DEEP LEARNING-BASED SIMPLE UROFLOWMETRY RESULT LEARNING AND LOWER URINARY TRACT DISORDER DIAGNOSIS METHOD

• Main Authors: CHO BAEK HWAN, HAN DEOK HYUN, LEE KYU SUNG, BANG SEOK HWAN
• Format: Patent
• Language: English; Korean
• Published: 02.05.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DIAGNOSIS; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; MEDICAL OR VETERINARY SCIENCE; PHYSICS; SURGERY

The present invention relates to a method for learning a simple uroflowmetry result and a method for diagnosing a lower urinary tract symptom, which learn a neural network using a uroflowmetry result which is non-invasive data, and diagnose a lower urinary tract symptom using a learned neural network. According to the method for diagnosing a lower urinary tract symptom of the present invention, a learning model is generated by using a simple uroflowmetry result which is a non-invasive test method based on deep-learning, and a lower urinary tract symptom is diagnosed by using the learning model, such that the occurrence of a pain and shame of a patient is prevented during a process of diagnosing a lower urinary tract symptom, and the risk of the secondary infection caused by an invasive diagnostic method is reduced. 본 발명은 단순요류검사 결과 학습방법 및 하부요로증상 진단방법에 관한 것으로, 더욱 상세하게는 비침습적인 데이터인 단순요류검사 결과를 이용하여 신경망을 학습시키고, 학습된 신경망을 이용하여 하부요로증상을 진단하는 단순요류검사 결과 학습방법 및 하부요로증상 진단방법에 관한 것이다. 본 발명은 딥러닝에 기반하여 비침습적인 검사방법인 단순요류검사 결과를 이용하여 학습모델을 생성하고, 이를 이용하여 하부요로증상을 진단함으로써, 하부요로증상 진단과정에서 환자의 고통과 수치심의 발생을 방지하고, 침습적인 진단방법을 통해 발생하는 2차 감염의 위험을 줄이는 하부요로증상 진단 방법을 제공한다.