Effectiveness analysis method for promoting stem cells to release exosomes in liver injury treatment

Abstract

The embodiment of the invention provides an effectiveness analysis method for promoting stem cells to release exosomes in liver injury treatment, and relates to the field of medicine and artificial intelligence. The method comprises the following steps: acquiring individualized first data of a first object, and acquiring second data related to an in-vivo stem cell exosome secretion process of the first object when a first recommendation scheme is implemented in a first time period; the first recommended scheme comprises a scheme for promoting stem cells to release exosomes to treat the liver injury problem of the first object; predicting the treatment effect of the first recommendation scheme based on the first data and the second data through a pre-trained first artificial intelligence AI model; feedback information of the first object in the second time period after the first recommendation scheme is implemented is obtained; and determining the effectiveness of the first recommendation scheme based on the treatment effect and the feedback information. The embodiment of the invention can be adapted to individual conditions, and the effectiveness of a scheme for recommending liver injury by promoting stem cells to release exosomes is accurately analyzed.

Description

Technical Field

[0001] This disclosure relates to the fields of biomedicine and artificial intelligence, and more specifically, to a method for analyzing the effectiveness of promoting the release of exosomes from stem cells in the treatment of liver injury. Background Technology

[0002] Stem cell exosomes are nanoscale vesicles secreted by stem cells, containing bioactive substances such as proteins, RNA (e.g., miRNA), and lipids. Stem cell exosomes can deliver the repair and regulatory capabilities of stem cells to target cells, achieving therapeutic effects without the need for stem cell transplantation.

[0003] Stem cell exosomes have demonstrated multidimensional roles in the treatment of liver injury. However, the mechanisms by which stem cell exosomes exert their therapeutic effects on liver injury are highly complex and not yet fully elucidated. Furthermore, exosomes derived from stem cells of different origins exhibit varying effects on recipient cells, further complicating and demystifying exosome therapy. Therefore, despite the significant potential of stem cell exosomes in treating liver injury, research on their safety and efficacy remains inadequate. Summary of the Invention

[0004] This disclosure provides a method for analyzing the effectiveness of promoting stem cell exosome release in the treatment of liver injury, which can be adapted to individual circumstances to accurately analyze the effectiveness of the recommended regimen for promoting stem cell exosome release in the treatment of liver injury.

[0005] According to one aspect of the present disclosure, a method for analyzing the effectiveness of promoting stem cell exosome release in the treatment of liver injury is provided, comprising: Acquire first individualized data for the first subject and second data related to the stem cell exosome secretion process in the first subject during a first time period, when implementing the first recommended treatment plan; the first recommended treatment plan includes a plan to treat the liver injury problem of the first subject by promoting the release of exosomes from stem cells. Based on the first data and the second data, a pre-trained first artificial intelligence (AI) model is used to predict the treatment effect of the first recommended treatment plan. Obtain feedback information from the first object after implementing the first recommendation scheme in the second time period; Based on the treatment effect and the feedback information, the effectiveness of the first recommended treatment plan is determined.

[0006] In one feasible embodiment, the first data includes at least one of medical indicators related to the degree of liver injury, previous treatment history, or history of underlying diseases; the medical indicators related to liver injury include at least one of liver function indicators or liver imaging results. And / or, the acquisition of the second data includes: During the first time period, at least one sample is collected from the first object, either a blood sample or a tissue sample. The collected samples were analyzed to obtain at least one of the following data as secondary data: the amount of stem cell exosomes secreted, the protein content, RNA content, or lipid content in the exosomes.

[0007] In one feasible embodiment, predicting the treatment effect of the first recommended treatment plan based on the first data and the second data using a pre-trained first AI model includes: The first AI model extracts and fuses features from the first data and the second data. Based on the processed data and preset evaluation indicators, it outputs the therapeutic effect of the first recommended solution on the liver injury of the first subject. The therapeutic effect includes at least one of the following: the degree of improvement of liver injury indicators, the recovery of liver function, or the degree of symptom relief.

[0008] In a feasible embodiment, obtaining feedback information of the first object after implementing the first recommendation scheme in the second time period includes: During the second time period, based on a preset second cycle, at least one of the active feedback information or passive feedback information of the first object is obtained; The active feedback information includes at least one of the changes in physical sensations or symptoms actively reported by the first subject; The passive feedback information includes conducting a medical examination on the first subject and obtaining at least one of the following as feedback information: liver function indicators, liver imaging results, or clinical symptoms.

[0009] In one feasible embodiment, determining the effectiveness of the first recommended regimen based on the treatment effect and the feedback information includes: The treatment effect was compared and analyzed with the feedback information; If the improvement in liver damage of the first subject indicated by the feedback information is consistent with the treatment effect and meets the preset effective standard, then the first recommended plan is determined to be effective. If the improvement in liver damage of the first subject indicated by the feedback information is inconsistent with the treatment effect, or fails to meet the preset effective standard, then the first recommended plan is determined to be invalid or needs to be adjusted.

[0010] In a feasible embodiment, when it is determined that the first recommended solution is invalid or needs adjustment, the method further includes: Based on the difference between the feedback information and the treatment effect, analyze the factors affecting the treatment effect; Based on the analysis results and the first recommended solution, a second recommended solution is generated using the second AI model.

[0011] In one feasible embodiment, the method further includes: Receive a query request input by a second object, the query request carrying question information related to the first object; Based on the question information, the target intent of the second object is determined using a third AI model. Based on at least one of the treatment effect, the feedback information, the effectiveness of the first recommended solution, or the second recommended solution, a response message corresponding to the target intent is output to the second object.

[0012] According to another aspect of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the methods described in the above embodiments.

[0013] According to another aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the methods described in the above embodiments.

[0014] According to one aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the methods described in the above embodiments.

[0015] The beneficial effects of the technical solutions provided in this disclosure are: This disclosure provides a method for analyzing the effectiveness of promoting stem cell exosome release in the treatment of liver injury. Specifically, by acquiring individualized first data of a first subject and second data related to the stem cell exosome secretion process during a first time period, and combining this with a pre-trained first AI model, the treatment effect of a first recommended treatment plan (such as a plan to treat the liver injury of the first subject by promoting stem cell exosome release) can be accurately predicted based on the acquired data. This prediction process is based on data and machine learning algorithms, which can more comprehensively consider the influence of various factors and improve the accuracy of the prediction. On this basis, by acquiring feedback information of the first subject after implementing the first recommended treatment plan during a second time period, the treatment effect and the first subject's response can be understood in real time. Based on the analysis of the treatment effect and feedback information, the effectiveness of the first recommended treatment plan can be determined, which helps to improve the safety and effectiveness of treatment and provides auxiliary information of reference value for research. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments of this disclosure will be briefly introduced below.

[0017] Figure 1 This is a schematic flowchart illustrating the effectiveness analysis method for promoting the release of exosomes from stem cells in the treatment of liver injury, as provided in an embodiment of this disclosure. Figure 2 A flowchart illustrating the processing of an AI model provided in this embodiment of the disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0018] The embodiments of this disclosure are described below with reference to the accompanying drawings. It should be understood that the embodiments described below with reference to the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of this disclosure, and do not constitute a limitation on the technical solutions of the embodiments of this disclosure.

[0019] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the terms “comprising” and “including” as used in embodiments of this disclosure mean that the corresponding feature can be implemented as the presented feature, information, data, step, operation, element, and / or component, but do not exclude implementation as other features, information, data, step, operation, element, component, and / or combinations thereof supported by the art. It should be understood that when we say that an element is “connected” or “coupled” to another element, the one element can be directly connected or coupled to the other element, or it can mean that the one element and the other element are connected through an intermediate element. Furthermore, “connected” or “coupled” as used herein can include wireless connection or wireless coupling. The term “and / or” as used herein indicates at least one of the items defined by the term, for example, “A and / or B” or “A, B” indicates implementation as “A,” or implementation as “B,” or implementation as “A and B.”

[0020] The term "based on" as used in the various embodiments of this disclosure can be interpreted as meaning that the premises, conditions, or information upon which it is based are not unique, but at least one or a part of them. That is, it indicates that at least one explicit basis exists, and does not exclude other possible basis.

[0021] The following description of several exemplary embodiments illustrates the technical solutions of this disclosure and the technical effects produced by these solutions. It should be noted that the following embodiments can be referenced, learned from, or combined with each other. Identical terms, similar features, and similar implementation steps in different embodiments will not be repeated.

[0022] The following is combined with Figure 1 and Figure 2 The method for analyzing the effectiveness of promoting stem cell exosome release in the treatment of liver injury, as provided in the embodiments of this disclosure, will be described in detail.

[0023] Specifically, such as Figure 1 As shown, the method provided in this embodiment includes S101 to S104: S101. Obtain first individualized data for the first subject and second data related to the stem cell exosome secretion process in the first subject during a first time period, when implementing the first recommended plan; the first recommended plan includes a plan to treat the liver injury problem of the first subject by promoting the release of exosomes from stem cells. S102. Using a pre-trained first artificial intelligence (AI) model, based on the first data and the second data, predict the treatment effect of the first recommended treatment plan; S103. Obtain feedback information from the first object after implementing the first recommendation scheme in the second time period; S104. Based on the treatment effect and the feedback information, determine the effectiveness of the first recommended plan.

[0024] Optionally, the first subject may be an individual receiving liver injury treatment and whose recommended regimen involves promoting the release of exosomes from stem cells. Specifically, the first subject may be a patient or an experimental animal.

[0025] Optionally, the individualized first data can be data related to the characteristics of the first object itself. For example, the first data may include age, gender, weight, height, basic health status (such as whether the person suffers from other chronic diseases, such as diabetes, hypertension, etc.), specific causes of liver damage (such as viral infection, drug-induced liver damage, alcoholic liver damage, etc.), and the severity of liver damage (such as determined by liver function indicators such as alanine aminotransferase, aspartate aminotransferase, bilirubin, etc.).

[0026] Optionally, the first time period can be a time interval set at the beginning of the implementation of the first recommended protocol, used to collect data related to the stem cell exosome secretion process. The length of this time period can be determined according to the actual situation, such as a few days or several weeks.

[0027] Optionally, the first recommended approach could be a treatment aimed at promoting the release of exosomes from stem cells, specifically addressing the liver injury in the first patient. This first recommended approach could include selecting a suitable stem cell source (such as autologous or allogeneic stem cells, with autologous stem cells potentially obtained from tissues like bone marrow or adipose tissue) and setting induction conditions for exosome release (such as using appropriate cytokines, growth factors, or physical stimulation).

[0028] Optionally, the second data may be data reflecting the secretion of stem cell exosomes in the first subject within the first time period. The second data may include the amount of exosomes secreted (which can be determined by appropriate detection techniques, such as nanoparticle tracking analysis, enzyme-linked immunosorbent assay, etc.), the composition of exosomes (such as the proteins, nucleic acids, lipids, etc. contained therein, which can be analyzed by proteomics, transcriptomics, etc.), and the release time pattern of exosomes.

[0029] Optionally, the pre-trained first artificial intelligence (AI) model can be an AI model that has been trained in advance using a large amount of relevant medical data (such as clinical data of patients with similar liver injuries, stem cell exosome research data, etc.) to enable it to analyze and predict input data. The first AI model can be a neural network model based on deep learning, such as convolutional neural networks (CNN), recurrent neural networks (RNN) and their variants (such as long short-term memory networks LSTM, gated recurrent units GRU), or other machine learning models, such as support vector machines (SVM), random forests, etc.

[0030] Optionally, the second time period can be another time interval set after a period of time following the implementation of the first recommended treatment, used to collect feedback information from the first subject after receiving treatment. This time period is usually after the first time period, and the length of the time period can be set according to needs; this disclosure does not limit this.

[0031] Optionally, the feedback information can be various information reflecting the treatment effect and physical response of the first subject after implementing the first recommended regimen during the second time period. For example, the feedback information may include changes in liver function indicators (such as whether various transaminases, bilirubin, etc. have decreased and tended to normal), the degree of improvement in clinical symptoms (such as whether jaundice has been reduced, whether fatigue has been relieved, whether appetite has increased, etc.), and whether adverse reactions have occurred (such as fever, allergic reactions, local pain, etc.).

[0032] Optionally, obtaining the first individualized data for the first subject can be done through methods such as medical history taking, physical examination, and various laboratory and imaging examinations. For example, this may involve inquiring about the patient's medical history, medication history, and lifestyle habits; conducting a physical examination to measure height and weight; drawing blood for liver function tests, complete blood counts, and biochemical indicators; and also performing imaging examinations such as liver ultrasound, CT, and MRI.

[0033] Optionally, the second data can be collected by treating the first subject according to the first recommended protocol within a set first time period, while simultaneously collecting exosome-related data periodically using appropriate detection technologies. For example, during the treatment process, samples such as the patient's blood and body fluids (e.g., ascites, if present) can be collected periodically, and the amount of exosome secretion can be measured using appropriate analytical techniques, and the exosome components can be analyzed using proteomics technology, etc.

[0034] Optionally, the collected individualized first data of the first subject and the second data related to the stem cell exosome secretion process are input into the pre-trained AI model. The first AI model analyzes and processes these input data according to the data patterns and rules it has learned, and outputs the prediction results of the treatment effect of the first recommended plan, such as the degree of improvement of liver damage indicators and the time of symptom relief.

[0035] Optionally, feedback information can be obtained by continuously following up with the first subject during the second time period. This includes regularly checking liver function indicators, recording changes in the patient's symptoms, and inquiring about any adverse reactions.

[0036] Optionally, the treatment effect predicted by the first AI model can be compared and analyzed with the collected feedback information. If the feedback information indicates that the first subject's liver function indicators have significantly improved, symptoms have been significantly relieved, and no serious adverse reactions have occurred, and this is consistent with or better than the predicted results, then the first recommended treatment plan can be determined to be effective; conversely, if the feedback information is not ideal and differs significantly from the predicted results, it may be necessary to adjust the recommended treatment plan or further investigate the reasons.

[0037] In this embodiment of the disclosure, by acquiring individualized first data of the first subject and second data related to the stem cell exosome secretion process during a first time period, and combining this with a pre-trained first AI model, the therapeutic effect of a first recommended treatment plan (such as a plan to treat the liver injury of the first subject by promoting the release of exosomes from stem cells) can be accurately predicted based on the acquired data. This prediction process is based on data and machine learning algorithms, which can more comprehensively consider the influence of various factors and improve the accuracy of the prediction. On this basis, by acquiring feedback information of the first subject after implementing the first recommended treatment plan during a second time period, the therapeutic effect and the first subject's response can be understood in real time. Based on the analysis of the therapeutic effect and feedback information, the effectiveness of the first recommended treatment plan can be determined, which helps to improve the safety and effectiveness of the treatment and provides auxiliary information of reference value for research.

[0038] In one feasible embodiment, the first data includes at least one of the following: medical indicators related to the degree of liver injury, previous treatment history, or history of underlying diseases.

[0039] Among them, medical indicators related to the degree of liver injury can be used to measure various medical test data of the degree of liver damage, and can intuitively reflect the liver's functional status and the severity of damage. For example, these medical indicators related to liver injury include at least one of liver function indicators or liver imaging examination results. Liver function indicators can be obtained through blood tests, such as alanine aminotransferase (ALT), aspartate aminotransferase (AST), total bilirubin, and globulin. Liver imaging examination results can be obtained by examining the liver using imaging techniques (such as CT, ultrasound, and MRI), and these results can show the liver's morphology, size, structure, presence of space-occupying lesions, and changes in the density or signal of the liver parenchyma.

[0040] In a feasible embodiment, the acquisition of the second data in S101 includes steps A1 to A2: Step A1: During the first time period, collect at least one of the blood or tissue samples from the first subject.

[0041] Step A2: Analyze the collected samples and obtain at least one of the following data as secondary data: secretion amount of stem cell exosomes, protein content, RNA content, or lipid content in the exosomes.

[0042] Optionally, the blood sample can be a sample collected within a first time period based on a preset first cycle. The first cycle can be a pre-set time interval for sample collection within the first time period, such as collecting samples once every day, three days, or one week, which can ensure relatively dynamic and continuous acquisition of stem cell exosome secretion data.

[0043] Optionally, the blood sample can be a sample obtained by collecting the blood pressure of the first subject. Considering that blood contains abundant cells and biomolecules, it can be used to detect the secretion amount and composition of stem cell exosomes, etc.

[0044] Optionally, the tissue sample may be a sample collected from the liver or other relevant tissues of the first subject, such as a liver tissue sample obtained by liver biopsy, to reflect the secretion of exosomes from local liver stem cells.

[0045] Optionally, when analyzing the collected samples, for blood samples, nanoparticle tracking analysis can be used to determine the secretion amount of stem cell exosomes, proteomics can be used to analyze the content and types of proteins in exosomes, RNA extraction and quantitative analysis can be used to detect the RNA content in exosomes, and lipidomics can be used to analyze the lipid content in exosomes. For tissue samples, appropriate processing (such as grinding, centrifugation, etc.) can be performed first, and then corresponding methods can be used to analyze the relevant components and secretion of stem cell exosomes.

[0046] In this embodiment, the acquired first data helps to gain a more comprehensive and in-depth understanding of the first subject's liver damage, treatment history, and basic physical condition, providing a reference for judging the effectiveness of the recommended treatment plan and improving the accuracy of the judgment results. The acquired second data helps to accurately understand the secretion and biological characteristics of stem cell exosomes in the first subject, providing more objective and accurate data support for judging the effectiveness of the first recommended treatment plan. When the first and second data are combined and processed by the first AI model, the treatment outcome of the first recommended treatment plan for the first subject's liver damage can be predicted more accurately, providing more reliable reference information.

[0047] In a feasible embodiment, in S102, a pre-trained first AI model predicts the treatment effect of the first recommended treatment plan based on the first data and the second data, including: The first AI model extracts and fuses features from the first data and the second data. Based on the processed data and preset evaluation indicators, it outputs the therapeutic effect of the first recommended solution on the liver injury of the first subject. The therapeutic effect includes at least one of the following: the degree of improvement of liver injury indicators, the recovery of liver function, or the degree of symptom relief.

[0048] Optionally, the first AI model can extract features from both the first and second datasets, such as mining key information and converting it into feature vectors. For example, for the first dataset, medical indicators related to liver damage, such as liver function indicators, can be normalized to map indicator values ​​of different dimensions to a unified range, eliminating the impact of dimensional differences on model processing. For textual data such as past medical history and underlying diseases, natural language processing techniques, such as word embedding, can be used to convert the text into vector representations and extract key information. For the second dataset, normalization can be applied to parameters such as the secretion amount of stem cell exosomes, protein content, RNA content, or lipid content within the exosomes.

[0049] Optionally, the fusion process can be achieved by directly concatenating the first and second data features after feature extraction, or by performing a weighted fusion based on the importance of the first and second data in predicting treatment effects, according to different assigned weights. The weights can be obtained based on historical data processing experience values, statistical data analysis, or other methods. Alternatively, fusion can be achieved by processing the first and second data features using a multilayer perceptron or attention mechanism to learn the complex relationships between different features and generate fused features.

[0050] Optionally, the preset assessment indicators can be pre-defined standards used to measure the therapeutic effect of the first recommended regimen on the liver injury of the first subject. The assessment indicators may include at least one of the following: the degree of improvement of liver injury indicators (such as the decrease in indicators such as alanine aminotransferase and aspartate aminotransferase), the recovery of liver function (such as the improvement of indicators such as albumin synthesis capacity and coagulation function), or the degree of symptom relief (such as the reduction of symptoms such as fatigue and jaundice).

[0051] Optionally, the treatment effect can be a predictive value of the degree of improvement in liver damage indicators, an assessment level of liver function recovery, or a probability value of the degree of symptom relief.

[0052] In this embodiment of the disclosure, by utilizing the first data and the second data, and performing feature extraction and fusion processing, various factors affecting the treatment effect can be considered more comprehensively, reducing prediction bias caused by insufficient information from a single data source, thereby improving the accuracy of the prediction of the treatment effect of the first recommended plan.

[0053] In a feasible embodiment, step S103 involves obtaining feedback information from the first object after implementing the first recommendation scheme during a second time period, including: During the second time period, based on a preset second cycle, at least one of the active feedback information or passive feedback information of the first object is obtained.

[0054] The proactive feedback information includes at least one of the changes in physical sensations or symptoms proactively reported by the first subject.

[0055] The passive feedback information includes conducting a medical examination on the first subject and obtaining at least one of the following as feedback information: liver function indicators, liver imaging results, or clinical symptoms.

[0056] Optionally, the second period can be a pre-set time interval for obtaining feedback information within the second time period, such as collecting feedback information once every day, three days, a week, or a month.

[0057] Optionally, proactive feedback can be the first subject's own expression of physical sensations or symptom changes to medical staff or researchers. It can be the patient's own subjective experience and perception of the treatment. Physical sensations can include various physical states experienced by the first subject during treatment, such as pain levels, fatigue, changes in appetite, and sleep quality. Symptom changes can refer to changes in the first subject's liver injury-related symptoms (such as jaundice, ascites, and liver area pain) during treatment, such as symptom relief, worsening, or the appearance of new symptoms.

[0058] Optionally, passive feedback information can be objective information about the liver condition of the primary patient obtained through medical examinations. This information is used to objectively assess the treatment effect and is not influenced by the patient's subjective feelings. Liver function indicators can be various biochemical indicators reflecting liver function obtained through blood tests, such as alanine aminotransferase (ALT), aspartate aminotransferase (AST), total bilirubin (TBIL), direct bilirubin (DBIL), indirect bilirubin (IBIL), albumin (ALB), and globulin (GLB). Abnormal changes in these indicators can indicate problems such as hepatocyte damage, abnormal bile metabolism, and decreased liver synthetic function. Liver imaging results can be images and related analysis results obtained after examining the liver using imaging techniques such as ultrasound, CT, and MRI. These results can visually display the liver's morphology, size, structure, presence of space-occupying lesions (such as tumors and cysts), and changes in the density or signal of the liver parenchyma, helping to determine the type and degree of liver damage and the treatment effect. Clinical symptoms can be external manifestations related to liver damage that medical staff observe and question the first subject, such as skin color, abdominal signs (such as ascites, hepatosplenomegaly, etc.), and mental state.

[0059] Optionally, the second time period and second cycle can be set based on the characteristics of the first recommended protocol, the expected recovery time of the liver injury in the first subject, and the study objectives. For example, for patients with acute liver injury, the second time period can be set to 2 to 4 weeks, and the second cycle can be set to 3 days; for patients with chronic liver injury, the second time period can be set to 3 to 6 months, and the second cycle can be set to one week.

[0060] In this embodiment of the disclosure, by acquiring both active and passive feedback information, the effectiveness of the first recommended treatment for liver injury in the first subject can be determined more comprehensively from both subjective and objective perspectives. Active feedback information reflects the patient's subjective feelings and experiences, while passive feedback information provides objective medical indicators and imaging evidence. The two complement each other, making the effectiveness analysis results more accurate and comprehensive.

[0061] In a feasible embodiment, in S104, the effectiveness of the first recommended regimen is determined based on the treatment effect and the feedback information, including steps B1 to B3: Step B1: Compare and analyze the treatment effect with the feedback information.

[0062] Step B2: If the improvement in liver damage of the first subject indicated by the feedback information is consistent with the treatment effect and meets the preset effective standard, then the first recommended plan is determined to be effective.

[0063] Step B3: If the improvement in liver damage of the first subject indicated by the feedback information is inconsistent with the treatment effect, or fails to meet the preset effective standard, then the first recommended plan is determined to be invalid or needs to be adjusted.

[0064] Optionally, a preset effectiveness criterion is used to determine whether the first recommended regimen is effective. This criterion can be set based on factors such as the type and severity of liver injury, treatment goals, and clinical experience, such as a certain percentage of liver function indicators returning to the normal range or symptoms being relieved to a set degree.

[0065] Optionally, in the comparative analysis of treatment effects and feedback information, the predicted data of treatment effects and feedback information can be processed to ensure that the two correspond in terms of time dimension and evaluation indicators. For example, if the treatment effect is a prediction of the degree of improvement of liver damage indicators in patients one month after treatment, then the feedback information also selects the actual liver damage indicator data obtained at one month of treatment.

[0066] Optionally, comparative analysis may include indicator comparison, such as comparing each assessment indicator involved in the treatment effect (e.g., the specific value of improvement in liver damage indicators, the level of liver function recovery, the degree of symptom relief, etc.) with the corresponding indicators in the feedback information one by one. For example, comparing the alanine aminotransferase (ALT) decrease value predicted by the first AI model with the actual ALT decrease value detected in the feedback information.

[0067] Optionally, comparative analysis may include comprehensive analysis, which can consider the interrelationships and influences between different indicators to determine the overall consistency and differences between treatment effects and feedback information. For example, although the ALT decrease is as expected, if the patient still has significant fatigue symptoms, a comprehensive evaluation of the effectiveness of the first recommended regimen is necessary.

[0068] Optionally, if the feedback information indicates that the improvement in liver damage in the first subject is consistent with the treatment effect and meets the preset effective criteria, then the first recommended regimen is determined to be effective. For example, if the first AI model predicts that the patient's albumin level will recover to above x after 3 months of treatment, the actual measured albumin level is y (y is greater than or equal to x), and the patient's symptoms such as fatigue and ascites are significantly relieved, meeting the preset effective criteria, then the recommended regimen can be determined to be effective.

[0069] Optionally, if the feedback information indicates that the improvement in liver damage in the first subject is inconsistent with the treatment effect, or fails to meet the preset effective criteria, then the first recommended regimen is determined to be ineffective or needs to be adjusted. For example, if the first AI model predicts that the patient's jaundice symptoms will be significantly reduced after 2 weeks of treatment, but the actual observation shows that the jaundice symptoms not only do not reduce but worsen, or although some indicators improve but do not meet the preset effective criteria (such as the ALT decrease not reaching the expected 30%), then the first recommended regimen is determined to be ineffective or its adjustment should be considered.

[0070] In this embodiment of the disclosure, by comparing and analyzing the predicted treatment effect with the feedback information, the effect of the first recommended treatment on the liver injury of the first subject can be determined more accurately, avoiding the limitations of relying on AI model prediction or single feedback information, and providing a more reliable basis for clinical decision-making.

[0071] In a feasible embodiment, when it is determined that the first recommended solution is invalid or needs adjustment, the method provided in this disclosure further includes steps C1 to C2: Step C1: Based on the difference between the feedback information and the treatment effect, analyze the factors affecting the treatment effect.

[0072] Step C2: Based on the analysis results and the first recommended solution, a second recommended solution is generated using the second AI model.

[0073] Optionally, a second AI model can be used to generate new recommendations based on the analysis results and the first recommendation. This second AI model can be trained on a large amount of medical data and cases to learn the complex relationships between different factors and the recommendations, thereby providing intelligent support for adjusting the recommendations.

[0074] Optionally, the second recommended plan can be a new set of treatment measures for the liver injury of the first subject generated by the second AI model after determining that the first recommended plan is ineffective or needs to be adjusted, based on the feedback information and the difference analysis results of the treatment effect, as well as the first recommended plan. The second recommended plan can also be obtained by adjusting the first recommended plan, such as modifying a certain medical parameter that promotes the release of exosomes from stem cells.

[0075] Optionally, the various indicators in the feedback information (such as specific values ​​of liver function indicators, severity of symptoms, etc.) can be compared with the corresponding predicted indicators in the treatment effect to determine the indicators and numerical differences between the two. For example, if the first AI model predicts that the alanine aminotransferase (ALT) of the first subject should drop below x after one month of treatment, but the actual measured ALT is y, then the difference in the indicator can be determined by x and y.

[0076] Optionally, in the differential analysis, factors such as the first subject's age, gender, underlying diseases (e.g., whether they also have diabetes, hypertension, etc.), immune system function, and genetic factors can be considered. For example, elderly patients may have a weaker ability to metabolize drugs, leading to drug accumulation in the body and affecting treatment efficacy.

[0077] Optionally, when analyzing factors influencing the recommended regimen, one can examine whether the drug selection in the first recommended regimen is appropriate, whether the dosage is accurate, whether the frequency of medication is reasonable, and whether the combination of treatment methods is suitable. External environmental factors can also be considered, including understanding the patient's living environment, lifestyle (such as whether they smoke, drink alcohol, or stay up late), and dietary habits (whether they consume excessive amounts of high-fat or high-sugar foods). For example, if the first patient continues to drink heavily during treatment, it may increase the burden on the liver and affect the treatment outcome.

[0078] Optionally, the difference analysis can be performed using statistical analysis methods, such as correlation analysis and regression analysis, to quantify the relationship between each factor and the treatment effect.

[0079] Optionally, the second AI model can generate a second recommended plan based on the input analysis results and the first recommended plan. The second recommended plan may include adjusting the type, dosage, and timing of medication, changing treatment methods, and adding adjuvant treatment measures.

[0080] Optionally, in actual treatment scenarios, the generated second recommended treatment plan will be implemented after further evaluation and optimization. For example, medical staff can review the second recommended treatment plan, combining their clinical experience and professional knowledge to determine its rationality and feasibility.

[0081] In this embodiment of the disclosure, by analyzing the difference between feedback information and treatment effect, the factors affecting the treatment effect are identified, and based on the analysis results and the first recommended plan, a second recommended plan can be generated. This can provide a more accurate recommended plan for the first subject's situation, thereby improving the targeting and effectiveness of the treatment.

[0082] In one feasible embodiment, the method provided by this disclosure further includes steps D1 to D3: Step D1: Receive a query request input by the second object, the query request carrying question information related to the first object.

[0083] Step D2: Using a third AI model, determine the target intent of the second object based on the problem information.

[0084] Step D3: Based on at least one of the treatment effect, the feedback information, the effectiveness of the first recommended plan, or the second recommended plan, output response information corresponding to the target intent to the second object.

[0085] Optionally, the second target group can be medical staff, medical researchers, etc., who can obtain the required information more conveniently through the configured AI agent.

[0086] Optionally, the question information is used to describe what the second subject intends to know, and the question information can be text data or voice data. For example, the question information could be "Has the first subject's liver injury symptoms improved in the past month?"

[0087] Optionally, the third AI model can be a configured interactive AI agent used to process query requests, analyze question information, and determine the target intent of the second object. The third AI model can be implemented using the relevant network architecture employed in natural language processing. Optionally, the response information can also be obtained through the third AI model.

[0088] Optionally, an interactive interface can be configured, allowing the second user to input question information and initiate a query request via text or voice input. Upon receiving the query request, the device can invoke a third AI model to perform semantic analysis of the question information using a natural language processing module, determining the user's intended intent.

[0089] Optionally, based on the defined target intent, content for generating response information can be retrieved from stored data such as treatment effects, feedback information, the effectiveness of the first recommended treatment plan, and the second recommended treatment plan. For example, if the second target's target intent is to understand the effectiveness of the first recommended treatment plan, the criteria and results for judging whether the first recommended treatment plan is effective or needs adjustment can be extracted. Then, the extracted information is integrated to obtain the response information. During the response information generation process, the response information can be presented to the second target in various forms such as text, charts, and reports. For instance, if the second target inquires about changes in the first target's liver damage indicators, a chart comparing the values ​​of liver damage indicators before and after treatment can be generated, along with a brief text description, to provide feedback to the second target.

[0090] Optionally, the generated response information can be output to the second object through an interactive interface or a specified result return method, such as sending it to the second object via SMS or email.

[0091] In this embodiment, the second subject does not need to go through complex processes or communicate with multiple medical personnel to obtain information. They can obtain a quick and accurate response through a simple query request, saving time and effort, improving information acquisition efficiency, and thus increasing the response efficiency to the recommended treatment plan. Furthermore, generating response information based on a unified data source (such as treatment effects, feedback information, etc.) avoids inaccuracies and inconsistencies caused by differences in statements from different individuals or errors in information transmission. This provides reliable information support for the second subject, helping to obtain more accurate information in the effectiveness analysis of promoting stem cell exosome release in liver injury treatment, and facilitating dynamic adjustments to the recommended treatment plan.

[0092] This disclosure provides an electronic device, including a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of the method provided in any optional embodiment of this disclosure. Compared with the prior art, this disclosure provides a method for analyzing the effectiveness of promoting stem cell exosome release in the treatment of liver injury. Specifically, by acquiring individualized first data of a first subject and second data related to the stem cell exosome secretion process in a first time period, and combining it with a pre-trained first AI model, the treatment effect of a first recommended plan (such as a plan to treat the liver injury problem of the first subject by promoting stem cell exosome release) can be accurately predicted based on the acquired data. This prediction process is based on data and machine learning algorithms, which can more comprehensively consider the influence of various factors and improve the accuracy of prediction. On this basis, by acquiring feedback information of the first subject after implementing the first recommended plan in a second time period, the treatment effect and the first subject's response can be understood in real time. Based on the analysis of the treatment effect and feedback information, the effectiveness of the first recommended plan can be determined, which helps to improve the safety and effectiveness of treatment and provides auxiliary information of reference value for research.

[0093] In one alternative embodiment, an electronic device is provided, such as Figure 3 As shown, Figure 3 The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of this disclosure.

[0094] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with this disclosure. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0095] Bus 4002 may include a pathway for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0096] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium capable of carrying or storing computer programs and capable of being read by a computer, without limitation herein.

[0097] The memory 4003 is used to store computer programs that execute embodiments of the present disclosure, and its execution is controlled by the processor 4001. The processor 4001 is used to execute the computer programs stored in the memory 4003 to implement the steps shown in the foregoing method embodiments.

[0098] Electronic devices include, but are not limited to: terminal devices and servers.

[0099] This disclosure provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the steps and corresponding content of the aforementioned method embodiments.

[0100] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, can implement the steps and corresponding content of the aforementioned method embodiments.

[0101] It should be understood that although arrows indicate various operation steps in the flowcharts of the embodiments of this disclosure, the order in which these steps are implemented is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of the embodiments of this disclosure, the implementation steps in each flowchart can be executed in other orders as required. Furthermore, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on the actual implementation scenario. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage can also be executed at different times. In scenarios where execution times differ, the execution order of these sub-steps or stages can be flexibly configured as required, and the embodiments of this disclosure do not limit this.

[0102] The above description is only an optional implementation method for some implementation scenarios of this disclosure. It should be noted that for those skilled in the art, other similar implementation methods based on the technical concept of this disclosure, without departing from the technical concept of this disclosure, also fall within the protection scope of the embodiments of this disclosure.

Claims

1. A method for analyzing the effectiveness of promoting the release of exosomes from stem cells in the treatment of liver injury, characterized in that, include: Acquire first individualized data for the first subject and second data related to the stem cell exosome secretion process in the first subject during a first time period, when implementing the first recommended treatment plan; the first recommended treatment plan includes a plan to treat the liver injury problem of the first subject by promoting the release of exosomes from stem cells. Based on the first data and the second data, a pre-trained first artificial intelligence (AI) model is used to predict the treatment effect of the first recommended treatment plan. Obtain feedback information from the first object after implementing the first recommendation scheme in the second time period; Based on the treatment effect and the feedback information, the effectiveness of the first recommended treatment plan is determined.

2. The method according to claim 1, characterized in that, The first data includes at least one of the following: medical indicators related to the degree of liver injury, previous treatment history, or history of underlying diseases; the medical indicators related to liver injury include at least one of the following: liver function indicators or liver imaging results. And / or, the acquisition of the second data includes: During the first time period, at least one sample is collected from the first object, either a blood sample or a tissue sample. The collected samples were analyzed to obtain at least one of the following data as secondary data: the amount of stem cell exosomes secreted, the protein content, RNA content, or lipid content in the exosomes.

3. The method according to claim 1, characterized in that, The first AI model, pre-trained, predicts the treatment effect of the first recommended treatment plan based on the first data and the second data, including: The first AI model extracts and fuses features from the first data and the second data. Based on the processed data and preset evaluation indicators, it outputs the therapeutic effect of the first recommended solution on the liver injury of the first subject. The therapeutic effect includes at least one of the following: the degree of improvement of liver injury indicators, the recovery of liver function, or the degree of symptom relief.

4. The method according to claim 1, characterized in that, The step of obtaining feedback information from the first object after implementing the first recommendation scheme in the second time period includes: During the second time period, based on a preset second cycle, at least one of the active feedback information or passive feedback information of the first object is obtained; The active feedback information includes at least one of the changes in physical sensations or symptoms actively reported by the first subject; The passive feedback information includes conducting a medical examination on the first subject and obtaining at least one of the following as feedback information: liver function indicators, liver imaging results, or clinical symptoms.

5. The method according to claim 1, characterized in that, Determining the effectiveness of the first recommended treatment plan based on the treatment effect and the feedback information includes: The treatment effect was compared and analyzed with the feedback information; If the improvement in liver damage of the first subject indicated by the feedback information is consistent with the treatment effect and meets the preset effective standard, then the first recommended plan is determined to be effective. If the improvement in liver damage of the first subject indicated by the feedback information is inconsistent with the treatment effect, or fails to meet the preset effective standard, then the first recommended plan is determined to be invalid or needs to be adjusted.

6. The method according to claim 5, characterized in that, When it is determined that the first recommended solution is invalid or needs to be adjusted, the method further includes: Based on the difference between the feedback information and the treatment effect, analyze the factors affecting the treatment effect; Based on the analysis results and the first recommended solution, a second recommended solution is generated using the second AI model.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Receive a query request input by a second object, the query request carrying question information related to the first object; Based on the question information, the target intent of the second object is determined using a third AI model. Based on at least one of the treatment effect, the feedback information, the effectiveness of the first recommended solution, or the second recommended solution, a response message corresponding to the target intent is output to the second object.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the method of any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images