Demonstrating Clinical Impact for AI Interventions: Importance of Robust Evaluation and Standardized Reporting

Gagandeep Sachdeva; Diana Han; Pearse A. Keane; Alastair K. Denniston; Xiaoxuan Liu

doi:10.1002/9781119790686.ch42

Demonstrating Clinical Impact for AI Interventions: Importance of Robust Evaluation and Standardized Reporting

Gagandeep Sachdeva
, Diana Han
, Pearse A. Keane
, Alastair K. Denniston
, Xiaoxuan Liu

Applied Health Sciences

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

Over recent years, tremendous progress has been made in the development of AI applications for healthcare. To demonstrate potential benefit to patients and the healthcare system, robust clinical evaluation should be carried out to generate the necessary evidence that AI systems are safe, accurate, and effective. Clinical studies should be designed with that intended impact in mind, and reported according to the relevant reporting standards. Several AI-specific reporting standards, including SPIRIT-AI, CONSORT-AI, STARD-AI, TRIPOD-AI, and DECIDE-AI, have been specifically developed, or are in the process of being developed, for clinical AI studies.

Original language	English
Title of host publication	AI in Clinical Medicine
Subtitle of host publication	A Practical Guide for Healthcare Professionals
Editors	Michael F. Byrne, Nasim Parsa, Alexandra T. Greenhill, Daljeet Chahal, Omer Ahmad, Ulas Bagci
Publisher	Wiley
Chapter	42
Pages	459-468
Number of pages	10
ISBN (Electronic)	9781119790686
ISBN (Print)	9781119790648
DOIs	https://doi.org/10.1002/9781119790686.ch42
Publication status	Published - 12 May 2023

Bibliographical note

Publisher Copyright:
© 2023 John Wiley & Sons Ltd.

Keywords

Clinical impact of AI
CONSORT‐AI
DECIDE‐AI
Randomized control trial
Reporting guideline
SPIRIT‐AI
STARD‐AI
TRIPOD‐AI

ASJC Scopus subject areas

General Medicine

Access to Document

10.1002/9781119790686.ch42Licence: None: All rights reserved

Cite this

Sachdeva, G., Han, D., Keane, P. A., Denniston, A. K., & Liu, X. (2023). Demonstrating Clinical Impact for AI Interventions: Importance of Robust Evaluation and Standardized Reporting. In M. F. Byrne, N. Parsa, A. T. Greenhill, D. Chahal, O. Ahmad, & U. Bagci (Eds.), AI in Clinical Medicine: A Practical Guide for Healthcare Professionals (pp. 459-468). Wiley. https://doi.org/10.1002/9781119790686.ch42

Sachdeva, Gagandeep ; Han, Diana ; Keane, Pearse A. et al. / Demonstrating Clinical Impact for AI Interventions : Importance of Robust Evaluation and Standardized Reporting. AI in Clinical Medicine: A Practical Guide for Healthcare Professionals. editor / Michael F. Byrne ; Nasim Parsa ; Alexandra T. Greenhill ; Daljeet Chahal ; Omer Ahmad ; Ulas Bagci. Wiley, 2023. pp. 459-468

@inbook{94712f8b404e4571a778d224ebda2dba,

title = "Demonstrating Clinical Impact for AI Interventions: Importance of Robust Evaluation and Standardized Reporting",

abstract = "Over recent years, tremendous progress has been made in the development of AI applications for healthcare. To demonstrate potential benefit to patients and the healthcare system, robust clinical evaluation should be carried out to generate the necessary evidence that AI systems are safe, accurate, and effective. Clinical studies should be designed with that intended impact in mind, and reported according to the relevant reporting standards. Several AI-specific reporting standards, including SPIRIT-AI, CONSORT-AI, STARD-AI, TRIPOD-AI, and DECIDE-AI, have been specifically developed, or are in the process of being developed, for clinical AI studies.",

keywords = "Clinical impact of AI, CONSORT‐AI, DECIDE‐AI, Randomized control trial, Reporting guideline, SPIRIT‐AI, STARD‐AI, TRIPOD‐AI",

author = "Gagandeep Sachdeva and Diana Han and Keane, \{Pearse A.\} and Denniston, \{Alastair K.\} and Xiaoxuan Liu",

note = "Publisher Copyright: {\textcopyright} 2023 John Wiley \& Sons Ltd.",

year = "2023",

month = may,

day = "12",

doi = "10.1002/9781119790686.ch42",

language = "English",

isbn = "9781119790648",

pages = "459--468",

editor = "Byrne, \{Michael F.\} and Nasim Parsa and Greenhill, \{Alexandra T.\} and Daljeet Chahal and Omer Ahmad and Ulas Bagci",

booktitle = "AI in Clinical Medicine",

publisher = "Wiley",

}

Sachdeva, G, Han, D, Keane, PA, Denniston, AK & Liu, X 2023, Demonstrating Clinical Impact for AI Interventions: Importance of Robust Evaluation and Standardized Reporting. in MF Byrne, N Parsa, AT Greenhill, D Chahal, O Ahmad & U Bagci (eds), AI in Clinical Medicine: A Practical Guide for Healthcare Professionals. Wiley, pp. 459-468. https://doi.org/10.1002/9781119790686.ch42

Demonstrating Clinical Impact for AI Interventions: Importance of Robust Evaluation and Standardized Reporting. / Sachdeva, Gagandeep; Han, Diana; Keane, Pearse A. et al.
AI in Clinical Medicine: A Practical Guide for Healthcare Professionals. ed. / Michael F. Byrne; Nasim Parsa; Alexandra T. Greenhill; Daljeet Chahal; Omer Ahmad; Ulas Bagci. Wiley, 2023. p. 459-468.

Research output: Chapter in Book/Report/Conference proceeding › Chapter

TY - CHAP

T1 - Demonstrating Clinical Impact for AI Interventions

T2 - Importance of Robust Evaluation and Standardized Reporting

AU - Sachdeva, Gagandeep

AU - Han, Diana

AU - Keane, Pearse A.

AU - Denniston, Alastair K.

AU - Liu, Xiaoxuan

PY - 2023/5/12

Y1 - 2023/5/12

N2 - Over recent years, tremendous progress has been made in the development of AI applications for healthcare. To demonstrate potential benefit to patients and the healthcare system, robust clinical evaluation should be carried out to generate the necessary evidence that AI systems are safe, accurate, and effective. Clinical studies should be designed with that intended impact in mind, and reported according to the relevant reporting standards. Several AI-specific reporting standards, including SPIRIT-AI, CONSORT-AI, STARD-AI, TRIPOD-AI, and DECIDE-AI, have been specifically developed, or are in the process of being developed, for clinical AI studies.

AB - Over recent years, tremendous progress has been made in the development of AI applications for healthcare. To demonstrate potential benefit to patients and the healthcare system, robust clinical evaluation should be carried out to generate the necessary evidence that AI systems are safe, accurate, and effective. Clinical studies should be designed with that intended impact in mind, and reported according to the relevant reporting standards. Several AI-specific reporting standards, including SPIRIT-AI, CONSORT-AI, STARD-AI, TRIPOD-AI, and DECIDE-AI, have been specifically developed, or are in the process of being developed, for clinical AI studies.

KW - Clinical impact of AI

KW - CONSORT‐AI

KW - DECIDE‐AI

KW - Randomized control trial

KW - Reporting guideline

KW - SPIRIT‐AI

KW - STARD‐AI

KW - TRIPOD‐AI

UR - https://www.scopus.com/pages/publications/85165386673

U2 - 10.1002/9781119790686.ch42

DO - 10.1002/9781119790686.ch42

M3 - Chapter

AN - SCOPUS:85165386673

SN - 9781119790648

SP - 459

EP - 468

BT - AI in Clinical Medicine

A2 - Byrne, Michael F.

A2 - Parsa, Nasim

A2 - Greenhill, Alexandra T.

A2 - Chahal, Daljeet

A2 - Ahmad, Omer

A2 - Bagci, Ulas

PB - Wiley

ER -

Sachdeva G, Han D, Keane PA, Denniston AK , Liu X. Demonstrating Clinical Impact for AI Interventions: Importance of Robust Evaluation and Standardized Reporting. In Byrne MF, Parsa N, Greenhill AT, Chahal D, Ahmad O, Bagci U, editors, AI in Clinical Medicine: A Practical Guide for Healthcare Professionals. Wiley. 2023. p. 459-468 Epub 2023 Mar 3. doi: 10.1002/9781119790686.ch42

Demonstrating Clinical Impact for AI Interventions: Importance of Robust Evaluation and Standardized Reporting

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this