Дослідження технології виділення функцій із даних медичних записів на основі великих даних і розпізнавання природної мови NLP
Year: 2024
Type: dissertation
Abstract: The topic of "Research on Feature Extraction Technology of Medical Record Data Based on Big Data and NLP Natural Language Recognition " is considered in the thesis. This article investigates a medical record data feature extraction technique based on big data and NLP natural language recognition. We propose a scheme to use Scispacy's English medical model to extract keywords from the original text medical records for the first time through NLP natural language recognition technology, and then use HPO standard words and OMIM disease words to extract keywords from the medical records for the second round through NLP natural language recognition technology. This article provides a detailed introduction to the processes of data preprocessing, model design, training, and validation, and discusses the results and future research directions. This experiment selected some long text electronic medical records and HPO medical records from the company's historical orders, and validated and compared the keywords selected from the long text with the HPO medical records. The experimental results showed that the algorithm can have good accuracy in data feature extraction and can assist medical tasks in feature extraction and classification of large text medical records.
Authors: Wang Chunmei, Ван Чуньмей
Language: Ukrainian
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W7198820659