CN114420284A - A kind of liver cancer screening method and device - Google Patents

Abstract

The invention discloses a liver cancer screening method and an application device. The method includes: (1) screening out five liver cancer tumor marker combinations through a large number of experiments, which are: alpha-fetoprotein AFP and alpha-fetoprotein heterogenous body AFP- L3, abnormal prothrombin DCP, Golgi protein GP73 and α-L-fucosidase AFU; (2) input the data of the five tumor markers into the ROC curve prediction model to obtain the area under the ROC curve AUC value (3) Compare the area AUC value with a preset threshold to determine the liver cancer risk level to which the five tumor markers belong. Compared with the prior art, the present invention can significantly improve the accuracy of liver cancer screening, and has the characteristics of high sensitivity and high accuracy.

Description

A kind of liver cancer screening method and device

technical field

The present invention relates to the technical field of Internet of medical data, in particular to a liver cancer screening method and device.

Background technique

Currently, primary hepatocellular carcinoma (HCC) is one of the most common malignant tumors in the world and the most common cause of death in patients with chronic liver disease. The five-year overall survival rate of liver cancer is currently only 14.1%. The morbidity and fatality rates are very close. The main reason for the low long-term survival rate of liver cancer is that the screening of high-risk groups for liver cancer is not popularized, and the early diagnosis rate is low, resulting in 70% to 80% of patients at the time of diagnosis. Radical methods such as liver resection and liver transplantation can significantly improve the prognosis of patients with liver cancer; secondly, the recurrence and metastasis rate after liver resection is as high as 40% to 70%.

The existing diagnosis and treatment strategies and measures are very limited in reducing the 5-year total mortality of liver cancer, so it is extremely urgent to explore new screening and diagnosis and treatment strategies for liver cancer.

At present, the commonly used early screening methods for liver cancer include: liver, gallbladder, pancreas and spleen B-ultrasound, liver function test, blood routine, AFP tumor markers, etc. AFP is one of the serum markers for the diagnosis of liver cancer. In general, the sensitivity of AFP for the diagnosis of liver cancer is 25% to 65%. In the detection of small liver cancer and early liver cancer, the false negative is relatively high. It is also used as an early screening indicator for liver cancer. Not very ideal. Alpha-fetoprotein heterogenous AFP-L3 is unique to liver cancer cells, and it increases with the increase of the degree of canceration. Therefore, the percentage of AFP-L3 in AFP (AFP-L3%) is often used as a detection index for primary liver cancer. Imaging detected small hepatocellular carcinomas <2 cm in diameter 4.0±4.9 months earlier (sensitivity 48%, specificity 81%). DCP, also known as PIVKA-II, is an abnormal prothrombin produced specifically with liver cancer.

As a supplement to AFP, DCP has a certain diagnostic value for AFP-negative liver cancer, and has entered the clinical application stage as a liver cancer tumor marker. Some studies have reported that the sensitivity of DCP≥40mAU/ml in the diagnosis of early liver cancer is 61.1%, which is significantly higher than that of AFP, which is 16.7%. Golgi protein-73 (GP73) and α-L-fucosidase AFU are also markers of liver cancer, but their specificity and sensitivity are low, and they are prone to false negatives or false positives. In addition, the method requires an experienced clinician to interpret the test results.

Liver cancer screening in hospitals is the detection of common tumor markers, with low sensitivity and accuracy, making it difficult to meet the requirements for early and rapid diagnosis. The conventional detection method is to detect the tumor marker AFP, but the specificity and sensitivity of AFP are low, and it is prone to false negative or false positive. Therefore, there is an urgent need for a better identification tool based on medical data in clinical diagnosis to screen liver cancer as soon as possible.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide a software method and device for liver cancer screening with high sensitivity and high accuracy, aiming at the shortcomings of the above-mentioned liver cancer screening.

In order to achieve the above object, the technical scheme adopted in the present invention is: a liver cancer screening method, comprising the following steps:

(1) 5 combinations of liver cancer tumor markers were screened through a large number of experiments, namely: alpha-fetoprotein AFP, alpha-fetoprotein heterogenous body AFP-L3, abnormal prothrombin DCP, Golgi protein GP73 and α-L-rock glucosidase AFU;

(2) Input the data of the 5 tumor markers into the ROC curve prediction model to obtain the AUC value of the area under the ROC curve;

(3) Comparing the area AUC value with a preset threshold to determine the liver cancer risk level to which the five tumor markers belong.

Further, the risk levels of liver cancer included: a) highly suspected liver cancer; b) suspected liver cancer; c) low risk of liver cancer.

Further, the area AUC value is compared with a preset threshold to determine the liver cancer risk level to which the five tumor markers belong, including:

When AUC>0.83, it is determined as a highly suspected liver cancer grade;

When 0.83≥AUC>0.55, it is determined as the grade of suspected liver cancer;

When AUC≤0.55, it was determined as a low-risk grade of liver cancer.

In a second aspect, an embodiment of the present invention further provides a liver cancer screening application device, including: a serum sample detection device and a processor;

Wherein, the serum sample detection device is used for detecting AFP, AFP-L3, DCP, GP73 and AFU data of serum samples, and sending the AFP, AFP-L3, DCP, GP73 and AFU data to the processor;

The processor is connected to the serum sample detection device, the processor has built-in SPSS software, and the processor is configured to execute the liver cancer screening method according to any one of the above embodiments.

Further, it also includes a display connected to the processor, and the display is used to display the liver cancer risk level to which the AFP, AFP-L3, DCP, GP73 and AFU data and/or screening results belong.

Further, it also includes a voice playing device connected to the processor, and the voice playing device is used to play the AFP, AFP-L3, DCP, GP73 and AFU data and/or the liver cancer risk level to which the screening result belongs.

Further, it also includes a keyboard and a mouse respectively connected to the processor; and an alarm device connected to the processor, the alarm device is used to issue an alarm message when the screening result is to determine a highly suspected liver cancer grade .

Further, it also includes: a 4G communication module and a mobile terminal connected to the processor, and the processor pushes alarm information to the mobile terminal through the 4G communication module.

The advantages of the present invention are: compared with the prior art, the present invention has the following beneficial effects: the accuracy of liver cancer screening can be significantly improved, and it has the characteristics of high sensitivity and high accuracy.

Description of drawings

1 is a flowchart of a liver cancer screening method provided by an embodiment of the present invention;

Fig. 2 is the software input interface diagram made by adopting the liver cancer screening method provided by the embodiment of the present invention;

Fig. 3 is a software output interface diagram made by adopting a liver cancer screening method provided by an embodiment of the present invention;

Fig. 4 is the schematic diagram of prior art diagnostic analysis ROC curve;

5 is a schematic diagram of a diagnostic analysis ROC curve provided by an embodiment of the present invention;

FIG. 6 is a structural block diagram of a liver cancer screening apparatus according to an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be more thoroughly understood, and will fully convey the scope of the present disclosure to those skilled in the art.

A liver cancer screening method provided by the present invention, as shown in FIG. 1 , includes the following steps:

(1) 5 combinations of liver cancer tumor markers were screened through a large number of experiments, namely: alpha-fetoprotein AFP, alpha-fetoprotein heterogenous body AFP-L3, abnormal prothrombin DCP, Golgi protein GP73 and α-L-rock glucosidase AFU;

(2) Input the data of the 5 tumor markers into the ROC curve prediction model to obtain the AUC value of the area under the ROC curve;

(3) Comparing the area AUC value with a preset threshold to determine the liver cancer risk level to which the five tumor markers belong.

Among them, the risk levels of liver cancer include: a) highly suspected liver cancer; b) suspected liver cancer; c) low risk of liver cancer, a total of three levels.

The present invention selects 5 tumor markers from numerous tumor markers: alpha-fetoprotein AFP, alpha-fetoprotein heterogenous body (AFP-L3), abnormal prothrombin (DCP), Golgi protein-73 (GP73) ) and α-L-fucosidase AFU, when implementing, can make liver cancer screening software system according to this method, after inputting above-mentioned 5 data, this software processes the detection data of these 5 indexes, The final diagnosis is made. Among them, AFP is one of the serum markers for the diagnosis of liver cancer, and it is not very ideal as an early screening index for liver cancer. Alpha-fetoprotein heterogenous body AFP-L3 is unique to liver cancer cells, and it increases with the increase of canceration degree. Therefore, the percentage of AFP-L3 in AFP (AFP-L3%) is often used as the detection index of primary liver cancer; DCP Also known as PIVKA-II, it is an abnormal prothrombin produced specifically with liver cancer. DCP has a certain diagnostic value for AFP-negative liver cancer, and has entered the clinical application stage as a liver cancer tumor marker. Golgi protein-73 (GP73) and α-L-fucosidase AFU are also liver cancer markers. However, the detection of liver cancer serum markers alone lacks sufficient sensitivity and specificity. Therefore, the present invention combines the five indicators to realize early screening of liver cancer, which can greatly improve the specificity and sensitivity of individual liver cancer markers, and provide new ideas and new methods for liver cancer screening.

Among them, the basic principle of the algorithm based on the ROC curve prediction model is as follows:

The algorithm of the ROC curve prediction model adopts the receiver operating characteristic curve (receiver operating characteristic curve, ROC curve for short), also known as the sensitivity curve. The basic principle of the ROC curve algorithm is to set multiple different critical values for continuous variables according to a series of different binary classification methods (cutoff value or decision threshold), thereby calculating a series of sensitivities and specificities to determine true positive The rate (sensitivity) is on the ordinate, and the false positive rate (1-specificity) is a curve drawn on the abscissa. The larger the area under the curve, the higher the diagnostic accuracy. By calculating the area under the ROC curve (AUC), combined with the patient's pathology report, the analysis was performed.

Algorithm implementation process:

All serum data were collected for statistical analysis, and ROC analysis was performed using SPSS software. First, for example, input the detection data of more than 1000 cases of AFP, AFP-L3, DCP, GP73 and AFU into the ROC curve prediction model to calculate the AUC value.

When AUC>0.83, it is highly suspected of liver cancer;

When 0.83≥AUC>0.55, it is determined as suspected liver cancer;

When AUC≤0.55, the risk of liver cancer was determined to be low.

During specific implementation, for example, the method of the present invention can be implemented in the form of software through programming, as shown in Figure 2-3:

Step 1: After entering the basic information of the patient, input the result data of the patient's serum detection AFP, AFP-L3, DCP, GP73 and AFU five indicators into the software;

Step 2: Click Next.

Step 3: The software interface returns the result, and the software will give a specific evaluation conclusion.

Among them, Figure 4 is a schematic diagram of the ROC curve corresponding to the existing triple inspection screening technology:

85 cases of liver cancer patients and 97 cases of non-hepatocellular carcinoma were randomly selected for diagnosis and analysis, and the detection data of AFP, AFP-L3 and DCP were respectively input into ROC analysis software for ROC analysis. As can be seen from Figure 4, the results of the receiver operating characteristic curve show that when AFP, AFP-L3 and DCP are used as markers to diagnose early-stage liver cancer, when the sensitivity is 89.8%, the specificity is only 66.7%; when the specificity is At 77.8%, its sensitivity is only 78%.

As shown in Fig. 5, using the liver cancer screening method of the present invention, which is a five-joint inspection technique, 85 cases of liver cancer patients and 97 cases of non-hepatocellular carcinoma were diagnosed and analyzed, and the receiver operating characteristic curve (receiver operating characteristic curve, referred to as ROC curve) The results showed that the sensitivity and specificity of this method in diagnosing early liver cancer were 91.43% and 89.66%, and its accuracy was much higher than that of the existing triple-check screening technology, and its sensitivity and accuracy were both above 88%.

Based on the same inventive concept, an embodiment of the present invention also provides a liver cancer screening application device. Since the principle of the problem solved by the device is similar to the aforementioned liver cancer screening method, the implementation of the device can refer to the implementation of the aforementioned method, and repeat the following It is not repeated here.

As shown in FIG. 6 , an application device for liver cancer screening includes: a serum sample detection device 201 and a processor 202;

Wherein, the serum sample detection device 201 is used to detect AFP, AFP-L3, DCP, GP73 and AFU data of the serum sample, and sends the AFP, AFP-L3, DCP, GP73 and AFU data to the processor 202;

The processor 202 is connected to the serum sample detection device 201, the processor 202 has built-in SPSS software, and the processor 202 is configured to execute the steps of the liver cancer screening method according to the above embodiment.

Further, a display 203 connected to the processor 202 is also included, and the display 203 is used for displaying the AFP, AFP-L3, DCP, GP73 and AFU data and/or the liver cancer risk level to which the screening result belongs.

Further, it also includes a voice playing device 204 connected to the processor 202, and the voice playing device 204 is used to play the AFP, AFP-L3, DCP, GP73 and AFU data and/or the liver cancer risk level to which the screening result belongs.

Further, it also includes a keyboard 208 and a mouse 209 respectively connected to the processor 202; and an alarm device 205 connected to the processor 202. The alarm device 205 is used to send out a message when the screening result is to determine a highly suspected liver cancer grade. Alarm information.

Further, it also includes: a 4G communication module 207 connected to the processor 202 and a mobile terminal, and the processor 202 pushes alarm information to the mobile terminal through the 4G communication module 207 . Additionally, a printer 210 may be included in connection with the processor connection 202 for printing the screening results.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied therein, including but not limited to disk storage, optical storage, and the like.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit and scope of the invention. Thus, provided that these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims (8)

1. a liver cancer screening method, is characterized in that, comprises the steps: (1) 5 combinations of liver cancer tumor markers were screened through a large number of experiments, namely: alpha-fetoprotein AFP, alpha-fetoprotein heterogenous body AFP-L3, abnormal prothrombin DCP, Golgi protein GP73 and α-L-rock glucosidase AFU; (2) Input the data of the 5 tumor markers into the ROC curve prediction model to obtain the AUC value of the area under the ROC curve; (3) Comparing the area AUC value with a preset threshold to determine the liver cancer risk level to which the five tumor markers belong. 2 . The method for screening liver cancer according to claim 1 , wherein the liver cancer risk levels to which it belongs include: a) highly suspected liver cancer; b) suspected liver cancer; c) low risk of liver cancer. 3 . 3. A liver cancer screening method according to claim 2, wherein the area AUC value is compared with a preset threshold to determine the liver cancer risk level to which the 5 tumor markers belong, comprising: When AUC>0.83, it is determined as a highly suspected liver cancer grade; When 0.83≥AUC>0.55, it is determined as the grade of suspected liver cancer; When AUC≤0.55, it was determined as a low-risk grade of liver cancer. 4. A liver cancer screening application device, comprising: a serum sample detection device and a processor; Wherein, the serum sample detection device is used for detecting AFP, AFP-L3, DCP, GP73 and AFU data of serum samples, and sending the AFP, AFP-L3, DCP, GP73 and AFU data to the processor; The processor is connected to the serum sample detection device, the processor has built-in SPSS software, and the processor is used to execute the liver cancer screening method according to any one of claims 1-3. 5 . The application device for liver cancer screening according to claim 4 , further comprising a display connected to the processor, wherein the display is used to display the AFP, AFP-L3, DCP, GP73 and The liver cancer risk class to which AFU data and/or screening results belong. 6 . The application device for liver cancer screening according to claim 5 , further comprising a voice playback device connected to the processor, and the voice playback device is used to play the AFP, AFP-L3, Liver cancer risk class to which DCP, GP73, and AFU data and/or screening results belong. 7. The liver cancer screening application device according to claim 6, further comprising a keyboard and a mouse respectively connected to the processor; and an alarm device connected to the processor, the alarm The device is used to issue an alarm message when the screening result is to determine the grade of high suspicion of liver cancer. 8 . The application device for liver cancer screening according to claim 7 , further comprising: a 4G communication module and a mobile terminal connected to the processor, and the processor communicates with the The mobile terminal pushes the alarm information.

Images