Five critical quality criteria for artificial intelligence-based prediction models

Florien S. Van Royen; Folkert W. Asselbergs; Fernando Alfonso; Panos Vardas; Maarten Van Smeden

doi:10.1093/eurheartj/ehad727

Five critical quality criteria for artificial intelligence-based prediction models

Florien S. Van Royen
, Folkert W. Asselbergs
, Fernando Alfonso
, Panos Vardas
, Maarten Van Smeden^*

^*Corresponding author for this work

Research output: Contribution to journal › Review article › peer-review

4 Downloads (Pure)

Abstract

To raise the quality of clinical artificial intelligence (AI) prediction modelling studies in the cardiovascular health domain and thereby improve their impact and relevancy, the editors for digital health, innovation, and quality standards of the European Heart Journal propose five minimal quality criteria for AI-based prediction model development and validation studies: complete reporting, carefully defined intended use of the model, rigorous validation, large enough sample size, and openness of code and software.

Original language	English
Pages (from-to)	4831-4834
Number of pages	4
Journal	European heart journal
Volume	44
Issue number	46
DOIs	https://doi.org/10.1093/eurheartj/ehad727
Publication status	Published - 7 Dec 2023

Keywords

Artificial intelligence
Diagnosis
Digital health
Prediction
Prognosis

Access to Document

10.1093/eurheartj/ehad727Licence: CC BY-NC

ehad727Final published version, 625 KBLicence: CC BY-NC

Cite this

@article{4e83c75c782c46a794cb9c983022a02e,

title = "Five critical quality criteria for artificial intelligence-based prediction models",

abstract = "To raise the quality of clinical artificial intelligence (AI) prediction modelling studies in the cardiovascular health domain and thereby improve their impact and relevancy, the editors for digital health, innovation, and quality standards of the European Heart Journal propose five minimal quality criteria for AI-based prediction model development and validation studies: complete reporting, carefully defined intended use of the model, rigorous validation, large enough sample size, and openness of code and software.",

keywords = "Artificial intelligence, Diagnosis, Digital health, Prediction, Prognosis",

author = "\{Van Royen\}, \{Florien S.\} and Asselbergs, \{Folkert W.\} and Fernando Alfonso and Panos Vardas and \{Van Smeden\}, Maarten",

note = "Publisher Copyright: {\textcopyright} 2023 The Author(s).",

year = "2023",

month = dec,

day = "7",

doi = "10.1093/eurheartj/ehad727",

language = "English",

volume = "44",

pages = "4831--4834",

journal = "European heart journal",

issn = "0195-668X",

publisher = "Oxford University Press",

number = "46",

}

TY - JOUR

T1 - Five critical quality criteria for artificial intelligence-based prediction models

AU - Van Royen, Florien S.

AU - Asselbergs, Folkert W.

AU - Alfonso, Fernando

AU - Vardas, Panos

AU - Van Smeden, Maarten

PY - 2023/12/7

Y1 - 2023/12/7

N2 - To raise the quality of clinical artificial intelligence (AI) prediction modelling studies in the cardiovascular health domain and thereby improve their impact and relevancy, the editors for digital health, innovation, and quality standards of the European Heart Journal propose five minimal quality criteria for AI-based prediction model development and validation studies: complete reporting, carefully defined intended use of the model, rigorous validation, large enough sample size, and openness of code and software.

AB - To raise the quality of clinical artificial intelligence (AI) prediction modelling studies in the cardiovascular health domain and thereby improve their impact and relevancy, the editors for digital health, innovation, and quality standards of the European Heart Journal propose five minimal quality criteria for AI-based prediction model development and validation studies: complete reporting, carefully defined intended use of the model, rigorous validation, large enough sample size, and openness of code and software.

KW - Artificial intelligence

KW - Diagnosis

KW - Digital health

KW - Prediction

KW - Prognosis

UR - https://www.scopus.com/pages/publications/85179139352

U2 - 10.1093/eurheartj/ehad727

DO - 10.1093/eurheartj/ehad727

M3 - Review article

C2 - 37897346

AN - SCOPUS:85179139352

SN - 0195-668X

VL - 44

SP - 4831

EP - 4834

JO - European heart journal

JF - European heart journal

IS - 46

ER -

Five critical quality criteria for artificial intelligence-based prediction models

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this