The number of samples; |D right | is the right subset D right The number of samples in the original dataset D; Gini(D left ) is the left subset D left Gini impurity; Gini (D right ) is the right subset D right The Gini impurity of .

[0019] In an optional manner, the left subset D left The calculation formula of Gini impurity is:

[0020]

[0021] The right subset D right The calculation formula of Gini impurity is:

[0022]

[0023] Among them, n k,left D left The number of samples in the kth category; n k,right D right The number of samples of the kth class in .

[0024] In an optional manner, the calculation formula for the recurrence risk index is:

[0025]

[0026] Among them, w i is the weight of feature i; r i (f i ) is the rule influence value corresponding to the actual value of feature i.

[0027] In an optional manner, prioritizing the feature values ​​of the patient data set according to Gini impurity reduction and the risk rule set further includes:

[0028] Features whose Gini impurity is less than a preset threshold are preferentially selected. If the feature is directly defined as a high-risk factor by the risk rule set, the feature is placed in a priority queue.

[0029] In an optional manner, presenting the personalized drug treatment and follow-up plan in a visual manner further comprises:

[0030] Display the schedule of treatment and follow-up, including medication schedule and follow-up dates, in the form of a timeline and calendar; and

[0031] A color-coded circle or bar graph shows the patient's recurrence risk level, with green representing low risk, yellow representing intermediate risk, and red representing high risk.

[0032] According to another aspect of the present invention, a rapid identification system based on stroke symptoms is provided, comprising:

[0033] The patient data set acquisition module is used to acquire the patient data set, which includes the patient's personal information, clinical characteristics, imaging manifestations, laboratory indicators, and medication records;

[0034] A risk index and level calculation module, used to obtain the patient's recurrence risk index and corresponding risk level according to the patient data set and recurrence risk factors;

[0035] A drug treatment and follow-up plan determination module, used to determine the patient's personalized drug treatment and follow-up plan based on the recurrence risk index and the corresponding risk level and NMOSD treatment guidelines;

[0036] The visualization display module is used to display the personalized drug treatment and follow-up plan in a visual manner.

[0037] 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 via the communication bus;

[0038] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the above-mentioned one-stop self-management method based on NMOSD.

[0039] (III) Beneficial effects

[0040] (1) By collecting multi-dimensional data such as the patient's personal information, clinical characteristics, imaging manifestations, laboratory indicators, and medication records, the patient's disease status can be comprehensively assessed.

[0041] (2) Based on the patient data set and recurrence risk factors, the C4.5 decision tree algorithm is used to calculate the patient's recurrence risk index and risk level to achieve early warning and intervention of the disease.

[0042] (3) Based on the recurrence risk index and risk level, combined with the NMOSD treatment guidelines, develop personalized drug treatment and follow-up plans for patients to improve the targetedness and effectiveness of treatment.

[0043] (4) Visualize personalized drug treatment and follow-up plans in the form of timelines, calendars, and color-coded graphics, so that patients can intuitively understand the treatment process and follow-up arrangements, thereby enhancing patient participation and self-management capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0045] Figure 1 A schematic diagram of a process flow of a one-stop self-management method based on NMOSD according to an embodiment of the present invention is shown;

[0046] Figure 2 A structural block diagram of a system for rapid identification of stroke symptoms according to an embodiment of the present invention is shown;

[0047] Figure 3 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0048] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying 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 in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0049] Figure 1 The flowchart of the one-stop self-management method based on NMOSD according to an embodiment of the present invention is shown. Specifically, the method includes the following steps.

[0050] Step S101, obtaining a patient data set, which includes the patient's personal information, clinical characteristics, imaging manifestations, laboratory indicators, and medication records.

[0051] Specifically, electronic medical record systems, imaging diagnostic systems, laboratory information systems, etc. are used to automatically or semi-automatically collect patients' personal information, clinical characteristics, imaging manifestations, laboratory indicators, medication records and other data. The collected data are integrated to form a unified patient data set. For example, the data is cleaned and organized to remove duplicate, erroneous or irrelevant information to ensure data availability.

[0052] In this embodiment, as shown in Table 1, the personal information includes age, gender, spinal cord involvement length, AQP4 antibody status, serum IL-6 level and previous relapse times; the clinical characteristics include symptom description, past medical history and family medical history; the imaging manifestations include MRI and CT scan results; the laboratory indicators include AQP4 antibody test results and serum IL-6 levels; the medication record includes current medication and previous medication information.

[0053] Table 1

[0054] category Field Name data personal information age 35 years old gender female Length of spinal cord affected T3-T7 AQP4 antibody status Positive Serum IL-6 levels 15pg / mL Number of previous relapses 2 times Clinical characteristics Symptom description Decreased vision, limb weakness Past medical history Diabetes, hypertension Family history No family history of NMOSD Imaging findings MRI results Long T2 signal shadows in multiple segments of the spinal cord CT scan results No obvious abnormalities Laboratory indicators AQP4 antibody test results Positive (+) Serum IL-6 levels After re-examination, 18 pg / mL Medication Records Current medication Immunosuppressant A 100 mg / d, glucocorticoid B 20 mg / d Previous medication Immunosuppressant C 50 mg / d (discontinued)

[0055] Step S102, obtaining the patient's recurrence risk index and corresponding risk level according to the patient data set and the recurrence risk factors.

[0056] In an optional manner, obtaining the patient's recurrence risk index and the corresponding risk level according to the patient data set and the recurrence risk factors further includes:

[0057] Adding the risk rule set to the C4.5 decision tree, wherein when selecting a split node, the feature values ​​of the patient data set are prioritized according to the reduction of Gini impurity and the risk rule set; if a rule directly determines the risk level, the corresponding leaf node is no longer split;

[0058] At the leaf node, the recurrence risk index and the corresponding risk level are calculated according to the characteristic values ​​accumulated on the path and the rule influence results of the risk rule set.

[0059] In this embodiment, the C4.5 decision tree model itself has good interpretability and can clearly show the decision path from input features to recurrence risk level. At the same time, by introducing risk rule sets, it can handle complex clinical rules more flexibly and make the prediction results closer to reality. In the process of decision tree construction, risk rules that directly determine risk levels are given priority, which can reduce unnecessary tree structure expansion and improve calculation efficiency.

[0060] Specifically, the collected patient data sets are preprocessed, including data cleaning, missing value processing, and outlier detection.

[0061] Based on clinical experience and expert knowledge, a risk rule set was constructed to assess the recurrence risk of NMOSD patients. These rules involved multiple aspects such as the patient's personal information, clinical characteristics, imaging manifestations, and laboratory indicators.

[0062] Initialize the decision tree and select the root node. When selecting the split node, first evaluate the importance of each feature based on the reduction of Gini impurity. At the same time, consider the priority of the risk rule set on the feature value, and give priority to the rules that have a direct impact on the risk of recurrence. If a rule directly determines the risk level, a leaf node is directly generated at the node and the corresponding risk level is marked without further splitting. For other cases, continue to select features for splitting according to the principle of reducing Gini impurity until the stopping condition is met (such as the node purity reaches the threshold, the number of node samples is too small, etc.).

[0063] At each leaf node, the recurrence risk index is calculated based on the accumulated feature values ​​on the path from the root node to the leaf node and the rule influence results of the risk rule set. The calculation of the recurrence risk index can be based on weighted summation, logistic regression or other suitable statistical methods, which are not limited in this article. According to the recurrence risk index, patients are divided into different risk levels (such as low risk, medium risk, high risk).

[0064] For example, NMOSD patients are older, have longer spinal cord involvement, are positive for AQP4 antibodies, and have persistently elevated serum IL-6 levels. According to the risk rule set, these features are considered high-risk factors. In the process of building the C4.5 decision tree, due to the existence of risk rules that directly determine the risk level (such as "positive AQP4 antibodies and persistently elevated serum IL-6 levels" are directly judged as high risk), leaf nodes representing high risk are directly generated at earlier nodes without further splitting. The patient's recurrence risk index is a high value and is classified as a high-risk level. Based on the evaluation results, a more active treatment and follow-up plan can be formulated for the patient to prevent or reduce the occurrence of recurrence events.

[0065] In an optional manner, the calculation formula of the Gini impurity is:

[0066]

[0067] Where D is the set of all samples contained in the current node; f i is the segmentation data set; t is the segmentation point; D left According to f i The data set that is located in the left subset after being divided by the split point t; D right According to f i The data set that is located in the right subset after being divided by the split point t; |D left | is the left subset D left The number of samples; |D right | is the right subset D right The number of samples in the original dataset D; Gini(D left ) is the left subset D left Gini impurity; Gini(D right ) is the right subset D right The Gini impurity of .

[0068] In this embodiment, Gini impurity is used as an indicator to measure the impurity of a data set, which can intuitively and quantitatively reflect the classification effect of the data set. In addition, Gini impurity is used as a reference indicator to help select the optimal splitting nodes and features. When building a decision tree on a large data set, the node splitting and tree construction can be completed quickly. By combining with the risk rule set, the prediction ability of the decision tree can be further improved.

[0069] Specifically, initialize the decision tree, select the root node and include all samples. For each node, traverse all features and possible split values. Use the Gini impurity formula to calculate the impurity of each split scheme, and select the split scheme with the smallest impurity as the splitting method of the current node. If there is a risk rule set, give priority to those risk rules that can directly determine the risk level. If a rule is directly applicable, generate a leaf node directly at the node and mark the corresponding risk level. Repeat the above steps until the stopping condition is met (such as the node purity reaches the threshold, the number of node samples is too small, the maximum depth of the tree is reached, etc.).

[0070] For example, NMOSD patients contain multiple features, including age, gender, and spinal cord involvement length. When constructing the decision tree, age is selected as the first split feature, and the age of 45 years old is used as the split point. According to the Gini impurity formula, the Gini impurity is reduced after the data set is divided into two subsets. Further, if there is a risk rule set, and there is a rule in the rule set that states that "patients aged over 45 years old and with spinal cord involvement length exceeding 3 segments are high risk", then for the subset of patients aged over 45 years old (i.e., D_right), a leaf node representing high risk is directly generated on this node without further splitting. For this patient, if his age is greater than 45 years old and the length of spinal cord involvement exceeds 3 segments, then according to the joint decision of the risk rule set and the decision tree, the patient will be classified as a high-risk level.

[0071] In an optional manner, the left subset D left The calculation formula of Gini impurity is:

[0072]

[0073] The right subset D right The calculation formula of Gini impurity is:

[0074]

[0075] Among them, n k,left D left The number of samples in the kth category; n k,right D right The number of samples of the kth class in .

[0076] For example, in the decision tree construction process of NMOSD patient recurrence risk assessment, "age" is selected as the split feature of the current node, and "45 years old" is used as the split point. The data set is divided into two subsets: the left subset D left The right subset D contains patients aged 45 years or less. right Includes patients older than 45 years old. left, assuming that 50% of the patients are at low risk, 30% are at medium risk, and 20% are at high risk. Then the left subset D left The Gini impurity of the left subset Gini (D left )=0.42. For the right subset D right , assuming that 20% of the patients are at low risk, 30% are at medium risk, and 50% are at high risk. Then the right subset D right The Gini impurity is: Gini(D right )=0.58.

[0077] By calculating the reduction in Gini impurity, the effect of "age" as a split feature and "45 years old" as a split point is evaluated, and compared with other possible splitting schemes, the optimal splitting scheme is finally selected.

[0078] In an optional manner, the calculation formula for the recurrence risk index is:

[0079]

[0080] Among them, w i is the weight of feature i; r i (f i ) is the rule influence value corresponding to the actual value of feature i.

[0081] Since the calculation is based on clear features and weights, the results are highly interpretable.

[0082] For example, suppose there are two features used to assess relapse risk in NMOSD patients: age and length of spinal cord involvement. The following rules are developed for these two features:

[0083] Age: under 30 years old, rule impact value = 0.2; 30-45 years old, rule impact value = 0.5; over 45 years old, rule impact value = 0.8.

[0084] Length of spinal cord involvement: less than 1 segment, rule impact value = 0.1; 1-3 segments, rule impact value = 0.4; greater than 3 segments, rule impact value = 0.7.

[0085] Then, patients with an RRI greater than 0.5 will be classified as high-risk patients. Based on this assessment result, a more aggressive treatment and follow-up plan can be formulated for the patient.

[0086] In an optional manner, prioritizing the feature values ​​of the patient data set according to Gini impurity reduction and the risk rule set further includes:

[0087] Features whose Gini impurity is less than a preset threshold are preferentially selected. If the feature is directly defined as a high-risk factor by the risk rule set, the feature is placed in a priority queue.

[0088] Combined with the definition of the risk rule set, features directly marked as high-risk factors are placed in the priority queue to ensure that these features that have an important impact on the risk of recurrence are given full attention during the model construction process. For example, because the Gini impurity of Age is less than the preset threshold (0.3<0.45), it is screened as a candidate feature. Although the Gini impurity of AQP4_Status is slightly higher than the threshold, it is also considered an important feature because it is directly defined as a high-risk factor by the risk rule set. During the decision tree construction process, AQP4_Status is placed in the priority queue due to its direct high-risk definition. When building a decision tree or other model, AQP4_Status will be given priority as a split node or given a higher weight to accurately assess the patient's recurrence risk. Although Age has a lower Gini impurity, it will also be ranked according to its position in the candidate feature set or other indicators.

[0089] Step S103, determining the patient's personalized drug treatment and follow-up plan according to the recurrence risk index and the corresponding risk level and NMOSD treatment guidelines.

[0090] The NMOSD (neuromyelitis optica spectrum disorder) treatment guidelines are diagnostic and treatment guidelines for neuromyelitis optica spectrum disorders (NMOSD), a rare, highly recurrent, and highly disabling inflammatory demyelinating disease of the central nervous system. By following the treatment principles and recommended drugs in the guidelines, patients' symptoms can be minimized, recurrences can be prevented, and prognosis can be improved. According to the recurrence risk index and the corresponding risk level and the NMOSD treatment guidelines, the patient's personalized drug treatment and follow-up plan are determined, as shown in Table 2.

[0091] Table 2

[0092]

[0093]

[0094] Step S104, displaying the personalized drug treatment and follow-up plan in a visual manner.

[0095] In an optional manner, presenting the personalized drug treatment and follow-up plan in a visual manner further comprises:

[0096] Display the schedule of treatment and follow-up, including medication schedule and follow-up dates, in the form of a timeline and calendar; and

[0097] A color-coded circle or bar graph shows the patient's recurrence risk level, with green representing low risk, yellow representing intermediate risk, and red representing high risk.

[0098] In this embodiment, the drug treatment and follow-up plan are displayed through a timeline axis and a calendar, so that patients and medical teams can see the treatment tasks and follow-up dates of each stage at a glance, thereby improving the efficiency of plan execution. The use of color-coded graphics to display the recurrence risk level can quickly attract attention and help patients and doctors intuitively understand the current risk status, so as to make corresponding adjustments and preventive measures. A personalized treatment and follow-up plan is formulated according to the patient's specific situation, and presented in a visual way to ensure the targeted treatment plan. Through visualization, patients can have a clearer understanding of their treatment progress and follow-up arrangements, and enhance their enthusiasm for self-management and participation in treatment.

[0099] For example, the entire treatment cycle of the patient from diagnosis to the present time is displayed through a timeline axis, marking the key nodes of acute treatment, remission treatment and multiple follow-ups. On the calendar, the first day of each month is marked as a follow-up day, and a reminder to take medication is marked every day (such as "take 80 mg of methylprednisolone in the morning"). For patients at high risk, their recurrence risk level is indicated by a red circle and displayed in a prominent position on the interface to remind the medical team and patients to pay close attention to changes in their condition.

[0100] The solution provided by the above embodiment of the present invention obtains a patient data set, which includes the patient's personal information, clinical characteristics, imaging manifestations, laboratory indicators and medication records; according to the patient data set and recurrence risk factors, the patient's recurrence risk index and corresponding risk level are obtained; according to the recurrence risk index and corresponding risk level and NMOSD treatment guidelines, the patient's personalized drug treatment and follow-up plan are determined; the personalized drug treatment and follow-up plan are displayed in a visual manner. The present invention adds a risk rule set to the C4.5 decision tree, and prioritizes the characteristic values ​​of the patient data set according to the reduction of Gini impurity and the risk rule set, thereby improving the accuracy and efficiency of the patient's self-risk assessment, thereby improving the level of patient self-management. Specifically, by collecting multi-dimensional data such as the patient's personal information, clinical characteristics, imaging manifestations, laboratory indicators and medication records, the patient's disease status can be comprehensively evaluated. Based on the patient data set and recurrence risk factors, the C4.5 decision tree algorithm is used to calculate the patient's recurrence risk index and risk level, and early warning and intervention of the disease are achieved. According to the recurrence risk index and risk level, combined with the NMOSD treatment guidelines, a personalized drug treatment and follow-up plan is formulated for the patient to improve the pertinence and effectiveness of the treatment. Personalized drug treatment and follow-up plans are visualized in the form of timelines, calendars, and color-coded graphics, allowing patients to intuitively understand the treatment process and follow-up arrangements, enhancing patient participation and self-management capabilities.

[0101] Figure 2 The structural block diagram of the system for rapid identification of stroke symptoms according to an embodiment of the present invention is shown, comprising:

[0102] The patient data set acquisition module 210 is used to acquire the patient data set, which includes the patient's personal information, clinical characteristics, imaging manifestations, laboratory indicators, and medication records;

[0103] A risk index and level calculation module 220, for obtaining a patient's recurrence risk index and a corresponding risk level according to the patient data set and the recurrence risk factors;

[0104] A drug treatment and follow-up plan determination module 230, for determining a personalized drug treatment and follow-up plan for a patient based on the recurrence risk index and the corresponding risk level and NMOSD treatment guidelines;

[0105] The visualization display module 240 is used to display the personalized drug treatment and follow-up plan in a visual manner.

[0106] Figure 3 A schematic diagram of the structure of an embodiment of a computing device of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computing device.

[0107] like Figure 3 As shown, the computing device may include: a processor (processor) 302 , a communication interface (Communications Interface) 304 , a memory (memory) 306 , and a communication bus 308 .

[0108] The processor 302, the communication interface 304, and the memory 306 communicate with each other via the communication bus 308. The communication interface 304 is used to communicate with other devices such as a client or other server network elements. The processor 302 is used to execute the program 310, which can specifically execute the relevant steps in the above-mentioned NMOSD one-stop self-management method embodiment.

[0109] Specifically, the program 310 may include program codes, which include computer operation instructions.

[0110] The processor 302 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0111] The memory 306 is used to store the program 310. The memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0112] The solution provided by the above embodiment of the present invention obtains a patient data set, which includes the patient's personal information, clinical characteristics, imaging manifestations, laboratory indicators and medication records; according to the patient data set and recurrence risk factors, the patient's recurrence risk index and corresponding risk level are obtained; according to the recurrence risk index and corresponding risk level and NMOSD treatment guidelines, the patient's personalized drug treatment and follow-up plan are determined; the personalized drug treatment and follow-up plan are displayed in a visual manner. The present invention adds a risk rule set to the C4.5 decision tree, and prioritizes the characteristic values ​​of the patient data set according to the reduction of Gini impurity and the risk rule set, thereby improving the accuracy and efficiency of the patient's self-risk assessment, thereby improving the level of patient self-management. Specifically, by collecting multi-dimensional data such as the patient's personal information, clinical characteristics, imaging manifestations, laboratory indicators and medication records, the patient's disease status can be comprehensively evaluated. Based on the patient data set and recurrence risk factors, the C4.5 decision tree algorithm is used to calculate the patient's recurrence risk index and risk level, and early warning and intervention of the disease are achieved. According to the recurrence risk index and risk level, combined with the NMOSD treatment guidelines, a personalized drug treatment and follow-up plan is formulated for the patient to improve the pertinence and effectiveness of the treatment. Personalized drug treatment and follow-up plans are visualized in the form of timelines, calendars, and color-coded graphics, allowing patients to intuitively understand the treatment process and follow-up arrangements, enhancing patient participation and self-management capabilities.

[0113] The algorithm or display provided herein is not inherently related to any particular computer, virtual system or other equipment. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious to construct the structure required for this type of system. In addition, the embodiment of the present invention is not directed to any specific programming language yet. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description made to specific languages ​​above is for disclosing the best mode of the present invention.

[0114] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0115] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0116] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0117] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0118] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components according to embodiments of the present invention. The present invention can also be implemented as a device or system program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0119] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present invention may be implemented with the aid of hardware comprising several different elements and with the aid of appropriately programmed computers. In a unit claim that lists several systems, several of these systems may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. A one-stop self-management method based on NMOSD, characterized in that: include: Obtain patient data sets, which include patients' personal information, clinical characteristics, imaging manifestations, laboratory indicators, and medication records; Obtaining a recurrence risk index and a corresponding risk level of the patient according to the patient data set and the recurrence risk factors; Determine the patient's personalized medication and follow-up plan based on the recurrence risk index and corresponding risk level and NMOSD treatment guidelines; The personalized drug treatment and follow-up plan are presented in a visual manner.

2. The one-stop self-management method based on NMOSD according to claim 1, characterized in that: The personal information includes age, gender, length of spinal cord involvement, AQP4 antibody status, serum IL-6 level and number of previous relapses; the clinical characteristics include symptom description, past medical history and family medical history; the imaging manifestations include MRI and CT scan results; the laboratory indicators include AQP4 antibody test results and serum IL-6 level; the medication records include current medication and previous medication information.

3. The one-stop self-management method based on NMOSD according to claim 1 or 2, characterized in that: Obtaining the patient's recurrence risk index and corresponding risk level according to the patient data set and the recurrence risk factors further includes: Adding the risk rule set to the C4.5 decision tree, wherein when selecting a split node, the feature values ​​of the patient data set are prioritized according to the reduction of Gini impurity and the risk rule set; if a rule directly determines the risk level, the corresponding leaf node is no longer split; At the leaf node, the recurrence risk index and the corresponding risk level are calculated according to the characteristic values ​​accumulated on the path and the rule influence results of the risk rule set.

4. The one-stop self-management method based on NMOSD according to claim 3, characterized in that: The calculation formula of the Gini impurity is: Where D is the set of all samples contained in the current node; f i is the segmentation data set; t is the segmentation point; D left According to f i The data set that is located in the left subset after being divided by the split point t; D right According to f i The data set that is located in the right subset after being divided by the split point t; |D left | is the left subset D left The number of samples; |D right | is the right subset D right The number of samples in the original dataset D; Gini(D left ) is the left subset D left Gini impurity; Gini (D right ) is the right subset D right The Gini impurity of .

5. The one-stop self-management method based on NMOSD according to claim 4, characterized in that: The left subset D left The calculation formula of Gini impurity is: The right subset D right The calculation formula of Gini impurity is: Among them, n k,left D left The number of samples in the kth category; n k,right D right The number of samples of the kth class in .

6. The one-stop self-management method based on NMOSD according to claim 1, characterized in that: The calculation formula of the recurrence risk index is: Among them, w i is the weight of feature i; r i (f i ) is the rule influence value corresponding to the actual value of feature i.

7. The one-stop self-management method based on NMOSD according to claim 3, characterized in that: Prioritizing feature values ​​of the patient dataset according to Gini impurity reduction and the risk rule set further includes: Features whose Gini impurity is less than a preset threshold are preferentially selected. If the feature is directly defined as a high-risk factor by the risk rule set, the feature is placed in a priority queue.

8. The one-stop self-management method based on NMOSD according to claim 1, characterized in that: Displaying the personalized drug treatment and follow-up plan in a visual manner further includes: Display the schedule of treatment and follow-up, including medication schedule and follow-up dates, in the form of a timeline and calendar; and A color-coded circle or bar graph shows the patient's recurrence risk level, with green representing low risk, yellow representing intermediate risk, and red representing high risk.

9. A one-stop self-management system based on NMOSD, comprising: The patient data set acquisition module is used to acquire the patient data set, which includes the patient's personal information, clinical characteristics, imaging manifestations, laboratory indicators, and medication records; A risk index and level calculation module, used to obtain the patient's recurrence risk index and corresponding risk level according to the patient data set and recurrence risk factors; A drug treatment and follow-up plan determination module, used to determine the patient's personalized drug treatment and follow-up plan based on the recurrence risk index and the corresponding risk level and NMOSD treatment guidelines; The visualization display module is used to display the personalized drug treatment and follow-up plan in a visual manner.

10. 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 via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the one-stop self-management method based on NMOSD as described in any one of claims 1-8.

Images