Artificial intelligence neural network learning model construction system and construction method

Abstract

The invention belongs to the technical field of computer model construction, and discloses an artificial intelligence neural network learning model construction system and method, and the method comprises the steps: obtaining effective related data of a lung cancer patient; performing feature extraction on the obtained data to obtain a feature sample set; preprocessing the obtained feature sampleset to obtain normalized sample data; dividing the obtained normalized sample data into a training data set and a verification data set; constructing an artificial intelligence algorithm model, and training the constructed artificial intelligence algorithm model by using the obtained training data set; verifying the constructed artificial intelligence algorithm model by utilizing the verificationdata set, and optimizing the artificial intelligence algorithm model based on a verification result; and obtaining an optimized artificial intelligence algorithm model. The artificial intelligence algorithm model is constructed, the lung cancer diagnosis efficiency can be effectively improved, the accuracy of disease evaluation in lung cancer treatment is improved, a corresponding treatment schemeis optimized, and the survival rate of lung cancer patients is increased.

Description

technical field [0001] The invention belongs to the technical field of computer model building, and in particular relates to an artificial intelligence neural network learning model building system and a building method. Background technique [0002] At present, the artificial intelligence screening system for pulmonary nodules has matured, and many artificial intelligence technology companies have achieved great success. Among them, the infereadTM system has been certified by the FDA. The artificial intelligence judgment of benign and malignant properties of pulmonary nodules has achieved good results. The artificial intelligence algorithm for lung nodule screening is open source, so the technology of extracting artificial intelligence imaging features of patients with lung adenocarcinoma is completely feasible. Systemic therapy currently plays a role in most stages of non-small cell lung cancer (NSCLC). The recommended treatment for stage II non-small cell lung cancer is...

AI Technical Summary

Problems solved by technology

But also because of the existence of many specific targeted drugs, the range of use and indications, the patient's own disease and special gene expression, and the combination of different mutated genes have a huge impact on treatment decisions

[0008] Through the above analysis, the problems and defects of the existing technology are: the existing technology does not have comprehensive processing for multiple lung cancer data (lung cancer imaging, genetics, genomics, whole body status similar to the thinking mode of clinicians,) artificial intelligence neural network model

[0009] Difficulties in solving the above problems and defects are: 1. Dispersion of the number of case data; 2. Uncertainty and non-standardization of post-line treatment

3. The understanding of the driving factors of lung cancer is incomplete and incomplete

4. Treatment influencing factors Difficult to define the range of treatment indications, high randomness

5. There is a large gap in the scientific research level of doctors at different levels and different hospitals, and it is difficult to concentrate all patients in large hospitals, and it is difficult to follow up

6. Clinicians have a lot of business pressure and lack of real-time tools, so it is difficult to have time to complete the comprehensive information assessment and tracking records of patients

7. Clinicians lack of interest in statistical records of patient information

Images