Naemi Amin, Tashk Ashkan, Sorayaie Azar Amir, Samimi Tahereh, Tavassoli Ghanbar, Bagherzadeh Mohasefi Anita, Nasiri Khanshan Elaheh, Heshmat Najafabad Mehrdad, Tarighi Vafa, Wiil Uffe Kock, Bagherzadeh Mohasefi Jamshid, Pirnejad Habibollah, Niazkhani Zahra
Nordcee, Department of Biology, University of Southern Denmark, 5230 Odense, Denmark.
Cognitive Systems, DTU Compute, The Technical University of Denmark (DTU), 2800 Copenhagen, Denmark.
Cancers (Basel). 2025 Feb 6;17(3):558. doi: 10.3390/cancers17030558.
BACKGROUND/OBJECTIVES: This systematic literature review examines the application of Artificial Intelligence (AI) in the diagnosis, treatment, and follow-up of metastatic gastrointestinal cancers.
The databases PubMed, Scopus, Embase (Ovid), and Google Scholar were searched for published articles in English from January 2010 to January 2022, focusing on AI models in metastatic gastrointestinal cancers.
forty-six studies were included in the final set of reviewed papers. The critical appraisal and data extraction followed the checklist for systematic reviews of prediction modeling studies. The risk of bias in the included papers was assessed using the prediction risk of bias assessment tool.
AI techniques, including machine learning and deep learning models, have shown promise in improving diagnostic accuracy, predicting treatment outcomes, and identifying prognostic biomarkers. Despite these advancements, challenges persist, such as reliance on retrospective data, variability in imaging protocols, small sample sizes, and data preprocessing and model interpretability issues. These challenges limit the generalizability, clinical application, and integration of AI models.
背景/目的：本系统文献综述探讨了人工智能（AI）在转移性胃肠道癌的诊断、治疗及随访中的应用。
检索了PubMed、Scopus、Embase（Ovid）和谷歌学术数据库，以查找2010年1月至2022年1月期间发表的英文文章，重点关注转移性胃肠道癌中的AI模型。
最终纳入综述的论文有46项研究。严格评价和数据提取遵循预测建模研究系统评价的清单。使用预测偏倚风险评估工具评估纳入论文中的偏倚风险。
包括机器学习和深度学习模型在内的AI技术在提高诊断准确性、预测治疗结果及识别预后生物标志物方面显示出前景。尽管有这些进展，但挑战依然存在，如依赖回顾性数据、成像方案的变异性、样本量小以及数据预处理和模型可解释性问题。这些挑战限制了AI模型的可推广性、临床应用及整合。
Zotero 插件