Perspectives on validation of clinical predictive algorithms

被引：31

作者：

de Hond, Anne A. H. ^{[1
,2
,3
]}

Shah, Vaibhavi B. B. ^{[2
]}

Kant, Ilse M. J. ^{[4
]}

Van Calster, Ben ^{[3
,5
]}

Steyerberg, Ewout W. ^{[1
,3
]}

Hernandez-Boussard, Tina ^{[2
,6
,7
]}

机构：

[1] Leiden Univ, Med Ctr, Clin AI Implementat & Res Lab, Leiden, Netherlands

[2] Stanford Univ, Dept Med Biomed Informat, Stanford, CA 94305 USA

[3] Leiden Univ, Med Ctr, Dept Biomed Data Sci, Leiden, Netherlands

[4] Univ Med Ctr Utrecht, Dept Digital Hlth, Utrecht, Netherlands

[5] Katholieke Univ Leuven, Dept Dev & Regenerat, Leuven, Belgium

[6] Stanford Univ, Dept Biomed Data Sci, Stanford, CA USA

[7] Stanford Univ, Dept Epidemiol & Populat Hlth by courtesy, Stanford, CA USA

来源：

NPJ DIGITAL MEDICINE | 2023年 / 6卷 / 01期

基金：

比利时弗兰德研究基金会; 美国国家卫生研究院;

关键词：

MODEL;

D O I：

10.1038/s41746-023-00832-9

中图分类号：

R19 [保健组织与事业（卫生事业管理）];

学科分类号：

摘要：

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.

引用

页数：3

共 22 条

[1] Geographic and temporal validity of prediction models: different approaches were useful to examine model performance [J].

Austin, Peter C. ;

van Klaveren, David ;

Vergouwe, Yvonne ;

Nieboer, Daan ;

Lee, Douglas S. ;

Steyerberg, Ewout W. .

JOURNAL OF CLINICAL EPIDEMIOLOGY, 2016, 79 :76-85

[2] Machine Learning Comes of Age Local Impact versus National Generalizability [J].

Burns, Michael L. ;

Kheterpal, Sachin .

ANESTHESIOLOGY, 2020, 132 (05) :939-941

[3]

Collins GS, 2015, J CLIN EPIDEMIOL, V68, P112, DOI [10.1016/j.jclinepi.2014.11.010, 10.1111/eci.12376, 10.7326/M14-0697, 10.7326/M14-0698, 10.1016/j.eururo.2014.11.025, 10.1002/bjs.9736, 10.1136/bmj.g7594, 10.1186/s12916-014-0241-z, 10.1038/bjc.2014.639]

[4] Methodological standards for the development and evaluation of clinical prediction rules: a review of the literature [J].

Laura E. Cowley ;

Daniel M. Farewell ;

Sabine Maguire ;

Alison M. Kemp .

Diagnostic and Prognostic Research, 3 (1)

[5] Predicting Readmission or Death After Discharge From the ICU: External Validation and Retraining of a Machine Learning Model [J].

de Hond, Anne A. H. ;

Kant, Ilse M. J. ;

Fornasa, Mattia ;

Cina, Giovanni ;

Elbers, Paul W. G. ;

Thoral, Patrick J. J. ;

Arbous, M. Sesmu ;

Steyerberg, Ewout W. W. .

CRITICAL CARE MEDICINE, 2023, 51 (02) :291-300

[6] Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review [J].

de Hond, Anne A. H. ;

Leeuwenberg, Artuur M. ;

Hooft, Lotty ;

Kant, Ilse M. J. ;

Nijman, Steven W. J. ;

van Os, Hendrikus J. A. ;

Aardoom, Jiska J. ;

Debray, Thomas P. A. ;

Schuit, Ewoud ;

van Smeden, Maarten ;

Reitsma, Johannes B. ;

Steyerberg, Ewout W. ;

Chavannes, Niels H. ;

Moons, Karel G. M. .

NPJ DIGITAL MEDICINE, 2022, 5 (01)

[7] A new framework to enhance the interpretation of external validation studies of clinical prediction models [J].

Debray, Thomas P. A. ;

Vergouwe, Yvonne ;

Koffijberg, Hendrik ;

Nieboer, Daan ;

Steyerberg, Ewout W. ;

Moons, Karel G. M. .

JOURNAL OF CLINICAL EPIDEMIOLOGY, 2015, 68 (03) :280-289

[8]

Efron B., 1994, An introduction to the bootstrap

[9]

Futoma J, 2020, LANCET DIGIT HEALTH, V2, pE489, DOI 10.1016/S2589-7500(20)30186-2

[10] Generalizability of Cardiovascular Disease Clinical Prediction Models: 158 Independent External Validations of 104 Unique Models [J].

Gulati, Gaurav ;

Upshaw, Jenica ;

Wessler, Benjamin S. ;

Brazil, Riley J. ;

Nelson, Jason ;

van Klaveren, David ;

Lundquist, Christine M. ;

Park, Jinny G. ;

McGinnes, Hannah ;

Steyerberg, Ewout W. ;

Van Calster, Ben ;

Kent, David M. .

CIRCULATION-CARDIOVASCULAR QUALITY AND OUTCOMES, 2022, 15 (04) :248-260

← 1 2 3 →