• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

临床研究和医疗保健中机器学习的泛化性神话。

The myth of generalisability in clinical research and machine learning in health care.

机构信息

School of Engineering & Applied Sciences, Harvard University, Cambridge, MA, USA.

Department of Medicine, NYU Langone Health, New York, NY, USA.

出版信息

Lancet Digit Health. 2020 Sep;2(9):e489-e492. doi: 10.1016/S2589-7500(20)30186-2. Epub 2020 Aug 24.

DOI:10.1016/S2589-7500(20)30186-2
PMID:32864600
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7444947/
Abstract

An emphasis on overly broad notions of generalisability as it pertains to applications of machine learning in health care can overlook situations in which machine learning might provide clinical utility. We believe that this narrow focus on generalisability should be replaced with wider considerations for the ultimate goal of building machine learning systems that are useful at the bedside.

摘要

过分强调机器学习在医疗保健应用中的泛化概念可能会忽略机器学习可能提供临床效用的情况。我们认为，这种对泛化的狭隘关注应该被更广泛地考虑最终目标所取代，即构建在床边有用的机器学习系统。

相似文献

1
The myth of generalisability in clinical research and machine learning in health care.临床研究和医疗保健中机器学习的泛化性神话。
Lancet Digit Health. 2020 Sep;2(9):e489-e492. doi: 10.1016/S2589-7500(20)30186-2. Epub 2020 Aug 24.
2
Machine learning in a time of COVID-19 - Can machine learning support Community Health Workers (CHWs) in low and middle income countries (LMICs) in the new normal?新冠疫情时代的机器学习——在新常态下，机器学习能否支持中低收入国家的社区卫生工作者？
J Glob Health. 2021 Jan 16;11:03017. doi: 10.7189/jogh.11.03017.
3
COVID-19 and the Futures of Machine Learning.新型冠状病毒肺炎与机器学习的未来
OMICS. 2020 Sep;24(9):512-514. doi: 10.1089/omi.2020.0093. Epub 2020 Jun 8.
4
Thoracic Point-of-Care Ultrasound: A SARS-CoV-2 Data Repository for Future Artificial Intelligence and Machine Learning.胸腔床旁超声：SARS-CoV-2 的未来人工智能和机器学习数据仓库。
Surg Innov. 2021 Apr;28(2):214-219. doi: 10.1177/15533506211018671. Epub 2021 May 7.
5
Accurately Differentiating Between Patients With COVID-19, Patients With Other Viral Infections, and Healthy Individuals: Multimodal Late Fusion Learning Approach.准确区分 COVID-19 患者、其他病毒感染患者和健康个体：多模态晚期融合学习方法。
J Med Internet Res. 2021 Jan 6;23(1):e25535. doi: 10.2196/25535.
6
Role of biological Data Mining and Machine Learning Techniques in Detecting and Diagnosing the Novel Coronavirus (COVID-19): A Systematic Review.生物数据挖掘和机器学习技术在检测和诊断新型冠状病毒 (COVID-19) 中的作用：系统评价。
J Med Syst. 2020 May 25;44(7):122. doi: 10.1007/s10916-020-01582-x.
7
Prediction of death status on the course of treatment in SARS-COV-2 patients with deep learning and machine learning methods.利用深度学习和机器学习方法预测 SARS-CoV-2 患者治疗过程中的死亡状态。
Comput Methods Programs Biomed. 2021 Apr;201:105951. doi: 10.1016/j.cmpb.2021.105951. Epub 2021 Jan 22.
8
Using Explainable Machine Learning to Improve Intensive Care Unit Alarm Systems.使用可解释机器学习来改进重症监护病房警报系统。
Sensors (Basel). 2021 Oct 27;21(21):7125. doi: 10.3390/s21217125.
9
Usefulness of machine learning in COVID-19 for the detection and prognosis of cardiovascular complications.机器学习在 COVID-19 中的应用，用于检测和预测心血管并发症。
Rev Cardiovasc Med. 2020 Sep 30;21(3):345-352. doi: 10.31083/j.rcm.2020.03.120.
10
Trends and Focus of Machine Learning Applications for Health Research.机器学习在健康研究中的应用趋势与重点。
JAMA Netw Open. 2019 Oct 2;2(10):e1914051. doi: 10.1001/jamanetworkopen.2019.14051.

引用本文的文献

1
An easily machine learning-based tool for preliminary risk assessment of microvascular invasion in hepatocellular carcinoma.一种基于机器学习的简易工具，用于肝细胞癌微血管侵犯的初步风险评估。
Surg Endosc. 2025 Aug 27. doi: 10.1007/s00464-025-12094-5.
2
Assessing the performance of the Iceland screens, treats, or prevents multiple myeloma (iStopMM) model in a multicultural Bronx cohort: implications for monoclonal gammopathy of undetermined significance risk stratification.评估冰岛骨髓瘤筛查、治疗或预防模型（iStopMM）在多元文化的布朗克斯队列中的表现：对意义未明的单克隆丙种球蛋白病风险分层的意义
Blood Cancer J. 2025 Aug 21;15(1):140. doi: 10.1038/s41408-025-01337-2.
3
Efficacy of artificial intelligence-based FFR technology for coronary CTA stenosis detection in clinical management of coronary artery disease: a systematic review.基于人工智能的血流储备分数技术在冠心病临床管理中检测冠状动脉CTA狭窄的疗效：一项系统评价
Front Physiol. 2025 Jul 31;16:1635923. doi: 10.3389/fphys.2025.1635923. eCollection 2025.
4
Bridging the Regulatory Divide: A Dual-Pathway Framework Using SRA Approvals and AI Evaluation to Ensure Drug Quality in Developing Countries.弥合监管差距：一种利用SRA批准和人工智能评估的双路径框架，以确保发展中国家的药品质量。
Pharmaceuticals (Basel). 2025 Jul 10;18(7):1024. doi: 10.3390/ph18071024.
5
Multicenter Validation of a Machine Learning Model for Surgical Transfusion Risk at 45 US Hospitals.美国45家医院手术输血风险机器学习模型的多中心验证
JAMA Netw Open. 2025 Jun 2;8(6):e2517760. doi: 10.1001/jamanetworkopen.2025.17760.
6
Detecting and Remediating Harmful Data Shifts for the Responsible Deployment of Clinical AI Models.检测并纠正有害数据偏移，以实现临床人工智能模型的负责任部署。
JAMA Netw Open. 2025 Jun 2;8(6):e2513685. doi: 10.1001/jamanetworkopen.2025.13685.
7
MRI-based artificial intelligence models for post-neoadjuvant surgery personalization in breast cancer: a narrative review of evidence from Western Pacific.基于MRI的人工智能模型在乳腺癌新辅助治疗后手术个性化中的应用：西太平洋地区证据的叙述性综述
Lancet Reg Health West Pac. 2024 Dec 6;57:101254. doi: 10.1016/j.lanwpc.2024.101254. eCollection 2025 Apr.
8
Scientific Evidence for Clinical Text Summarization Using Large Language Models: Scoping Review.使用大语言模型进行临床文本摘要的科学证据：范围综述
J Med Internet Res. 2025 May 15;27:e68998. doi: 10.2196/68998.
9
A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis.领域转移的教科书式解决方案：医学图像分析的知识先验
Adv Neural Inf Process Syst. 2024;37:90683-90713.
10
Generalizability of FDA-Approved AI-Enabled Medical Devices for Clinical Use.美国食品药品监督管理局（FDA）批准的用于临床的人工智能医疗设备的可推广性。
JAMA Netw Open. 2025 Apr 1;8(4):e258052. doi: 10.1001/jamanetworkopen.2025.8052.

本文引用的文献

1
Clinical applications of continual learning machine learning.持续学习机器学习的临床应用。
Lancet Digit Health. 2020 Jun;2(6):e279-e281. doi: 10.1016/S2589-7500(20)30102-3.
2
"Yes, but will it work for patients?" Driving clinically relevant research with benchmark datasets.“是的，但它对患者有效吗？”利用基准数据集推动临床相关研究。
NPJ Digit Med. 2020 Jun 19;3:87. doi: 10.1038/s41746-020-0295-6. eCollection 2020.
3
Early warning scores for detecting deterioration in adult hospital patients: systematic review and critical appraisal of methodology.成人住院患者病情恶化预警评分的研究：系统评价与方法学的严格评价。
BMJ. 2020 May 20;369:m1501. doi: 10.1136/bmj.m1501.
4
Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal.COVID-19 诊断和预后预测模型：系统评价和批判性评估。
BMJ. 2020 Apr 7;369:m1328. doi: 10.1136/bmj.m1328.
5
Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies.人工智能与临床医生：深度学习研究的设计、报告标准和主张的系统评价。
BMJ. 2020 Mar 25;368:m689. doi: 10.1136/bmj.m689.
6
The Toughest Triage - Allocating Ventilators in a Pandemic.最艰难的分诊——在大流行中分配呼吸机
N Engl J Med. 2020 May 21;382(21):1973-1975. doi: 10.1056/NEJMp2005689. Epub 2020 Mar 23.
7
Development and Reporting of Prediction Models: Guidance for Authors From Editors of Respiratory, Sleep, and Critical Care Journals.预测模型的制定和报告：呼吸、睡眠和危重病期刊编辑给作者的指南。
Crit Care Med. 2020 May;48(5):623-633. doi: 10.1097/CCM.0000000000004246.
8
Assessing Radiology Research on Artificial Intelligence: A Brief Guide for Authors, Reviewers, and Readers-From the Editorial Board.评估人工智能放射学研究：给作者、审稿人和读者的简要指南——来自编辑委员会
Radiology. 2020 Mar;294(3):487-489. doi: 10.1148/radiol.2019192515. Epub 2019 Dec 31.
9
Performance of a Deep-Learning Algorithm vs Manual Grading for Detecting Diabetic Retinopathy in India.深度学习算法与人工分级在印度检测糖尿病视网膜病变中的性能比较
JAMA Ophthalmol. 2019 Sep 1;137(9):987-993. doi: 10.1001/jamaophthalmol.2019.2004.
10
Untapped potential of multicenter studies: a review of cardiovascular risk prediction models revealed inappropriate analyses and wide variation in reporting.多中心研究的未开发潜力：对心血管风险预测模型的综述揭示了分析不当和报告差异巨大的问题。
Diagn Progn Res. 2019 Feb 22;3:6. doi: 10.1186/s41512-019-0046-9. eCollection 2019.