System and method for monitoring influence of atorvastatin on mitochondrial function in real time

Abstract

The invention discloses a system for monitoring the influence of atorvastatin on mitochondrial functions in real time, and the system comprises a biosensor module which is used for monitoring biomarkers related to the mitochondrial functions and glycometabolism in blood in real time; the micro-fluidic chip is used for rapidly separating and enriching cells or specific components in blood; the optical detection module monitors the active oxygen level of mitochondria in real time; the data processing and transmission module processes and analyzes the collected data in real time; the equipment terminal receives the processed data and displays the data on a user interface in real time; the analysis and early warning module analyzes the monitoring data in real time and provides early warning and personalized suggestions for diabetes mellitus; the database module is used for storing monitoring data and historical records; through a biosensor, optical detection, a micro-fluidic chip and the like, after a patient takes atorvastatin, indexes of blood sugar, insulin and the like in a blood sample, and mitochondrial functions and oxidative damage indexes of active oxygen level, mitochondrial membrane potential and the like are detected.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical monitoring, in particular to a system and method for real-time monitoring of the influence of atorvastatin on mitochondrial function. BACKGROUND

[0002] Atorvastatin belongs to statin lipid-lowering drugs, which can reduce cholesterol synthesis by inhibiting the activity of HMG-CoA reductase in the liver, thereby reducing the levels of plasma total cholesterol and low-density lipoprotein cholesterol (LDL-C) and playing an important role in clinical treatment. However, while atorvastatin exerts its lipid-lowering effect, it also has the potential risk of negatively affecting mitochondrial function. For example, during the process of inhibiting cholesterol synthesis, atorvastatin will also affect the synthesis of coenzyme Q10 (ubiquinone) on the mitochondrial membrane. Coenzyme Q10 is a key component of the mitochondrial respiratory chain, and its reduced synthesis can lead to mitochondrial respiratory chain dysfunction, thereby causing ATP production deficiency and accumulation of large amounts of reactive oxygen species (ROS). Long-term accumulation of reactive oxygen species (ROS) can cause oxidative damage to pancreatic beta cells and inhibit insulin secretion, thereby increasing the risk of new-onset diabetes in patients under the double effects.

[0003] Currently, the monitoring means for the safety of atorvastatin medication in clinical practice mainly relies on routine laboratory tests, which cannot monitor the influence of atorvastatin on mitochondrial function in real time and comprehensively, especially in terms of the influence on glucose metabolism-related indicators. Moreover, routine tests only focus on basic glucose metabolism indicators such as blood glucose and glycated hemoglobin (HbA1c), and do not directly correlate with core indicators of mitochondrial function such as mitochondrial membrane potential, ROS levels, and antioxidant enzyme activity. Therefore, it is difficult to determine whether glucose metabolism abnormalities are caused by drug-induced mitochondrial damage, making it difficult for clinicians to timely warn and intervene in the risk of diabetes that may be caused by the use of atorvastatin. Therefore, it is particularly urgent to develop a system that can monitor the changes in mitochondrial function after taking atorvastatin in real time, which has important clinical significance for preventing the occurrence of diabetes. SUMMARY

[0004] The present application provides a system for real-time monitoring of the influence of atorvastatin on mitochondrial function. After the patient takes atorvastatin, the collected blood sample can be used to monitor the changes in mitochondrial function in real time, which helps doctors and patients better manage the use of atorvastatin, and thus better prevent the occurrence of diabetes.

[0005] The present application provides a system for real-time monitoring of the influence of atorvastatin on mitochondrial function, comprising: A biosensor module for real-time monitoring of biomarkers related to mitochondrial function and glucose metabolism in blood, such as changes in the concentration of blood glucose, insulin, malondialdehyde (MDA), superoxide dismutase (SOD), catalase (CAT), etc. A microfluidic chip for rapid separation and enrichment of cells or specific components in blood to more accurately detect indicators related to mitochondrial function, such as mitochondrial membrane potential, etc. An optical detection module for real-time monitoring of reactive oxygen species (ROS) levels in mitochondria, etc., to reflect the state of mitochondrial function through fluorescence or spectral analysis techniques. A data processing and transmission module for real-time processing and analysis of collected data. A device terminal for receiving processed data through wireless communication technology and displaying it on the user interface in real time for doctors or users to view and analyze at any time. An analysis and early warning module for real-time analysis of monitoring data through data analysis algorithms, providing early warning of diabetes and personalized recommendations. A database module for storing monitoring data and historical records, and for long-term tracking and analysis of patient data.

[0006] A method for real-time monitoring of the effects of atorvastatin on mitochondrial function using the above system, comprising: S1, after the user takes atorvastatin, a small amount of blood sample is collected by a blood sampling device and introduced into a microfluidic chip; S2, after the microfluidic chip separates and enriches the blood sample, the biosensor module and the optical detection module respectively detect the biomarkers and indicators related to mitochondrial function in the blood in real time; S3, the biosensor module and the optical detection module respectively transmit the collected data to the data processing and transmission module, the data processing module processes and analyzes the collected data in real time, and transmits the data to the device terminal through wireless communication technology; S4, the analysis and early warning module analyzes the monitoring data received by the device terminal in real time through data analysis algorithms, generates a data trend chart and provides early warning of diabetes and personalized recommendations, which are displayed on the user interface of the device terminal for doctors or users to view and analyze at any time.

[0007] The one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: through a biosensor, optical detection, a microfluidic chip, etc., the sugar metabolism indicators such as blood glucose and insulin, and the mitochondrial function and oxidative damage indicators such as a reactive oxygen species (ROS) level, a mitochondrial membrane potential, SOD, and CAT in a blood sample of a patient after the patient takes atorvastatin are detected, the function change of mitochondria in the blood of the patient after the patient takes atorvastatin can be monitored in real time, and a mitochondrial function scoring model and a diabetes risk early warning model are constructed, so that the diabetes risk can be early warned, a quantitative basis is provided for a doctor to judge the degree of mitochondrial damage caused by a drug and to adjust the drug, and the risk of new-onset diabetes is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0008] Figure 1 FIG. 1 is a schematic diagram of a system structure of the present application; Figure 2 FIG. 2 is a schematic diagram of a hardware connection structure of the system of the present application; Figure 3 FIG. 3 is a flowchart of a processing procedure of the system of the present application; Figure 4 FIG. 4 is a flowchart of a specific working method of the system of the present application. DETAILED DESCRIPTION

[0009] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the related drawings. The preferred embodiments of the present application are shown in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0010] It should be noted that when an element is referred to as being "fixed" to another element, it can be directly on the other element or there can be an intervening element. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or there can be an intervening element. The terms "vertical", "horizontal", "left", "right", and similar expressions used herein are for illustrative purposes only and are not intended to be the only implementation.

[0011] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terminology used in the description of the present application herein only for the purpose of describing the specific embodiments and is not intended to limit the present application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0012] Embodiment one Please refer to Figures 1-2 A system for real-time monitoring of the influence of atorvastatin on mitochondrial function comprises: The biosensor module is used for real-time monitoring of the concentration changes of biomarkers related to mitochondrial function and sugar metabolism in blood, such as blood glucose, insulin, malondialdehyde (MDA), superoxide dismutase (SOD), catalase (CAT), etc.; wherein a three-electrode system glucose oxidase biosensor is used to convert the blood glucose concentration by detecting the current signal generated by the glucose oxidation reaction; an immunosensor is used, and the antibody of the immunosensor is fixed on a quartz crystal microbalance (QCM) chip modified by amino silane, and the concentration of insulin is quantified based on the specific binding reaction of antigen-antibody and the fluorescence signal intensity; a thiobarbituric acid (TBA) colorimetric sensor is used to detect the absorbance of the colored compound generated by the reaction of MDA and TBA, and the MDA concentration is converted to reflect the degree of lipid oxidative damage; an enzyme sensor is used to calculate the enzyme activity by detecting the superoxide anion scavenging ability of SOD; and an ultraviolet sensor is used to detect the change rate of absorbance at 240 nm wavelength in the process of CAT catalyzing hydrogen peroxide decomposition, and the enzyme activity is calculated; The microfluidic chip is made of polydimethylsiloxane (PDMS) material and is provided with a multi-channel integrated chip structure. The multi-channel integrated structure includes 1 sample inlet channel, 1 separation channel, 5 biosensor detection channels corresponding to blood glucose, insulin, MDA, SOD, CAT respectively, and 1 mitochondrial enrichment channel. The microfluidic chip can quickly separate and enrich cells or specific components in blood, so as to more accurately detect indicators related to mitochondrial function, such as mitochondrial membrane potential. The optical detection module integrates a laser excitation light source, a fluorescent probe, and an optical lens group to ensure real-time monitoring of the reactive oxygen species (ROS) level of mitochondria and other indicators by fluorescence or spectral analysis technology, so as to reflect the functional state of mitochondria. The data processing and transmission module uses a microcontroller (MCU) to filter and process the current / absorbance signals of the sensor module and the fluorescence signals of the optical module, remove noise interference such as ambient light and electromagnetic interference, and convert the original signals into quantitative index values based on a pre-set standard curve such as a blood glucose concentration-current signal curve and a mitochondrial reactive oxygen species (ROS) level-fluorescence intensity curve. The index values are formed into a structured data frame in the format of time-index name-value-unit. The device terminal receives the processed data through LoRa wireless communication technology and displays the data in real time on the user interface for doctors or users to view and analyze at any time. The analysis and early warning module analyzes the received data in real time by constructing a mitochondrial function scoring model and a diabetes risk early warning model, so as to provide early warning and personalized suggestions for diabetes, and provide report information support for medical staff and users. The database module can adopt a local storage unit and a remote server storage unit for storing monitoring data and historical records, and for long-term tracking and analysis of patient data.

[0013] The microfluidic chip adopts dielectrophoresis separation technology and microchannel filtering structure. Specifically, the blood sample is driven into the chip inlet channel by a micropump, and the red blood cells, white blood cells and plasma are separated by dielectrophoresis force. The plasma enters the biosensor detection channel, the white blood cells are mainly peripheral blood mononuclear cells, and the mitochondria enter the enrichment channel. A nanoscale filter membrane is arranged in the enrichment channel to intercept the white blood cells and lyse the cells by a hypotonic solution to release the mitochondria. The enriched mitochondrial suspension is delivered to the optical detection module.

[0014] The laser excitation light source adopts a blue laser and a green laser.

[0015] A fluorescent probe such as dihydrofluorescein diacetate (DCFH-DA) probe is used. After the probe enters the mitochondria, it is oxidized by the reactive oxygen species (ROS) of the mitochondria to DCF with fluorescence. By detecting the fluorescence intensity, the level of reactive oxygen species (ROS) of the mitochondria is quantified. Similarly, a fluorescent probe such as tetramethyl rhodamine ethyl ester (TMRE) probe is used. The probe is aggregated in the mitochondrial matrix due to the membrane potential difference of the mitochondria. The fluorescence intensity is positively correlated with the membrane potential. By detecting the fluorescence intensity, the change of the membrane potential of the mitochondria is reflected.

[0016] The device terminal can adopt a mobile device or a cloud platform, such as a computer, a tablet computer, etc. The medical staff enters the basic information of the patient such as age, gender, medication dose, medication duration, etc. on the user interface. The received detection data is displayed in the form of numbers and curves on the interface to show the index values and change trends in real time, and an atorvastatin medication monitoring report is automatically generated. The report content includes index mean value, abnormal times, risk level, so as to facilitate the doctor or user to check and analyze.

[0017] Construction of the mitochondrial function scoring model Based on the influence mechanism of atorvastatin on mitochondrial function, 4 core indicators are screened to ensure that the indicators are directly related to mitochondrial function and can be detected in real time by the system: Reactive oxygen species (ROS) level: reflects the degree of oxidative stress of mitochondria. ROS accumulation is a direct marker of mitochondrial function damage. Mitochondrial membrane potential: a core indicator of mitochondrial function. A decrease in membrane potential means dysfunction of the mitochondrial respiratory chain and a decrease in ATP production. Superoxide dismutase (SOD) activity: a key antioxidant enzyme of mitochondria that can scavenge superoxide anions. A decrease in its activity indicates a decrease in the antioxidant capacity of mitochondria. Catalase (CAT) activity: synergizes with SOD to scavenge hydrogen peroxide, and together with SOD constitutes the mitochondrial antioxidant defense system, and the activity change directly reflects the repair ability of mitochondrial oxidative damage.

[0018] The mitochondrial function scoring model selects the above four indicators of reactive oxygen species (ROS) level, mitochondrial membrane potential, SOD activity, and CAT activity, and determines the index weight by Delphi method (expert scoring method) combined with analytic hierarchy process (AHP). Specifically, each expert scores the four indicators based on the importance of the index to mitochondrial function, with 10 points indicating the most important. At least three rounds of scoring are conducted until the expert consistency coefficient is ≥0.85. The expert scoring results are converted into a judgment matrix, and after consistency check (CR<0.1), the weight of each index is calculated: Reactive oxygen species (ROS) level: 30% is a direct representation of mitochondrial function damage, with the highest weight; Mitochondrial membrane potential: 30% is parallel to ROS level, which reflects the core function state of mitochondria, and is a key prerequisite for ATP generation; Superoxide dismutase (SOD) activity: 20% is the primary defense line of the antioxidant system, with a weight lower than the first two; Catalase (CAT) activity: 20% synergizes with SOD to function, with the same weight as SOD; Based on clinical large sample data, at least 1000 blood samples of healthy people who have not taken atorvastatin are collected, and the four indicators are detected by the system to determine the normal reference range of each indicator. The detection value is converted into a standardized score of 0-100 points. The standardized score is 80-100 points within the normal reference range, 60-79 points for a 10%-30% deviation from the normal reference range, and 0-59 points for a >30% deviation from the normal reference range. The weighted sum formula is used, that is: Mitochondrial function comprehensive score = ROS level standardized score × 30% + mitochondrial membrane potential standardized score × 30% + SOD activity standardized score × 20% + CAT activity standardized score × 20%. Set the grading threshold of mitochondrial function comprehensive score. The mitochondrial function is normal with no obvious oxidative damage and low risk of abnormal glucose metabolism for a score of 80-100 points, mild oxidative damage and close monitoring for a score of 60-79 points, and moderate / severe abnormal glucose metabolism with high risk of oxidative damage for a score of less than 60 points.

[0019] Construction of a diabetes risk warning model Based on the mechanism of atorvastatin-induced diabetes, determine the warning indicators covering mitochondrial function, glucose metabolism, and individual basic risk: The mitochondrial function index reflects the degree of mitochondrial damage, which is the core cause of abnormal glucose metabolism. The glucose metabolism index (blood glucose) directly reflects the state of glucose metabolism. The insulin secretion capacity is reflected by the glucose metabolism index (insulin). The oxidative damage index (MDA) reflects the lipid oxidative damage. The individual basic index is the individual inherent risk factor. The above at least 5 kinds of indexes are used as the early warning indexes of the diabetes risk early warning model.

[0020] The LASSO regression algorithm is used to construct the diabetes risk early warning model. The algorithm can screen the key indicators while avoiding overfitting. Clinical data of at least 800 patients taking atorvastatin are collected, of which 120 cases of new-onset diabetes are used as positive samples. Each sample contains the detection value / information of the above-mentioned 5 kinds of indexes. The samples are divided into training set and validation set in the ratio of 7:3; The LASSO regression model is constructed on the training set. The optimal regularization parameter λ (penalty coefficient) is determined by 5-fold cross-validation. When λ = 0.01, the AUC (area under the receiver operating characteristic curve) of the model on the validation set is the largest, and the prediction accuracy of the model is the highest at this time. The regression coefficients of each index are output to reflect the contribution of the index to the risk of diabetes: for example, the coefficient of family history of diabetes = 0.25 > the coefficient of mitochondrial function score = 0.22, the lower the score, the higher the risk > the coefficient of age = 0.18 > the coefficient of blood glucose = 0.15 > the coefficient of MDA = 0.12 > the coefficient of insulin = 0.10, the lower the insulin, the higher the risk > the coefficient of drug dosage = 0.08 > the coefficient of drug duration = 0.05. The model performance is tested on the validation set. The results show that the model sensitivity is 82%-85%, which can identify at least 82% of new-onset diabetes patients, the specificity is 85%-87%, which can exclude at least 85% of non-diabetes patients, and the accuracy is 81%-84%, which meets the clinical early warning needs. Based on the diabetes risk probability output by the model, 0%-100%, the risk threshold is set: risk probability ≤ 30% is low risk, risk probability in 30%-60% is medium risk, and risk probability ≥ 60% is high risk.

[0021] The local storage unit is used for offline storage of patient short-term monitoring data by device terminals such as tablet computers. The remote server storage unit is used for storage of patient long-term monitoring data by hospital / cloud platform, which supports multi-terminal query and analysis by medical staff, meets the requirements of large capacity, high reliability, and adapts to the needs of clinical scale application.

[0022] Please refer to Figures 3-4 , a method for real-time monitoring of the effect of atorvastatin on mitochondrial function using the above system, the method comprising: S1, after the user takes atorvastatin, a small amount of blood sample is collected by a wearable blood collection device or a disposable blood collection needle, the collected blood sample is added dropwise through the sample inlet of the microfluidic chip, and the built-in micro pump of the chip is started to transport the sample to the separation channel; S2, the microfluidic chip starts dielectrophoresis separation to complete the separation of red blood cells, white blood cells and plasma; the plasma enters the multi-channel detection area of the biosensor module, the white blood cells enter the enrichment channel and are lysed by a hypotonic solution such as 0.45% sodium chloride solution to release mitochondria; the biosensor module starts the detection program, the blood glucose channel outputs the detection result, and the insulin, MDA, SOD and CAT channels output the detection results in turn; at the same time, the enriched mitochondria suspension is transported to the detection cell of the optical detection module, after passing through the fluorescence probe, laser excitation and fluorescence detection are started, and the active oxygen (ROS) level and mitochondrial membrane potential data are recorded; S3, the biosensor module and the optical detection module respectively transmit the collected data to the data processing and transmission module, the data processing and transmission module receives the original signals of each detection module, removes noise by a digital filtering algorithm such as Kalman filtering, marks and automatically removes abnormal signals such as signals exceeding the detection range, converts the filtered original signals into quantitative index values, such as converting the current signal (nA) of the glucose oxidase sensor into the blood glucose concentration (mmol / L), and transmits the processed structured data containing time, index name, value, unit, etc. to the device terminal through LoRa wireless communication technology, after the transmission is completed, the terminal feeds back the data reception success signal to ensure the data integrity; S4, after the device terminal receives the completed data, the analysis and early warning module calls the mitochondrial function score model and the diabetes risk early warning model, analyzes and calculates the data, generates the function score and risk level at the time point, displays the current values of blood glucose, insulin, MDA, SOD, CAT, ROS and mitochondrial membrane potential in the form of a digital list on the user interface, and displays the change trend of each index at different time points in the form of a line chart, after the monitoring is completed, a monitoring report is automatically generated, including the mean value, maximum value, minimum value, abnormal times, risk level and personalized suggestions of each index, the report is stored in the database at the same time, and medical staff or users can query at any time.

[0023] The above only describes the preferred embodiments of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A system for monitoring the effect of atorvastatin on mitochondrial function in real time, characterized by: The application relates to a portable and wearable device for early detection and early warning of diabetes, which comprises the following modules: a biosensor module for real-time monitoring of biomarkers related to mitochondrial function and glucose metabolism in blood; a microfluidic chip for rapid separation and enrichment of cells or specific components in blood; an optical detection module for real-time monitoring of the level of reactive oxygen species of mitochondria through fluorescence or spectral analysis technology to reflect the mitochondrial function state; a data processing and transmission module for real-time processing and analysis of collected data; a device terminal for receiving the processed data through wireless communication technology and displaying the data on a user interface in real time; an analysis and early warning module for real-time analysis of monitoring data through data analysis algorithms to provide early warning of diabetes and personalized suggestions; a database module for storing monitoring data and historical records and long-term tracking and analysis of patient data.

2. A system for monitoring the effect of atorvastatin on mitochondrial function in real time as claimed in claim 1, wherein: The biosensor module comprises a glucose oxidase biosensor for detecting the current signal generated by the glucose oxidation reaction to convert the blood glucose concentration; an immunosensor, antibody fixation of the immunosensor adopts a quartz crystal microbalance chip modified by amino silane, and the insulin concentration is quantified by using the fluorescence signal intensity based on the specific antigen-antibody binding reaction; and a thio-barbituric acid colorimetric sensor for detecting the absorbance of the colored compound generated by the reaction of MDA and TBA to convert the MDA concentration. An enzyme sensor is adopted to calculate the enzyme activity by detecting the superoxide anion scavenging capacity of SOD; and an ultraviolet sensor is adopted to detect the change rate of absorbance at the wavelength in the hydrogen peroxide decomposition process catalyzed by CAT to calculate the enzyme activity.

3. A system for monitoring the effect of atorvastatin on mitochondrial function in real time as claimed in claim 1, wherein: The microfluidic chip is made of polydimethylsiloxane and is provided with a multi-channel integrated chip structure, and the multi-channel integrated structure comprises one sample inlet channel, one separation channel, five biosensor detection channels corresponding to blood glucose, insulin, MDA, SOD and CAT respectively and one mitochondrion enrichment channel.

4. A system for monitoring the effect of atorvastatin on mitochondrial function in real time as claimed in claim 3, wherein: The microfluidic chip adopts dielectrophoresis separation technology and a microchannel filtering structure. Specifically, blood samples are driven into the chip inlet channel by a micropump, red blood cells, white blood cells and plasma are separated by dielectrophoresis force, the plasma enters the biosensor detection channel, the white blood cells are mainly peripheral blood mononuclear cells, the mitochondria enter the enrichment channel, a nanoscale filter membrane is arranged in the enrichment channel, the white blood cells are intercepted and the cells are lysed through a hypotonic solution to release the mitochondria, and the enriched mitochondria suspension is delivered to the optical detection module.

5. The system for monitoring the effect of atorvastatin on mitochondrial function in real time as claimed in claim 1, wherein: The optical detection module integrates a laser excitation light source, a fluorescence probe and an optical lens group. The fluorescence probe comprises a dihydrofluorescein diacetate probe and a tetramethyl rhodamine ethyl ester probe.

6. A system for monitoring the effect of atorvastatin on mitochondrial function in real time as claimed in claim 1, wherein: The analysis and early warning module analyzes the received data in real time by constructing a mitochondrial function scoring model and a diabetes risk early warning model. The mitochondrial function score model selects four indexes of active oxygen level, mitochondrial membrane potential, SOD activity and CAT activity, the index weight is determined by the Delphi method combined with the analytic hierarchy process, the weight of active oxygen level is 30%, the weight of mitochondrial membrane potential is 30%, the weight of SOD activity is 20%, and the weight of CAT activity is 20%, and the normal reference range of each index is determined by detecting the four indexes by the system, and the detection value is converted into a standardized score of 0-100 points, and the weighted sum formula is used to obtain the comprehensive score of mitochondrial function; The diabetes risk early warning model uses at least five types of mitochondrial function indexes, sugar metabolism indexes (blood sugar), sugar metabolism indexes (insulin), oxidative damage indexes, and individual basic indexes as early warning indexes for constructing the diabetes risk early warning model, and uses the LASSO regression algorithm to construct the diabetes risk early warning model.

7. A system for monitoring the effect of atorvastatin on mitochondrial function in real time as claimed in claim 6, wherein: The specific process of constructing the diabetes risk early warning model by using the LASSO regression algorithm is as follows, Collect the clinical data of patients taking atorvastatin, and the newly diagnosed diabetes is used as a positive sample, each sample contains the detection value / information of the above-mentioned five types of indexes, and is divided into a training set and a validation set in a ratio of 7:3; The LASSO regression model is constructed on the training set, and the optimal regularization parameter λ is determined by 5-fold cross-validation, when λ=0.01, the AUC of the model on the validation set is the largest, and at this time the prediction accuracy of the model is the highest; The regression coefficient of each index is output to reflect the contribution of the index to the risk of diabetes, and the performance of the model is tested on the validation set; Based on the diabetes risk probability output by the model, the risk threshold is set: the risk probability ≤30% is low risk, the risk probability is 30%-60% is medium risk, and the risk probability ≥60% is high risk.

8. A system for monitoring the effect of atorvastatin on mitochondrial function in real time according to any one of claims 1 to 7, wherein: The method for monitoring the effect of atorvastatin on mitochondrial function in real time by using the above system, the method comprises the following steps: S1, after the user takes atorvastatin, a small amount of blood sample is collected by a blood sampling device, the collected blood sample is added dropwise through the sample inlet of the microfluidic chip, and the built-in micro pump of the chip is started to transport the sample to the separation channel; S2, the microfluidic chip starts dielectric electrophoresis separation to complete the separation of red blood cells, white blood cells and plasma; the plasma enters the multi-channel detection area of the biosensor module, the white blood cells enter the enrichment channel and are lysed by a hypotonic solution to release mitochondria; the biosensor module outputs detection data in sequence; at the same time, the enriched mitochondrial suspension is transported to the detection pool of the optical detection module, and after passing through the fluorescence probe, laser excitation and fluorescence detection are started, and the active oxygen level and mitochondrial membrane potential data are recorded; S3, the biosensor module and the optical detection module transmit the collected data to the data processing and transmission module, the data processing and transmission module transmits the structured data processed from the original signals of each detection module to the equipment terminal through LoRa wireless communication technology, and after the transmission is completed, the terminal feeds back a data reception success signal to ensure data integrity; S4, after the device terminal receives the completed data, analyzes and calls the mitochondrial function score model and the diabetes risk warning model with the warning module, analyzes and calculates the data, generates the function score and risk level at the time point, and displays the current values of blood glucose, insulin, MDA, SOD, CAT, ROS and mitochondrial membrane potential in the form of a digital list on the user interface, and displays the change trend of each index at different time points in the form of a line chart. After the monitoring is completed, a monitoring report is automatically generated, and the report is stored in the database at the same time, supporting medical staff or users to query at any time.

Images