A medical biochip detection quality monitoring method and system

Abstract

The application provides a medical biochip detection quality monitoring method and system, relates to the technical field of detection quality monitoring, and corresponds to detection of monitoring and control of a biochip, time sequence division and correspondence of detection data, acquisition of detection corresponding data, acquisition of interference detection feature data according to the detection corresponding data, acquisition of data signal fitting curves of the monitoring detection data and the interference detection data after time sequence division, curve change analysis, further determination of an influence trend of an interference feature, further acquisition of feature interference trend determination information, identification and analysis of abnormal indexes of the monitoring detection data, acquisition of actual detection state analysis data, acquisition of a negative influence index according to the actual detection state analysis data in combination with the feature interference trend determination information, index abnormality adjustment, acquisition of detection abnormality adjustment data, and dynamic high-precision detection quality analysis and monitoring of the biochip are realized.

Description

Technical Field

[0001] This invention proposes a method and system for monitoring the quality of medical biochip detection, which relates to the field of detection quality monitoring technology, specifically to the field of medical biochip detection quality monitoring technology. Background Technology

[0002] In clinical testing, biochips are susceptible to interference from factors such as sample matrix, environmental fluctuations, and equipment deviations, which can easily lead to distorted test data, resulting in false positives / false negatives and impacting clinical decision-making. Traditional quality control relies on static standard calibration, which can only assess quality at the endpoint of the test and cannot capture the dynamic changes of interference throughout the testing process, creating blind spots in quality control. Furthermore, it is difficult to distinguish between false anomalies caused by interference and genuine anomalies caused by equipment or operation, leading to blind or missed adjustments. At the same time, the analysis of the impact of interference is mostly qualitative, lacking quantitative trend prediction, resulting in high retest rates and low testing efficiency. Summary of the Invention

[0003] This invention provides a method and system for monitoring the quality of medical biochip detection, in order to solve the above-mentioned problems: This invention proposes a method and system for quality monitoring in medical biochip detection, the method comprising: S1. Monitor and control the biochip for corresponding detection, divide and correspond the obtained monitoring detection data and interference detection data into time series, obtain the detection corresponding data, and obtain the interference detection feature data based on the detection corresponding data; S2. Obtain the data signal fitting curves of the monitoring and detection data and interference detection data after time-series division, perform curve change analysis, and then determine the influence trend of interference characteristics to obtain characteristic interference trend determination information. S3. Identify and analyze abnormal indicators in the monitoring and detection data to obtain actual detection status analysis data. Based on the actual detection status analysis data and the characteristic interference trend judgment information, obtain negative impact indicators, adjust the indicators abnormally, and obtain detection abnormal adjustment data.

[0004] Further, S1 includes: The biochip is divided into monitoring and control areas to obtain the corresponding monitoring and control areas; Obtain biochip detection samples, set up a gradient concentration standard array for the biochip, and perform separate detection in the monitoring area and control area to obtain monitoring detection data and interference detection data; During the detection process, interfering substances are sequentially input into the control area according to a preset time sequence to obtain control interference detection data. Interference detection feature data is obtained by combining the monitoring and detection data with the control interference detection data.

[0005] Further, the step of performing interference detection analysis based on the monitoring detection data and the control interference detection data to obtain interference detection feature data includes: The monitoring and detection data are divided into time series according to the preset time series information to obtain multiple time series monitoring and detection data. The interference detection data is divided into time series according to the preset time series information to obtain multiple time series interference detection data; According to the preset timing information, multiple timing monitoring and detection data are matched with multiple timing interference detection data to obtain the corresponding detection data; Obtain the detection change data of the time-series interference detection data relative to the time-series monitoring detection data in the corresponding detection data, and obtain the interference detection characteristic data of the interference substance corresponding to the time sequence.

[0006] Further, S2 includes: Obtain the fitting curve data of time-series monitoring and detection data and corresponding fluorescence signals to obtain monitoring curve data; Obtain the fitting curve data of the temporal interference detection data and the corresponding fluorescence signal to obtain the interference curve data; Obtain the curve change data of the interference curve data relative to the monitoring curve data, and obtain the interference characteristic curve data of the interference monitoring characteristic data. The change state of the interference characteristic curve data is analyzed to obtain change state analysis data; Based on the analysis of the changing state data, the interference trend of the interference characteristics is determined, and the interference trend determination information is obtained.

[0007] Furthermore, the step of analyzing the changing states of the interference characteristic curve data to obtain changing state analysis data includes: Obtain the change data of the interference feature curve, determine the upward trend and downward trend of the change data, and obtain the change trend determination information; Based on the changing trend of the interference feature curve, the influence trend of the interference feature is determined, and the influence trend determination information of the feature is obtained. Based on the changing trend, the amount of change in the data determines the influence of the feature on the trend; The information on the trend determination of the feature influence and the amount of feature influence are the change state analysis data.

[0008] Further, S3 includes: By analyzing the actual detection status through monitoring and detection data, actual detection status analysis data is obtained. Perform actual detection anomaly analysis on the actual detection status analysis data to obtain actual detection anomaly analysis data; Based on the characteristic interference trend determination information, the actual detection anomaly analysis data is adjusted to obtain detection anomaly adjustment data; Based on the anomaly detection adjustment data, the monitoring and detection quality optimization data is obtained, and the biochip detection quality optimization results are obtained.

[0009] Furthermore, the step of analyzing the actual detection status through monitoring and detection data to obtain actual detection status analysis data includes: Anomaly identification is performed on multiple indicators based on monitoring and detection data to obtain indicator anomaly identification data; The abnormal indicator identification data is compared with the corresponding preset threshold to obtain the abnormal indicator comparison result. Based on the results of the anomaly comparison of the indicators, multiple abnormal indicator data of the monitoring and detection data are determined; The number of abnormal indicator data is compared with a preset number threshold to obtain the number of abnormal comparison results. Based on the results of the number anomaly comparison, anomaly detection is performed on the monitoring and detection data, and actual detection status analysis data is obtained.

[0010] Furthermore, the step of adjusting the actual detection anomaly analysis data based on the characteristic interference trend determination information to obtain detection anomaly adjustment data includes: Interference monitoring feature data is extracted from multiple abnormal indicator data to obtain indicator interference feature data; Based on the characteristic interference trend determination information, generate indicator interference trend determination information from the indicator interference characteristic data; Based on the information on the interference trend of indicators, determine the positive and negative impact indicators; The negative impact index is compared with a preset negative index threshold to obtain a negative comparison result; Adjust the negative impact index based on the negative comparison results to obtain abnormality adjustment data.

[0011] Furthermore, the characteristic interference trend determination information includes: When the negative impact indicator exceeds the preset negative impact indicator threshold, the negative impact indicator is adjusted. When the negative impact index is less than or equal to the preset negative impact index threshold, no negative impact index adjustment will be performed.

[0012] Furthermore, the system includes: The detection feature analysis module is used to monitor and control the biochip and perform corresponding detection. It divides and matches the obtained monitoring detection data and interference detection data in time sequence to obtain the detection corresponding data and obtains the interference detection feature data based on the detection corresponding data. The influence trend analysis module is used to obtain the data signal fitting curves of the monitoring and detection data and interference detection data after time-series division, perform curve change analysis, and then determine the influence trend of interference characteristics, thereby obtaining characteristic interference trend determination information. The anomaly adjustment module is used to identify and analyze abnormal indicators in monitoring and detection data, obtain actual detection status analysis data, obtain negative impact indicators based on the actual detection status analysis data and characteristic interference trend judgment information, perform anomaly adjustment of indicators, and obtain detection anomaly adjustment data.

[0013] The beneficial effects of this invention are as follows: This method overcomes the limitations of traditional quality control that relies solely on static standards. By actively injecting interfering substances, it systematically covers common interference types in clinical scenarios, avoiding quality control blind spots caused by unknown interference. The temporal correlation design solves the problem of interference and signal asynchrony in dynamic detection, making interference feature extraction more accurate. Curve fitting and trend analysis enable proactive prediction of interference effects, avoiding blind corrections. Through the linkage of features, trends, and regulation, it can accurately identify true detection anomalies and effectively eliminate false anomalies caused by interference, significantly improving the reliability of biochip detection data. It is particularly suitable for high-precision detection scenarios of complex clinical samples (such as serum from cancer patients and heel prick blood from newborns). Attached Figure Description

[0014] Figure 1 This is a schematic diagram of a medical biochip detection quality monitoring method. Detailed Implementation

[0015] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0016] In one embodiment of the present invention, a method and system for quality monitoring of medical biochip detection is provided, the method comprising: S1. Monitor and control the biochip for corresponding detection, divide and correspond the obtained monitoring detection data and interference detection data into time series, obtain the detection corresponding data, and obtain the interference detection feature data based on the detection corresponding data; S2. Obtain the data signal fitting curves of the monitoring and detection data and interference detection data after time-series division, perform curve change analysis, and then determine the influence trend of interference characteristics to obtain characteristic interference trend determination information. S3. Identify and analyze abnormal indicators in the monitoring and detection data to obtain actual detection status analysis data. Based on the actual detection status analysis data and the characteristic interference trend judgment information, obtain negative impact indicators, adjust the indicators abnormally, and obtain detection abnormal adjustment data.

[0017] The working principle and technical effects of the above technical solution are as follows: This invention constructs a closed-loop quality monitoring process based on interference feature capture, influence trend analysis, and precise anomaly adjustment. The core is to upgrade from passive quality control to active regulation through time-series correlation and multi-dimensional analysis. First, the biochip is functionally partitioned to clearly define the monitoring area and the control area. During the detection process, raw data from both areas are collected simultaneously. At the same time, at preset time intervals (e.g., every 5 minutes), gradient concentrations of interfering substances (such as hemoglobin and anticoagulants commonly found in clinical samples) are injected into the control area, forming a correspondence between time series, interference, and signal. Then, a data alignment algorithm is used to extract the specific characteristics of different interfering substances at each time point. Time-series data is acquired, and fitting curves for the monitoring area and the control area are constructed respectively. The changes in parameters of the two curves are analyzed through a curve comparison module to determine the influence trend of interference on the detection signal. Anomaly screening is performed on the detection data in the monitored area: first, indicators that exceed the normal range are identified by threshold comparison, and then the interference feature library is matched to determine whether the anomaly is caused by interference. For negative indicators caused by interference, adjustment algorithms (such as signal amplification coefficient correction and dynamic adjustment of detection time) are called for targeted optimization to form a complete quality monitoring link. This method overcomes the limitations of traditional quality control methods that rely solely on static standards. By actively injecting interfering substances, it systematically covers common interference types encountered in clinical settings, avoiding quality control blind spots caused by unknown interferences. The temporal correlation design addresses the issue of interference and signal asynchrony in dynamic detection, enabling more accurate interference feature extraction. Curve fitting and trend analysis provide a forward-looking prediction of interference effects, avoiding blind corrections. Through the linkage of features, trends, and regulation, it can accurately identify true detection anomalies and effectively eliminate false anomalies caused by interference, significantly improving the reliability of biochip detection data. It is particularly suitable for high-precision detection scenarios involving complex clinical samples (such as serum from cancer patients and heel prick blood from newborns).

[0018] In one embodiment of the present invention, S1 includes: The biochip is divided into monitoring and control areas to obtain the corresponding monitoring and control areas; Obtain biochip detection samples, set up a gradient concentration standard array for the biochip, and perform separate detection in the monitoring area and control area to obtain monitoring detection data and interference detection data; During the detection process, interfering substances are sequentially input into the control area according to a preset time sequence to obtain control interference detection data. Interference detection feature data is obtained by combining the monitoring and detection data with the control interference detection data.

[0019] The working principle and technical effect of the above solution are as follows: Precise capture of interference characteristics is achieved through spatial partitioning and temporal interference injection. First, a monitoring area and a control area are divided. While routine detection is performed in the monitoring area, interference substances are injected into the control area according to a preset time sequence, and both types of data are collected simultaneously. By dividing the data into time sequences, a one-to-one correspondence is established between the monitoring data and the interference data. The signal changes after the introduction of interference are calculated, and interference characteristic data are extracted. Through active interference experiments in the control area, a dedicated feature library of interference substances and signal changes is established.

[0020] This innovative method employs active interference and control experimental designs, overcoming the limitations of passively waiting for interference to occur, and can systematically capture the characteristic spectra of various types of interference. Spatial partitioning ensures the independence of monitoring and interference data, while temporal correspondence eliminates the impact of time deviations on interference analysis, providing standardized characteristic data for interference trend judgment and improving the comprehensiveness and accuracy of interference identification.

[0021] In one embodiment of the present invention, the step of performing interference detection analysis based on the monitoring detection data and the control interference detection data to obtain interference detection feature data includes: The monitoring and detection data are divided into time series according to the preset time series information to obtain multiple time series monitoring and detection data. The interference detection data is divided into time series according to the preset time series information to obtain multiple time series interference detection data; According to the preset timing information, multiple timing monitoring and detection data are matched with multiple timing interference detection data to obtain the corresponding detection data; Obtain the detection change data of the time-series interference detection data relative to the time-series monitoring detection data in the corresponding detection data, and obtain the interference detection characteristic data of the interference substance corresponding to the time sequence.

[0022] The working principle and technical effect of the above technical solution are as follows: Monitoring data and interference data are segmented according to a preset time interval to form time-series segments, and a one-to-one correspondence is achieved through timestamps. The signal changes (such as intensity deviation, fluctuation frequency, etc.) of the interference data relative to the monitoring data within the same time-series segment are calculated, and these changes are used as the specific characteristics of the interference substance corresponding to that time-series point. The core is to eliminate the interference of time variables in dynamic detection through time-series alignment, thereby achieving the quantitative extraction of interference characteristics.

[0023] The time-series partitioning and corresponding mechanism solves the problem of asynchronous interference and signal in dynamic detection, making the extraction of interference features more accurate. By quantifying the signal changes caused by interference, the abstract interference effects are transformed into analyzable feature data, providing structured input for curve analysis and improving the interpretability and application value of interference features.

[0024] In one embodiment of the present invention, S2 includes: Obtain the fitting curve data of time-series monitoring and detection data and corresponding fluorescence signals to obtain monitoring curve data; Obtain the fitting curve data of the temporal interference detection data and the corresponding fluorescence signal to obtain the interference curve data; Obtain the curve change data of the interference curve data relative to the monitoring curve data, and obtain the interference characteristic curve data of the interference monitoring characteristic data. The change state of the interference characteristic curve data is analyzed to obtain change state analysis data; Based on the analysis of the changing state data, the interference trend of the interference characteristics is determined, and the interference trend determination information is obtained.

[0025] The working principle and technical effects of the above technical solution are as follows: Through curve modeling and trend mining, the acquired discrete feature data is transformed into predictable interference impact patterns. The core is to achieve a leap from feature description to trend prediction. The acquired time-series monitoring and interference detection data are cleaned to remove outliers caused by equipment fluctuations and retain valid signal points. The curve fitting module uses a nonlinear regression algorithm to model the time-series relationship of monitoring data and fluorescence signal intensity, and the time-series relationship of interference data and fluorescence signal intensity, respectively, generating monitoring curve data and interference curve data. The curve comparison module calculates the difference parameters of the two curves at each time-series node, including signal intensity deviation, slope deviation, and inflection point offset, and constructs interference feature curves based on these difference parameters. The overall trend of the curve is judged by slope calculation (e.g., a negative slope indicates that the interference impact weakens over time, and a positive slope indicates that the impact intensifies). The rate of change of the curve is analyzed by the second derivative (e.g., a positive second derivative indicates that the rate of impact intensification is slowing down). Peak detection identifies the node with the greatest interference impact (e.g., the interference impact reaches its peak and begins to decay after a certain time-series node). By combining information such as trend direction, rate of change, and peak nodes, characteristic interference trend judgment information is generated (e.g., "As the detection time increases, the attenuation effect of a certain interfering substance on the signal increases linearly, and the attenuation rate reaches a maximum of 25% at 30 minutes"). By transforming discrete time-series data into a continuous mathematical model through curve fitting, the signal variation patterns under normal detection and interference effects can be presented more intuitively, avoiding analytical biases caused by fluctuations in single-point data. Curve comparison and difference parameter calculation accurately quantify the degree of interference's impact on the signal, upgrading interference characteristics from qualitative description to quantitative analysis. The trend analysis module can not only identify the current state of interference impact but also predict the impact of interference at future time-series nodes based on curve patterns, realizing a shift from post-event quality control to pre-event prediction and gaining initiative in anomaly adjustment. In addition, multi-dimensional trend determination can comprehensively depict the dynamic characteristics of interference impact, avoiding the one-sidedness caused by single-dimensional analysis, and is particularly suitable for scenarios with complex interference impacts.

[0026] In one embodiment of the present invention, the step of analyzing the changing state of the interference characteristic curve data to obtain changing state analysis data includes: Obtain the change data of the interference feature curve, determine the upward trend and downward trend of the change data, and obtain the change trend determination information; Based on the changing trend of the interference feature curve, the influence trend of the interference feature is determined, and the influence trend determination information of the feature is obtained. Based on the changing trend, the amount of change in the data determines the influence of the feature on the trend; The information on the trend determination of the feature influence and the amount of feature influence are the change state analysis data.

[0027] The working principle and technical effect of the above solution are as follows: Multi-dimensional trend analysis of the interference characteristic curve. First, the upward / downward trend of the curve is identified to determine the direction of the interference's influence; then, the influence intensity is calculated based on the trend slope to quantify the degree of interference's effect on the signal; the trend direction and intensity are integrated into change state analysis data. The core is to achieve a refined description of the interference's influence through two-dimensional analysis of direction and intensity.

[0028] This method breaks through the limitations of traditional methods that only focus on signal strength, simultaneously capturing the directionality and degree of interference effects, thus providing a more comprehensive description of interference characteristics. Trend direction determination provides directional guidance for anomaly adjustments (such as enhancement / weakening compensation), while intensity quantification provides a basis for adjustment amplitude, laying the foundation for precise adjustment and improving the level of precision in quality monitoring.

[0029] In one embodiment of the present invention, S3 includes: By analyzing the actual detection status through monitoring and detection data, actual detection status analysis data is obtained. Perform actual detection anomaly analysis on the actual detection status analysis data to obtain actual detection anomaly analysis data; Based on the characteristic interference trend determination information, the actual detection anomaly analysis data is adjusted to obtain detection anomaly adjustment data; Based on the anomaly detection adjustment data, the monitoring and detection quality optimization data is obtained, and the biochip detection quality optimization results are obtained.

[0030] The working principle and technical effects of the above-mentioned technical solution are as follows: Through multi-dimensional indicator screening and interference feature matching, the detection status is accurately characterized, with the core being the solution to distinguish between true abnormalities and false abnormalities caused by interference. A multi-dimensional indicator system is constructed, covering key quality dimensions of biochip detection: signal dimension (e.g., fluorescence signal intensity, signal uniformity, background signal value), quantitative dimension (e.g., standard goodness of fit R² value, quantitative error rate), repeatability dimension (e.g., coefficient of variation (CV) value of multiple tests at the same detection site), and specificity dimension (e.g., negative control signal value, cross-reactivity rate). Each dimension has 3-5 specific indicators, forming a complete indicator screening list. The raw data of each indicator is obtained through the data analysis interface of the detection equipment. Random fluctuations are removed using a noise reduction algorithm, and then standardized according to indicator type. The pre-processed indicator data is compared with preset thresholds (thresholds are determined based on industry standards, chip manufacturer recommendations, and clinical validation results, such as R²≥0.98, CV value≤10%). Indicators exceeding the threshold range are marked, forming a preliminary list of abnormal indicators. The system calls upon an interference feature library to extract signal change patterns of preliminary abnormal indicators. Similarity calculations are then performed between these patterns and the features of various interfering substances in the library (using a cosine similarity algorithm; a similarity ≥ 0.8 is considered a match). If a match is successful, the abnormal indicator is determined to be affected by the corresponding interference. Precise adjustment is achieved by combining abnormal indicator identification with interference trends. First, monitoring data is analyzed to identify abnormal indicators. Then, combined with the interference trend determination results, a distinction is made between genuine anomalies and false anomalies caused by interference. For anomalies caused by interference, adjustment strategies are formulated based on trend information to correct abnormal parameters, ultimately outputting optimized detection quality results. The core is establishing a linkage mechanism between abnormal indicators, interference trends, and adjustment strategies.

[0031] By filtering out false anomalies through interference trends, false adjustment is reduced, improving the accuracy of anomaly identification. Targeted adjustment based on interference features avoids the limitations of general adjustment methods, making the correction more precise. The final output quality optimization result takes into account both the original detection information and the influence of interference.

[0032] In one embodiment of the present invention, the step of analyzing the actual detection status through monitoring and detection data to obtain actual detection status analysis data includes: Anomaly identification is performed on multiple indicators based on monitoring and detection data to obtain indicator anomaly identification data; The abnormal indicator identification data is compared with the corresponding preset threshold to obtain the abnormal indicator comparison result. Based on the results of the anomaly comparison of the indicators, multiple abnormal indicator data of the monitoring and detection data are determined; The number of abnormal indicator data is compared with a preset number threshold to obtain the number of abnormal comparison results. Based on the results of the number anomaly comparison, anomaly detection is performed on the monitoring and detection data, and actual detection status analysis data is obtained.

[0033] The working principle and technical effect of the above technical solution are as follows: The detection status is determined through multi-indicator anomaly screening and quantitative comparison. Multiple key indicators (such as signal strength and signal-to-noise ratio) are extracted from the monitoring data, and each is compared with a preset threshold to identify abnormal indicators exceeding the threshold. The number of abnormal indicators is counted and compared with a preset threshold number to determine whether the overall detection status is abnormal. The core is to achieve a comprehensive assessment of the detection status through a two-layer judgment of single-indicator screening and multi-indicator statistics.

[0034] Multi-indicator analysis avoids misjudgments caused by anomalies in a single indicator, improving the comprehensiveness of status assessment. Quantitative comparison mechanisms reduce the influence of subjective judgment, making anomaly identification more objective. By statistically analyzing the number of abnormal indicators, local anomalies can be distinguished from systemic anomalies, providing targeted directions for regulation and enhancing the practicality of quality analysis.

[0035] In one embodiment of the present invention, the step of adjusting the actual detection anomaly analysis data according to the feature interference trend determination information to obtain detection anomaly adjustment data includes: Interference monitoring feature data is extracted from multiple abnormal indicator data to obtain indicator interference feature data; Based on the characteristic interference trend determination information, generate indicator interference trend determination information from the indicator interference characteristic data; Based on the information on the interference trend of indicators, determine the positive and negative impact indicators; The negative impact index is compared with a preset negative index threshold to obtain a negative comparison result; Adjust the negative impact index based on the negative comparison results to obtain abnormality adjustment data.

[0036] When the negative impact indicator exceeds the preset negative impact indicator threshold, the negative impact indicator is adjusted. When the negative impact index is less than or equal to the preset negative impact index threshold, no negative impact index adjustment will be performed.

[0037] The working principle and technical effect of the above technical solution are as follows: Graded adjustment is performed on negative interference indicators. Interference characteristics of abnormal indicators are extracted, and their impact on detection results is determined by combining interference trends. Negatively impactful indicators (i.e., interference that leads to a decrease in detection quality) are screened and compared with preset thresholds. For negative indicators exceeding the threshold, adjustment schemes (such as signal compensation, parameter correction, etc.) are formulated based on the intensity of the impact; those below the threshold are not adjusted. The core is a graded adjustment strategy based on the degree of interference impact.

[0038] By using negative indicators to screen and focus on key issues, ineffective adjustments are avoided, thus improving optimization efficiency. A tiered adjustment mechanism (threshold judgment) ensures resources are concentrated on significantly impactful interfering factors, balancing adjustment costs and effectiveness. Targeted adjustment schemes reduce interference with normal signals, correcting anomalies while preserving the authenticity of the original detection information to the greatest extent possible.

[0039] According to one embodiment of the present invention, the system includes: The detection feature analysis module is used to monitor and control the biochip and perform corresponding detection. It divides and matches the obtained monitoring detection data and interference detection data in time sequence to obtain the detection corresponding data and obtains the interference detection feature data based on the detection corresponding data. The influence trend analysis module is used to obtain the data signal fitting curves of the monitoring and detection data and interference detection data after time-series division, perform curve change analysis, and then determine the influence trend of interference characteristics, thereby obtaining characteristic interference trend determination information. The anomaly adjustment module is used to identify and analyze abnormal indicators in monitoring and detection data, obtain actual detection status analysis data, obtain negative impact indicators based on the actual detection status analysis data and characteristic interference trend judgment information, perform anomaly adjustment of indicators, and obtain detection anomaly adjustment data.

[0040] The working principle and technical effects of the above technical solution are as follows: This invention constructs a closed-loop quality monitoring process based on interference feature capture, influence trend analysis, and precise anomaly adjustment. The core is to upgrade from passive quality control to active regulation through time-series correlation and multi-dimensional analysis. First, the biochip is functionally partitioned to clearly define the monitoring area and the control area. During the detection process, raw data from both types of areas are collected simultaneously. At the same time, at preset time intervals (e.g., every 5 minutes), gradient concentrations of interfering substances (such as hemoglobin and anticoagulants commonly found in clinical samples) are injected into the control area, forming a correspondence between time series, interference, and signal. Then, a data alignment algorithm is used to extract the specific characteristics of different interfering substances at each time point. Time-series data is acquired, and the concentration and fluorescence signal fitting curves of the monitoring area and the interference concentration and fluorescence signal fitting curves of the control area are constructed respectively. The parameter changes of the two curves are analyzed through a curve comparison module to determine the influence trend of interference on the detection signal. Anomaly screening is performed on the detection data in the monitored area: first, indicators that exceed the normal range are identified by threshold comparison, and then the interference feature library is matched to determine whether the anomaly is caused by interference. For negative indicators caused by interference, adjustment algorithms (such as signal amplification coefficient correction and dynamic adjustment of detection time) are called for targeted optimization to form a complete quality monitoring link. This system overcomes the limitations of traditional quality control that relies solely on static standards. By actively injecting interfering substances, it systematically covers common interference types encountered in clinical scenarios, avoiding quality control blind spots caused by unknown interference. The time-series correlation design solves the problem of interference and signal asynchrony in dynamic detection, making interference feature extraction more accurate. Curve fitting and trend analysis enable proactive prediction of interference effects, avoiding blind corrections. Through the linkage of features, trends, and regulation, it can accurately identify true detection anomalies and effectively eliminate false anomalies caused by interference, significantly improving the reliability of biochip detection data. It is particularly suitable for high-precision detection scenarios of complex clinical samples (such as serum from cancer patients and heel prick blood from newborns).

[0041] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for quality monitoring of medical biochip detection, characterized in that, The method includes: S1. Monitor and control the biochip for corresponding detection, divide and correspond the obtained monitoring detection data and interference detection data in time sequence, obtain the detection corresponding data, and obtain the interference detection feature data based on the detection corresponding data; S2. Obtain the data signal fitting curves of the monitoring and detection data and interference detection data after time-series division, perform curve change analysis, and then determine the influence trend of interference characteristics to obtain characteristic interference trend determination information. S3. Identify and analyze abnormal indicators in the monitoring and detection data to obtain actual detection status analysis data. Based on the actual detection status analysis data and the characteristic interference trend judgment information, obtain negative impact indicators, adjust the indicators abnormally, and obtain detection abnormal adjustment data. Wherein, S2 includes: Obtain the fitting curve data of time-series monitoring and detection data and corresponding fluorescence signals to obtain monitoring curve data; Obtain the fitting curve data of the temporal interference detection data and the corresponding fluorescence signal to obtain the interference curve data; Obtain the curve change data of the interference curve data relative to the monitoring curve data, and obtain the interference characteristic curve data of the interference monitoring characteristic data. The change state of the interference characteristic curve data is analyzed to obtain change state analysis data; Based on the analysis data of the changing state, the interference trend of the interference characteristics is determined, and the interference trend determination information is obtained. Wherein, S3 includes: By analyzing the actual detection status through monitoring and detection data, actual detection status analysis data is obtained. Perform actual detection anomaly analysis on the actual detection status analysis data to obtain actual detection anomaly analysis data; Based on the characteristic interference trend determination information, the actual detection anomaly analysis data is adjusted to obtain detection anomaly adjustment data; Based on the anomaly detection adjustment data, the monitoring and detection quality optimization data is obtained to get the biochip detection quality optimization results; The step of analyzing the actual detection status through monitoring and detection data to obtain actual detection status analysis data includes: Anomaly identification is performed on multiple indicators based on monitoring and detection data to obtain indicator anomaly identification data; The abnormal indicator identification data is compared with the corresponding preset threshold to obtain the abnormal indicator comparison result. Based on the results of the anomaly comparison of the indicators, multiple abnormal indicator data of the monitoring and detection data are determined; The number of abnormal indicator data is compared with a preset number threshold to obtain the number of abnormal comparison results. Based on the results of the number anomaly comparison, anomaly detection is performed on the monitoring and detection data, and actual detection status analysis data is obtained.

2. The method for quality monitoring of medical biochip detection according to claim 1, characterized in that, S1 includes: The biochip is divided into monitoring and control areas to obtain the corresponding monitoring and control areas; Obtain biochip detection samples, set up a gradient concentration standard array for the biochip, and perform separate detection in the monitoring area and control area to obtain monitoring detection data and interference detection data; During the detection process, interfering substances are sequentially input into the control area according to a preset time sequence to obtain control interference detection data. Interference detection feature data is obtained by combining the monitoring and detection data with the control interference detection data.

3. The method for quality monitoring of medical biochip detection according to claim 2, characterized in that, The step of performing interference detection analysis based on the monitoring detection data and the control interference detection data to obtain interference detection feature data includes: The monitoring and detection data are divided into time series according to the preset time series information to obtain multiple time series monitoring and detection data. The interference detection data is divided into time series according to the preset time series information to obtain multiple time series interference detection data; According to the preset timing information, multiple timing monitoring and detection data are matched with multiple timing interference detection data to obtain the corresponding detection data; Obtain the detection change data of the time-series interference detection data relative to the time-series monitoring detection data in the corresponding detection data, and obtain the interference detection characteristic data of the interference substance corresponding to the time sequence.

4. The method for quality monitoring of medical biochip detection according to claim 1, characterized in that, The step of analyzing the changing states of the interference characteristic curve data to obtain changing state analysis data includes: Obtain the change data of the interference feature curve, determine the upward trend and downward trend of the change data, and obtain the change trend determination information; Based on the changing trend of the interference feature curve, the influence trend of the interference feature is determined, and the influence trend determination information of the feature is obtained. Based on the changing trend, the amount of change in the data determines the influence of the feature on the trend; The information on the trend determination of the feature influence and the amount of feature influence are the change state analysis data.

5. The method for quality monitoring of medical biochip detection according to claim 1, characterized in that, The step of adjusting the actual detection anomaly analysis data based on the characteristic interference trend determination information to obtain detection anomaly adjustment data includes: Interference monitoring feature data is extracted from multiple abnormal indicator data to obtain indicator interference feature data; Based on the characteristic interference trend determination information, generate indicator interference trend determination information from the indicator interference characteristic data; Based on the information on the interference trend of indicators, determine the positive and negative impact indicators; The negative impact index is compared with a preset negative index threshold to obtain a negative comparison result; Adjust the negative impact index based on the negative comparison results to obtain abnormality adjustment data.

6. The method for quality monitoring of medical biochip detection according to claim 5, characterized in that, The characteristic interference trend determination information includes: When the negative impact indicator exceeds the preset negative impact indicator threshold, the negative impact indicator is adjusted. When the negative impact index is less than or equal to the preset negative impact index threshold, no negative impact index adjustment will be performed.

7. A medical biochip detection quality monitoring system, characterized in that, The system includes: The detection feature analysis module is used to monitor and control the biochip and perform corresponding detection. It divides and correlates the obtained monitoring detection data and interference detection data in time sequence to obtain the detection corresponding data and obtains the interference detection feature data based on the detection corresponding data. The influence trend analysis module is used to obtain the data signal fitting curves of the monitoring and detection data and interference detection data after time-series division, perform curve change analysis, and then determine the influence trend of interference features, thereby obtaining feature interference trend determination information. The anomaly adjustment module is used to identify and analyze abnormal indicators in monitoring and detection data, obtain actual detection status analysis data, obtain negative impact indicators based on the actual detection status analysis data and characteristic interference trend judgment information, perform anomaly adjustment of indicators, and obtain detection anomaly adjustment data. The influence trend analysis module includes: Obtain the fitting curve data of time-series monitoring and detection data and corresponding fluorescence signals to obtain monitoring curve data; Obtain the fitting curve data of the temporal interference detection data and the corresponding fluorescence signal to obtain the interference curve data; Obtain the curve change data of the interference curve data relative to the monitoring curve data, and obtain the interference characteristic curve data of the interference monitoring characteristic data. The change state of the interference characteristic curve data is analyzed to obtain change state analysis data; Based on the analysis data of the changing state, the interference trend of the interference characteristics is determined, and the interference trend determination information is obtained. The abnormal adjustment module includes: By analyzing the actual detection status through monitoring and detection data, actual detection status analysis data is obtained. Perform actual detection anomaly analysis on the actual detection status analysis data to obtain actual detection anomaly analysis data; Based on the characteristic interference trend determination information, the actual detection anomaly analysis data is adjusted to obtain detection anomaly adjustment data; Based on the anomaly detection adjustment data, the monitoring and detection quality optimization data is obtained to get the biochip detection quality optimization results; The step of analyzing the actual detection status through monitoring and detection data to obtain actual detection status analysis data includes: Anomaly identification is performed on multiple indicators based on monitoring and detection data to obtain indicator anomaly identification data; The abnormal indicator identification data is compared with the corresponding preset threshold to obtain the abnormal indicator comparison result. Based on the results of the anomaly comparison of the indicators, multiple abnormal indicator data of the monitoring and detection data are determined; The number of abnormal indicator data is compared with a preset number threshold to obtain the number of abnormal comparison results. Based on the results of the number anomaly comparison, anomaly detection is performed on the monitoring and detection data, and actual detection status analysis data is obtained.

Images