지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학위논문
- 저자정보
- 지도교수
- 김철용
- 발행연도
- 2018
- 저작권
- 고려대학교 논문은 저작권에 의해 보호받습니다.
이용수9
이 논문의 연구 히스토리 (2)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
Purpose: The aim of this study is to develop a model for predicting the probability of radiation pneumonitis using a machine learning algorithm through big data analysis.
Methods: Unstructured data, such as previously published papers, was structured through text mining techniques and stored in a semantic database. We combined both structured data and unstructured data and developed a model for predicting radiation pneumonitis using machine learning algorithm through big data analysis.
Results: After uploading the dose-volume histogram data and inputting the six clinical factors into a web-based model, the artificial intelligence is used to quantify and visualize the predicted incidence of radiation pneumonitis based on the learned big data. Data mining and machine learning algorithms were used to develop a prediction model that can integrate not only structured data but also unstructured data. We confirmed that the probability of radiation pneumonitis in each patient can be quantified and visualized in the treatment planning stage and reflected immediately in the treatment plan.
Conclusion: The development of a radiation pneumonia prediction model based on big data will be of great help in the decision making of the optimal treatment plan for each individual patient with lung cancer in the treatment planning stage.
Methods: Unstructured data, such as previously published papers, was structured through text mining techniques and stored in a semantic database. We combined both structured data and unstructured data and developed a model for predicting radiation pneumonitis using machine learning algorithm through big data analysis.
Results: After uploading the dose-volume histogram data and inputting the six clinical factors into a web-based model, the artificial intelligence is used to quantify and visualize the predicted incidence of radiation pneumonitis based on the learned big data. Data mining and machine learning algorithms were used to develop a prediction model that can integrate not only structured data but also unstructured data. We confirmed that the probability of radiation pneumonitis in each patient can be quantified and visualized in the treatment planning stage and reflected immediately in the treatment plan.
Conclusion: The development of a radiation pneumonia prediction model based on big data will be of great help in the decision making of the optimal treatment plan for each individual patient with lung cancer in the treatment planning stage.
목차
Abstract 1I. 서론 3II. 연구방법 61. 비정형 임상 데이터 획득 및 텍스트 마이닝 71) 정형화 단계 72) 시맨틱 분석 및 색인 82. 정형 임상 데이터 분석 81) 선량-체적 히스토그램 분석 82) 방사선 부작용 평가 기준 93) 선량 제한 인자 94) 임상 데이터 학습 및 테스트 113. 기계학습 124. 분석 도구 125. 윤리 규정 및 통계 14III. 연구결과 151. 시맨틱 분석 및 색인 152. 정형 및 비정형 데이터 통합 분석 153. 방사선폐렴 예측 모델 사용자 인터페이스 16IV. 고찰 17V. 결론 23
최근 본 자료
댓글(0)
0