• 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

临床预测算法的验证视角。

Perspectives on validation of clinical predictive algorithms.

作者信息

de Hond Anne A H, Shah Vaibhavi B, Kant Ilse M J, Van Calster Ben, Steyerberg Ewout W, Hernandez-Boussard Tina

机构信息

Clinical AI Implementation and Research Lab, Leiden University Medical Centre, Leiden, the Netherlands.

Department of Medicine (Biomedical Informatics), Stanford University, Stanford, CA, USA.

出版信息

NPJ Digit Med. 2023 May 6;6(1):86. doi: 10.1038/s41746-023-00832-9.

DOI:10.1038/s41746-023-00832-9
PMID:37149704
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10163568/
Abstract

The generalizability of predictive algorithms is of key relevance to application in clinical practice. We provide an overview of three types of generalizability, based on existing literature: temporal, geographical, and domain generalizability. These generalizability types are linked to their associated goals, methodology, and stakeholders.

摘要

预测算法的可推广性对于临床实践中的应用至关重要。基于现有文献,我们概述了三种可推广性类型:时间可推广性、地理可推广性和领域可推广性。这些可推广性类型与其相关目标、方法和利益相关者相联系。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/afe9/10164133/7231fe789f53/41746_2023_832_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/afe9/10164133/7231fe789f53/41746_2023_832_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/afe9/10164133/7231fe789f53/41746_2023_832_Fig1_HTML.jpg

相似文献

1
Perspectives on validation of clinical predictive algorithms.临床预测算法的验证视角。
NPJ Digit Med. 2023 May 6;6(1):86. doi: 10.1038/s41746-023-00832-9.
2
Validation of differential gene expression algorithms: application comparing fold-change estimation to hypothesis testing.差异基因表达算法的验证:应用比较折叠变化估计与假设检验。
BMC Bioinformatics. 2010 Jan 28;11:63. doi: 10.1186/1471-2105-11-63.
3
Predictive model algorithms identifying early and advanced stage ER+/HER2- breast cancer in claims data.预测模型算法在理赔数据中识别早期和晚期 ER+/HER2- 乳腺癌。
Pharmacoepidemiol Drug Saf. 2019 Feb;28(2):171-178. doi: 10.1002/pds.4681. Epub 2018 Nov 9.
4
The Development and Validation of Simplified Machine Learning Algorithms to Predict Prognosis of Hospitalized Patients With COVID-19: Multicenter, Retrospective Study.中文译文:简化机器学习算法预测 COVID-19 住院患者预后的开发和验证:多中心回顾性研究。
J Med Internet Res. 2022 Jan 21;24(1):e31549. doi: 10.2196/31549.
5
A strategy for validation of variables derived from large-scale electronic health record data.基于大规模电子健康记录数据衍生变量的验证策略。
J Biomed Inform. 2021 Sep;121:103879. doi: 10.1016/j.jbi.2021.103879. Epub 2021 Jul 27.
6
The validation of interviews for estimating morbidity.用于估计发病率的访谈的验证
Health Policy Plan. 1992 Mar;7(1):30-9. doi: 10.1093/heapol/7.1.30.
7
Systematic comparison of machine learning algorithms to develop and validate predictive models for periodontitis.系统比较机器学习算法,以开发和验证牙周炎预测模型。
J Clin Periodontol. 2022 Oct;49(10):958-969. doi: 10.1111/jcpe.13692. Epub 2022 Jul 28.
8
Validation of claims-based algorithms for pulmonary arterial hypertension.基于索赔数据的肺动脉高压算法的验证
Pulm Circ. 2018 Apr-Jun;8(2):2045894018759246. doi: 10.1177/2045894018759246.
9
Development and validation of algorithms to identify acute diverticulitis.用于识别急性憩室炎的算法的开发与验证
Pharmacoepidemiol Drug Saf. 2015 Jan;24(1):27-37. doi: 10.1002/pds.3708. Epub 2014 Sep 25.
10
Methods for systematic reviews of administrative database studies capturing health outcomes of interest.系统评价行政数据库研究中捕获感兴趣的健康结果的方法。
Vaccine. 2013 Dec 30;31 Suppl 10:K2-6. doi: 10.1016/j.vaccine.2013.06.048.

引用本文的文献

1
Operationalization of Artificial Intelligence Applications in the Intensive Care Unit: A Systematic Review.重症监护病房中人工智能应用的实施:一项系统综述。
JAMA Netw Open. 2025 Jul 1;8(7):e2522866. doi: 10.1001/jamanetworkopen.2025.22866.
2
So You've Got a High AUC, Now What? An Overview of Important Considerations when Bringing Machine-Learning Models from Computer to Bedside.你已经获得了较高的曲线下面积(AUC),接下来怎么办?将机器学习模型从计算机应用到临床床边时的重要考量概述。
Med Decis Making. 2025 Aug;45(6):640-653. doi: 10.1177/0272989X251343082. Epub 2025 May 29.
3
External validation of a proprietary risk model for 1-year mortality in community-dwelling adults aged 65 years or older.

本文引用的文献

1
There is no such thing as a validated prediction model.没有经过验证的预测模型这种东西。
BMC Med. 2023 Feb 24;21(1):70. doi: 10.1186/s12916-023-02779-w.
2
Targeted validation: validating clinical prediction models in their intended population and setting.靶向验证:在目标人群和环境中验证临床预测模型。
Diagn Progn Res. 2022 Dec 22;6(1):24. doi: 10.1186/s41512-022-00136-8.
3
Predicting Readmission or Death After Discharge From the ICU: External Validation and Retraining of a Machine Learning Model.预测 ICU 出院后再入院或死亡:机器学习模型的外部验证和重新训练。
针对65岁及以上社区居住成年人1年死亡率的专有风险模型的外部验证。
J Am Med Inform Assoc. 2025 Jul 1;32(7):1110-1119. doi: 10.1093/jamia/ocaf062.
4
Clinician Suicide Risk Assessment for Prediction of Suicide Attempt in a Large Health Care System.大型医疗系统中临床医生自杀风险评估对自杀未遂的预测
JAMA Psychiatry. 2025 Apr 9. doi: 10.1001/jamapsychiatry.2025.0325.
5
Enhancing Patient Outcome Prediction Through Deep Learning With Sequential Diagnosis Codes From Structured Electronic Health Record Data: Systematic Review.通过深度学习利用结构化电子健康记录数据中的顺序诊断代码增强患者预后预测:系统评价
J Med Internet Res. 2025 Mar 18;27:e57358. doi: 10.2196/57358.
6
Clinical trials informed framework for real world clinical implementation and deployment of artificial intelligence applications.用于人工智能应用在现实世界临床实施和部署的临床试验信息框架。
NPJ Digit Med. 2025 Feb 17;8(1):107. doi: 10.1038/s41746-025-01506-4.
7
Risk prediction tools for pressure injury occurrence: an umbrella review of systematic reviews reporting model development and validation methods.压力性损伤发生风险预测工具:对报告模型开发与验证方法的系统评价的伞状综述
Diagn Progn Res. 2025 Jan 14;9(1):2. doi: 10.1186/s41512-024-00182-4.
8
Myelofibrosis predicts deep molecular response 4.5 in chronic myeloid leukaemia patients initially treated with imatinib: An extensive, multicenter and retrospective study to develop a prognostic model.骨髓纤维化可预测初始接受伊马替尼治疗的慢性髓性白血病患者的深度分子反应4.5:一项旨在建立预后模型的广泛、多中心回顾性研究。
Clin Transl Med. 2024 Nov;14(11):e70101. doi: 10.1002/ctm2.70101.
9
HKA-Net: clinically-adapted deep learning for automated measurement of hip-knee-ankle angle on lower limb radiography for knee osteoarthritis assessment.HKA-Net:适用于临床的深度学习,用于自动测量下肢 X 线摄影中膝骨关节炎评估的髋膝踝角度。
J Orthop Surg Res. 2024 Nov 20;19(1):777. doi: 10.1186/s13018-024-05265-y.
10
Algorithmovigilance, lessons from pharmacovigilance.算法警戒,来自药物警戒的经验教训。
NPJ Digit Med. 2024 Oct 2;7(1):270. doi: 10.1038/s41746-024-01237-y.
Crit Care Med. 2023 Feb 1;51(2):291-300. doi: 10.1097/CCM.0000000000005758. Epub 2022 Dec 16.
4
A Unified Framework on Generalizability of Clinical Prediction Models.临床预测模型可推广性的统一框架
Front Artif Intell. 2022 Apr 29;5:872720. doi: 10.3389/frai.2022.872720. eCollection 2022.
5
Generalizability of Cardiovascular Disease Clinical Prediction Models: 158 Independent External Validations of 104 Unique Models.心血管疾病临床预测模型的可推广性:104 个独特模型的 158 个独立外部验证。
Circ Cardiovasc Qual Outcomes. 2022 Apr;15(4):e008487. doi: 10.1161/CIRCOUTCOMES.121.008487. Epub 2022 Mar 31.
6
Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review.医疗保健中基于人工智能的预测模型的指南和质量标准:一项范围综述
NPJ Digit Med. 2022 Jan 10;5(1):2. doi: 10.1038/s41746-021-00549-7.
7
How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals.医学人工智能设备的评估方式:基于对美国食品药品监督管理局批准情况分析的局限性与建议
Nat Med. 2021 Apr;27(4):582-584. doi: 10.1038/s41591-021-01312-x.
8
Best practices for authors of healthcare-related artificial intelligence manuscripts.医疗保健相关人工智能手稿作者的最佳实践。
NPJ Digit Med. 2020 Oct 16;3:134. doi: 10.1038/s41746-020-00336-w. eCollection 2020.
9
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.
10
Machine Learning Comes of Age: Local Impact versus National Generalizability.机器学习走向成熟:局部影响与全国通用性
Anesthesiology. 2020 May;132(5):939-941. doi: 10.1097/ALN.0000000000003223.