Effect evaluation method and system for combined treatment of diabetes mellitus by liver stem cells and intestinal flora

Abstract

The invention discloses an effect evaluation method and system for combined treatment of diabetes by liver stem cells and intestinal flora, and relates to the technical field of medical data processing. According to the method, quality detection is carried out on liver stem cell suspension and intestinal flora suspension before treatment, in-vivo liver stem cell and intestinal flora detection is carried out periodically during treatment, and subsequent metabolic influence detection, diabetes related index detection, risk probability identification and adjuvant therapy scheme determination are carried out. The whole process from before treatment to during treatment is accurately evaluated, the quality of substances used for treatment is ensured, the state of in-vivo treatment components is mastered in time, the metabolic influence and the treatment effect are accurately judged, risks are effectively identified, and a targeted auxiliary treatment scheme is provided; the problems that comprehensive and dynamic evaluation of liver stem cell and intestinal flora combined treatment is lacked in traditional diabetes treatment effect evaluation, and treatment quality, in-vivo conditions, metabolic influences, treatment effects and potential risks cannot be accurately judged in time can be solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical data processing, in particular to an effect evaluation method and system for liver stem cells and intestinal flora combined treatment of diabetes. BACKGROUND

[0002] Diabetes is a metabolic disorder syndrome of sugar, fat and protein with high blood sugar as the basic pathophysiological change. If the disease is not controlled, it can easily lead to various vascular and neurological complications such as heart, brain, kidney, foot and fundus, which seriously endanger the life and health of patients. The Chinese patent application with publication number CN117174327A discloses a diabetes treatment effect evaluation system based on a matrix decomposition model and a storage medium. The diabetes treatment effect evaluation system based on the matrix decomposition model includes a data acquisition module, a data processing module and a human-computer interaction device. The data processing module obtains the diabetes and its complication prevention and treatment effect evaluation results of the diabetes patients according to the information and data before and after the treatment and its complication prevention and treatment of the diabetes patients, including: based on the obtained information and data, labeling the diabetes treatment and its complication prevention and treatment effect evaluation standard and the evaluation result classification, establishing the diabetes and its complication prevention and treatment effect evaluation index standard information database; through the constructed diabetes and its complication prevention and treatment effect evaluation model, the sample data provided by the diabetes patients to be tested are evaluated to obtain the diabetes and its complication prevention and treatment effect evaluation results of the diabetes patients.

[0003] However, the existing diabetes treatment effect evaluation method lacks comprehensive and dynamic evaluation of liver stem cells and intestinal flora combined treatment, and cannot accurately judge the treatment quality, in vivo situation, metabolic influence, treatment effect and potential risk in time. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application provides an effect evaluation method and system for liver stem cells and intestinal flora combined treatment of diabetes, which solves the problem that the traditional diabetes treatment effect evaluation method lacks comprehensive and dynamic evaluation of liver stem cells and intestinal flora combined treatment, and cannot accurately judge the treatment quality, in vivo situation, metabolic influence, treatment effect and potential risk in time.

[0005] To achieve the above object, the present application is implemented by the following technical solutions: An effect evaluation method for liver stem cells and intestinal flora combined treatment of diabetes, comprising the following steps: performing pre-treatment quality detection on liver stem cell suspension and intestinal flora suspension to determine whether the quality meets the standard; if not, replacing the liver stem cell suspension and intestinal flora suspension and re-performing pre-treatment quality detection; if yes, performing in-vivo liver stem cell detection and intestinal flora detection according to a set period during treatment to determine whether the in-vivo liver stem cell detection and intestinal flora detection meet the standard; if yes, continuing the treatment; if not, performing in-vivo liver stem cell metabolism influence detection and intestinal flora metabolism influence detection:

[0006] If the in-vivo liver stem cell metabolism influence detection and intestinal flora metabolism influence detection are both normal, performing diabetes-related index detection to obtain a treatment effect evaluation coefficient; if either of the in-vivo liver stem cell metabolism influence detection and intestinal flora metabolism influence detection is abnormal, performing sign abnormality risk identification to determine liver risk probability and intestinal risk probability, and simultaneously determining an auxiliary treatment scheme.

[0007] Further, the pre-treatment quality detection on the liver stem cell suspension and intestinal flora suspension to determine whether the quality meets the standard comprises the following steps: obtaining liver stem cell pre-treatment characteristic data and intestinal flora pre-treatment characteristic data, wherein the liver stem cell pre-treatment characteristic data comprises liver stem cell activity value Gx hx , cell purity percentage Gx cd , telomere length Gx dl , sugar metabolism related gene expression amount Gx td , and insulin sensitivity related cytokine content Gx yd , and the intestinal flora pre-treatment characteristic data comprises Akkermansia relative abundance CA xf , Bifidobacterium relative abundance Sq xf , flora Shannon diversity index Jq dy , Simpson dominance index Yq dy , short-chain fatty acid content Dx aj , and branched-chain amino acid content Zx aj ; obtaining liver stem cell pre-treatment characteristic reference data and intestinal flora pre-treatment characteristic reference data from a database, wherein the liver stem cell pre-treatment characteristic reference data comprises liver stem cell activity value reference value Gc hx , cell purity percentage reference value Gc cd , telomere length reference value Gc dl , sugar metabolism related gene expression amount reference value Gc tdThe insulin sensitivity-related cytokine content reference value Gc yd The intestinal flora pre-treatment characteristic reference data includes Akkermansia relative abundance reference value Cc xf Bifidobacterium relative abundance reference value Sc xf Shannon diversity index of flora reference value Jc dy Simpson dominance index reference value Yc dy Short-chain fatty acid content reference value Dc aj And branched-chain amino acid content reference value Zc aj ;

[0008] Based on the liver stem cell pre-treatment characteristic data and the liver stem cell pre-treatment characteristic reference data, stem cell property detection and stem cell metabolic secretion detection are performed, respectively, to obtain stem cell property evaluation coefficient Gx tx And stem cell metabolic secretion evaluation coefficient Gx fm , and the liver stem cell quality detection coefficient Gx jc is obtained based on the stem cell property evaluation coefficient and the stem cell metabolic secretion evaluation coefficient; if the liver stem cell quality detection coefficient is greater than the liver stem cell quality detection threshold value set in the database, the liver stem cell quality meets the standard; if the liver stem cell quality detection coefficient is not greater than the liver stem cell quality detection threshold value set in the database, the liver stem cell quality does not meet the standard.

[0009] Based on the intestinal flora pre-treatment characteristic data and the intestinal flora pre-treatment characteristic reference data, intestinal flora property detection and intestinal flora metabolism detection are performed, respectively, to obtain intestinal flora property evaluation coefficient Cx tx And intestinal flora metabolism evaluation coefficient Cx fm , and the intestinal flora quality detection coefficient Cx jc is obtained based on the intestinal flora property evaluation coefficient and the intestinal flora metabolism evaluation coefficient; if the intestinal flora quality detection coefficient is greater than the intestinal flora quality detection threshold value set in the database, the intestinal flora quality meets the standard; if the intestinal flora quality detection coefficient is not greater than the intestinal flora quality detection threshold value set in the database, the intestinal flora quality does not meet the standard.

[0010] Further, the liver stem cell quality detection coefficient Gx jc The calculation formula is:

[0011]

[0012] Wherein, α1 is the weight factor of Gx tx , and α2 is the weight factor of Gx fm ;

[0013] The intestinal flora quality detection coefficient Cx jc :

[0014]

[0015] wherein a3 is a weight factor of Cx tx and a4 is a weight factor of Cx fm .

[0016] Further, determining whether the in-vivo liver stem cell detection is qualified includes the following steps: obtaining a stem cell factor concentration parameter based on blood detection, wherein the stem cell factor concentration parameter includes a hepatocyte growth factor concentration and an insulin-like growth factor-1 concentration; obtaining a stem cell behavior parameter based on a marker tracing technology, wherein the stem cell behavior parameter includes a stem cell survival proportion Gx ch , a stem cell migration organ set A1, and a stem cell distribution data set B1 in each organ in the body; performing weighted summation processing on the stem cell factor concentration parameter after standardization processing to obtain a stem cell factor concentration comprehensive coefficient; obtaining a stem cell reference behavior parameter stored in a database, and combining the stem cell behavior parameter to obtain a stem cell behavior evaluation coefficient Gx xw .

[0017]

[0018] wherein Gc ch is a stem cell survival reference proportion in the stem cell reference behavior parameter, A2 is a stem cell migration organ reference set in the stem cell reference behavior parameter, B2 is a stem cell distribution data reference set in each organ in the body in the stem cell reference behavior parameter, and σ(·) is a cosine similarity function, and e is a natural constant;

[0019] performing weighted summation on the stem cell factor concentration comprehensive coefficient and the stem cell behavior evaluation coefficient to obtain an in-vivo liver stem cell detection index; if the in-vivo liver stem cell detection index is greater than an in-vivo liver stem cell detection threshold value set in the database, the in-vivo liver stem cell detection is qualified; if the in-vivo liver stem cell detection index is not greater than the in-vivo liver stem cell detection threshold value set in the database, the in-vivo liver stem cell detection is not qualified.

[0020] Determining whether the intestinal flora detection is qualified includes the following steps: obtaining a concentration ratio of bile acid metabolites and short-chain fatty acids, a change rate of relative abundance of key species, and a relative content change trend of acetic acid, propionic acid, and butyric acid in the short-chain fatty acids; if the concentration ratio of the bile acid metabolites and the short-chain fatty acids and the change rate of the relative abundance of the key species are both within a corresponding set range, and the relative content change trends of the acetic acid, the propionic acid, and the butyric acid in the short-chain fatty acids all conform to an expected change trend, the intestinal flora detection is qualified, otherwise the intestinal flora detection is not qualified.

[0021] Further, the in-vivo liver stem cell metabolism influence detection is performed, including the following steps: obtaining stem cell metabolism influence detection data, including liver stem cell self-characteristic parameters, stem cell metabolism product related parameters and whole body metabolism correlation parameters; after normalization processing of the stem cell metabolism influence detection data, the stem cell metabolism influence detection feature vector is formed; the stem cell metabolism influence detection feature vector is input into the trained decision tree, starting from the root node of the decision tree, gradually traversing downward according to the node division condition, until reaching the leaf node, and the number of samples with normal metabolism and the number of samples with abnormal metabolism in the leaf node are counted; the proportion of normal metabolism and the proportion of abnormal metabolism are calculated based on the number of samples with normal metabolism and the number of samples with abnormal metabolism, if the proportion of normal metabolism is greater than the proportion of abnormal metabolism, the in-vivo liver stem cell metabolism influence detection is normal, otherwise it is not normal.

[0022] The intestinal flora metabolism influence detection is performed, including the following steps: obtaining intestinal flora metabolism influence detection data, including intestinal flora structure parameters, intestinal flora metabolism product related parameters and whole body metabolism correlation parameters; after normalization processing of the intestinal flora metabolism influence detection data, the intestinal flora metabolism influence detection feature vector is formed; the intestinal flora metabolism influence detection feature vector is input into the trained gradient decision tree model, and the final prediction value is obtained; the final prediction value is converted into a probability value through a logic function, if the probability value is less than a set probability threshold, the intestinal flora metabolism influence detection is normal, otherwise it is not normal.

[0023] Further, the treatment effect evaluation coefficient is obtained, including the following steps: change amount analysis is performed on the current obtained diabetes related indicators and the last obtained diabetes related indicators, to obtain a change amount factor bh yz :

[0024]

[0025] Wherein, Ssx i is the difference between the i-th diabetes indicator exceeding the reference value and the corresponding reference value in the last obtained diabetes related indicators, Dsx i is the difference between the corresponding diabetes indicator and the corresponding reference value corresponding to Ssx i , n is the total number of diabetes indicators exceeding the reference value in the last obtained diabetes related indicators; Sx j is the absolute value of the difference between the j-th diabetes indicator lower than the reference value and the corresponding reference value in the last obtained diabetes related indicators, Ddx j is the absolute value of the difference between the corresponding diabetes indicator and the corresponding reference value corresponding to Sx j , m is the total number of diabetes indicators lower than the reference value in the last obtained diabetes related indicators;

[0026] Perform cosine similarity analysis on the normalized diabetes-related indicators currently obtained and the expected normalized diabetes-related indicators to obtain the similarity factor xs yz ; Obtain the current comprehensive body parameter index, perform cosine similarity comparison between the current comprehensive body parameter index and the comprehensive index in the comprehensive index-comprehensive risk value mapping table stored in the database, determine the comprehensive index that is most similar to the current comprehensive body parameter index, and obtain the corresponding comprehensive risk value. The current comprehensive body parameter index includes metabolic syndrome related indicators, insulin secretion and sensitivity indicators, inflammation and oxidative stress indicators, renal function indicators and liver function indicators; the change factor bh yz , similarity factor xs yz 、Comprehensive risk valuezh fx , the proportion of normal metabolism zc bl and probability value P gl Input into the treatment effect evaluation model to obtain the treatment effect evaluation coefficient ZL xs , where the treatment effect evaluation model is as follows:

[0027]

[0028] Furthermore, the steps for obtaining the comprehensive indicator-comprehensive risk value mapping table are as follows: obtain the historical physical comprehensive parameter indicators of each treatment cycle, perform cluster analysis on the historical physical comprehensive parameter indicators based on the DBSCAN clustering algorithm, and obtain the cluster center corresponding to each treatment cycle; perform mean processing on the historical physical comprehensive parameter indicators corresponding to each cluster center to obtain the averaged historical physical comprehensive parameter indicators, recorded as comprehensive indicators, and each cluster center corresponds to a comprehensive indicator; count the number of samples of abnormal historical physical comprehensive parameter indicators corresponding to each cluster center in the next detection cycle, and calculate the abnormal probability; correspond each comprehensive indicator with the abnormal probability to obtain the comprehensive indicator-comprehensive risk value mapping table corresponding to each treatment cycle.

[0029] Furthermore, the liver risk probability and the intestinal risk probability are determined, including the following steps: obtaining diabetic liver lesion risk indicators and performing standardization processing, wherein the standardized diabetic liver lesion risk indicators include metabolic indicators and liver damage fibrosis marker parameters, and the metabolic indicators include glycated hemoglobin content TH hl , triglyceride content GY hl , low-density lipoprotein cholesterol content DG hl and non-esterified fatty acid content ZH hl , liver injury fibrosis marker parameters include alanine aminotransferase content BA hl , aspartate aminotransferase content TD hl and liver stiffness value GZ hl; based on the trained Logistic regression model, the standardized diabetes liver lesion risk indicators are processed to obtain a first liver lesion probability P1:

[0030] P1' = β0' + β1' * TH hl + β2' * GY hl + β3' * DG hl + β4' * ZH hl ;

[0031] P1'' = β0'' + β1'' * BA hl + β2'' * TD hl + β3'' * GZ hl ;

[0032]

[0033] wherein β0' and β0'' are intercepts, β1', β2', β3', β4', β1'', β2'' and β3'' are regression coefficients, and P1' and P1'' are transfer functions;

[0034] Based on the trained liver lesion decision tree model, the standardized diabetes liver lesion risk indicators are processed to obtain a second liver lesion probability P2; the first liver lesion probability P1, the second liver lesion probability P2 and the proportion of metabolic abnormalities yc bl are processed to obtain a liver risk probability:

[0035] P gz = (δ1*P1+δ2*P2)*(1+yc bl ); wherein δ1 is the weight factor of P1, and δ2 is the weight factor of P2;

[0036] Diabetes intestinal risk indicators are obtained and standardized, and the standardized diabetes intestinal risk indicators include intestinal flora characteristics, inflammation and oxidative stress marker parameters and intestinal function indicators; based on the trained intestinal lesion decision tree model, the standardized diabetes intestinal risk indicators are processed to obtain a first intestinal lesion probability; based on the weighted scoring rules stored in the database, the standardized diabetes intestinal risk indicators are processed to obtain a total risk score, and the total risk score is mapped to a second intestinal lesion probability; the first intestinal lesion probability and the second intestinal lesion probability are weighted and summed to obtain an intestinal risk probability.

[0037] Further, the auxiliary treatment scheme is determined, including the following steps: acquiring the physical data of the diabetic patient, including height, age, BIM, diabetes-related indicators and current physical comprehensive parameter indicators; comparing the physical data of the diabetic patient with the stored physical matching data-auxiliary treatment scheme set mapping set in the database, determining the physical matching data closest to the physical data of the diabetic patient, acquiring the auxiliary treatment scheme set, the auxiliary treatment scheme set including a plurality of historical auxiliary treatment schemes, each historical auxiliary treatment scheme corresponding to a priority value; the historical auxiliary treatment scheme corresponding to the maximum priority value in the auxiliary treatment scheme set is taken as the auxiliary treatment scheme corresponding to the current physical data of the diabetic patient; after a set auxiliary treatment period, the in-vivo liver stem cell metabolism influence detection and the intestinal flora metabolism influence detection are re-performed: if the in-vivo liver stem cell metabolism influence detection and the intestinal flora metabolism influence detection are both normal, the auxiliary treatment is stopped; if either the in-vivo liver stem cell metabolism influence detection or the intestinal flora metabolism influence detection is abnormal, the physical data of the diabetic patient is re-acquired, and the auxiliary treatment scheme is re-determined, and the priority value of the current auxiliary treatment scheme is updated.

[0038] An effect evaluation system for liver stem cell and intestinal flora combined treatment of diabetes, comprising a pre-treatment quality detection module for pre-treatment quality detection of liver stem cell suspension and intestinal flora suspension to determine whether the quality meets the standard; if not, replace the liver stem cell suspension and intestinal flora suspension and re-perform the pre-treatment quality detection; an in-vivo detection module for in-vivo liver stem cell detection and intestinal flora detection at a set period during treatment when the quality of the liver stem cell suspension and intestinal flora suspension meets the standard to determine whether the in-vivo liver stem cell detection and intestinal flora detection meet the standard; if both meet the standard, continue the treatment.

[0039] A metabolism influence detection module for in-vivo liver stem cell metabolism influence detection and intestinal flora metabolism influence detection when either the in-vivo liver stem cell detection or the intestinal flora detection does not meet the standard; if both the in-vivo liver stem cell metabolism influence detection and the intestinal flora metabolism influence detection are normal, perform diabetes-related indicator detection to obtain a treatment effect evaluation coefficient; a risk probability and auxiliary scheme determination module for risk identification of physical abnormalities, determination of liver risk probability and intestinal risk probability, and determination of an auxiliary treatment scheme when either the in-vivo liver stem cell metabolism influence detection or the intestinal flora metabolism influence detection is abnormal.

[0040] The present application has the following beneficial effects:

[0041] The method for evaluating the effect of liver stem cells combined with intestinal flora in treating diabetes, through quality detection of the liver stem cell suspension and the intestinal flora suspension before treatment, in-vivo liver stem cell and intestinal flora detection in the treatment, and subsequent metabolic influence detection, diabetes-related index detection, risk probability identification and auxiliary treatment scheme determination, realizes the whole-process precise evaluation from before treatment to during treatment, ensures the quality of the substances used for treatment, timely masters the in-vivo treatment component state, accurately judges the metabolic influence and treatment effect, effectively identifies the risk and provides the targeted auxiliary treatment scheme, and can solve the problems in the traditional diabetes treatment effect evaluation, such as lack of comprehensive and dynamic evaluation of the liver stem cells combined with intestinal flora treatment, and inability to timely and accurately judge the treatment quality, in-vivo situation, metabolic influence, treatment effect and potential risk.

[0042] Of course, implementing any product of the application does not necessarily require achieving all the advantages described above at the same time. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 The flow chart of the method for evaluating the effect of liver stem cells combined with intestinal flora in treating diabetes according to the application.

[0044] Figure 2 The flow chart of the system for evaluating the effect of liver stem cells combined with intestinal flora in treating diabetes according to the application. DETAILED DESCRIPTION

[0045] Please refer to Figure 1 The embodiment of the application provides a technical scheme: a method for evaluating the effect of liver stem cells combined with intestinal flora in treating diabetes, comprising the following steps: performing pre-treatment quality detection on liver stem cell suspension and intestinal flora suspension to determine whether the quality meets the standard; if not, replacing the liver stem cell suspension and the intestinal flora suspension and performing pre-treatment quality detection again.

[0046] Obtaining liver stem cell pre-treatment characteristic data and intestinal flora pre-treatment characteristic data, wherein the liver stem cell pre-treatment characteristic data comprises liver stem cell activity value Gx hx , cell purity percentage Gx cd , telomere length Gx dl , expression amount of a gene related to sugar metabolism Gx td , and insulin sensitivity related cytokine content Gx yd The intestinal flora pre-treatment characteristic data comprises Akkermansia relative abundance CA xf , Bifidobacterium relative abundance Sq xf , flora Shannon diversity index Jq dy , Simpson dominance index Yq dy , and short-chain fatty acid content Dxaj and branched-chain amino acid content Zx aj .

[0047] The activity value, purity, and other data of liver stem cells directly affect their differentiation and metabolic functions. The telomere length can reflect the degree of cell aging, and the sugar metabolism genes and insulin-related factors are related to their blood glucose regulation ability. The characteristic data of intestinal flora (such as Akkermansia, Bifidobacterium abundance, and short-chain fatty acid content) are closely related to intestinal barrier function and metabolic regulation. The key indicators affecting the function of liver stem cells and the metabolism of intestinal flora are comprehensively covered, ensuring that the subsequent evaluation is based on complete and accurate basic data, avoiding quality judgment bias due to data loss, and ensuring the quality reliability of treatment substances from the source.

[0048] The liver stem cell pre-treatment characteristic reference data and the intestinal flora pre-treatment characteristic reference data are obtained from the database. The liver stem cell pre-treatment characteristic reference data includes liver stem cell activity value reference Gc hx , cell purity percentage reference Gc cd , telomere length reference Gc dl , sugar metabolism-related gene expression amount reference Gc td , and insulin sensitivity-related cytokine content reference Gc yd The intestinal flora pre-treatment characteristic reference data includes Akkermansia relative abundance reference Cc xf , Bifidobacterium relative abundance reference Sc xf , flora Shannon diversity index reference Jc dy , Simpson dominance index reference Yc dy , short-chain fatty acid content reference Dc aj , and branched-chain amino acid content reference Zc aj .

[0049] The liver stem cell pre-treatment characteristic reference data and the intestinal flora pre-treatment characteristic reference data are obtained from the database. The liver stem cell pre-treatment characteristic reference data includes liver stem cell activity value reference, flora diversity index reference, etc., which provides a clear quantitative standard for quality detection. By comparing the actual detection data with the reference data, it can be directly judged whether the treatment substance meets the preset quality requirements, making the quality evaluation objective and operable, and avoiding the errors caused by subjective judgment.

[0050] Based on the liver stem cell pre-treatment characteristic data and the liver stem cell pre-treatment characteristic reference data, stem cell property detection and stem cell metabolic secretion detection are performed, respectively obtaining stem cell property evaluation coefficient Gx tx and stem cell metabolic secretion evaluation coefficient Gx fm , and obtaining liver stem cell quality detection coefficient Gx jcIf the liver stem cell quality detection coefficient is greater than the liver stem cell quality detection threshold value set in the database, the liver stem cell quality meets the standard; if the liver stem cell quality detection coefficient is not greater than the liver stem cell quality detection threshold value set in the database, the liver stem cell quality does not meet the standard.

[0051] The property detection focuses on the biological function (such as activity, purity) of the cells themselves, and the metabolic secretion detection focuses on the regulation ability of the cells on sugar metabolism, and the combination of the two can evaluate the quality of the liver stem cells from the two dimensions of "structure" and "function". Through weighted calculation to form a comprehensive coefficient, the complex quality evaluation is converted into a specific numerical value, which is convenient for intuitive judgment of whether the cells meet the treatment requirements.

[0052] Based on the intestinal flora pre-treatment characteristic data and the intestinal flora pre-treatment characteristic parameter data, intestinal flora property detection and intestinal flora metabolic detection are performed, respectively obtaining intestinal flora property evaluation coefficient Cx tx and intestinal flora metabolic evaluation coefficient Cx fm , and based on the intestinal flora property evaluation coefficient and the intestinal flora metabolic evaluation coefficient, the intestinal flora quality detection coefficient Cx jc is obtained; if the intestinal flora quality detection coefficient is greater than the intestinal flora quality detection threshold value set in the database, the intestinal flora quality meets the standard; if the intestinal flora quality detection coefficient is not greater than the intestinal flora quality detection threshold value set in the database, the intestinal flora quality does not meet the standard.

[0053] The property detection (such as the Shannon diversity index) reflects the stability of the structure of the flora, and the metabolic detection (such as the content of short-chain fatty acids) is directly related to its regulation effect on the host sugar metabolism (such as short-chain fatty acids can improve insulin resistance). Through quantitative calculation, flora with structural imbalance or insufficient metabolic capacity can be identified, for example, a low Shannon diversity index may indicate that the flora has weak regulation function on the host metabolism, and needs to be prepared again to avoid affecting the combined treatment effect.

[0054] Ensure zero-risk access of treatment substances: through the closed-loop process of "detection-replacement-re-detection", unqualified treatment substances with insufficient activity and flora imbalance are forcibly excluded, and the treatment invalidation or safety risk caused by quality problems (such as low-activity stem cells cannot differentiate to repair islets, and abnormal flora may cause inflammation) is eliminated from the source, providing a basic guarantee for the safety and effectiveness of subsequent combined treatment.

[0055] The liver stem cell quality detection coefficient Gx jc The calculation formula is:

[0056]

[0057] Among them, α1 is the weight factor of Gx tx , and α2 is the weight factor of Gx fmweight factor; the formula combines the "structure" (characteristics) and "function" (metabolism) by weighted summation, avoiding the one-sidedness of single index evaluation.

[0058] Intestinal flora quality detection coefficient Cx jc :

[0059]

[0060] Wherein, α3 is the weight factor of Cx tx , and α4 is the weight factor of Cx fm , which combines the structure and metabolic potential, can identify the flora with "normal structure but weak metabolic capacity" (such as the standard of Bifidobacterium abundance but insufficient short-chain fatty acid content), and avoid poor treatment effect caused by metabolic defects.

[0061] If it meets the standard, in the process of treatment, in vivo liver stem cell detection and intestinal flora detection are carried out according to the set period to determine whether the in vivo liver stem cell detection and intestinal flora detection meet the standard: if the in vivo liver stem cell detection and intestinal flora detection meet the standard, the treatment is continued; wherein the liver stem cell suspension is transplanted with blood by intravenous injection, and the intestinal flora suspension is oral.

[0062] Determining whether the in vivo liver stem cell detection meets the standard, comprising the following steps: based on blood detection, obtaining stem cell factor concentration parameters, wherein the stem cell factor concentration parameters include hepatocyte growth factor concentration (HGF, which can promote hepatocyte proliferation and differentiation, and its concentration reflects the regulation ability of liver stem cells to liver microenvironment) and insulin-like growth factor-1 concentration (IGF-1, which improves glucose metabolism through insulin-like signal pathway and is directly related to the regulation effect of stem cells on blood glucose); based on marker tracing technology, obtaining stem cell behavior parameters, including stem cell survival rate Gx ch , stem cell migration organ set A1 (normal stem cells should migrate to target organs such as liver and pancreas, and abnormal migration may cause safety risk) and stem cell distribution data set B1 in each organ in vivo (quantifying the colonization density of stem cells in target organs, which directly affects the treatment effect); after standardizing the stem cell factor concentration parameters, weighted summation is carried out to obtain the stem cell factor concentration comprehensive coefficient; obtaining the stem cell reference behavior parameters stored in the database, and combining the stem cell behavior parameters to obtain the stem cell behavior evaluation coefficient Gx xw ;

[0063]

[0064] Wherein, Gc chA2 is a set of data of the migration organs of the stem cells in the behavior parameter of the stem cells, B2 is a set of data of the distribution of the stem cells in each organ in the behavior parameter of the stem cells, σ(·) is a cosine similarity function, and e is a natural constant;

[0065] The cosine similarity can measure the directional similarity between vectors, and is suitable for evaluating the matching degree of the behavior parameter of the stem cells (such as the migration organ set can be converted into an organ distribution vector) and the reference data. For example, if the cosine value of the measured migration organ set and the reference set is close to 1, it indicates that the migration path of the stem cells conforms to the expectation, otherwise it indicates that the migration is abnormal (such as aggregation to the inflammation site). Considering the survival, migration and distribution of the three types of parameters, the single index misjudgment is avoided. For example, when the survival rate of the stem cells meets the standard but migrates to a non-target organ, the behavior evaluation coefficient will be reduced due to the low cosine value of the migration set, thereby exposing the potential risk.

[0066] The in-vivo liver stem cell detection index is obtained by weighted summation of the stem cell factor concentration comprehensive coefficient and the stem cell behavior evaluation coefficient. If the in-vivo liver stem cell detection index is greater than the in-vivo liver stem cell detection threshold set in the database, the in-vivo liver stem cell detection meets the standard; if the in-vivo liver stem cell detection index is not greater than the in-vivo liver stem cell detection threshold set in the database, the in-vivo liver stem cell detection does not meet the standard.

[0067] The detection process realizes the all-round evaluation of the in-vivo state of the liver stem cells through the combination design of “blood factor (functional metabolism) + marker tracing (behavior trajectory)”, integrates the factor concentration and the behavior parameter into a single detection index, and avoids subjective judgment by comparing with the threshold value (such as the index > 0.8 meets the standard). For example, when the stem cell factor concentrations of two groups of patients are similar but the behavior parameters are significantly different, the comprehensive index can clearly distinguish the in-vivo activity of the two groups, thereby providing a quantitative basis for clinical decision-making.

[0068] The determination of whether the intestinal flora detection meets the standard includes the following steps: obtaining the concentration ratio of bile acid metabolites and short-chain fatty acids, the change rate of the relative abundance of key species (such as Akkermansia and Bifidobacterium), and the relative content change trend of acetic acid, propionic acid and butyric acid in the short-chain fatty acids; if the concentration ratio of the bile acid metabolites and the short-chain fatty acids and the change rate of the relative abundance of the key species are both within the corresponding set range, and the relative content change trend of acetic acid, propionic acid and butyric acid in the short-chain fatty acids all conforms to the expected change trend, the intestinal flora detection meets the standard, otherwise the intestinal flora detection does not meet the standard.

[0069] Bile acid metabolism and gut microbiota interact with each other: normal flora can convert primary bile acids into secondary bile acids, regulate glucose and lipid metabolism; SCFAs (such as butyric acid) can improve insulin resistance by inhibiting bile acid reabsorption, and the imbalance of the ratio (such as the increase of bile acids and the decrease of SCFAs) often indicates the disorder of the flora (such as the decrease of SCFAs-producing bacteria), which may exacerbate insulin resistance.

[0070] In normal treatment, the key bacterial species abundance should show a gradual increase (such as 10%-15% per week), and if the growth rate is too slow (such as <5%), it indicates that the flora is not well colonized; if the growth rate is too fast (such as >20%), it may cause the risk of excessive proliferation (such as intestinal flora disorder). Through dynamic rate monitoring, problems such as "insufficient activation" or "abnormal proliferation" of the flora can be found in time, avoiding fluctuations in treatment effect caused by dynamic imbalance of the flora.

[0071] In combination therapy, the SCFAs content should show a continuous upward trend (such as 8%-12% per week) with the treatment cycle. If the trend stagnates or decreases, it indicates that the metabolic function of the flora is weakened (such as the activity of acid-producing bacteria is reduced), which directly affects the hypoglycemic effect (such as insufficient butyric acid can exacerbate intestinal inflammation and worsen insulin resistance). Through trend evaluation, the positive regulation of the metabolic products of the flora on the host can be verified in real time.

[0072] If either the in vivo liver stem cell detection or the intestinal flora detection is not up to standard, in vivo liver stem cell metabolism influence detection and intestinal flora metabolism influence detection are performed: if both the in vivo liver stem cell metabolism influence detection and the intestinal flora metabolism influence detection are normal, diabetes-related index detection is performed to obtain a treatment effect evaluation coefficient;

[0073] The in vivo liver stem cell metabolism influence detection includes the following steps: obtaining stem cell metabolism influence detection data, including liver stem cell self-characteristics parameters (cell activity value, cell purity percentage, telomere length, expression amount of hepatocyte differentiation marker), stem cell metabolism product related parameters (HGF concentration, IGF-1 concentration, glucose kinase activity) and whole body metabolism related parameters (blood glucose index, serum insulin concentration, insulin resistance index); from the "cell-product-organism" three-layer data correlation analysis, avoiding single-dimensional misjudgment.

[0074] The detection data of the influence on stem cell metabolism is normalized to form a detection feature vector of the influence on stem cell metabolism; the detection feature vector of the influence on stem cell metabolism is input into the trained decision tree, starting from the root node of the decision tree, and gradually traversing downward according to the division conditions of the nodes until reaching the leaf nodes, and the number of samples with normal metabolism and the number of samples with abnormal metabolism in the leaf nodes are counted; the proportion of normal metabolism and the proportion of abnormal metabolism are calculated based on the number of samples with normal metabolism and the number of samples with abnormal metabolism, and if the proportion of normal metabolism is greater than the proportion of abnormal metabolism, the detection of the influence on liver stem cell metabolism in vivo is normal, that is, the liver stem cell metabolism is normal, otherwise it is not normal.

[0075] The decision tree can be explained by hierarchical division (such as "IGF-1 concentration > threshold value → blood glucose reduction rate > threshold value"), has strong interpretability, and can clearly determine the key influencing factors of abnormal metabolism (such as too low concentration of a certain metabolite); the proportion of samples with normal metabolism in the leaf nodes is used as the basis for judgment, which conforms to the clinical logic of "most samples are normal, which is considered as the whole normal", and reduces the interference of individual abnormal data.

[0076] The intestinal flora metabolism influence detection includes the following steps: obtaining intestinal flora metabolism influence detection data, including intestinal flora structure parameters (relative abundance of key bacteria, flora diversity index), intestinal flora metabolite related parameters (short chain fatty acid content, bile acid metabolite concentration, branched chain amino acid content) and whole body metabolism related parameters (inflammation and oxidative stress indicators, intestinal function indicators); intestinal flora affects diabetes through "metabolites → intestinal barrier repair → whole body metabolism regulation", and the detection indicators cover flora structure, metabolites and body inflammation / metabolism indicators, forming a complete evidence chain.

[0077] The intestinal flora metabolism influence detection data is normalized to form an intestinal flora metabolism influence detection feature vector; the intestinal flora metabolism influence detection feature vector is input into the trained gradient decision tree model to obtain a final prediction value; the final prediction value is converted into a probability value through a logic function, and if the probability value is less than a set probability threshold, the intestinal flora metabolism influence detection is normal, that is, the intestinal flora metabolism is normal, otherwise it is not normal.

[0078] The logic function is X refers to the final prediction value.

[0079] The treatment effect evaluation coefficient is obtained, including the following steps: performing change amount analysis on the current acquired diabetes related indicators and the last acquired diabetes related indicators to obtain a change amount factor bh yz :

[0080]

[0081] Wherein, Ssx iDsx is the difference between the i-th diabetes indicator exceeding the reference value and the corresponding reference value among the diabetes-related indicators obtained last time, i For Ssx i The difference between the corresponding diabetes index and the corresponding reference value, n is the total number of diabetes indexes exceeding the reference value among the diabetes-related indexes obtained last time; Sx j Ddx is the absolute value of the difference between the jth diabetes indicator lower than the reference value and the corresponding reference value among the diabetes-related indicators obtained last time, j For Sx j The absolute value of the difference between the corresponding diabetes index and the corresponding reference value, m is the total number of diabetes indexes lower than the reference value among the diabetes-related indexes obtained last time.

[0082] Use positive and negative values ​​to distinguish the "too high" and "too low" attributes of indicators to avoid unified calculations that mask real changes.

[0083] Perform cosine similarity analysis on the normalized diabetes-related indicators currently obtained and the expected normalized diabetes-related indicators to obtain the similarity factor xs yz Directional similarity calculations are performed between indicator vectors (such as blood glucose, insulin, and inflammatory factors) and expected vectors, unaffected by numerical magnitude (e.g., blood glucose mmol / L and inflammatory factors pg / mL can be evaluated uniformly), focusing on the synergistic trends among indicators. Expected indicators are based on clinical criteria for diabetes remission (e.g., blood glucose <7.0 mmol / L, HOMA-IR <2.5). Similarity analysis directly quantifies the distance between treatment effects and target outcomes.

[0084] Obtain the current comprehensive body parameter index, perform cosine similarity comparison between the current comprehensive body parameter index and the comprehensive index in the comprehensive index-comprehensive risk value mapping table stored in the database, determine the comprehensive index that is most similar to the current comprehensive body parameter index, and obtain the corresponding comprehensive risk value. The current comprehensive body parameter index includes metabolic syndrome related indicators, insulin secretion and sensitivity indicators, inflammation and oxidative stress indicators, renal function indicators and liver function indicators; the change factor bh yz , similarity factor xs yz 、Comprehensive risk valuezh fx , the proportion of normal metabolism zc bl and probability value P gl Input into the treatment effect evaluation model to obtain the treatment effect evaluation coefficient ZL xs , where the treatment effect evaluation model is as follows:

[0085]

[0086] The acquisition steps of the comprehensive index-comprehensive risk value mapping table are as follows: acquiring historical body comprehensive parameter indexes of each treatment cycle, performing clustering analysis on the historical body comprehensive parameter indexes based on a DBSCAN clustering algorithm to obtain clustering centers corresponding to each treatment cycle; performing mean value processing on the historical body comprehensive parameter indexes corresponding to each clustering center to obtain homogenized historical body comprehensive parameter indexes, denoted as comprehensive indexes, each clustering center corresponding to one comprehensive index; counting the number of samples of the historical body comprehensive parameter indexes corresponding to each clustering center that are abnormal in the next detection cycle to calculate an abnormal probability; and corresponding each comprehensive index with the abnormal probability to obtain a comprehensive index-comprehensive risk value mapping table corresponding to each treatment cycle.

[0087] By clustering the historical comprehensive indexes through the DBSCAN algorithm, patients with similar health states are classified into one category, the abnormal probability of each category is calculated, and the multi-dimensional indexes (metabolism, inflammation, liver and kidney function) of the current patient are mapped to the most similar risk category by using the statistical rules of historical data.

[0088] If any of the in-vivo liver stem cell metabolism influence detection and the intestinal flora metabolism influence detection is abnormal, a physical sign abnormality risk identification is performed to determine a liver risk probability and an intestinal risk probability, and an auxiliary treatment scheme is determined.

[0089] Determining the liver risk probability and the intestinal risk probability includes the following steps: acquiring diabetes liver lesion risk indexes and performing standardization processing, the standardization-processed diabetes liver lesion risk indexes including metabolism indexes and liver injury fibrosis marker parameters, the metabolism indexes including glycated hemoglobin content TH hl , triglyceride content GY hl , low-density lipoprotein cholesterol content DG hl , and non-esterified fatty acid content ZH hl , starting from "glucose and lipid metabolism disorder" to capture early causes of diabetes liver lesions and avoid lagging evaluation caused by only focusing on liver injury markers.

[0090] The liver injury fibrosis marker parameters include alanine aminotransferase content BA hl , aspartate aminotransferase content TD hl , and liver stiffness value GZ hl ; directly reflecting liver organic injury, and combining with the metabolism indexes to form a complete evidence chain (such as glucose and lipid metabolism disorder→liver cell injury→fibrosis).

[0091] Based on the trained Logistic regression model, the standardization-processed diabetes liver lesion risk indexes are processed to obtain a first liver lesion probability P1:

[0092] P1′=β0′+β1′*TH hl +β2′*GY hl +β3′*DG hl +β4′*ZH hl ;

[0093] P1″=β0″+β1″*BA hl +β2″*TD hl +β3″*GZ hl ;

[0094]

[0095] wherein β0′ and β0″ are intercepts, β1′, β2′, β3′, β4′, β1″, β2″ and β3″ are regression coefficients, and P1′ and P1″ are transfer functions;

[0096] The logistic regression model has strong interpretability, which is convenient for doctors to trace the source of risk (e.g., "P1 increases mainly due to HbA1c exceeding the reference value by 2.3%") and provides clear targets for individualized intervention (e.g., prioritizing glycemic control).

[0097] The trained liver lesion decision tree model is used to process the standardized diabetes liver lesion risk indicators to obtain a second liver lesion probability P2. The liver lesion decision tree model identifies the interaction between indicators through hierarchical division (e.g., "LSM>9.5 kPa→ALT>40 U / L"), for example, when LSM and ALT are both abnormal, the liver lesion risk increases nonlinearly, while the logistic regression may underestimate the risk due to the linear assumption;

[0098] The first liver lesion probability P1, the second liver lesion probability P2, and the proportion of metabolic abnormalities yc bl are processed to obtain a liver risk probability:

[0099] P gz =(δ1*P1+δ2*P2)*(1+yc bl ); wherein δ1 is the weight factor of P1, and δ2 is the weight factor of P2.

[0100] Logistic regression is good at handling linear relationships and the results are easy to interpret, but it may ignore high-order interactions between indicators (e.g., the synergistic damage effect of LDL-C and ALT). Decision trees are good at capturing nonlinear relationships, but the black box nature makes it difficult to interpret the results (e.g., the division basis of a leaf node is not intuitive). After fusion, the interpretability of the linear model is retained, and the prediction accuracy in complex scenarios is improved through decision trees.

[0101] The diabetes intestinal tract risk index is acquired and standardized, the standardized diabetes intestinal tract risk index including intestinal tract flora characteristics, inflammation and oxidative stress marker parameters and intestinal tract function indexes; the standardized diabetes intestinal tract risk index is processed based on the trained intestinal tract lesion decision tree model to obtain a first intestinal tract lesion probability; the standardized diabetes intestinal tract risk index is processed based on the weighted scoring rule stored in the database to obtain a risk total score, and the risk total score is mapped to a second intestinal tract lesion probability; the first intestinal tract lesion probability and the second intestinal tract lesion probability are processed by weighted summation to obtain an intestinal tract risk probability.

[0102] The decision tree model is good at processing nonlinear relationships and feature interactions, improving the risk prediction accuracy of complex cases (such as diabetes patients with intestinal inflammation); the weighted scoring rule is based on guideline weights, and the results can be traced back to specific indicators, meeting the clinical demand for "transparent evidence chain" (such as explaining to patients that "the high risk is due to abnormal intestinal flora and endotoxin").

[0103] The auxiliary treatment scheme is determined, including the following steps: acquiring the physical data of the diabetes patient, including height, age, BIM, diabetes-related indicators and current physical comprehensive parameter indicators; comparing the physical data of the diabetes patient with the stored physical matching data-auxiliary treatment scheme set mapping set in the database to determine the physical matching data closest to the physical data of the diabetes patient, and acquiring the auxiliary treatment scheme set, the auxiliary treatment scheme set including multiple historical auxiliary treatment schemes, each historical auxiliary treatment scheme corresponding to a priority value; the historical auxiliary treatment scheme corresponding to the maximum priority value in the auxiliary treatment scheme set is taken as the auxiliary treatment scheme corresponding to the current physical data of the diabetes patient; after setting the auxiliary treatment period, the in-vivo liver stem cell metabolism influence detection and intestinal flora metabolism influence detection are re-performed: if the in-vivo liver stem cell metabolism influence detection and intestinal flora metabolism influence detection are both normal, the auxiliary treatment is stopped; if either the in-vivo liver stem cell metabolism influence detection or the intestinal flora metabolism influence detection is abnormal, the physical data of the diabetes patient is re-acquired, and the auxiliary treatment scheme is re-determined, and the priority value of the current auxiliary treatment scheme is updated.

[0104] The database stores a large amount of "physical-scheme-effect" data of historical cases, and through cosine similarity matching (such as the smaller the angle between the physical vectors, the higher the similarity), the current patient obtains a "similar case verified" scheme, avoiding experiential decision-making, and the auxiliary treatment is established on the basis of successful historical cases, improving the effectiveness of the scheme.

[0105] The priority value is calculated based on the treatment effect (such as blood glucose reduction amplitude, metabolic abnormality improvement rate) of the historical scheme. The higher the effect, the higher the priority value. The scheme with the highest "cost performance" is automatically screened out. For example, in a scheme with two similar signs, the scheme with a higher priority value may be selected because of "less side effects and more lasting effects", optimizing the safety and economy of treatment. Set the auxiliary treatment period (such as 2 weeks) to avoid unnecessary long-term use of auxiliary schemes (such as overuse of probiotics which may lead to intestinal flora dependence), and use "metabolic function recovery" as the drug withdrawal standard instead of fixed treatment course to achieve "precise drug withdrawal" and avoid over-treatment.

[0106] The updating method of the priority value can be: when the in vivo liver stem cell metabolism influence detection or abnormal intestinal flora metabolism influence detection is performed, the corresponding value is deducted, and the priority value is updated.

[0107] An effect evaluation system for liver stem cell and intestinal flora combined treatment of diabetes, as shown in Figure 2 Fig. 1, comprising a pre-treatment quality detection module for pre-treatment quality detection of liver stem cell suspension and intestinal flora suspension to determine whether the quality meets the standard. If not, replace the liver stem cell suspension and intestinal flora suspension and re-perform the pre-treatment quality detection. An in vivo detection module for in vivo liver stem cell detection and intestinal flora detection at a set period during treatment when the quality of the liver stem cell suspension and intestinal flora suspension meets the standard to determine whether the in vivo liver stem cell detection and intestinal flora detection meets the standard. If both the in vivo liver stem cell detection and intestinal flora detection meet the standard, continue the treatment.

[0108] A metabolic influence detection module for in vivo liver stem cell metabolism influence detection and intestinal flora metabolism influence detection when either the in vivo liver stem cell detection or the intestinal flora detection does not meet the standard. If both the in vivo liver stem cell metabolism influence detection and intestinal flora metabolism influence detection are normal, perform diabetes-related index detection to obtain a treatment effect evaluation coefficient. A risk probability and auxiliary scheme determination module for risk identification of abnormal signs, determination of liver risk probability and intestinal risk probability, and determination of auxiliary treatment scheme when either the in vivo liver stem cell metabolism influence detection or the intestinal flora metabolism influence detection is abnormal.

[0109] An electronic device comprising: a processor; and a memory having computer program instructions stored therein, which, when executed by the processor, cause the processor to perform the effect evaluation method for liver stem cell and intestinal flora combined treatment of diabetes as described above.

[0110] A computer readable storage medium for storing a program, which, when executed by a processor, implements the effect evaluation method for liver stem cell and intestinal flora combined treatment of diabetes as described above.

[0111] Those skilled in the art will appreciate that embodiments of the present application can be readily used as software, hardware, or a combination of software and hardware. In a software embodiment, the methods can be tangibly embodied in a machine-readable storage medium having stored thereon instructions that can be used to program a computer to perform any of the operations described herein. The software implementation can be for example, in the form of a computer program product. The software implementation can be implemented in a centralized fashion in one computer system or network, or be distributed over a network such that it is stored and executed in local and remote computer systems.

[0112] The present application is described in relation to flow diagrams and / or block diagrams of systems, apparatuses (systems), and computer program products according to embodiments of the present application. It is to be understood that each block of the flow diagrams and / or block diagrams, and combinations of blocks in the flow diagrams and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks. Figure 1 means for performing each of the functions specified in the flow diagram and / or block diagram block or blocks.

[0113] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flow diagram and / or block diagram block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks. Figure 1 means for performing each of the functions specified in the flow diagram and / or block diagram block or blocks.

[0114] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow diagram and / or block diagram block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks. Figure 1 means for performing each of the functions specified in the flow diagram and / or block diagram block or blocks.

[0115] While preferred embodiments of the application have been described, modifications and alterations thereto will occur to those skilled in the art upon reading the preceding description. In particular, it will be apparent to those skilled in the art that parts can be added to, or substituted for, parts of the described embodiment. It is therefore contemplated that the application be construed as including all such alterations and modifications as fall within the scope of the application. Accordingly, while the preferred embodiment of the application has been described above, it will be appreciated that those skilled in the art will be able to devise modifications and alternatives which, although contrary to or depart from the spirit and scope of the application, can be used as alternatives thereto.

[0116] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for evaluating the effect of combined liver stem cells and intestinal flora in treating diabetes, characterized in that: The following steps are involved: Perform quality testing on liver stem cell suspension and intestinal flora suspension before treatment to determine whether the quality meets the standards: If the standards are not met, the liver stem cell suspension and intestinal flora suspension will be replaced and the pre-treatment quality test will be repeated; If the target is met, liver stem cell testing and intestinal flora testing will be performed according to the set cycle during the treatment process to determine whether the liver stem cell testing and intestinal flora testing meet the target: If the liver stem cell test and intestinal flora test are both up to standard, treatment will continue; If any of the in vivo liver stem cell test and intestinal flora test does not meet the standard, the in vivo liver stem cell metabolic impact test and intestinal flora metabolic impact test will be performed: If the in vivo liver stem cell metabolism impact test and intestinal flora metabolism impact test are both normal, diabetes-related index tests will be performed to obtain the treatment effect evaluation coefficient; If any of the in vivo liver stem cell metabolic impact tests and intestinal flora metabolic impact tests are abnormal, the risk of abnormal physical signs will be identified to determine the liver risk probability and intestinal risk probability, and the auxiliary treatment plan will be determined at the same time.

2. The method for evaluating the effect of combined treatment of diabetes with liver stem cells and intestinal flora according to claim 1, characterized in that: Perform pre-treatment quality testing on the liver stem cell suspension and intestinal flora suspension to determine whether the quality meets the standards, including the following steps: Obtain the characteristic data of liver stem cells before treatment and the characteristic data of intestinal flora before treatment, wherein the characteristic data of liver stem cells before treatment include the liver stem cell activity value Gx hx , cell purity percentage Gx cd , telomere length Gx dl , expression levels of genes related to glucose metabolism Gx td and insulin sensitivity-related cytokine levels Gx yd , the intestinal flora characteristics before treatment included the relative abundance of Akkermansia CA xf , relative abundance of Bifidobacterium Sq xf , Shannon diversity index Jq dy , Simpson dominance index Yq dy , short-chain fatty acid content Dx aj and branched-chain amino acid content Zx aj ; Obtain the characteristic parameter data of liver stem cell treatment and intestinal flora treatment before treatment from the database. The characteristic parameter data of liver stem cell treatment before treatment includes the liver stem cell activity parameter value Gc hx , cell purity percentage parameter value Gc cd , telomere length parameter Gc dl , and the expression parameter value of genes related to glucose metabolism Gc td Gc, a cytokine content parameter associated with insulin sensitivity yd The characteristic parameter data of intestinal flora before treatment include the relative abundance parameter value Cc of Akkermansia xf , Bifidobacterium relative abundance parameter Sc xf , Shannon diversity index parameter value Jc dy , Simpson dominance index parameter value Yc dy , short-chain fatty acid content reference value Dc aj and branched-chain amino acid content reference value Zc aj ; Based on the liver stem cell pre-treatment characteristic data and liver stem cell pre-treatment characteristic parameter data, stem cell characteristic detection and stem cell metabolism secretion detection were performed to obtain the stem cell characteristic evaluation coefficient Gx tx and stem cell metabolism and secretion evaluation coefficient Gx fm , and based on the stem cell characteristic evaluation coefficient and the stem cell metabolism and secretion evaluation coefficient, the liver stem cell quality detection coefficient Gx is obtained jc ; If the liver stem cell quality detection coefficient is greater than the liver stem cell quality detection threshold set in the database, the liver stem cell quality meets the standard; If the liver stem cell quality detection coefficient is not greater than the liver stem cell quality detection threshold set in the database, the liver stem cell quality does not meet the standard; Based on the intestinal flora characteristic data before treatment and the intestinal flora characteristic parameter data before treatment, the intestinal flora characteristic detection and intestinal flora metabolism detection were performed to obtain the intestinal flora characteristic evaluation coefficient Cx tx and intestinal flora metabolic evaluation coefficient Cx fm , and the intestinal flora quality detection coefficient Cx is obtained based on the intestinal flora characteristic evaluation coefficient and the intestinal flora metabolism evaluation coefficient jc ; If the intestinal flora quality detection coefficient is greater than the intestinal flora quality detection threshold set in the database, the intestinal flora quality meets the standard; If the intestinal flora quality detection coefficient is not greater than the intestinal flora quality detection threshold set in the database, the intestinal flora quality does not meet the standard.

3. The method for evaluating the effect of combined treatment of diabetes with liver stem cells and intestinal flora according to claim 2, characterized in that: Liver stem cell quality detection coefficient Gx jc The calculation formula is: Among them, α1 is Gx tx The weight factor of Gx, α2 is fm The weight factor of Intestinal flora quality detection coefficient Cx jc : Among them, α3 is Cx tx The weight factor of Cx fm The weight factor of .

4. The method for evaluating the effect of combined treatment of diabetes with liver stem cells and intestinal flora according to claim 1, characterized in that: Determining whether the in vivo liver stem cell test meets the standards includes the following steps: Based on blood tests, stem cell factor concentration parameters are obtained, wherein the stem cell factor concentration parameters include hepatocyte growth factor concentration and insulin-like growth factor-1 concentration; Based on labeling and tracing technology, stem cell behavior parameters are obtained, including the stem cell survival ratio Gx ch , stem cell migration organ set A1 and stem cell distribution data set B1 in various organs in the body; After the stem cell factor concentration parameters were standardized, weighted summation was performed to obtain the comprehensive coefficient of stem cell factor concentration; Obtain the stem cell behavior parameters stored in the database, and combine them to obtain the stem cell behavior evaluation coefficient Gx xw ; Among them, Gc ch is the stem cell survival parameter ratio in the stem cell parameter behavior parameters, A2 is the stem cell migration organ parameter set in the stem cell parameter behavior parameters, B2 is the stem cell distribution data parameter set in various organs in the body in the stem cell parameter behavior parameters, σ(·) is the cosine similarity function, and e is a natural constant; The in vivo liver stem cell detection index is obtained by weighted summing the comprehensive coefficient of stem cell factor concentration and the stem cell behavior assessment coefficient: If the in vivo liver stem cell detection index is greater than the in vivo liver stem cell detection threshold set in the database, the in vivo liver stem cell detection meets the standard; If the in vivo liver stem cell detection index is not greater than the in vivo liver stem cell detection threshold set in the database, the in vivo liver stem cell detection fails to meet the standard; Determining whether the intestinal flora test meets the standards includes the following steps: Obtain the concentration ratio of bile acid metabolites to short-chain fatty acids, the rate of change of the relative abundance of key bacterial species, and the relative content change trend of acetate, propionate, and butyrate in short-chain fatty acids; If the concentration ratio of bile acid metabolites to short-chain fatty acids and the rate of change of the relative abundance of key bacterial species are both within the corresponding set range, and the change trends of the relative contents of acetic acid, propionic acid, and butyric acid in short-chain fatty acids are in line with the expected change trends, then the intestinal flora test meets the standards; otherwise, the intestinal flora test does not meet the standards.

5. The method for evaluating the effect of combined liver stem cells and intestinal flora in treating diabetes according to claim 1, characterized in that: The in vivo liver stem cell metabolic impact assay was performed, including the following steps: Obtaining stem cell metabolic impact test data, including liver stem cell characteristic parameters, stem cell metabolite related parameters, and overall body metabolism related parameters; Normalizing the stem cell metabolism impact detection data and forming a stem cell metabolism impact detection feature vector; Input the stem cell metabolic impact detection feature vector into the trained decision tree. Starting from the root node of the decision tree, the tree is traversed downward step by step according to the node partitioning conditions until a leaf node is reached. The number of samples with normal metabolism and the number of samples with abnormal metabolism in the leaf node are counted. Based on the number of samples with normal metabolism and the number of samples with abnormal metabolism, the proportion of normal metabolism and the proportion of abnormal metabolism are calculated respectively. If the proportion of normal metabolism is greater than the proportion of abnormal metabolism, the in vivo liver stem cell metabolic impact test is normal, otherwise it is abnormal; Conducting intestinal flora metabolic impact testing includes the following steps: Obtain intestinal flora metabolic impact detection data, including intestinal flora structure parameters, intestinal flora metabolite related parameters and overall body metabolism related parameters; The intestinal flora metabolic impact detection data is normalized and then sorted to form the intestinal flora metabolic impact detection feature vector; Input the intestinal flora metabolic impact detection feature vector into the trained gradient decision tree model to obtain the final prediction value; The final predicted value is converted into a probability value through a logical function. If the probability value is less than the set probability threshold, the intestinal flora metabolic impact test is normal, otherwise it is abnormal.

6. The method for evaluating the effect of combined liver stem cells and intestinal flora in treating diabetes according to claim 5, characterized in that: Obtaining the treatment effect evaluation coefficient includes the following steps: Perform a change analysis on the current diabetes-related indicators and the last diabetes-related indicators to obtain the change factor bh yz : Among them, Ssx i Dsx is the difference between the i-th diabetes indicator exceeding the reference value and the corresponding reference value among the diabetes-related indicators obtained last time, i For Ssx i The difference between the corresponding diabetes index and the corresponding reference value, where n is the total number of diabetes indexes exceeding the reference value among the diabetes-related indexes obtained last time; Sx j Ddx is the absolute value of the difference between the jth diabetes indicator lower than the reference value and the corresponding reference value among the diabetes-related indicators obtained last time, j For Sx j The absolute value of the difference between the corresponding diabetes index and the corresponding reference value, m is the total number of diabetes indexes lower than the reference value among the diabetes-related indexes obtained last time; Perform cosine similarity analysis on the normalized diabetes-related indicators currently obtained and the expected normalized diabetes-related indicators to obtain the similarity factor xs yz ; Obtaining the current comprehensive body parameter indicators, performing a cosine similarity comparison between the current comprehensive body parameter indicators and the comprehensive indicators in the comprehensive indicator-comprehensive risk value mapping table stored in the database, determining the comprehensive indicator that is most similar to the current comprehensive body parameter indicators, and obtaining the corresponding comprehensive risk value. The current comprehensive body parameter indicators include metabolic syndrome-related indicators, insulin secretion and sensitivity indicators, inflammation and oxidative stress indicators, renal function indicators, and liver function indicators; The change factor bh yz , similarity factor xs yz 、Comprehensive risk valuezh fx , the proportion of normal metabolism zc bl and probability value P gl Input into the treatment effect evaluation model to obtain the treatment effect evaluation coefficient ZL xs , where the treatment effect evaluation model is as follows:

7. The method for evaluating the effect of combined liver stem cells and intestinal flora in treating diabetes according to claim 6, characterized in that: The steps to obtain the comprehensive indicator-comprehensive risk value mapping table are as follows: Obtain historical comprehensive physical parameter indicators for each treatment cycle, perform cluster analysis on the historical comprehensive physical parameter indicators based on the DBSCAN clustering algorithm, and obtain the cluster center corresponding to each treatment cycle; The historical physical comprehensive parameter indicators corresponding to each cluster center are averaged to obtain the averaged historical physical comprehensive parameter indicators, which are recorded as comprehensive indicators. Each cluster center corresponds to a comprehensive indicator. Count the number of samples with abnormal historical comprehensive physical parameter indicators corresponding to each cluster center in the next detection cycle, and calculate the abnormal probability; Each comprehensive indicator is matched with the abnormal probability to obtain a comprehensive indicator-comprehensive risk value mapping table corresponding to each treatment cycle.

8. The method for evaluating the effect of combined liver stem cells and intestinal flora in treating diabetes according to claim 4, characterized in that: Determining the liver risk probability and the intestinal risk probability involves the following steps: Obtain diabetic liver disease risk indicators and perform standardized processing. The standardized diabetic liver disease risk indicators include metabolic indicators and liver damage fibrosis marker parameters. Metabolic indicators include glycated hemoglobin content TH hl , triglyceride content GY hl , low-density lipoprotein cholesterol content DG hl and non-esterified fatty acid content ZH hl , liver injury fibrosis marker parameters include alanine aminotransferase content BA hl , aspartate aminotransferase content TD hl and liver stiffness value GZ hl ; The standardized diabetic liver lesion risk index is processed based on the trained Logistic regression model to obtain the first liver lesion probability P1: P1′=β0′+β1′*TH hl +β2′*GY hl +β3′*DG hl +β4′*ZH hl ; P1″=β0″+β1″*BA hl +β2″*TD hl +β3″*GZ hl ; Among them, β0′ and β0″ are intercepts, β1′, β2′, β3′, β4′, β1″, β2″ and β3″ are regression coefficients, and P1′ and P1″ are transition functions; The standardized diabetic liver lesion risk index is processed based on the trained liver lesion decision tree model to obtain the second liver lesion probability P2; The probability of first liver lesion P1, the probability of second liver lesion P2 and the ratio of metabolic abnormality yc bl Processing is performed to obtain the liver risk probability: P gz =(δ1*P1+δ2*P2)*(1+yc bl ); Among them, δ1 is the weight factor of P1, and δ2 is the weight factor of P2; Obtain and standardize diabetic intestinal risk indicators, including intestinal flora characteristics, inflammatory and oxidative stress marker parameters, and intestinal function indicators; The standardized diabetes intestinal risk index is processed based on the trained intestinal lesion decision tree model to obtain the first intestinal lesion probability; The standardized diabetes intestinal risk index is processed based on the weighted scoring rules stored in the database to obtain a total risk score, and the total risk score is mapped to the probability of second intestinal lesions; The first intestinal lesion probability and the second intestinal lesion probability are weighted and summed to obtain the intestinal risk probability.

9. The method for evaluating the effect of combined treatment of diabetes with liver stem cells and intestinal flora according to claim 1, characterized in that: Determine adjuvant treatment options, including the following steps: Obtain the physical data of diabetic patients, including height, age, BIM, diabetes-related indicators and current comprehensive physical parameters; Comparing the diabetic patient's physical sign data with a physical sign matching data-auxiliary treatment plan set mapping set stored in a database, determining the physical sign matching data closest to the diabetic patient's physical sign data, and obtaining an auxiliary treatment plan set, wherein the auxiliary treatment plan set includes multiple historical auxiliary treatment plans, and each historical auxiliary treatment plan corresponds to a priority value; The historical auxiliary treatment plan corresponding to the largest priority value in the auxiliary treatment plan set is used as the auxiliary treatment plan corresponding to the current diabetic patient's physical sign data; After setting the adjuvant treatment period, re-test the in vivo liver stem cell metabolism and intestinal flora metabolism: If the in vivo liver stem cell metabolism impact test and intestinal flora metabolism impact test are both normal, then adjuvant treatment will be stopped; If any of the in vivo liver stem cell metabolic impact tests and intestinal flora metabolic impact tests are abnormal, the diabetic patient's physical sign data will be re-obtained, the auxiliary treatment plan will be re-determined, and the priority value of the current auxiliary treatment plan will be updated.

10. A system for evaluating the effect of combined treatment of diabetes with liver stem cells and intestinal flora, used in the method for evaluating the effect of combined treatment of diabetes with liver stem cells and intestinal flora according to any one of claims 1 to 9, characterized in that: include: A pre-treatment quality testing module is used to perform pre-treatment quality testing on the liver stem cell suspension and intestinal flora suspension to determine whether the quality meets the standards. If not, the liver stem cell suspension and intestinal flora suspension are replaced and the pre-treatment quality testing is repeated; An in vivo testing module is used to perform in vivo liver stem cell testing and intestinal flora testing at set intervals during treatment, provided that the liver stem cell suspension and intestinal flora suspension meet the quality standards, to determine whether the in vivo liver stem cell testing and intestinal flora testing meet the standards. If both the in vivo liver stem cell testing and intestinal flora testing meet the standards, treatment will continue; The metabolic impact detection module is used to perform in vivo liver stem cell metabolic impact detection and intestinal flora metabolic impact detection when either the in vivo liver stem cell detection or the intestinal flora detection does not meet the standard. If both the in vivo liver stem cell metabolic impact detection and the intestinal flora metabolic impact detection are normal, diabetes-related indicator detection is performed to obtain the treatment effect evaluation coefficient; The risk probability and auxiliary plan determination module is used to identify the risk of abnormal physical signs, determine the liver risk probability and intestinal risk probability, and determine the auxiliary treatment plan when there is an abnormality in any of the in vivo liver stem cell metabolic impact detection and intestinal flora metabolic impact detection.

Images