권호기사보기
| 기사명 | 저자명 | 페이지 | 원문 | 기사목차 |
|---|
결과 내 검색
동의어 포함
Pancreatic ductal adenocarcinoma (PDAC) is a highly lethal malignancy with poor survivalrates, primarily due to its late-stage diagnosis. Early detection is crucial for improving patientoutcomes. The present review summarized the recent advancements in artificial intelligence (AI)for the early detection and prognosis of PDAC. This review synthesized studies on the applicationsof AI that were conducted over a 5-year period (2020–2025). These applications includemachine learning models analyzing radiomic features from computed tomography (CT) scans,automated analysis of circulating microRNA (miRNA) profiles, and personalized circulatingtumor DNA (ctDNA) assays for monitoring molecular residual disease. AI-driven radiomicsidentified PDAC on CT scans with high accuracy at a median of 398 days before clinical diagnosis.
A diagnostic model combining miRNA and cancer antigen 19-9 demonstrated excellentperformance (area under the curve value, 0.99), even in early-stage asymptomatic patients.
Post-operative ctDNA positivity was strongly associated with shorter disease-free survival (hazardratio, 5.45) and higher recurrence rates. AI-based analyses of CT scans, miRNA, and ctDNAhold promise for the early diagnosis and risk stratification of PDAC. The clinical integration ofthese technologies has the potential to considerably improve the prognosis of patients with thisdevastating disease.
Pancreatic ductal adenocarcinoma (PDAC) is a highly lethal malignancy with poor survivalrates, primarily due to its late-stage diagnosis. Early detection is crucial for improving patientoutcomes. The present review summarized the recent advancements in artificial intelligence (AI)for the early detection and prognosis of PDAC. This review synthesized studies on the applicationsof AI that were conducted over a 5-year period (2020–2025). These applications includemachine learning models analyzing radiomic features from computed tomography (CT) scans,automated analysis of circulating microRNA (miRNA) profiles, and personalized circulatingtumor DNA (ctDNA) assays for monitoring molecular residual disease. AI-driven radiomicsidentified PDAC on CT scans with high accuracy at a median of 398 days before clinical diagnosis.
A diagnostic model combining miRNA and cancer antigen 19-9 demonstrated excellentperformance (area under the curve value, 0.99), even in early-stage asymptomatic patients.
Post-operative ctDNA positivity was strongly associated with shorter disease-free survival (hazardratio, 5.45) and higher recurrence rates. AI-based analyses of CT scans, miRNA, and ctDNAhold promise for the early diagnosis and risk stratification of PDAC. The clinical integration ofthese technologies has the potential to considerably improve the prognosis of patients with thisdevastating disease.*표시는 필수 입력사항입니다.
| 전화번호 |
|---|
| 기사명 | 저자명 | 페이지 | 원문 | 기사목차 |
|---|
| 번호 | 발행일자 | 권호명 | 제본정보 | 자료실 | 원문 | 신청 페이지 |
|---|
도서위치안내: 정기간행물실(524호) / 서가번호: 국내17
2021년 이전 정기간행물은 온라인 신청(원문 구축 자료는 원문 이용)
우편복사 목록담기를 완료하였습니다.
*표시는 필수 입력사항입니다.
저장 되었습니다.