Method for predicting stability of anti-tumor drug tablets based on multi-source data fusion

Abstract

The invention discloses an anti-tumor drug tablet stability prediction method based on multi-source data fusion, and particularly relates to the field of pharmaceutical preparation stability prediction, and the method comprises the following steps: S1, data acquisition; s2, extracting multi-dimensional characteristic parameters; s3, constructing a stability prediction reference model; s4, calculating a real-time attenuation index; s5, determining a deviation threshold range; s6, analyzing a stability deviation index; s7, dynamically updating a prediction result; according to the method, accurate prediction of content attenuation, related substance growth and disintegration time limit change indexes is realized through integration of multi-source data, construction of a stability prediction reference model, simple trend analysis not limited to a single factor, key influence factor marking, critical threshold setting and theoretical attenuation curve fitting; the accuracy and timeliness of stability prediction of antitumor drug tablets are effectively improved, and a scientific basis is provided for drug validity period evaluation and quality risk management and control.

Description

Technical Field

[0001] This invention relates to the field of pharmaceutical formulation stability prediction, and more specifically, to a method for predicting the stability of antitumor drug tablets based on multi-source data fusion. Background Technology

[0002] With the development trend of digital quality control in pharmaceutical preparations, ensuring the stability of anti-tumor drug tablets is crucial for medication safety. Their stability is affected by multiple factors such as raw material characteristics, production process, and storage environment, and the data throughout the entire life cycle is characterized by multi-source and large scale. Among the existing anti-tumor drug tablet stability prediction technologies, the empirical formula method based on accelerated testing relies on idealized conditions for extrapolation and ignores batch differences in raw materials and process fluctuations; single-factor regression analysis only focuses on the correlation of local parameters and is difficult to capture the synergistic effect of multiple factors; and traditional periodic sampling and testing have data lag and cannot reflect the dynamic changes in stability in real time.

[0003] These technical deficiencies lead to significant limitations in practical applications: First, multi-source data are not systematically integrated. Raw material characteristic data, production process data, storage environment data, and historical stability test data are scattered across different systems. The data formats are inconsistent, and the correlations are not explored, making it impossible to provide complete data support for model construction, resulting in a single and one-sided prediction dimension. Second, there is a lack of dynamic deviation correction mechanisms. Once the baseline model is built, it remains unchanged and cannot be adjusted by combining real-time monitoring of the current storage environment data and quality test data. When the actual decay index deviates significantly from the theoretical baseline, the initial model is still used for prediction, which can easily lead to distortion of stability assessment. Third, the setting of key parameters lacks flexibility. Once the weights of key influencing factors, critical thresholds for stability, and parameters of theoretical decay curves are determined, they remain fixed for a long time. This makes it impossible to respond to changes in stability patterns caused by fluctuations in raw materials, process optimization, or changes in storage conditions. As a result, the predicted results are out of sync with the actual quality status, making it difficult to meet the precise quality control requirements of antitumor drug tablets throughout their entire life cycle. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method for predicting the stability of antitumor drug tablets based on multi-source data fusion. To achieve the above objectives, the present invention provides the following technical solution: S1. The multi-source data acquisition module collects raw data from multiple batches of antitumor drug tablets and uploads the raw data to the tablet stability database. S2. The data fusion processing module extracts multi-dimensional feature parameters of tablets from the tablet stability database in batches and transmits them to the stability model construction module. S3. The stability model construction module constructs a tablet stability prediction benchmark model based on the extracted multi-dimensional feature parameters, and marks key influencing factors, stability critical thresholds and theoretical decay curves. S4. The real-time monitoring data acquisition module collects the current storage environment data and real-time quality detection data of the batch of tablets to be predicted in real time, and transmits them to the data fusion processing module to calculate the real-time decay index of various stability indicators under the current conditions. S5. The stability deviation calculation module compares the real-time decay index with the theoretical decay benchmark in the stability prediction benchmark model and calculates the deviation threshold range of each index. S6. The stability deviation index analysis module analyzes the deviation threshold range of multiple indicators to obtain the stability deviation index, which measures the degree of deviation between the current tablet state and the theoretical model. S7. The prediction result generation and dynamic update module, based on the stability deviation index, if the deviation exceeds the threshold, triggers the model dynamic optimization algorithm to regenerate the stability prediction curve; if the deviation is small, it performs local correction based on the baseline model.

[0005] The technical effects and advantages of this invention are as follows: This invention integrates data from the entire chain, including raw material characteristics, production process, storage environment, and historical stability testing, through a multi-source data acquisition module. The data fusion processing module extracts multi-dimensional feature parameters, not limited to a single data dimension or simple statistical analysis. On the one hand, it can provide complete data support for the construction of stability models, comprehensively covering the core factors affecting tablet stability. On the other hand, through multi-source data correlation analysis, it avoids prediction bias caused by data partiality and improves the accuracy of capturing stability patterns. The stability model construction module of this invention marks key influencing factors, stability critical thresholds, and theoretical decay curves. Combined with the current environmental and quality data obtained by the real-time monitoring data acquisition module, the real-time decay index is calculated by the data fusion processing module. The degree of deviation is quantified by the stability deviation calculation module and the deviation index analysis module. If the deviation exceeds the threshold, the model dynamic optimization algorithm is triggered to regenerate the prediction curve. If the deviation is small, local correction is performed. This dynamic update mechanism can optimize parameters to improve the fit between the prediction curve and the actual state, and can quickly respond to environmental fluctuations through local correction. It ensures that the prediction results are adapted to tablet quality changes in real time, while avoiding long-term prediction distortion caused by model staticization, and provides accurate data support for quality control throughout the entire life cycle. This invention calculates a stability deviation index based on the deviation threshold range of multiple indicators. By setting differentiated indicator weights, it strengthens the influence of key quality attributes and achieves a quantitative assessment of the degree of stability deviation. This not only identifies potential quality risks with high accuracy, but also avoids resource waste caused by over-adjustment through a hierarchical processing mechanism of dynamic optimization and local correction, reducing model maintenance costs and improving the scientificity and efficiency of quality control of antitumor drug tablets. Attached Figure Description

[0006] Figure 1 This is a flowchart illustrating the overall structure of the present invention.

[0007] Figure 2 This is a schematic diagram of the overall modules of the present invention. Detailed Implementation

[0008] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0009] As attached Figure 1 The method for predicting the stability of antitumor drug tablets based on multi-source data fusion includes: a multi-source data acquisition module, a tablet stability database, a data fusion processing module, a stability model construction module, a real-time monitoring data acquisition module, a stability deviation calculation module, a stability deviation index analysis module, and a prediction result generation and dynamic update module. A multi-source data acquisition module is used to collect raw data from multiple batches of antitumor drug tablets; The tablet stability database is used to store the raw data of multiple batches of antitumor drug tablets collected by the multi-source data acquisition module; The data fusion processing module is used to extract multi-dimensional feature parameters from the tablet stability database and calculate the real-time decay index of various stability indicators. The stability model building module is used to build a baseline model for predicting tablet stability. The real-time monitoring data acquisition module is used to collect the current data of the batch of tablets to be predicted in real time. The stability deviation calculation module is used to calculate the deviation threshold range of various indicators; The stability deviation index analysis module is used to obtain the stability deviation index; The prediction result generation and dynamic update module is used to determine whether to regenerate the stability prediction curve.

[0010] As attached Figure 2The method for predicting the stability of antitumor drug tablets based on multi-source data fusion, as shown, includes the following steps in its specific implementation: S1. The multi-source data acquisition module collects raw data from multiple batches of antitumor drug tablets and uploads the raw data to the tablet stability database.

[0011] In this embodiment, it should be specifically stated that the original data includes: raw material characteristic data, production process data, storage environment data, and historical stability test data; raw material characteristic data includes the content of active ingredient in the active pharmaceutical ingredient, purity of excipients, particle size distribution, crystal structure, moisture content, and density; production process data includes granulation parameters: stirring speed and granulation time; tableting parameters: tableting pressure and tableting speed; drying parameters: temperature and time; coating parameters: thickness and curing time; storage environment data includes temperature, relative humidity, light intensity, oxygen concentration, and vibration frequency; historical stability test data includes content changes, related substance formation, disintegration time, dissolution rate, hardness, and friability under different storage durations.

[0012] It should be further explained that the raw material characteristic data are mainly collected through laboratory precision instrument testing methods. The content of active ingredients in the active pharmaceutical ingredient and the purity of excipients are determined by high performance liquid chromatography or gas chromatography-mass spectrometry. The particle size distribution of the raw materials is detected by a laser particle size analyzer. The crystal structure is analyzed by X-ray diffraction. The moisture content is determined by a Karl Fischer moisture analyzer. The density is obtained by a tap density meter or a specific gravity bottle method. The production process data are mainly collected through the built-in sensors of the production equipment and the industrial control system. Parameters such as granulation stirring speed and time, tableting pressure and speed, drying temperature and time are captured in real time by the equipment sensors and transmitted to the tablet stability database via industrial Ethernet. The coating thickness is detected by an online laser thickness gauge, and the curing time is recorded by a process timer. The storage environment data are mainly collected through a distributed environmental sensor network. Temperature and relative humidity are monitored by an integrated temperature and humidity sensor. Light intensity is collected by a photoelectric sensor. Oxygen concentration is detected by an electrochemical oxygen sensor. Vibration frequency is captured by an accelerometer. All environmental data are transmitted to the tablet stability database in real time via a wireless sensor network.

[0013] S2. The data fusion processing module extracts multi-dimensional feature parameters of tablets from the same batch from the tablet stability database and transmits them to the stability model construction module.

[0014] In this embodiment, it should be specifically explained that the multi-dimensional characteristic parameters specifically refer to the following dimensions: raw material characteristics: active ingredient content, excipient purity, raw material particle size distribution, crystal structure, moisture content, and density; production process dimensions: granulation stirring speed, granulation time, tableting pressure, tableting speed, drying temperature, drying time, coating thickness, and coating curing time; storage environment dimensions: temperature, relative humidity, light intensity, oxygen concentration, and vibration frequency; and historical stability dimensions: content changes, related substance formation, disintegration time, dissolution rate, hardness, and friability under different storage durations.

[0015] It should be explained that these parameters construct a complete data chain from four core dimensions: the inherent properties of raw materials, production process control, the impact of storage environment, and the law of quality decay. This chain can comprehensively reflect the characteristics of anti-tumor drug tablets throughout their entire life cycle from production to storage, providing multi-perspective input data for the stability prediction model and ensuring that the model can capture the key factors affecting stability.

[0016] It should be further explained that the data fusion processing module performs batch-wise data alignment when extracting parameters, ensuring that raw material, process, environmental, and stability data from the same batch form a one-to-one corresponding feature matrix. Simultaneously, the data undergoes standardization transformation, such as normalizing parameters like pressure and temperature to the [0, 1] interval, and outlier detection algorithms are used to remove data points deviating from the normal range, improving the accuracy of subsequent model construction. S3. The stability model construction module constructs a tablet stability prediction benchmark model based on the extracted multi-dimensional feature parameters, marking key influencing factors, stability critical thresholds, and theoretical decay curves. In this embodiment, it should be specifically noted that the calculation formula for marking key influencing factors is as follows: , The weight of the i-th parameter, Let be the measured value of the i-th parameter in the k-th batch. The average value of the i-th parameter across multiple batches. The overall stability score for the kth batch is calculated based on indicators from historical stability testing data, where m is the total number of parameters and n is the number of batches. The formula for calculating the stability critical threshold is: , Let j be the critical threshold of the stability index. Let j be the pass / fail value for the j-th indicator. The standard deviation of the j-th indicator in multiple batches of historical data; the formula for calculating the theoretical decay curve is: , S0 is the theoretical value of the stability index at storage time t, Wi is the influence weight of the key factor, Ki is the decay number of the i-th key factor, which is obtained by fitting historical data, ai is the time exponent of the i-th key factor, reflecting the decay acceleration, and t is the storage time in days.

[0017] It needs to be explained that the formula for calculating the weights of key influencing factors determines the weights by quantifying the correlation between parameter fluctuations and stability scores. The greater the parameter fluctuation and the worse the stability of the corresponding batch, the higher the weight. The numerator measures the contribution of a single parameter to stability, and the denominator is normalized to ensure that the sum of the weights is 1. For example, if the moisture content of a batch of raw materials is far above the average and the stability score is low, the weight of moisture content will be increased. The formula for calculating the critical stability threshold is based on the statistical principle of normal distribution. It adds a statistical margin of 95% confidence interval to the qualified standard value, which not only complies with regulations but also covers production fluctuations. For example, when the relevant substance standard is 0.1% and the standard deviation is 0.02%, the threshold is 0.14%, leaving room for error in production. The formula for the theoretical decay curve is based on the exponential decay model of multi-factor synergy, which integrates the weights of key factors, decay coefficients, and time exponents. For example, the decay coefficient of temperature reflects the influence of temperature on the decay rate, and the time exponent reflects the accelerating decay trend of factors such as humidity.

[0018] It should be further explained that Yk in the calculation of key influencing factors is synthesized through the analytic hierarchy process. The weights for content change, related substance generation, and disintegration time are 0.4, 0.3, and 0.2, respectively. Absolute values ​​are used to reduce the impact of outliers. For the stability critical threshold, the skewed distribution index is first transformed using Box-Cox transformation. A warning threshold with a 90% confidence interval is added to the key index for early intervention. The theoretical decay curve only takes the first 5 key factors to balance complexity and accuracy. Different dosage forms require refitting parameters. In practical applications, the curve will also be dynamically adjusted according to real-time environmental parameters to improve prediction accuracy.

[0019] S4. The real-time monitoring data acquisition module collects the current storage environment data and real-time quality detection data of the batch of tablets to be predicted in real time, and transmits them to the data fusion processing module to calculate the real-time decay index of various stability indicators under the current conditions.

[0020] In this embodiment, it should be specifically noted that the real-time decay index of each stability indicator includes: content decay index, related substance growth decay index, and disintegration time decay index. Specifically, the formula for calculating the content decay index is: Ac is the real-time content decay index, C is the current content detection value, C0 is the initial content value, T is the current storage temperature, T0 is the theoretical storage temperature, i.e. the standard temperature in the benchmark model, H is the current storage humidity, H0 is the theoretical storage humidity, W1 and W4 are the weights of key influencing factors in the benchmark model.

[0021] The formula for calculating the growth and decay index of relevant substances is as follows: AI is the real-time decay index of related substance growth, I is the current amount of related substance generated, TI is the critical threshold for related substance stability, t is the current storage time, T is the current storage temperature, T0 is the theoretical storage temperature, K1 is the temperature decay coefficient, M is the current measured value of raw material moisture content, M0 is the initial moisture content, and W2 is the key factor influence weight of raw material moisture content.

[0022] The formula for calculating the decay exponent over time is: AD is the real-time decay index of disintegration time limit, D is the measured value of the current disintegration time limit, D0 is the initial disintegration time limit, P is the residual influence value corresponding to the current tableting pressure, P0 is the reference tableting pressure, L is the current light intensity, L0 is the standard light intensity, W3 is the key factor influence weight of tableting pressure, and W5 is the influence weight of light intensity. It needs to be explained that the content decay index calculation formula integrates the effects of actual content loss and environmental deviations. It reflects the basic decay by the ratio of the current content to the initial value, and then adds the effects of temperature and humidity deviations from the theoretical value, so that the index can fully reflect the actual situation of content decay. For example, when the current content is 95% and the temperature is 5°C higher than the theoretical value, the index will increase accordingly, intuitively showing the degree of decay. The related substance growth decay index considers both the ratio of the current related substance generation to the critical threshold and the effects of temperature decay coefficient, storage time and moisture content deviation. It can dynamically reflect the growth trend of related substances with the environment and time. For example, when the storage time is extended or the temperature is increased, the index will increase significantly, providing early warning of risks. The disintegration time decay index combines the actual changes in disintegration time, the effect of residual tableting pressure and the effect of light intensity, reflecting the decay of disintegration performance in multiple dimensions. For example, when the current disintegration time is extended or the light is too strong, the index increases, reflecting the decline in disintegration performance.

[0023] It should be further explained that the weights of key influencing factors W1 to W5 involved in the calculation of each index are all derived from the key influencing factor weights marked in the stability prediction benchmark model, ensuring consistency with the benchmark model; the real-time acquisition frequency of environmental parameters such as temperature and humidity is once every 5 minutes, and the average value is taken to reduce the interference of instantaneous fluctuations on the index; real-time quality detection data, such as C and I, are measured using precision laboratory instruments, and the data are uploaded after being verified by the LIMS system to ensure the accuracy of the index calculation; for the residual influence value P of the tableting pressure, the residual influence after decay is calculated by associating it with the tableting parameters of this batch in the production process database and combining it with the storage time, so that the index is more in line with the actual state of the tablets.

[0024] S5. The stability deviation calculation module compares the real-time decay index with the theoretical decay benchmark in the stability prediction benchmark model to calculate the deviation threshold range of each index. In this embodiment, the calculation formula for the deviation threshold range of the content decay index needs to be specifically explained: , These represent the lower and upper limits of the deviation threshold for the content decay index, respectively. Ac is actually the real-time content decay index. The standard deviation of the content decay index in the theoretical decay benchmark is calculated based on multiple batches of historical theoretical data. The formula for calculating the deviation threshold range of relevant substance growth indicators is as follows: , These represent the lower and upper limits of the deviation threshold for the relevant material growth index, respectively. AI is actually the real-time decay index of relevant material growth. This represents the standard deviation of the growth index of relevant substances in the theoretical decay baseline. The formula for calculating the disintegration time limit index deviation threshold range is as follows: , These represent the lower and upper limits of the disintegration time limit deviation threshold, respectively. AD is actually the disintegration time limit decay index. This represents the standard deviation of the disintegration time decay index in the theoretical decay benchmark, calculated based on historical theoretical data from multiple batches. It should be explained that in the formula for calculating the threshold range of the disintegration time index deviation, the coefficient 1.3 × σDtheoretical is set between 1.2 times the content decay and 1.5 times the increase of related substances, taking into account both the significant impact of disintegration time on tablet efficacy and setting a reasonable theoretical fluctuation coefficient based on its fluctuation characteristics; the fixed error correction value of 0.08 is determined based on the systematic error analysis of disintegration time detection in historical data, ensuring that the threshold range can cover normal deviations in the detection process; for example, if ADactual = 0.387 and σDtheoretical = 0.04, then... , The deviation threshold range for the disintegration time limit index is [0.255, 0.519]. This range includes reasonable fluctuations in the real-time index while effectively identifying abnormal deviations beyond the normal range. It should be further noted that the σD theorem is calculated using at least 30 batches of historical theoretical decay data. Outliers exceeding three times the standard deviation are removed before calculating the standard deviation to reduce the interference of extreme data on the theoretical fluctuation range. Simultaneously, σD theorem and fixed error correction values ​​are recalibrated for every five additional batches of historical data, ensuring that the deviation threshold range dynamically adapts to long-term changes in production processes and storage conditions, thus maintaining the accuracy and applicability of the determination of disintegration time limit deviation.

[0025] S6. The stability deviation index analysis module, based on the deviation threshold ranges of multiple indicators, comprehensively analyzes and obtains the stability deviation index, which measures the degree of deviation between the current tablet state and the theoretical model. Stability deviation index calculation formula: SDI is the stability deviation index, n is the number of indicators involved in the calculation, Wj is the weight of the j-th indicator, Ajreal is the real-time decay index of the j-th indicator, and Ajtheoretical is the theoretical decay benchmark of the j-th indicator. Let be the width of the deviation threshold range for the j-th indicator. An example calculation shows that... It needs to be explained that the stability deviation index calculation formula integrates the deviation of various indicators into a single index through standardization, where the numerator... The denominator measures the absolute deviation between the real-time decay index and the theoretical decay benchmark. The deviation is standardized by defining the range of deviation thresholds to eliminate the influence of differences in the magnitude of different indicators. Then, a weighted sum is performed using the indicator weights Wj, allowing the index to comprehensively reflect the overall situation of multi-dimensional deviations. For example, the weight of the content decay indicator is 0.4, and the weight of the related substances growth indicator is 0.6, reflecting the higher priority of related substances in influencing stability. When the related substances deviation is large, it will dominate the change in the SDI value, which is more in line with the logic of actual quality risk assessment. It needs further explanation that the number of indicators n involved in the calculation is dynamically adjusted according to the tablet type. For high-risk formulations, all three core indicators (content, related substances, and disintegration time) are included, while for ordinary formulations, this can be simplified to two key indicators. The indicator weights Wj are determined using the Delphi method combined with expert scoring. The weights of related substances, content, and disintegration time are usually set to 0.6, 0.3, and 0.1, respectively, to strengthen the influence of safety indicators. During the calculation process, if the real-time decay index of a certain indicator exceeds the deviation threshold range, i.e., > If the deviation percentage of this indicator is 1.0, it avoids excessive dilution of extreme deviations. Furthermore, the SDI threshold classification—SDI < 0.2 for slight deviation, SDI between 0.2 and 0.5 for moderate deviation, and SDI > 0.5 for significant deviation—is determined based on deviation analysis results from historical batch data. This ensures accurate mapping of the deviation between the actual quality state of the tablets and the theoretical model, providing a quantitative basis for subsequent model optimization or correction. In the S7 prediction result generation and dynamic update module, if the deviation exceeds the threshold based on the stability deviation index, the model's dynamic optimization algorithm is triggered to regenerate the stability prediction curve; if the deviation is small, local corrections are made based on the baseline model.

[0026] In this embodiment, it should be specifically noted that the deviation threshold is set to 0.2. This threshold is determined based on statistical analysis of multiple batches of historical data. The stability deviation index (SDI) between 0.2 and 0.5 indicates moderate deviation, and SDI > 0.5 indicates significant deviation. When the stability index SDI ≥ 0.2, the model dynamic optimization algorithm is triggered; when SDI < 0.2, it is determined to be a slight deviation, and local correction is performed. The model dynamic optimization algorithm adopts an improved particle swarm optimization algorithm combined with a Bayesian network. By introducing adaptive inertia weights and mutation operations, it avoids getting trapped in local optima and re-optimizes the weights of key influencing factors, the critical stability threshold, and the theoretical decay curve parameters. The local correction is aimed at the real-time fluctuations of storage environment parameters. While retaining the core structure of the baseline model, the prediction curve is fine-tuned by adjusting the local slope of the decay curve.

[0027] It should be explained that setting the deviation threshold to 0.2 is a balance point determined after comprehensively considering the model prediction error and actual production fluctuations. Historical data shows that when SDI ≥ 0.2, the average deviation between the model prediction and the actual detection value exceeds 5%, which has affected the accuracy of the expiration date prediction. When SDI < 0.2, the deviation mainly stems from short-term fluctuations in environmental parameters, and the difference between prediction and reality can be effectively bridged through local correction. In the model's dynamic optimization algorithm, the particle swarm optimization algorithm is responsible for globally searching for the optimal parameter combination, while the Bayesian network updates the parameter distribution based on prior knowledge and real-time data. The combination of the two can ensure optimization efficiency while avoiding overfitting. For example, when the growth of related substances in a batch of tablets is abnormal, the algorithm will automatically increase the weight of related factors such as temperature and moisture, and adjust the critical threshold of related substances to make the newly generated prediction curve closer to the actual degradation trend.

[0028] Secondly: The accompanying drawings of the embodiments disclosed in this invention only involve the structures involved in the embodiments disclosed in this invention. Other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of this invention can be combined with each other. In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for predicting the stability of antitumor drug tablets based on multi-source data fusion, characterized in that, The method includes a multi-source data acquisition module, a tablet stability database, a data fusion processing module, a stability model construction module, a real-time monitoring data acquisition module, a stability deviation calculation module, a stability deviation index analysis module, and a prediction result generation and dynamic update module. The specific steps of the method are as follows: S1. The multi-source data acquisition module collects raw data from multiple batches of antitumor drug tablets and uploads the raw data to the tablet stability database. S2. The data fusion processing module extracts multi-dimensional feature parameters of tablets from the tablet stability database in batches and transmits them to the stability model construction module. S3. The stability model construction module constructs a tablet stability prediction benchmark model based on the extracted multi-dimensional feature parameters, and marks key influencing factors, stability critical thresholds and theoretical decay curves. S4. The real-time monitoring data acquisition module collects the current storage environment data and real-time quality detection data of the batch of tablets to be predicted in real time, and transmits them to the data fusion processing module to calculate the real-time decay index of various stability indicators under the current conditions. S5. The stability deviation calculation module compares the real-time decay index with the theoretical decay benchmark in the stability prediction benchmark model and calculates the deviation threshold range of each index. S6. The stability deviation index analysis module analyzes the deviation threshold range of multiple indicators to obtain the stability deviation index, which measures the degree of deviation between the current tablet state and the theoretical model. S7. The prediction result generation and dynamic update module, based on the stability deviation index, if the deviation exceeds the threshold, triggers the model dynamic optimization algorithm to regenerate the stability prediction curve; if the deviation is small, it performs local correction based on the baseline model.

2. The method for predicting the stability of antitumor drug tablets based on multi-source data fusion according to claim 1, characterized in that: The multi-dimensional characteristic parameters specifically refer to the content of active pharmaceutical ingredient in the raw material, purity of excipients, particle size distribution, crystal structure, moisture content, and density of the raw material characteristics. Production process dimensions include granulation stirring speed, granulation time, tableting pressure, tableting speed, drying temperature, drying time, coating thickness, and coating curing time; storage environment dimensions include temperature, relative humidity, light intensity, oxygen concentration, and vibration frequency; and historical stability dimensions include content changes, related substance formation, disintegration time, dissolution rate, hardness, and friability under different storage durations.

3. The method for predicting the stability of antitumor drug tablets based on multi-source data fusion according to claim 1, characterized in that: The formula for calculating the key impact factor is as follows: , The weight of the i-th parameter, Let be the measured value of the i-th parameter in the k-th batch. The average value of the i-th parameter across multiple batches. Let m be the overall stability score for the kth batch, where m is the total number of parameters and n is the number of batches.

4. The method for predicting the stability of antitumor drug tablets based on multi-source data fusion according to claim 1, characterized in that: The formula for calculating the theoretical attenuation curve is: , S0 is the theoretical value of the stability index at storage time t, Wi is the influence weight of the key factor, Ki is the decay number of the i-th key factor, ai is the time exponent of the i-th key factor, reflecting the decay acceleration, and t is the storage time in days.

5. The method for predicting the stability of antitumor drug tablets based on multi-source data fusion according to claim 1, characterized in that: The real-time decay indices of the various stability indicators include: content decay index, related substance growth decay index, and disintegration time decay index.

6. The method for predicting the stability of antitumor drug tablets based on multi-source data fusion according to claim 5, characterized in that: The formula for calculating the content decay index is as follows: Ac is the real-time content decay index, C is the current content detection value, C0 is the initial content value, T is the current storage temperature, T0 is the theoretical storage temperature, H is the current storage humidity, H0 is the theoretical storage humidity, and W1 and W4 are the weights of key influencing factors in the baseline model.

7. The method for predicting the stability of antitumor drug tablets based on multi-source data fusion according to claim 5, characterized in that: The formula for calculating the growth and decay index of the relevant substance is as follows: AI is the real-time decay index of related substance growth, I is the current amount of related substance generated, TI is the critical threshold for related substance stability, t is the current storage time, T is the current storage temperature, T0 is the theoretical storage temperature, K1 is the temperature decay coefficient, M is the current measured value of raw material moisture content, M0 is the initial moisture content, and W2 is the key factor influence weight of raw material moisture content.

8. The method for predicting the stability of antitumor drug tablets based on multi-source data fusion according to claim 5, characterized in that: The formula for calculating the disintegration time decay index is as follows: AD is the real-time decay index of disintegration time limit, D is the measured value of the current disintegration time limit, D0 is the initial disintegration time limit, P is the residual influence value corresponding to the current tableting pressure, P0 is the reference tableting pressure, L is the current light intensity, L0 is the standard light intensity, W3 is the key factor influence weight of tableting pressure, and W5 is the influence weight of light intensity.

9. The method for predicting the stability of antitumor drug tablets based on multi-source data fusion according to claim 1, characterized in that: The formula for calculating the stability deviation index is as follows: SDI is the stability deviation index, n is the number of indicators involved in the calculation, Wj is the weight of the j-th indicator, Ajreal is the real-time decay index of the j-th indicator, and Ajtheoretical is the theoretical decay benchmark of the j-th indicator. denoted as the width of the deviation threshold range for the j-th indicator.

Images