Method and System for select of pulmonary auscultation information that determines lung disease

• Main Authors: LIM JOON SHIK, WANG BO HYUN, SHIN BYUNG JU
• Format: Patent
• Language: English; Korean
• Published: 02.11.2022
• Subjects: DIAGNOSIS; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; MEDICAL OR VETERINARY SCIENCE; PHYSICS; SURGERY

The present invention relates to a method and a system for selecting pulmonary auscultation information for determining a lung disease performed in a computing system for determining a lung disease, and more specifically, to a method and a system for selecting pulmonary auscultation information for determining a lung disease performed in a computing system, wherein pulmonary auscultation information for diagnosing a lung disease is derived among a plurality of pieces of pulmonary auscultation information and is determined to be main pulmonary sound information using pulmonary auscultation information and pulmonary disease information to which labeling information on whether a pulmonary disease is contracted or the kind of a pulmonary disease has been given, from a plurality of patients as training data, and an inference model based on deep learning, which is trained by the derived main pulmonary sound information to derive pulmonary disease information from the main pulmonary sound information, can be generated. 본 발명은 폐질환을 결정하는 컴퓨팅 시스템에서 수행되는 폐질환을 결정하는 폐음청진정보의 선택방법 및 시스템에 관한 것으로서, 더욱 상세하게는, 복수의 환자들로부터 폐음청진정보와 폐질환의 발병여부 혹은 폐질환종류에 대한 라벨링정보가 부여된 폐질환정보를 학습데이터로 하여, 복수의 폐음청진정보 중 폐질환 진단을 위한 폐음청진정보를 도출하여 주요폐음정보로 결정하고, 도출된 주요폐음정보에 의해 학습되어 주요폐음정보로부터 폐질환정보를 도출하는 딥러닝 기반의 추론모델을 생성할 수 있는, 컴퓨팅 시스템에서 수행되는 폐질환을 결정하는 폐음청진정보의 선택방법 및 시스템에 관한 것이다.