Herpes zoster neuralgia chronic detection and AI identification model training method and system

Abstract

In the herpes zoster neuralgia chronic detection and AI identification model training method and system, information of a detector is collected, and the information of the detector comprises age, gender and herpes zoster definite diagnosis time; collecting detection information of a detector, wherein the detection information comprises a ratio of IL18 to IL18BP; pain information of the detected person is collected; the pain information of the detector comprises pain intensity and attack frequency; the pain information of the detected person is marked, marked information is obtained, and the marked information comprises acute pain, chronic pain and the risk degree of converting the acute pain into the chronic pain; performing AI training according to the detector information, the detection information and the annotation information, and obtaining a herpes zoster neuropathic pain AI feature data set after the AI training; the herpes zoster neuralgia AI feature data set is used for detecting the possibility that the herpes zoster neuralgia of the testee is converted from acute pain to chronic pain in combination with AI software. And diagnosis and treatment basis information from a brand new perspective is provided for the post-herpes zoster neuralgia.

Description

Technical Field

[0001] The present application belongs to the technical field of herpes zoster-related detection and AI analysis, and specifically relates to a detection system and method for evaluating the chronic progression of herpes zoster neuralgia and its AI recognition model training system and method. Background Art

[0002] Postherpetic neuralgia occurs after infection with the herpes zoster virus. In 10% of patients, pain persists for more than a month. If left untreated or treated improperly, the pain can persist even after the rash disappears, and in some cases, it can persist for decades. It's related to age of onset, rarely occurring in patients under 40, but occurring in 50% of those over 60 and 75% of those over 70. Approximately 10% to 25% of patients experience persistent pain for more than a year. Pain can occur before or alongside the appearance of a rash. This painful condition is one of the most difficult to treat in the medical field, earning it the nickname "immortal cancer."

[0003] Pain intensity: In clinical practice, we often use the visual analogue scale (VAS) and numeric rating scale (NRS) to measure pain intensity.

[0004] The more common treatments include: 1. Local treatment: 5% lidocaine patch and capsaicin patch are commonly used topical medications in clinical practice.

[0005] 2. Pharmacological Treatment: First-line systemic medications include calcium channel modulators (pregabalin and gabapentin) and tricyclic antidepressants (amitriptyline). Second-line medications include opioids and tramadol. Other medications include serotonin and norepinephrine reuptake inhibitors (SNRIs) (venlafaxine and duloxetine), extracts from inflammatory skin of vaccinia-vaccinated rabbits, other antiepileptic drugs (lamotrigine, sodium valproate, topiramate), and aconitine A.

[0006] 3. Minimally invasive interventional therapy, including neurointerventional technology and neuromodulation technology. Neurointerventional technology includes nerve block, selective nerve damage and intrathecal drug infusion therapy; neuromodulation technology includes nerve block, selective nerve damage and intrathecal drug infusion therapy.

[0007] 4. Other treatments: Physical therapy such as microwave therapy, ultrasound therapy, laser therapy, vibration therapy, etc. In addition, acupuncture therapy, ozone therapy and other technologies have shown certain effects in clinical practice. There are domestic reports that the efficacy of ozone interventional treatment for refractory PHN is stable after 5 years of follow-up, but more research data is needed.

[0008] Pain, one of the most common clinical symptoms, is a global challenge affecting human health. Chronic pain often originates from acute pain, and the transition from acute to chronic pain involves a series of changes in biopsychosocial patterns. However, the pathogenesis of the transition from acute to chronic pain remains unclear, and reliable indicators for monitoring pain chronicity are lacking.

[0009] However, whether pain will turn from acute pain to chronic pain is usually not accurately known or predicted in the existing technology. It is even more difficult to determine or assess the risk of acute pain turning into chronic pain for different individual patients. How to assess the conversion risk of acute pain turning into chronic pain is a technical problem to be solved. If the risk assessment of acute pain turning into chronic pain can be carried out, the risk can be predicted in advance and corresponding measures can be taken early. If it is known that the conversion risk is high, further treatment measures can be taken as soon as possible to prevent the conversion to chronic pain and reduce the time of chronic pain. Summary of the Invention

[0010] In this application, the inventors propose a method and system for detecting the chronicity of postherpetic neuralgia and its AI recognition model training. These methods and systems can assess the chronicity of pain. The AI ​​recognition model training method and system can also assess the risk of pain conversion. By leveraging AI computing power to learn from large sample data, effective information can be extracted to assess the risk of chronic pain. This addresses the previous lack of scientific means for detection and intervention, providing a new perspective on the diagnosis and treatment of postherpetic neuralgia.

[0011] The technical solution to the technical problem solved in this application is a training method for an AI recognition model for detecting chronic herpes zoster neuralgia, which collects information of the tester, including age, gender, and time of diagnosis of herpes zoster; collects tester information, including the ratio of IL18 to IL18BP; collects pain information of the tester, including pain intensity and frequency of attacks; labels the pain information of the tester to obtain labeled information, including acute pain, chronic pain, and the risk of acute pain turning into chronic pain; performs AI training based on the above-mentioned tester information, test information, and labeled information, and obtains an AI feature data set for herpes zoster neuralgia after AI training; the AI ​​feature data set for herpes zoster neuralgia is used in combination with AI software to detect the possibility of the test subject's herpes zoster neuralgia turning from acute pain to chronic pain.

[0012] Alternatively, the test information includes the unit volume content of IL18 and IL18BP, and the test information is obtained by measuring a blood sample of the test subject.

[0013] The frequency of attacks includes the number of pain episodes per day and the average duration of a single pain episode.

[0014] It can be that the risk of acute pain turning into chronic pain is expressed as a percentage, and also includes the length of time it takes for herpes zoster neuralgia to turn from acute pain to chronic pain.

[0015] The technical solution to the technical problem solved by the present application can also be an AI recognition model training system for detecting chronic herpes zoster neuralgia, including a detector information collection component, a detection information collection component, a pain information collection component, a labeling information collection component, and an AI training and calculation component; the detector information collection component is used to collect detector information, and the detector information includes age, gender, and time of diagnosis of herpes zoster; the detection information collection component is used to collect detection information, and the detection information includes the ratio of IL18 to IL18BP; the pain information collection component is used to collect pain information, and the pain information includes pain intensity and attack frequency; the labeling information collection component is used to collect labeling information, and the labeling information includes acute pain, chronic pain, and the risk of acute pain turning into chronic pain; the AI ​​training and calculation component performs AI training based on the above-mentioned detector information, detection information, pain information and labeling information, and obtains an AI feature data set for herpes zoster neuralgia after AI training; the AI ​​feature data set for herpes zoster neuralgia is used in combination with AI software to detect the possibility of the herpes zoster neuralgia of the test subject turning from acute pain to chronic pain.

[0016] The technical solution to the technical problem solved in the present application can also be a chronic herpes zoster neuralgia detection system, including a tester information collection component, a detection information collection component, and an AI calculation component; the tester information collection component is used to collect tester information, and the tester information includes age, gender, and herpes zoster diagnosis time; the detection information collection component is used to collect detection information, and the detection information includes the ratio of IL18 to IL18BP; the AI ​​calculation component includes a herpes zoster neuralgia AI feature data set; the AI ​​calculation component combines the tester information and the detection information to calculate and obtain a herpes zoster neuralgia assessment report; the herpes zoster neuralgia assessment report includes a risk assessment value for the herpes zoster neuralgia to turn from acute pain to chronic pain.

[0017] It may also include a pain information collection component, which is used to collect pain information, including pain intensity and attack frequency; the AI ​​calculation component combines the detector information, detection information, and pain information to calculate and obtain a herpes zoster neuralgia assessment report.

[0018] The technical solution to the technical problem solved in the present application can also be a method for detecting the chronicity of herpes zoster neuralgia, which collects the information of the tester, including age, gender, and time of diagnosis of herpes zoster; collects the tester's detection information, including the ratio of IL18 to IL18BP; AI software combines the tester information and detection information with the herpes zoster neuralgia AI feature data set to calculate the herpes zoster neuralgia assessment report; the herpes zoster neuralgia assessment report includes a risk assessment value for the herpes zoster neuralgia to transform from acute pain to chronic pain.

[0019] Alternatively, the test information includes the unit volume content of IL18 and IL18BP, and the test information is obtained by measuring a blood sample of the test subject.

[0020] It can be that the AI ​​feature data set of herpes zoster neuralgia is obtained by training the historical data of herpes zoster neuralgia patients; the historical data of herpes zoster neuralgia patients include the tester information including age, gender, and herpes zoster diagnosis time; the historical data of herpes zoster neuralgia patients include the tester information including the ratio of IL18 to IL18BP; the historical data of herpes zoster neuralgia patients include the tester's pain information; the tester's pain information includes pain intensity and attack frequency.

[0021] The frequency of attacks includes the number of pain episodes per day and the average duration of a single pain episode.

[0022] One of the technical effects of the above technical solution is that pain assessment based on the ratio of IL18 to IL18BP is not only the applicant's scientific research achievement, but also an industry first.

[0023] One of the technical effects of the above technical solution is: based on the detection information such as the ratio of IL18 to IL18BP, the information of the tester, and the pain information of the tester, through AI training, an AI feature data set of herpes zoster neuralgia pain is obtained. Based on the AI ​​feature data set of herpes zoster neuralgia pain, combined with AI software, it can detect the possibility of the test subject's herpes zoster neuralgia from acute pain to chronic pain, thereby giving the possibility of its conversion from acute pain to chronic pain, and providing a conversion possibility parameter as one of the basis for subsequent treatment decisions. The possibility can be a data between 0-100%, or it can be a graded identification data, such as 1-4, representing the possibility from low to high, or from high to low, respectively.

[0024] One of the technical effects of the above technical solution is that the unit volume content of IL18 and IL18BP provides accurate basic data for AI training, and the imbalance of the data ratio is one of the signs leading to the chronic development of neuropathic pain.

[0025] One of the technical effects of the above technical solution is that the information of the tester includes age, gender, and time of diagnosis of herpes zoster, and corresponding data in more dimensions can be obtained, making the AI ​​feature data set of herpes zoster neuralgia richer and more accurate.

[0026] One of the technical effects of the above technical solution is that pain information includes pain intensity and frequency of attacks. The frequency of attacks includes the number of pains per day and the average duration of a single pain. Corresponding data in more dimensions can be obtained, making the AI ​​feature data set of herpes zoster neuralgia richer and more accurate.

[0027] One of the technical effects of the above technical solution is that the AI ​​recognition model training system provides a material basis for AI training, enabling long-term implementation of a cycle of data accumulation and training.

[0028] One of the technical effects of the above technical solution is that the chronicity detection system for herpes zoster neuralgia provides a basis for the chronicity detection method for herpes zoster neuralgia, allowing the detection to be carried out.

[0029] One of the technical effects of the above technical solution is that the method for detecting the chronicity of herpes zoster neuralgia can obtain a herpes zoster neuralgia assessment report based on the output of the herpes zoster neuralgia AI feature data set. The herpes zoster neuralgia assessment report includes a risk assessment value for the transition of herpes zoster neuralgia from acute pain to chronic pain, providing a quantitative assessment data for the progression of pain for reference by clinicians.

[0030] The AI ​​dataset for herpes zoster neuralgia pain provides a foundation for repetitive iteration. The more data involved in training, the closer the output probability assessment results are to reality. AI recognition and detection information, as well as pain information, can be collected through network connectivity, improving AI data collection capabilities. The more data, the more adaptable the trained model and dataset. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a schematic diagram of the AI ​​recognition model training method for detecting chronic herpes zoster neuralgia; and the system; Figure 2 This is a schematic diagram of the AI ​​recognition model training system for detecting chronic herpes zoster neuralgia; Figure 3 This is a schematic diagram of an AI recognition method for detecting chronic herpes zoster neuralgia; Figure 4 This is a schematic diagram of the AI ​​recognition system for detecting chronic herpes zoster neuralgia; Figure 5 This is a schematic diagram of the AI ​​recognition system for detecting chronic herpes zoster neuralgia. DETAILED DESCRIPTION

[0032] The contents of this application are further described in detail below in conjunction with the accompanying drawings. It should be noted that the following is a description of the preferred embodiments of the present invention and does not constitute any limitation to the present invention. The description of the preferred embodiments of the present invention is only an illustration of the general principles of the present invention. The numbers such as "first", "second" and "A" and "B" involved in the present invention are only for the convenience of explanation and do not represent the order relationship in time or space. The combination of letters and numbers "TA", "TB" and "H" involved in the present invention are only for the convenience of explanation, and the specific meaning is determined by the specific words referred to.

[0033] Postherpetic neuralgia (PHN) is a common clinical neuropathic pain condition caused by the varicella zoster virus (VZV), often characterized by excruciating pain and severity. Following VZV infection, some patients develop PHN, while others do not. To date, our understanding of its pathogenesis remains limited, resulting in limited preventive and therapeutic measures. Although PHN is associated with abnormal expression of various cytokines, this remains controversial and lacks systematic observation. In previous studies, the applicant's research team found that expression levels of IL18BP (interleukin-18 binding protein, IL18BP) were significantly higher in VZV-infected patients without PHN than in patients who developed PHN following VZV infection (unpublished).

[0034] Vecchié, Marino, and others reported that under physiological conditions, the ratio of IL18 (interleukin-18, IL18) to IL18bp is in equilibrium. However, upon viral infection, the ratio of IL18 to IL18BP becomes unbalanced, leading to the onset of disease. Studies published in Nature further confirm that IL18BP binds to IL18, thereby attenuating the immune overreaction caused by IL18. Noguchi et al., through intrathecal injection of IL18, found that it exacerbated pain symptoms in rats with a neuropathic pain model. Other studies have found that intrathecal injection of IL18BP in rats with a neuropathic pain model effectively alleviated pain behaviors and enhanced the analgesic effect of morphine.

[0035] Interleukin-18 (IL-18), also known as IFN-γ-inducing factor, is a member of the IL-1 cytokine family and is constitutively expressed in immune cells and other non-immune cells (such as intestinal epithelial cells, keratinocytes, and endothelial cells). IL-18 exists intracellularly as an inactive precursor. During inflammation, it is cleaved by inflammasomes such as NLRP3 and NLRP1, and mature IL-18 is released extracellularly to mediate downstream inflammatory responses. It drives Myd88 signaling through heterodimerization of IL-18 receptor subunits (IL-18Rα and IL-18Rβ), activating downstream MAPK and NF-κB signaling.

[0036] IL18BP: Interleukin-18 binding protein (IL18BP) is a constitutively secreted protein with an exceptionally high affinity for IL18 (400 pM). In the serum of healthy individuals, it is present at a 20-fold higher molar concentration than IL18. Studies by Kim, Im, and others have demonstrated that the IL18 / IL18BP complex negatively regulates the interaction between IL18 and the IL18 receptor, thereby inhibiting IL18-induced IFN-γ production and suppressing its potent immune-stimulating activity.

[0037] The interaction between IL18 and IL18BP is involved in the occurrence of many diseases: Under physiological conditions, IL18 and IL18BP interact and regulate each other, participating in the occurrence and development of many autoimmune diseases.

[0038] There has been considerable progress in the study of IL-18 / IL-18BP in characterizing and treating autoimmune and inflammatory diseases. Patent project CN 115925928 A provides suitable tools for detecting free IL-18 and for diagnosing inflammatory diseases associated with free IL-18 in body fluids, and effectively treats patients using binding molecules that specifically bind to free IL-18. The binding molecules invented in patent project CN 109517065 A can be used as therapeutic molecules for treating IL-18-related autoimmune and inflammatory diseases or as diagnostic tools for characterizing, detecting, and / or measuring IL-18 unbound to IL-18BP as a component of the total IL-18 pool. Patent project CN 116472059 A provides IL18 antagonist molecules for treating and preventing atopic dermatitis or related diseases. Although recent studies at home and abroad tend to believe that inflammation and immune mechanisms are important causes of chronic neuropathic pain, this view cannot explain many problems encountered in clinical treatment, and there is currently no technology to discover IL-18 or IL-8BP for predicting or treating neuropathic pain-related diseases.

[0039] This suggests that, combined with the applicant's team's previous research and existing technological achievements, IL-18 / IL-18BP is expected to serve as a pair of biomarkers for predicting the chronicity of neuropathic pain, particularly for the development of postherpetic neuralgia. This approach could help predict the risk of acute pain patients developing chronic pain, provide guidance for early intervention, assess the causes of persistent chronic pain, and guide the use of clinical analgesics or the determination of treatment methods, ultimately helping to alleviate or eliminate patients' pain and improve their quality of life.

[0040] The current progress of clinical trials of drugs targeting IL-18 for the treatment of inflammatory diseases is as follows: Tadekinig alfa (human recombinant IL-18 binding protein) – for rheumatoid arthritis and psoriasis – Study results: Free IL-18 levels were not increased in patients with rheumatoid arthritis or psoriatic arthritis compared with healthy individuals.

[0041] Pralnacasan (interleukin-1β converting enzyme inhibitor) – for rheumatoid arthritis – study results: well tolerated, can suppress inflammation, but is suspected of promoting hepatotoxicity.

[0042] GSK1070806 (anti-IL-18 monoclonal antibody) – for type 2 diabetes – study results: inhibition of IL-18 failed to improve glycemic control.

[0043] The existing technology targets IL-18-related inflammatory diseases or autoimmune disorders, including chronic obstructive pulmonary disease (COPD), infusion-related lung injury, bronchopulmonary dysplasia (BPD), acute respiratory distress syndrome (ARDS), adult-onset Still's disease, juvenile-onset Still's disease, interstitial lung disease (ILD), idiopathic pulmonary fibrosis, cystic fibrosis, pulmonary hypertension, asthma, bronchiectasis, heart failure, amyotrophic lateral sclerosis (ALS), dry eye disease (DED), keratitis, corneal ulcers and abrasions, corneal angiogenesis, pathological intraocular neovascularization, iritis, glaucoma, macular degeneration, Sjögren's syndrome, autoimmune uveitis, Behçet's disease, and other diseases. The scope of this application includes: leukemia, conjunctivitis, allergic conjunctivitis, blepharodermatitis, type 2 diabetes, non-alcoholic fatty liver disease (NAFLD), steatohepatitis, solid organ and blood transplantation, ischemia-reperfusion injury, familial Mediterranean fever, tumor necrosis factor receptor 1-related periodic syndrome, cryopyrin-related periodic fever syndrome, hyper-IgD syndrome, gout, Schnitzler syndrome, Wegener's granulomatosis, also known as granulomatosis with polyangiitis (GPA), Hashimoto's thyroiditis, Crohn's disease, ulcerative colitis, immunoglobulin-4 (IgG4)-related diseases, and stem cell therapy. However, it does not cover chronic neuropathic pain disorders including postherpetic neuralgia or similar diseases.

[0044] The number of patients with chronic pain in my country is increasing year by year. Chronic pain often originates from acute pain. The theory of pathophysiological mechanisms involved in the transition from acute pain to chronic pain has not yet been established and perfected. Currently, there are still great challenges in the early diagnosis and precise intervention of chronic pain.

[0045] One of the objectives of this invention is to guide clinicians in assessing and predicting the progression of chronic pain in patients by measuring the IL18 / IL18BP ratio as a biological indicator. This involves proposing a new theoretical model for chronic pain and exploring the potential for specific biomarkers of chronic pain to monitor and prevent the transition from acute pain to chronic pain. Furthermore, the power of AI is employed to quantitatively assess the progression of pain.

[0046] IL-18 activity in the body is tightly regulated by the negative regulation of IL-18 Binding Protein (IL-18BP). Under normal or physiological conditions, the ratio of IL-18 to IL-18BP is in a dynamic equilibrium. An imbalance in this ratio can lead to the chronic development of neuropathic pain. Existing ELISA methods are used to measure the IL18 / IL18BP ratio in patient serum samples to assess and predict the chronicity of neuropathic pain, particularly in patients with postherpetic neuralgia.

[0047] Under normal or physiological compensation conditions, the ratio of IL18 and IL18BP is in a dynamic equilibrium state. An imbalance in the ratio of IL18 and IL18BP leads to the chronic development of neuropathic pain.

[0048] After extensive research, we found that the imbalance in the ratio of IL18 and IL18BP is associated with the chronic development of herpes zoster neuralgia. However, this imbalance has a complex correlation mechanism with the patient's gender, age, and onset time. It is difficult for clinicians to judge the chronicity of herpes zoster neuralgia from these data. With the development of AI computing, we have found through a lot of data analysis and experiments that the use of AI technology, after training with massive data, can more accurately judge the chronic transformation process of patients' herpes zoster neuralgia, which can serve as a diagnostic reference for clinicians.

[0049] The ratio of IL18 and IL18BP is used as the key parameter for AI training to obtain the AI ​​feature dataset of herpes zoster neuralgia.

[0050] like Figure 1 In an embodiment of a method for training an AI recognition model for detecting chronic herpes zoster neuralgia, the method includes collecting information of the tester, including age, gender, and time of diagnosis of herpes zoster; collecting detection information of the tester, including the ratio of IL18 to IL18BP; collecting pain information of the tester, including pain intensity and frequency of attacks; labeling the pain information of the tester to obtain labeling information, including acute pain, chronic pain, and risk of acute pain turning into chronic pain; performing AI training based on the above-mentioned tester information, detection information, and labeling information, and obtaining an AI feature data set for herpes zoster neuralgia after AI training; the AI ​​feature data set for herpes zoster neuralgia is used in combination with AI software to detect the possibility of the test subject's herpes zoster neuralgia turning from acute pain to chronic pain.

[0051] An AI recognition model training method for detecting chronic herpes zoster neuralgia. The detection information includes the unit volume content of IL18 and IL18BP, and the detection information is obtained by measuring the blood sample of the tester.

[0052] Attack frequency includes the number of pain episodes per day and the average duration of a single pain episode.

[0053] The risk of acute pain turning into chronic pain is expressed as a percentage and also includes the time it takes for herpes zoster neuralgia to turn from acute pain into chronic pain.

[0054] like Figure 2In an embodiment of an AI recognition model training system for detecting chronic herpes zoster neuralgia, the system includes a detector information collection component, a detection information collection component, a pain information collection component, a labeling information collection component, and an AI training calculation component; the detector information collection component is used to collect detector information, and the detector information includes age, gender, and herpes zoster diagnosis time; the detection information collection component is used to collect detection information, and the detection information includes the ratio of IL18 to IL18BP; the pain information collection component is used to collect pain information, and the pain information includes pain intensity and attack frequency; the labeling information collection component is used to collect labeling information, and the labeling information includes acute pain, chronic pain, and the risk of acute pain turning into chronic pain; the AI ​​training calculation component performs AI training based on the above-mentioned detector information, detection information, pain information and labeling information, and obtains an AI feature data set for herpes zoster neuralgia after AI training; the AI ​​feature data set for herpes zoster neuralgia is used to be combined with AI software to detect the possibility of the herpes zoster neuralgia of the tested person turning from acute pain to chronic pain.

[0055] like Figure 4 and Figure 5 In an embodiment of a chronic herpes zoster neuralgia detection system, the system includes a detector information collection component, a detection information collection component, and an AI calculation component; the detector information collection component is used to collect detector information, and the detector information includes age, gender, and herpes zoster diagnosis time; the detection information collection component is used to collect detection information, and the detection information includes the ratio of IL18 to IL18BP; the AI ​​calculation component includes a herpes zoster neuralgia AI feature data set; the AI ​​calculation component combines the detector information and the detection information to calculate and obtain a herpes zoster neuralgia assessment report; the herpes zoster neuralgia assessment report includes a risk assessment value of herpes zoster neuralgia turning from acute pain to chronic pain.

[0056] like Figure 5 In an embodiment of a chronic herpes zoster neuralgia detection system, a pain information collection component is used to collect pain information, including pain intensity and attack frequency; an AI computing component combines the detector information, detection information, and pain information to calculate and obtain a herpes zoster neuralgia assessment report.

[0057] like Figure 3 In an embodiment of a method for detecting chronic herpes zoster neuralgia, information of the tester is collected, including age, gender, and time of diagnosis of herpes zoster; test information of the tester is collected, including the ratio of IL18 to IL18BP; AI software combines the tester information and the test information with the herpes zoster neuralgia AI feature data set to calculate a herpes zoster neuralgia assessment report; the herpes zoster neuralgia assessment report includes a risk assessment value for the herpes zoster neuralgia to transition from acute pain to chronic pain.

[0058] The test information includes the unit volume content of IL18 and IL18BP, and the test information is obtained by measuring the blood sample of the test subject.

[0059] The AI ​​feature dataset for herpes zoster neuralgia is obtained by training with historical data of patients with herpes zoster neuralgia; the historical data of patients with herpes zoster neuralgia includes the tester information including age, gender, and time of diagnosis of herpes zoster; the historical data of patients with herpes zoster neuralgia includes the tester information including the ratio of IL18 to IL18BP; the historical data of patients with herpes zoster neuralgia includes the tester's pain information; the tester's pain information includes pain intensity and frequency of attacks.

[0060] Attack frequency includes the number of pain episodes per day and the average duration of a single pain episode.

[0061] Although the present invention is illustrated and described based on the preferred embodiment and several alternatives, the invention is not limited by the specific description in this specification. Other additional replacement or equivalent components can also be used to practice the present invention.

Claims

1. A method for training an AI recognition model for chronic herpes zoster neuralgia detection, characterized in that: Collecting information of the tester, including age, gender, and time of diagnosis of herpes zoster; Collecting test information of testers, including the ratio of IL18 to IL18BP; Collect the pain information of the tester; the pain information of the tester includes pain intensity and frequency of attacks; The pain information of the tester is labeled to obtain the labeled information, which includes acute pain, chronic pain, and the risk of acute pain turning into chronic pain; AI training is performed based on the above-mentioned detector information, detection information, and annotation information, and an AI feature data set of herpes zoster neuralgia is obtained after AI training; The herpes zoster neuralgia AI feature data set is used in combination with AI software to detect the possibility of the test subject's herpes zoster neuralgia turning from acute pain to chronic pain.

2. The AI ​​recognition model training method for detecting chronic herpes zoster neuralgia according to claim 1 is characterized in that: Include any of the following technical features: TA10: The detection information includes the unit volume content of IL18 and IL18BP, and the detection information is obtained by measuring the blood sample of the test subject; TA20: The attack frequency includes the number of pain episodes per day and the average duration of a single pain episode.

3. The AI ​​recognition model training method for detecting chronic herpes zoster neuralgia according to claim 1, characterized in that: The risk of acute pain turning into chronic pain is expressed as a percentage and also includes the time required for herpes zoster neuralgia to turn from acute pain to chronic pain.

4. An AI recognition model training system for chronic herpes zoster neuralgia detection, characterized by: It includes the detector information collection component, the detection information collection component, the pain information collection component, the annotation information collection component, and the AI ​​training calculation component; The tester information collection component is used to collect tester information, including age, gender, and time of diagnosis of herpes zoster; The detection information collection component is used to collect detection information, and the detection information includes the ratio of IL18 to IL18BP; The pain information collection component is used to collect pain information, including pain intensity and attack frequency; The annotation information collection component is used to collect annotation information, including acute pain, chronic pain, and the risk of acute pain turning into chronic pain; The AI ​​training computing component performs AI training based on the above-mentioned detector information, detection information, pain information and annotation information, and obtains the AI ​​feature data set of herpes zoster neuralgia after AI training; The herpes zoster neuralgia AI feature data set is used in combination with AI software to detect the possibility of the test subject's herpes zoster neuralgia turning from acute pain to chronic pain.

5. A chronicity detection system for herpes zoster neuralgia, characterized in that: Including detector information collection component, detection information collection component, and AI computing component; The tester information collection component is used to collect tester information, including age, gender, and time of diagnosis of herpes zoster; The detection information collection component is used to collect detection information, and the detection information includes the ratio of IL18 to IL18BP; The AI ​​computing component includes the herpes zoster neuralgia AI feature dataset; The AI ​​computing component calculates the tester information and the test information to obtain a herpes zoster neuralgia assessment report; The herpes zoster neuralgia assessment report includes a risk assessment value for the herpes zoster neuralgia to transform from acute pain to chronic pain.

6. The chronicity detection system for herpes zoster neuralgia according to claim 5, characterized in that: It also includes a pain information collection component. The pain information collection component is used to collect pain information, including pain intensity and attack frequency; The AI ​​computing component combines the tester information, test information, and pain information to obtain a herpes zoster neuralgia assessment report.

7. A method for detecting chronicity of herpes zoster neuralgia, characterized in that: Collecting information of the tester, including age, gender, and time of diagnosis of herpes zoster; Collecting test information of testers, including the ratio of IL18 to IL18BP; The AI ​​software calculates the tester information and the test information in combination with the herpes zoster neuralgia AI feature data set to obtain a herpes zoster neuralgia assessment report; The herpes zoster neuralgia assessment report includes a risk assessment value for the herpes zoster neuralgia to transform from acute pain to chronic pain.

8. The method for detecting chronicity of herpes zoster neuralgia according to claim 7, characterized in that: The detection information includes the unit volume content of IL18 and IL18BP, and the detection information is obtained by measuring the blood sample of the test subject.

9. The method for detecting chronicity of herpes zoster neuralgia according to claim 7, characterized in that: The herpes zoster neuralgia AI feature data set is obtained by training with historical data of herpes zoster neuralgia patients; The historical data of patients with herpes zoster neuralgia include the information of the tester including age, gender, and time of diagnosis of herpes zoster; The historical data of patients with herpes zoster neuralgia included the tester information including the ratio of IL18 to IL18BP; The historical data of patients with herpes zoster neuralgia include the pain information of the examinee; The tester's pain information includes pain intensity and frequency of attacks.

10. The method for detecting chronicity of herpes zoster neuralgia according to claim 7, characterized in that: The attack frequency includes the number of pain episodes per day and the average duration of a single pain episode.

Images