Generative artificial intelligence in medical oncology: A clinically focused narrative review of large language, vision‐language, and agentic artificial intelligence systems

作者
HARRY B. BURKE
出处
期刊:Cancer [Wiley]
卷期号:132 (21)
标识
DOI:10.1002/cncr.70652
摘要

Rapid advances in cancer genetics and genomics, pathophysiology, diagnostics, and therapeutics have substantially increased the complexity of clinical oncology. Integrating large and diverse data streams into timely, patient-specific decisions provides a compelling rationale for incorporating artificial intelligence (AI) into cancer care. Generative artificial intelligence (GenAI) encompasses several classes of models capable of generating new content. This clinically focused review concentrates on GenAI applications based primarily on large language models (LLMs) and vision-language models (VLMs), as well as emerging agentic systems that use these models to perform coordinated, multistep tasks. LLMs demonstrate substantial medical knowledge, strong performance on oncology-related assessments, and emerging capabilities in clinical reasoning. Guideline- and retrieval-augmented systems can improve concordance with expert recommendations and interpretation of complex treatment algorithms. LLMs and VLMs have been applied to documentation, patient communication, information extraction and summarization, clinical decision support, and multimodal data synthesis. However, performance varies substantially across tasks and clinical domains, with important limitations including incomplete or outdated information, training-data bias, automation bias, and confabulation. Agentic AI represents an emerging extension of these technologies in which LLMs or VLMs are incorporated into systems capable of multistep planning, external information retrieval, specialized tool use, and iterative evaluation and refinement. Early oncology applications include evidence synthesis, multimodal clinical decision support, radiology, pathology, surgery, and individualized treatment planning. With rigorous validation, transparent implementation, continual updating, and appropriate expert oversight, GenAI may augment oncologists' judgment, improve patient understanding and experience, streamline cancer care delivery, and advance personalized oncology.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
yzm发布了新的文献求助10
刚刚
lizard956完成签到 ,获得积分10
1秒前
hanyangyang完成签到,获得积分10
1秒前
丘比特的应助被pota_o采纳,获得10
1秒前
李健的粉丝团团长的应助被Yego采纳,获得10
1秒前
温暖的含羞草完成签到,获得积分10
1秒前
kai150333429完成签到,获得积分10
1秒前
1秒前
日桉发布了新的文献求助10
1秒前
未来完成签到,获得积分20
1秒前
天道发布了新的文献求助10
1秒前
mof完成签到,获得积分10
2秒前
gly完成签到,获得积分10
2秒前
yu发布了新的文献求助10
2秒前
jianguo发布了新的文献求助10
3秒前
科研小飞舞完成签到,获得积分10
3秒前
3秒前
小虫完成签到,获得积分10
3秒前
3秒前
River完成签到,获得积分10
4秒前
5秒前
深情帆布鞋完成签到,获得积分10
5秒前
6秒前
MichaelQiang的应助被xhn采纳,获得10
6秒前
迪aaa完成签到 ,获得积分10
6秒前
ZIYE的应助被shoemaker采纳,获得10
6秒前
咎如天发布了新的文献求助10
6秒前
luogan完成签到,获得积分10
6秒前
唯恋完成签到,获得积分10
6秒前
Orange的应助被yzm采纳,获得10
7秒前
啊德哈卡完成签到,获得积分10
7秒前
王豆豆完成签到,获得积分10
7秒前
moon123完成签到,获得积分10
7秒前
7秒前
今后的应助被沐凉风i采纳,获得10
7秒前
何88888888完成签到,获得积分10
7秒前
Maestro_S的应助被听风采纳,获得10
7秒前
lps123456发布了新的文献求助10
8秒前
斯文败类的应助被豆子采纳,获得10
8秒前
8秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8173962
求助须知:如何正确求助?哪些是违规求助? 9566073
关于积分的说明 21784460
捐赠科研通 7768184
什么是DOI,文献DOI怎么找? 3431663
关于科研通互助平台的介绍 2555907
邀请新用户注册赠送积分活动 2476936