Method for determining the effect of medication against anlotinib and related devices

Abstract

This disclosure provides a method and related apparatus for determining the efficacy of anlotinib, involving artificial intelligence technologies such as efficacy prediction, machine learning, deep learning, and pharmacokinetic models. The method includes: acquiring the patient's anlotinib dosage, treatment duration, weight, and blood drug concentration observation time points; using the dosage, treatment duration, weight, and blood drug concentration observation time points as input data for a pre-set blood drug concentration prediction model to obtain the output blood drug concentration parameter; responding to a patient's efficacy prediction function selection command, acquiring the patient's actual age; and using the blood drug concentration parameter and actual age as input data for the pre-set efficacy prediction model to obtain the output cancer progression probability. Applying this method can improve the accuracy of determining the actual efficacy of anlotinib in individual patients based on individual differences, thus facilitating precision medication.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, specifically to artificial intelligence technologies such as efficacy prediction, machine learning, deep learning, and pharmacokinetic models, and particularly to a method, apparatus, electronic device, computer-readable storage medium, and computer program product for determining the efficacy of anlotinib. Background Technology

[0002] Anlotinib, a multi-target tyrosine kinase inhibitor, has shown promising efficacy in the treatment of various cancers. However, due to significant individual differences in pharmacokinetics and pharmacodynamics, patient response and tolerability to treatment are highly individualized. This individual variation means that standard dosing regimens cannot meet the needs of all patients, resulting in some patients experiencing insufficient drug exposure and poor efficacy, while others may face excessive adverse reactions.

[0003] In clinical practice, the efficacy and adverse reactions of drugs are not only influenced by a single factor, but are often the result of the combined effects of multiple factors. Traditional statistical methods are usually unable to capture these complex nonlinear relationships.

[0004] Therefore, how to better combine individual differences among different patients and accurately determine the efficacy of anlotinib in different patients is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] This disclosure provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for determining the efficacy of anlotinib.

[0006] In a first aspect, this disclosure proposes a method for determining the efficacy of anlotinib, comprising: acquiring the dosage, treatment period, weight, and blood drug concentration observation time points of a patient taking anlotinib; using the dosage, treatment period, weight, and blood drug concentration observation time points as input data for a preset blood drug concentration prediction model to obtain output blood drug concentration parameters; wherein, the blood drug concentration prediction model is trained on a population pharmacokinetic model using a training sample consisting of medication-related parameters and actual blood drug concentration parameters of sample patients matched with anlotinib, and the medication-related parameters include at least dosage, treatment period, weight, and blood drug concentration observation time points; in response to receiving a efficacy prediction function selection instruction from a patient, acquiring the patient's actual age; using the blood drug concentration parameters and actual age as input data for a preset efficacy prediction model to obtain output cancer progression probability; wherein, the efficacy prediction model is trained on a gradient booster model using a training sample consisting of the sample patient's actual blood drug concentration parameters, actual age, and actual cancer progression within a preset time period; and determining the actual efficacy of anlotinib for the patient based on the blood drug concentration parameters and cancer progression probability.

[0007] Secondly, this disclosure provides an apparatus for determining the efficacy of anlotinib, comprising: a medication parameter acquisition unit configured to acquire the dosage, treatment period, weight, and blood drug concentration observation time points of a patient taking anlotinib; and a blood drug concentration prediction unit configured to use the dosage, treatment period, weight, and blood drug concentration observation time points as input data for a preset blood drug concentration prediction model to obtain output blood drug concentration parameters; wherein the blood drug concentration prediction model is trained on a population pharmacokinetic model using a training sample consisting of medication-related parameters and actual blood drug concentration parameters of sample patients matched with anlotinib, and the medication-related parameters include at least dosage, treatment period, and blood drug concentration observation time points. The system includes: a weight and blood drug concentration observation time point; an actual age acquisition unit configured to acquire the patient's actual age in response to receiving a patient's instruction to select the efficacy prediction function; a cancer progression probability prediction unit configured to use the blood drug concentration parameter and actual age as input data for a preset efficacy prediction model to obtain the output cancer progression probability; wherein, the efficacy prediction model is trained on the basis of a gradient booster model using training samples consisting of the sample patients' actual blood drug concentration parameter, actual age, and actual cancer progression within a preset time period; and an actual medication effect determination unit configured to determine the actual medication effect of the patient taking anlotinib based on the blood drug concentration parameter and the cancer progression probability.

[0008] Thirdly, embodiments of this disclosure provide an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to implement the method for determining the efficacy of anlotinib as described in the first aspect.

[0009] Fourthly, embodiments of this disclosure provide a non-transitory computer-readable storage medium storing computer instructions that, when executed by a computer, enable the method for determining the efficacy of anlotinib as described in the first aspect.

[0010] Fifthly, embodiments of this disclosure provide a computer program product including a computer program that, when executed by a processor, can implement the steps of the method for determining the efficacy of anlotinib as described in the first aspect.

[0011] The proposed method for determining the efficacy of anlotinib, as disclosed herein, first obtains the patient's anlotinib dosage, treatment duration, weight, and blood drug concentration observation time points. These data are then used together in a pre-defined blood drug concentration prediction model to predict blood drug concentration, yielding output blood drug concentration parameters. This blood drug concentration prediction model is trained on a population pharmacokinetic model using training samples consisting of patient-matched medication-related parameters and actual blood drug concentration parameters. By controlling that the medication-related parameters include at least the four specific parameters mentioned above as input data, the accuracy of subsequent blood drug concentration prediction results can be improved. Next, after receiving the patient's selection instruction for the efficacy prediction function, the patient's actual age is obtained and used together with the blood drug concentration parameters output by the blood drug concentration prediction model as input data for a pre-defined efficacy prediction model, yielding the output cancer progression probability. This efficacy prediction model is trained on a gradient booster model using training samples consisting of patient-matched actual blood drug concentration parameters, actual age, and actual cancer progression within a pre-defined time period, allowing the efficacy prediction model to learn the correspondence between input and output through training. Ultimately, based on the obtained blood drug concentration parameters and cancer progression probability, the actual therapeutic effect of anlotinib on the patient was determined, so as to facilitate subsequent medication adjustments based on individual differences.

[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0013] Other features, objects, and advantages of this disclosure will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0014] Figure 1 This is an exemplary system architecture to which this disclosure can be applied;

[0015] Figure 2 A flowchart illustrating a method for determining the efficacy of anlotinib as provided in this embodiment of the disclosure;

[0016] Figure 3-1 This is a schematic diagram of an interface for a blood drug concentration prediction function provided in an embodiment of this disclosure;

[0017] Figure 3-2 This is a schematic diagram of an interface for predicting therapeutic efficacy provided in an embodiment of the present disclosure;

[0018] Figure 4-1 A flowchart illustrating another method for determining the efficacy of anlotinib as provided in this disclosure embodiment;

[0019] Figure 4-2 This is a schematic diagram of an interface for a prognostic prediction function provided in an embodiment of the present disclosure;

[0020] Figure 5-1 A flowchart illustrating yet another method for determining the efficacy of anlotinib as provided in this disclosure embodiment;

[0021] Figure 5-2 This is a schematic diagram of an interface for an adverse reaction prediction function provided in an embodiment of the present disclosure;

[0022] Figure 6 A flowchart illustrating yet another method for determining the efficacy of anlotinib as provided in this embodiment of the present disclosure;

[0023] Figure 7 This is a schematic diagram of the initial interface of a tool for evaluating the efficacy of anlotinib provided in an embodiment of this disclosure;

[0024] Figure 8 A structural block diagram of a device for determining the efficacy of anlotinib provided in an embodiment of this disclosure;

[0025] Figure 9 This is a schematic diagram of an electronic device suitable for performing a method for determining the efficacy of anlotinib, as provided in an embodiment of this disclosure. Detailed Implementation

[0026] Existing population pharmacokinetic studies have identified body weight as a significant factor influencing drug exposure, but clinical dose adjustments based on body weight are unnecessary. Similarly, some studies have used longitudinal metabolomics to establish predictive models for efficacy and safety with good results. However, this method still faces challenges in practical clinical application. Currently, anlotinib dose adjustment primarily relies on patients' clinical presentations and laboratory indicators, which often lags behind changes in patient drug response, making timely optimal dose adjustments difficult.

[0027] In clinical practice, drug efficacy and adverse reactions are not only influenced by a single factor, but are often the result of multiple factors working together. Traditional statistical methods often struggle to capture these complex nonlinear relationships. Machine learning, through adaptive algorithms, can efficiently identify complex interaction effects between variables, helping to better predict individualized drug responses. Clinical data typically involves multiple patient characteristics (such as age, weight, genes, medical history, etc.) and multiple drug exposure levels (such as Cmax, AUC, etc.). These high-dimensional data may face overfitting problems in traditional models, but machine learning models excel at handling high-dimensional heterogeneous data, fully utilizing useful information within the data to improve prediction accuracy. Therefore, this disclosure provides a method for better predicting the aforementioned nonlinear relationships by using various models trained with machine learning and deep learning algorithms, improving prediction accuracy and reflecting individual differences.

[0028] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding; these should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description. It should be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0029] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0030] Figure 1 An exemplary system architecture 100 is shown, in which embodiments of the methods, apparatus, electronic devices, and computer-readable storage media for determining the efficacy of anlotinib as disclosed herein can be applied.

[0031] like Figure 1As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0032] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various applications for enabling information communication between the terminal devices 101, 102, and 103 and server 105 can be installed. These applications include drug efficacy evaluation applications, medication advice applications, and instant messaging applications.

[0033] Terminal devices 101, 102, and 103 and server 105 can be either hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices with displays, including but not limited to smartphones, tablets, laptops, and desktop computers. When terminal devices 101, 102, and 103 are software, they can be installed in the aforementioned electronic devices, and can be implemented as multiple software programs or software modules, or as a single software program or software module; no specific limitation is made here. When server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server. When server 105 is software, it can be implemented as multiple software programs or software modules, or as a single software program or software module; no specific limitation is made here.

[0034] Server 105 can provide various services through its built-in applications. Taking a drug efficacy evaluation application as an example, when running this application, server 105 can achieve the following: First, it receives data from users via terminal devices 101, 102, and 103, including the patient's dosage of anlotinib, treatment cycle, weight, and blood drug concentration observation time points. Then, it uses this dosage, treatment cycle, weight, and blood drug concentration observation time points as input data to a preset blood drug concentration prediction model, obtaining the output blood drug concentration parameters. This blood drug concentration prediction model is based on a population pharmacokinetic model and uses the anlotinib... The model is trained using a training sample consisting of medication-related parameters and actual blood drug concentration parameters of matched sample patients. Next, in response to the user's continued input of a efficacy prediction function selection command, the model obtains the patient's actual age. Then, the blood drug concentration parameter and the actual age are used as input data for a preset efficacy prediction model to obtain the output cancer progression probability. This efficacy prediction model is trained on the basis of a gradient booster model using a training sample consisting of the sample patient's actual blood drug concentration parameter, actual age, and actual cancer progression within a preset time period. Finally, based on the blood drug concentration parameter and the cancer progression probability, the actual therapeutic effect of anlotinib on the patient is determined.

[0035] Furthermore, server 105 can also transmit the assessed actual medication effect to professional doctors or medical institutions for processing, and send the processed results back to terminal devices 101, 102, and 103 via network 104.

[0036] It should be noted that the input parameters required for each function, such as dosage, medication cycle, weight, and blood drug concentration observation time points, can be obtained from terminal devices 101, 102, and 103 via network 104, or can be pre-stored locally on server 105 through various means. Therefore, when server 105 detects that this data is already stored locally (e.g., when starting to process previously reserved pending tasks), it can choose to directly retrieve this data from locally. In this case, the exemplary system architecture 100 may not include terminal devices 101, 102, and 103 and network 104.

[0037] The methods for determining the efficacy of anlotinib provided in the subsequent embodiments of this disclosure are generally executed by a server 105 with strong computing power and abundant computing resources. Correspondingly, the device for determining the efficacy of anlotinib is also generally located in the server 105. However, it should also be noted that when terminal devices 101, 102, and 103 also have sufficient computing power and resources, they can also complete the aforementioned calculations performed by the server 105 through their installed drug efficacy evaluation applications, and thus output the same results as the server 105. Especially when multiple terminal devices with different computing capabilities exist simultaneously, but the drug efficacy evaluation application determines that the terminal device has strong computing power and abundant remaining computing resources, the terminal device can perform the aforementioned calculations, thereby appropriately reducing the computing pressure on the server 105. Accordingly, the device for determining the efficacy of anlotinib can also be located in terminal devices 101, 102, and 103. In this case, the exemplary system architecture 100 may also exclude the server 105 and the network 104.

[0038] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0039] Please refer to Figure 2 , Figure 2 A flowchart of a method for determining the efficacy of anlotinib provided in this disclosure embodiment is included, wherein process 200 includes the following steps:

[0040] Step 201: Obtain the patient's dosage of anlotinib, treatment cycle, weight, and blood drug concentration observation time points;

[0041] This step is intended for the entity implementing the method for determining the efficacy of anlotinib (e.g., Figure 1 The server 105 shown obtains medication-related parameters of the patient for the drug anlotinib, such as dosage, treatment cycle, weight, and blood drug concentration observation time points.

[0042] Specifically, the medication-related parameters can come directly from user (or patient) input, or they can be extracted from an image containing relevant information or analyzed from relevant reports or documents generated by certain professional diagnostic and treatment institutions. There are no specific limitations here, and you can choose flexibly according to the actual situation.

[0043] Step 202: Use the dosage, medication cycle, body weight, and blood drug concentration observation time points as input data for the preset blood drug concentration prediction model to obtain the output blood drug concentration parameters;

[0044] Building upon step 201, this step aims to have the aforementioned executing entity use dosage, medication cycle, weight, and blood drug concentration observation time points as input data for a pre-defined blood drug concentration prediction model. This model is trained on a population pharmacokinetic model using a training sample comprised of medication-related parameters and actual blood drug concentration parameters from sample patients matched with anlotinib. The medication-related parameters at least include the output blood drug concentration parameters obtained from dosage, medication cycle, weight, and blood drug concentration observation time points. In this way, the blood drug concentration prediction model learns the correspondence between input and output data through training, thereby enabling it to output matching blood drug concentration parameters for actual input data. It should be noted that by controlling the medication-related parameters to include at least the four specific parameters mentioned above as input data, the accuracy of subsequent blood drug concentration prediction results can be improved. That is, when the user can continue to provide more medication-related parameters included in the training sample, the accuracy of the output blood drug concentration parameters should be further improved.

[0045] Specifically, the blood drug concentration prediction model can be a one-compartment pharmacokinetic model of first-order absorption and elimination derived from population pharmacokinetic analysis. The blood drug concentration parameters output by the model can include: AUC (Area Under the Curve, the area between the curve showing the drug concentration over time and the time axis, reflecting the degree of drug exposure in the body, i.e., the total amount of drug absorbed. A larger AUC indicates a higher degree of drug exposure), Cmax (peak concentration, the highest concentration reached by the drug in the body, an important indicator for evaluating drug bioavailability and efficacy. Excessively high peak concentrations may lead to drug toxicity, while excessively low peak concentrations may affect efficacy), C1min (first-cycle trough concentration, the lowest concentration of the drug at the end of the first dosing cycle. This indicator helps assess the elimination rate and accumulation of the drug in the body), C2min (second-cycle trough concentration, the lowest concentration of the drug at the end of the second dosing cycle. Comparing the first and second cycle trough concentrations can determine whether drug accumulation has occurred in the body), and the blood drug concentration at any point, etc.

[0046] The steps provided in steps 201-202 can be referred to. Figure 3-1 A schematic diagram of the interface for the provided blood drug concentration prediction function, i.e. Figure 3-1 The document clearly defines the format and location of each input and output data.

[0047] Step 203: In response to receiving the patient's instruction to select the efficacy prediction function, obtain the patient's actual age;

[0048] Building upon step 202, this step aims to allow the executing entity to further obtain the patient's actual age upon receiving the patient's instruction to select the efficacy prediction function, in order to satisfy the input required for the efficacy prediction function to perform efficacy prediction.

[0049] It should be noted that the reason there is no similar blood drug concentration prediction function selection instruction before step 201 is because the prediction result of the blood drug concentration prediction function serves as basic information. Therefore, it is usually required to perform blood drug concentration prediction first, and whether to use the efficacy prediction function subsequently can be based on the actual needs of the user or patient. Of course, it is not impossible to add a trigger instruction before step 201, that is, it is also possible to add a trigger instruction based on the blood drug concentration prediction function selection instruction received from the user as a trigger instruction for step 201.

[0050] Step 204: Use the blood drug concentration parameter and actual age as input data for the preset efficacy prediction model to obtain the output cancer progression probability;

[0051] Building upon step 203, this step aims to have the aforementioned executing entity use the blood drug concentration parameter and actual age as input data for a preset efficacy prediction model. This efficacy prediction model is trained on a gradient booster model using training samples consisting of the actual blood drug concentration parameter, actual age, and actual cancer progression within a preset time period of the sample patient. In this way, the efficacy prediction model learns the correspondence between input and output data through training, thereby outputting the cancer progression probability corresponding to the actual input blood drug concentration parameter and actual age.

[0052] The steps provided in steps 203-204 can be referred to. Figure 3-2 A schematic diagram of the interface for the provided efficacy prediction function, namely Figure 3-2 The document clearly defines the format and location of each input and output data.

[0053] Specifically, the efficacy prediction model may only require the AUC and Cmax parameters from the blood drug concentration.

[0054] Step 205: Determine the actual therapeutic effect of anlotinib on the patient based on blood drug concentration parameters and cancer progression probability.

[0055] Building upon steps 202 and 204, this step aims to have the aforementioned implementing entity comprehensively determine the actual therapeutic effect of anlotinib on the patient based on blood drug concentration parameters and the probability of cancer progression.

[0056] The method for determining the efficacy of anlotinib provided in this embodiment first obtains the patient's anlotinib dosage, treatment cycle, weight, and blood drug concentration observation time points. These are then used together as the basis for a pre-defined blood drug concentration prediction model to predict blood drug concentration, yielding output blood drug concentration parameters. This blood drug concentration prediction model is trained on a population pharmacokinetic model using training samples consisting of patient-matched medication-related parameters and actual blood drug concentration parameters. By controlling that the medication-related parameters include at least the four specific parameters mentioned above as input data, the accuracy of subsequent blood drug concentration prediction results can be improved. Next, after receiving the patient's selection instruction for the efficacy prediction function, the patient's actual age is obtained and used together with the blood drug concentration parameters output by the blood drug concentration prediction model as input data for a pre-defined efficacy prediction model, yielding the output cancer progression probability. This efficacy prediction model is trained on a gradient booster model using training samples consisting of the patient's actual blood drug concentration parameters, actual age, and actual cancer progression within a preset time period, allowing the efficacy prediction model to learn the correspondence between input and output through training. Ultimately, based on the obtained blood drug concentration parameters and cancer progression probability, the actual therapeutic effect of anlotinib on the patient was determined, so as to facilitate subsequent medication adjustments based on individual differences.

[0057] Please refer to Figure 4-1 , Figure 4-1 A flowchart of another method for determining the efficacy of anlotinib provided for embodiments of this disclosure, wherein process 400 includes the following steps:

[0058] Step 401: Obtain the patient's dosage of anlotinib, treatment cycle, weight, and blood drug concentration observation time points;

[0059] Step 402: Use the dosage, medication cycle, body weight, and blood drug concentration observation time points as input data for the preset blood drug concentration prediction model to obtain the output blood drug concentration parameters;

[0060] Step 403: In response to receiving the patient's instruction to select the efficacy prediction function, obtain the patient's actual age;

[0061] Step 404: Use the blood drug concentration parameter and actual age as input data for the preset efficacy prediction model to obtain the output cancer progression probability;

[0062] The above steps 401-404 and as follows Figure 2 The steps 201-204 shown are the same. For the same parts, please refer to the corresponding parts of the previous embodiment. They will not be repeated here.

[0063] Step 405: In response to receiving the prognostic prediction function selection instruction from the patient, obtain the actual age;

[0064] Building upon step 404, this step aims to allow the executing entity to further obtain the patient's actual age upon receiving the prognostic prediction function selection instruction from the patient, in order to satisfy the input required for the prognostic prediction function to perform prognostic prediction.

[0065] Prognostic prediction refers to predicting the possible outcomes of disease progression and the patient's potential survival based on various factors such as the patient's condition, physiological indicators, and gene expression. Prognostic prediction is crucial for developing treatment plans, evaluating treatment effectiveness, and improving patients' quality of life.

[0066] Step 406: Use the blood drug concentration parameter and actual age as input data for the preset prognostic prediction model to obtain the output cancer progression risk score;

[0067] Building upon step 405, this step aims to have the aforementioned executing entity use the blood drug concentration parameter and actual age as input data for a pre-defined prognostic prediction model. This prognostic prediction model is trained on a proportional hazards model using training samples consisting of the actual blood drug concentration parameter, actual age, and actual cancer progression risk score of the sample patients. In this way, the prognostic prediction model learns the correspondence between the input and output data through training, thereby outputting a cancer progression risk score corresponding to the actual input blood drug concentration parameter and actual age.

[0068] The steps provided in steps 405-406 can be referred to. Figure 4-2 A schematic diagram of the interface for the provided prognostic prediction function, namely Figure 4-2 The document clearly defines the format and location of each input and output data.

[0069] Specifically, the efficacy prediction model may only require the AUC and Cmax parameters from the blood drug concentration.

[0070] Furthermore, in special circumstances where the user has not used the blood drug concentration prediction model before using the prognostic prediction model, the user can be asked to directly input globulin concentration (GLB, which reflects the functional state of the liver. Abnormal globulin concentration may indicate immune system diseases, liver diseases, etc.) to replace the blood drug concentration parameter.

[0071] Step 407: Determine the actual therapeutic effect of anlotinib on the patient based on blood drug concentration parameters, cancer progression probability, and cancer progression risk score.

[0072] Adaptively, due to the additional prognostic prediction function introduced in steps 405-406, this step will comprehensively determine the actual therapeutic effect of anlotinib on the patient based on three parameters: blood drug concentration parameter, cancer progression probability, and cancer progression risk score.

[0073] Compared to Figure 2 The embodiment shown here additionally provides a prognostic prediction function to provide patients with a score of cancer progression risk, thereby combining blood drug concentration parameters and cancer progression probability to more comprehensively determine the actual drug effect.

[0074] Please refer to Figure 5-1 , Figure 5-1 A flowchart of another method for determining the efficacy of anlotinib provided in this disclosure embodiment, wherein process 500 includes the following steps:

[0075] Step 501: Obtain the patient's dosage of anlotinib, treatment cycle, weight, and blood drug concentration observation time points;

[0076] Step 502: Use the dosage, medication cycle, body weight, and blood drug concentration observation time points as input data for the preset blood drug concentration prediction model to obtain the output blood drug concentration parameters;

[0077] Step 503: In response to receiving the patient's instruction to select the efficacy prediction function, obtain the patient's actual age;

[0078] Step 504: Use the blood drug concentration parameter and actual age as input data for the preset efficacy prediction model to obtain the output cancer progression probability;

[0079] The above steps 501-504 and as follows Figure 2 The steps 201-204 shown are the same. For the same parts, please refer to the corresponding parts of the previous embodiment. They will not be repeated here.

[0080] Step 505: In response to receiving the adverse reaction prediction function selection instruction from the patient, obtain the patient's height, white blood cell ratio, white blood cell count, and neutrophil count;

[0081] Based on step 504, this step aims to have the aforementioned executing entity further obtain the patient's height, white blood cell ratio, white blood cell count, and neutrophil count when it receives the adverse reaction prediction function selection instruction from the patient, so as to meet the input items required for the adverse reaction prediction function to perform adverse reaction prediction.

[0082] The white blood cell ratio, white blood cell count, and neutrophil count can be directly derived from user (or patient) input, or extracted from an image containing relevant information, or analyzed from relevant reports or documents (such as laboratory reports) generated by certain professional medical institutions. No specific limitations are imposed here, and the choice can be made flexibly according to the actual situation.

[0083] Step 506: Use the second-cycle trough concentration, height, white blood cell ratio, white blood cell count, and neutrophil count from the blood drug concentration parameters as input data for the preset adverse reaction prediction model to obtain the output probability of adverse reaction occurrence.

[0084] Building upon step 505, this step aims to have the aforementioned executing entity use the second-cycle trough concentration, height, albumin / globulin ratio, white blood cell count, and neutrophil count from the blood drug concentration parameters as input data for a pre-defined adverse reaction prediction model. This adverse reaction prediction model is trained on a random forest model using training samples composed of adverse reaction-related parameters from sample patients and actual adverse reactions. The adverse reaction-related parameters include at least: second-cycle trough concentration (C2min), height, and albumin / globulin ratio (the ratio of albumin to globulin, abbreviated as A / G; albumin and globulin are plasma...). The two main proteins in the body are normally in a ratio of 1.5-2.5:1. An abnormal A / G ratio may indicate liver disease, malnutrition, etc. For example, a decreased A / G ratio may be seen in chronic liver disease, cirrhosis, etc. White blood cell count (WBC) and neutrophil count (NEUT) are also important indicators. In this way, the adverse reaction prediction model learns the correspondence between input and output data through training, and then outputs the probability of adverse reactions corresponding to the actual input second-cycle trough concentration, height, white blood cell / globulin ratio, white blood cell count, and neutrophil count.

[0085] By controlling the adverse reaction-related parameters to include at least the four specific parameters mentioned above that are used as input data, there is potential to improve the accuracy of the prediction results of the probability of adverse reactions occurring. That is, when the user can continue to provide more adverse reaction-related parameters included in the training samples, the accuracy of the output probability of adverse reactions should be further improved.

[0086] The steps provided in steps 505-506 can be referred to. Figure 5-2 A schematic diagram of the interface for the provided adverse reaction prediction function, i.e. Figure 5-2 The document clearly defines the format and location of each input and output data.

[0087] It should be noted that, including Figure 3-1 , 3-2Interfaces including 4-2 and 5-2 should provide a user-friendly data input environment. Users can input or upload basic patient information, clinical data, and treatment data. The corresponding applications or plugins will perform format and logic validation on the user-input data to ensure its accuracy and completeness. In addition, the results of the blood drug concentration prediction model will be automatically input into the efficacy, prognosis, and adverse reaction models for prediction, meaning that parameters can be transferred between models as needed.

[0088] Step 507: Determine the actual therapeutic effect of anlotinib on the patient based on blood drug concentration parameters, cancer progression probability, and adverse reaction probability.

[0089] Adaptively, due to the additional adverse reaction prediction function introduced in steps 505-506, this step will comprehensively determine the actual therapeutic effect of anlotinib on the patient based on three parameters: blood drug concentration parameter, cancer progression probability, and adverse reaction occurrence probability.

[0090] Compared to Figure 2 The embodiment shown here additionally provides an adverse reaction prediction function to provide patients with a predicted probability of adverse reactions after medication, thereby combining blood drug concentration parameters and cancer progression probability to more comprehensively determine the actual medication effect.

[0091] Please refer to Figure 6 , Figure 6 A flowchart of another method for determining the efficacy of anlotinib provided in this disclosure embodiment, wherein process 600 includes the following steps:

[0092] Step 601: Obtain the patient's dosage of anlotinib, treatment cycle, weight, and blood drug concentration observation time points;

[0093] Step 602: Use the dosage, medication cycle, body weight, and blood drug concentration observation time points as input data for the preset blood drug concentration prediction model to obtain the output blood drug concentration parameters;

[0094] Step 603: In response to receiving the patient's instruction to select the efficacy prediction function, obtain the patient's actual age;

[0095] Step 604: Use the blood drug concentration parameter and actual age as input data for the preset efficacy prediction model to obtain the output cancer progression probability;

[0096] The above steps 601-604 and as follows Figure 2 The steps 201-204 shown are the same. For the same parts, please refer to the corresponding parts of the previous embodiment. They will not be repeated here.

[0097] Step 605: In response to receiving the prognostic prediction function selection instruction from the patient, obtain the actual age;

[0098] Step 606: Use the blood drug concentration parameter and actual age as input data for the preset prognostic prediction model to obtain the output cancer progression risk score;

[0099] Steps 605-606 above are similar to... Figure 4-1 Steps 405-406 shown are the same. For the same parts, please refer to the corresponding parts of the previous embodiment. They will not be repeated here.

[0100] Step 607: In response to receiving the adverse reaction prediction function selection instruction from the patient, obtain the patient's height, white blood cell ratio, white blood cell count, and neutrophil count;

[0101] Step 608: Use the second-cycle trough concentration, height, white blood cell ratio, white blood cell count, and neutrophil count from the blood drug concentration parameters as input data for the preset adverse reaction prediction model to obtain the output probability of adverse reaction occurrence;

[0102] Steps 607-608 above are similar to... Figure 5-1 Steps 505-506 shown are the same. For the same parts, please refer to the corresponding parts of the previous embodiment. They will not be repeated here.

[0103] It should be noted that blood drug concentration parameters, cancer progression probability, cancer progression risk score, and adverse reaction occurrence probability can all be presented using at least one of the following visualization methods:

[0104] Text, tables, and graphs. For example, blood drug concentration parameters represented by concentration change curves, blood drug concentration-time curves and corresponding tables, cancer progression probability represented by line graphs, cancer progression risk scores and adverse reaction probabilities expressed numerically, etc.

[0105] In addition, each model can generate a detailed text description for each prediction, including the basis for the prediction, its possible clinical significance, and recommendations. For predictions indicating potential adverse reactions, a warning signal is generated to alert the user.

[0106] Step 609: Determine the actual therapeutic effect of anlotinib on the patient based on blood drug concentration parameters, cancer progression probability, cancer progression risk score, and probability of adverse reactions.

[0107] Adaptively, since steps 605-608 additionally introduce prognostic and adverse reaction prediction functions, this step will comprehensively determine the actual therapeutic effect of anlotinib on the patient based on four parameters: blood drug concentration parameter, cancer progression probability, cancer progression risk score, and adverse reaction occurrence probability.

[0108] Compared to Figure 4-1 and Figure 5-1 The embodiments shown in this embodiment combine the functions provided independently by the two embodiments to simultaneously provide patients with a predicted probability of adverse reactions after medication and a cancer progression risk score for prognosis, thereby combining blood drug concentration parameters and cancer progression probability to more comprehensively determine the actual medication effect.

[0109] It should be noted that the efficacy prediction model mentioned in the above embodiments was trained using a Gradient Boosting Machine (GBM) model based on machine learning algorithms, the prognosis prediction model was trained using a proportional hazards model, and the adverse reaction prediction model was trained using a Random Forest (RF) model based on machine learning algorithms. These three different model bases were not arbitrarily selected or replaceable. They were chosen through cross-sectional comparisons after experimenting with various types of base models, based on a determined set of training samples corresponding to each prediction function. In other words, these three models were selected because they have all been well validated on the test set and exhibit better prediction accuracy compared to other types of base models.

[0110] To enhance understanding, this disclosure also provides a specific implementation scheme based on a particular application scenario. Please refer to the example below. Figure 7 :

[0111] A patient, X, suffering from a type of cancer that can be treated with anlotinib, continued using anlotinib for a period of time as prescribed after the initial consultation. The patient then accessed the medication via a mobile device or web browser. Figure 7 The anlotinib efficacy evaluation tool shown is as follows: Figure 7 As shown, the main interface has various prediction functions, which are listed in order from top to bottom as blood drug concentration prediction, efficacy prediction, prognosis prediction, and adverse reaction prediction, and also include the instruction "It is recommended to use them in the following order".

[0112] Assuming patient X can access the blood drug concentration prediction function after clicking or selecting the button, Figure 3-1 The user interface shown allows users to input the required medication parameters as instructed, and then run the operation to obtain the blood drug concentration prediction results presented below.

[0113] Next, patient X returned Figure 7 After the initial interface shown, click or select the efficacy prediction button to enter... Figure 3-2 The user interface shown allows users to input new parameters (blood drug concentration parameters can be inherited from blood drug concentration prediction results and do not need to be entered manually) and obtain the cancer development probability shown below by running the operation.

[0114] Next, patient X returned Figure 7 After the initial screen shown, click or select the prognosis prediction button to enter... Figure 4-2 The user interface shown allows users to input new parameters (blood drug concentration parameters can be inherited from blood drug concentration prediction results and do not need to be entered manually) and obtain the cancer development risk score presented below by running the operation.

[0115] Finally, patient X returned Figure 7 After the initial interface shown, click or select the adverse reaction prediction button to enter... Figure 5-2 The user interface shown allows users to input new parameters (blood drug concentration parameters can be inherited from blood drug concentration prediction results and do not need to be entered manually) and obtain the probability of adverse reactions shown below by running the operation.

[0116] This embodiment constructs a multimodal clinical prediction model for advanced cancer patients taking anlotinib based on population pharmacokinetics and machine learning, fully considering factors affecting patient safety and efficacy, and develops a web-based tool that can be applied to guide personalized medication in clinical practice, achieving the following technical effects:

[0117] 1) By accurately predicting blood drug concentration, efficacy, prognosis and adverse reactions, doctors can customize more personalized treatment plans for each patient, improving the effectiveness and safety of treatment;

[0118] 2) The provided prediction results can serve as a powerful aid to doctors' clinical decision-making, helping them adjust treatment plans based on the prediction results, thereby improving treatment outcomes and patients' quality of life;

[0119] 3) Accurate prediction can avoid unnecessary drug use and overtreatment, reduce the waste of medical resources, and reduce the economic burden on patients.

[0120] 4) Patients can better understand their condition and treatment process through intuitive prediction results, which improves their satisfaction and trust in the treatment.

[0121] 5) Utilizing advanced machine learning algorithms and big data analytics, it can provide more accurate prediction results than traditional methods;

[0122] 6) By predicting adverse reactions, especially serious side effects such as bone marrow suppression, doctors can take measures in advance to reduce the risk of patients suffering from adverse reactions.

[0123] Further reference Figure 8 As an implementation of the methods shown in the above figures, this disclosure provides an embodiment of a device for determining the efficacy of anlotinib, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0124] like Figure 8 As shown, the anlotinib efficacy determination device 800 of this embodiment may include: a medication parameter acquisition unit 801, a blood drug concentration prediction unit 802, an actual age acquisition unit 803, a cancer progression probability prediction unit 804, and an actual medication efficacy determination unit 805. The medication parameter acquisition unit 801 is configured to acquire the patient's anlotinib dosage, medication cycle, weight, and blood drug concentration observation time points; the blood drug concentration prediction unit 802 is configured to use the dosage, medication cycle, weight, and blood drug concentration observation time points as input data for a preset blood drug concentration prediction model to obtain output blood drug concentration parameters; wherein, the blood drug concentration prediction model is trained on a population pharmacokinetic model using a training sample consisting of medication-related parameters and actual blood drug concentration parameters of sample patients matched with anlotinib, and the medication-related parameters at least include dosage, medication cycle, weight, and blood drug concentration observation time points; the actual age acquisition unit 803, the actual age acquisition unit 804, the actual age acquisition unit 805, and the actual age acquisition unit 806, the actual age acquisition unit 807, the actual age acquisition unit 808, the actual age acquisition unit 809, the actual age acquisition unit 80 ... Unit 803 is configured to obtain the patient's actual age in response to receiving a patient's instruction to select the efficacy prediction function; cancer progression probability prediction unit 804 is configured to use the blood drug concentration parameter and the actual age as input data for a preset efficacy prediction model to obtain the output cancer progression probability; wherein, the efficacy prediction model is trained on the basis of the gradient booster model using training samples consisting of the sample patient's actual blood drug concentration parameter, actual age, and actual cancer progression within a preset time period; actual medication effect determination unit 805 is configured to determine the actual medication effect of the patient taking anlotinib based on the blood drug concentration parameter and the cancer progression probability.

[0125] In this embodiment, the specific processing and technical effects of the following components in the anlotinib efficacy determination device 800—namely, the medication parameter acquisition unit 801, the blood drug concentration prediction unit 802, the actual age acquisition unit 803, the cancer progression probability prediction unit 804, and the actual medication efficacy determination unit 805—can be referred to separately. Figure 2 The relevant descriptions of steps 201-205 in the corresponding embodiments will not be repeated here.

[0126] In some optional implementations of this embodiment, the device 800 for determining the efficacy of anlotinib may further include:

[0127] The prognostic prediction function selection processing unit is configured to obtain the actual age in response to receiving a prognostic prediction function selection instruction from the patient;

[0128] The prognostic prediction unit is configured to use blood drug concentration parameters and actual age as input data for a preset prognostic prediction model to obtain an output cancer progression risk score. The prognostic prediction model is trained on a proportional hazards model using training samples consisting of the actual blood drug concentration parameters, actual age, and actual cancer progression risk scores of the sample patients.

[0129] Correspondingly, the actual drug efficacy determination unit 805 is further configured as follows:

[0130] The actual therapeutic effect of anlotinib on patients is determined based on blood drug concentration parameters, cancer progression probability, and cancer progression risk score.

[0131] In some optional implementations of this embodiment, the device 800 for determining the efficacy of anlotinib may further include:

[0132] The adverse reaction prediction function selection processing unit is configured to, in response to receiving an adverse reaction prediction function selection instruction from a patient, acquire the patient's height, white blood cell ratio, white blood cell count, and neutrophil count.

[0133] The adverse reaction prediction unit is configured to take the second-cycle trough concentration, height, white blood cell ratio, white blood cell count, and neutrophil count from the blood drug concentration parameters as input data for a preset adverse reaction prediction model, and obtain the output probability of adverse reaction occurrence. The adverse reaction prediction model is trained on a random forest model using adverse reaction-related parameters of sample patients and training samples composed of actual adverse reactions. The adverse reaction-related parameters include at least the second-cycle trough concentration, height, white blood cell ratio, white blood cell count, and neutrophil count.

[0134] Correspondingly, the actual drug efficacy determination unit 805 is further configured as follows:

[0135] The actual therapeutic effect of anlotinib on patients is determined based on blood drug concentration parameters, cancer progression probability, and adverse reaction probability.

[0136] In some optional implementations of this embodiment, the device 800 for determining the efficacy of anlotinib may further include:

[0137] The adverse reaction prediction function selection processing unit is configured to, in response to receiving an adverse reaction prediction function selection instruction from a patient, acquire the patient's height, white blood cell ratio, white blood cell count, and neutrophil count.

[0138] The adverse reaction prediction unit is configured to take the second-cycle trough concentration, height, white blood cell ratio, white blood cell count, and neutrophil count from the blood drug concentration parameters as input data for a preset adverse reaction prediction model, and obtain the output probability of adverse reaction occurrence. The adverse reaction prediction model is trained on a random forest model using adverse reaction-related parameters of sample patients and training samples composed of actual adverse reactions. The adverse reaction-related parameters include at least the second-cycle trough concentration, height, white blood cell ratio, white blood cell count, and neutrophil count.

[0139] Correspondingly, the actual drug efficacy determination unit 805 is further configured as follows:

[0140] The actual therapeutic effect of anlotinib on patients is determined based on blood drug concentration parameters, cancer progression probability, cancer progression risk score, and the probability of adverse reactions.

[0141] In some other implementations of this embodiment, the blood drug concentration parameters, cancer progression probability, cancer progression risk score, and adverse reaction occurrence probability are presented using at least one of the following visualization methods:

[0142] Text, tables, and graphics.

[0143] In some other implementations of this embodiment, the device 800 for determining the efficacy of anlotinib may further include:

[0144] The alternative parameter import unit is configured to extract globulin concentration from the patient's imported laboratory reports as an alternative parameter to the blood drug concentration parameter in the input data of the efficacy prediction model;

[0145] The parameter import unit is configured to extract the white blood cell ratio, white blood cell count, and neutrophil count from the patient's imported laboratory reports.

[0146] In some other implementations of this embodiment, the device 800 for determining the efficacy of anlotinib may further include:

[0147] The adjustment unit is configured to adjust the dosage and / or frequency of medication for the patient based on the actual medication effect.

[0148] This embodiment exists as a device embodiment corresponding to the above method embodiment. The device for determining the efficacy of anlotinib provided in this embodiment first obtains the patient's anlotinib dosage, dosing cycle, weight, and blood drug concentration observation time points, and then uses them together as a preset blood drug concentration prediction model to predict the blood drug concentration, obtaining the output blood drug concentration parameters. This blood drug concentration prediction model is trained on the basis of a population pharmacokinetic model using training samples composed of matching patient-related parameters and actual blood drug concentration parameters. By controlling that the medication-related parameters include at least the four specific parameters mentioned above that are used as input data, it is possible to provide potential for improving the accuracy of subsequent blood drug concentration prediction results. Then, after receiving the patient's selection instruction for the efficacy prediction function, the system further obtains the patient's actual age and uses it, along with the blood drug concentration parameters output by the blood drug concentration prediction model, as input data for the preset efficacy prediction model. This yields the output cancer progression probability. The efficacy prediction model is trained on a gradient booster model using training samples matching the patient's actual blood drug concentration parameters, actual age, and actual cancer progression within a preset time period, allowing the model to learn the correspondence between input and output. Finally, based on the obtained blood drug concentration parameters and cancer progression probability, the actual therapeutic effect of anlotinib on the patient is determined, facilitating subsequent adjustments to medication based on individual differences.

[0149] According to embodiments of this disclosure, this disclosure also provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to implement the method for determining the efficacy of anlotinib as described in any of the above embodiments.

[0150] According to embodiments of this disclosure, this disclosure also provides a readable storage medium storing computer instructions that, when executed by a computer, enable the method for determining the efficacy of anlotinib as described in any of the above embodiments.

[0151] According to embodiments of this disclosure, this disclosure also provides a computer program product that, when executed by a processor, can implement the method for determining the efficacy of anlotinib as described in any of the above embodiments.

[0152] Figure 9A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0153] like Figure 9 As shown, device 900 includes a computing unit 901, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 902 or a computer program loaded from storage unit 908 into random access memory (RAM) 903. RAM 903 may also store various programs and data required for the operation of device 900. The computing unit 901, ROM 902, and RAM 903 are interconnected via bus 904. Input / output (I / O) interface 905 is also connected to bus 904.

[0154] Multiple components in device 900 are connected to I / O interface 905, including: input unit 906, such as keyboard, mouse, etc.; output unit 907, such as various types of monitors, speakers, etc.; storage unit 908, such as disk, optical disk, etc.; and communication unit 909, such as network card, modem, wireless transceiver, etc. Communication unit 909 allows device 900 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0155] The computing unit 901 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above, such as the method for determining the efficacy of anlotinib. For example, in some embodiments, the method for determining the efficacy of anlotinib may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on device 900 via ROM 902 and / or communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps of the method for determining the efficacy of anlotinib described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured by any other suitable means (e.g., by means of firmware) to perform a method for determining the efficacy of anlotinib.

[0156] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0157] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0158] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0159] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0160] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0161] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0162] The beneficial effects of the technical solutions according to the embodiments of this disclosure are repeated.

[0163] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0164] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for determining the efficacy of anlotinib, characterized in that, include: Obtain the patient's dosage, treatment cycle, weight, and blood drug concentration monitoring time points for anlotinib; The dosage, the medication cycle, the body weight, and the blood drug concentration observation time points are used together as input data for a preset blood drug concentration prediction model to obtain output blood drug concentration parameters. The blood drug concentration prediction model is trained on the basis of a population pharmacokinetic model using a training sample consisting of medication-related parameters and actual blood drug concentration parameters of sample patients matched with the anlotinib. The medication-related parameters include at least the dosage, the medication cycle, the body weight, and the blood drug concentration observation time points. In response to receiving the efficacy prediction function selection instruction from the patient, the patient's actual age is obtained; The blood drug concentration parameter and the actual age are used together as input data for a preset efficacy prediction model to obtain the output cancer progression probability. The efficacy prediction model is trained on the basis of the gradient booster model using the actual blood drug concentration parameter, actual age and actual cancer progression within a preset time period of the sample patients. In response to receiving the prognostic prediction function selection instruction from the patient, the blood drug concentration parameter and the actual age are used together as input data for the preset prognostic prediction model to obtain the output cancer progression risk score. The prognostic prediction model is trained on the basis of the proportional hazards model using training samples composed of the actual blood drug concentration parameter, actual age and actual cancer progression risk score of the sample patients. Based on the blood drug concentration parameters, the cancer progression probability, and the cancer progression risk score, the actual therapeutic effect of the patient taking anlotinib is determined.

2. The method according to claim 1, characterized in that, Also includes: In response to receiving the adverse reaction prediction function selection instruction from the patient, the patient's height, white blood cell ratio, white blood cell count, and neutrophil count are obtained; The second-cycle trough concentration, height, white blood cell ratio, white blood cell count, and neutrophil count in the blood drug concentration parameters are used together as input data for a preset adverse reaction prediction model to obtain the output probability of adverse reaction occurrence. Correspondingly, determining the actual therapeutic effect of anlotinib on the patient based on the blood drug concentration parameter, the cancer progression probability, and the cancer progression risk score includes: The actual therapeutic effect of the patient taking anlotinib is determined based on the blood drug concentration parameters, the cancer progression probability, the cancer progression risk score, and the adverse reaction occurrence probability.

3. The method according to claim 2, characterized in that, The blood drug concentration parameter, the cancer progression probability, the cancer progression risk score, and the adverse reaction occurrence probability are presented using at least one of the following visualization methods: Text, tables, and graphics.

4. The method according to claim 2, characterized in that, Also includes: The globulin concentration is extracted from the patient's imported laboratory reports and used as a substitute parameter for the blood drug concentration parameter in the input data of the efficacy prediction model. The white blood cell ratio, white blood cell count, and neutrophil count are extracted from the laboratory reports imported from the patient.

5. A device for determining the efficacy of anlotinib, characterized in that, include: The medication parameter acquisition unit is configured to acquire the patient's dosage of anlotinib, the duration of treatment, weight, and blood drug concentration observation time points; The blood drug concentration prediction unit is configured to take the dose, the medication cycle, the body weight, and the blood drug concentration observation time point as input data to a preset blood drug concentration prediction model, and obtain output blood drug concentration parameters. The blood drug concentration prediction model is trained on a population pharmacokinetic model using a training sample consisting of medication-related parameters and actual blood drug concentration parameters of sample patients matched with the anlotinib. The medication-related parameters include at least the dose, the medication cycle, the body weight, and the blood drug concentration observation time point. The actual age acquisition unit is configured to acquire the patient's actual age in response to receiving a treatment prediction function selection instruction from the patient; The cancer progression probability prediction unit is configured to take the blood drug concentration parameter and the actual age as input data for a preset efficacy prediction model to obtain the output cancer progression probability. The efficacy prediction model is trained on the basis of the gradient booster model using training samples consisting of the actual blood drug concentration parameter, actual age and actual cancer progression within a preset time period of the sample patients. The prognostic prediction function selection processing unit is configured to respond to the prognostic prediction function selection instruction received from the patient, and use the blood drug concentration parameter and the actual age as input data for the preset prognostic prediction model to obtain the output cancer progression risk score. The prognostic prediction model is trained on the basis of the proportional hazards model using training samples consisting of the actual blood drug concentration parameter, actual age and actual cancer progression risk score of the sample patients. The actual drug efficacy determination unit is configured to determine the actual drug efficacy of the patient taking the anlotinib based on the blood drug concentration parameter, the cancer progression probability, and the cancer progression risk score.

6. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method for determining the efficacy of anlotinib as described in any one of claims 1-4.

7. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method for determining the efficacy of anlotinib as described in any one of claims 1-4.

8. A computer program product comprising a computer program that, when executed by a processor, implements the steps of the method for determining the efficacy of anlotinib according to any one of claims 1-4.

Images