Future-ai: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare

Karim Lekadir; Aasa Feragen; Abdul Joseph Fofanah; Alejandro F Frangi; Alena Buyx; Anais Emelie; Andrea Lara; Antonio R Porras; An-Wen Chan; Arcadi Navarro; Ben Glocker; Benard O Botwe; Bishesh Khanal; Brigit Beger; Carol C Wu; Celia Cintas; Curtis P Langlotz; Daniel Rueckert; Deogratias Mzurikwao; Dimitrios I Fotiadis; Doszhan Zhussupov; Enzo Ferrante; Erik Meijering; Eva Weicken; Fabio A González; Folkert W Asselbergs; Fred Prior; Gabriel P Krestin; Gary Collins; Geletaw S Tegenaw; Georgios Kaissis; Gianluca Misuraca; Gianna Tsakou; Girish Dwivedi; Haridimos Kondylakis; Harsha Jayakody; Henry C Woodruf; Hugo JWL Aerts; Ian Walsh; Ioanna Chouvarda; Irène Buvat; Islem Rekik; James Duncan; Jayashree Kalpathy-Cramer; Jihad Zahir; Jinah Park; John Mongan; Judy W Gichoya; Julia A Schnabel; Kaisar Kushibar; Katrine Riklund; Kensaku Mori; Kostas Marias; Lameck M Amugongo; Lauren A Fromont; Lena Maier-Hein; Leonor Cerdá Alberich; Leticia Rittner; Lighton Phiri; Linda Marrakchi-Kacem; Lluís Donoso-Bach; Luis Martí-Bonmatí; M Jorge Cardoso; Maciej Bobowicz; Mahsa Shabani; Manolis Tsiknakis; Maria A Zuluaga; Maria Bielikova; Marie-Christine Fritzsche; Marius George Linguraru; Markus Wenzel; Marleen De Bruijne; Martin G Tolsgaard; Marzyeh Ghassemi; Md Ashrafuzzaman; Melanie Goisauf; Mohammad Yaqub; Mohammed Ammar; Mónica Cano Abadía; Mukhtar M E Mahmoud; Mustafa Elattar; Nicola Rieke; Nikolaos Papanikolaou; Noussair Lazrak; Oliver Díaz; Olivier Salvado; Oriol Pujol; Ousmane Sall; Pamela Guevara; Peter Gordebeke; Philippe Lambin; Pieta Brown; Purang Abolmaesumi; Qi Dou; Qinghua Lu; Richard Osuala; Rose Nakasi; S Kevin Zhou; Sandy Napel; Sara Colantonio; Shadi Albarqouni; Smriti Joshi; Stacy Carter; Stefan Klein; Steffen E Petersen; Susanna Aussó; Suyash Awate; Tammy Riklin Raviv; Tessa Cook; Tinashe E M Mutsvangwa; Wendy A Rogers; Wiro J Niessen; Xènia Puig-Bosch; Yi Zeng; Yunusa G Mohammed; Yves Saint James Aquino; Zohaib Salahuddin; Martijn P A Starmans

Future-ai: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare

Karim Lekadir, Aasa Feragen, Abdul Joseph Fofanah, Alejandro F Frangi, Alena Buyx, Anais Emelie, Andrea Lara, Antonio R Porras, An-Wen Chan, Arcadi Navarro, Ben Glocker, Benard O Botwe, Bishesh Khanal, Brigit Beger, Carol C Wu, Celia Cintas, Curtis P Langlotz, Daniel Rueckert, Deogratias Mzurikwao, Dimitrios I FotiadisDoszhan Zhussupov, Enzo Ferrante, Erik Meijering, Eva Weicken, Fabio A González, Folkert W Asselbergs, Fred Prior, Gabriel P Krestin, Gary Collins, Geletaw S Tegenaw, Georgios Kaissis, Gianluca Misuraca, Gianna Tsakou, Girish Dwivedi, Haridimos Kondylakis, Harsha Jayakody, Henry C Woodruf, Hugo JWL Aerts, Ian Walsh, Ioanna Chouvarda, Irène Buvat, Islem Rekik, James Duncan, Jayashree Kalpathy-Cramer, Jihad Zahir, Jinah Park, John Mongan, Judy W Gichoya, Julia A Schnabel, Kaisar Kushibar, Katrine Riklund, Kensaku Mori, Kostas Marias, Lameck M Amugongo, Lauren A Fromont, Lena Maier-Hein, Leonor Cerdá Alberich, Leticia Rittner, Lighton Phiri, Linda Marrakchi-Kacem, Lluís Donoso-Bach, Luis Martí-Bonmatí, M Jorge Cardoso, Maciej Bobowicz, Mahsa Shabani, Manolis Tsiknakis, Maria A Zuluaga, Maria Bielikova, Marie-Christine Fritzsche, Marius George Linguraru, Markus Wenzel, Marleen De Bruijne, Martin G Tolsgaard, Marzyeh Ghassemi, Md Ashrafuzzaman, Melanie Goisauf, Mohammad Yaqub, Mohammed Ammar, Mónica Cano Abadía, Mukhtar M E Mahmoud, Mustafa Elattar, Nicola Rieke, Nikolaos Papanikolaou, Noussair Lazrak, Oliver Díaz, Olivier Salvado, Oriol Pujol, Ousmane Sall, Pamela Guevara, Peter Gordebeke, Philippe Lambin, Pieta Brown, Purang Abolmaesumi, Qi Dou, Qinghua Lu, Richard Osuala, Rose Nakasi, S Kevin Zhou, Sandy Napel, Sara Colantonio, Shadi Albarqouni, Smriti Joshi, Stacy Carter, Stefan Klein, Steffen E Petersen, Susanna Aussó, Suyash Awate, Tammy Riklin Raviv, Tessa Cook, Tinashe E M Mutsvangwa, Wendy A Rogers, Wiro J Niessen, Xènia Puig-Bosch, Yi Zeng, Yunusa G Mohammed, Yves Saint James Aquino, Zohaib Salahuddin, Martijn P A Starmans

Research output: Preprint/Working paper › Preprint

73 Downloads (Pure)

Abstract

Despite major advances in artificial intelligence (AI) for medicine and healthcare, the deployment and adoption of AI technologies remain limited in real-world clinical practice. In recent years, concerns have been raised about the technical, clinical, ethical and legal risks associated with medical AI. To increase real world adoption, it is essential that medical AI tools are trusted and accepted by patients, clinicians, health organisations and authorities. This work describes the FUTURE-AI guideline as the first international consensus framework for guiding the development and deployment of trustworthy AI tools in healthcare. The FUTURE-AI consortium was founded in 2021 and currently comprises 118 inter-disciplinary experts from 51 countries representing all continents, including AI scientists, clinicians, ethicists, and social scientists. Over a two-year period, the consortium defined guiding principles and best practices for trustworthy AI through an iterative process comprising an in-depth literature review, a modified Delphi survey, and online consensus meetings. The FUTURE-AI framework was established based on 6 guiding principles for trustworthy AI in healthcare, i.e. Fairness, Universality, Traceability, Usability, Robustness and Explainability. Through consensus, a set of 28 best practices were defined, addressing technical, clinical, legal and socio-ethical dimensions. The recommendations cover the entire lifecycle of medical AI, from design, development and validation to regulation, deployment, and monitoring. FUTURE-AI is a risk-informed, assumption-free guideline which provides a structured approach for constructing medical AI tools that will be trusted, deployed and adopted in real-world practice. Researchers are encouraged to take the recommendations into account in proof-of-concept stages to facilitate future translation towards clinical practice of medical AI.

Original language	English
Publication status	Published - 11 Aug 2023

Keywords

cs.CY
cs.AI
cs.CV
cs.LG
I.2.0; I.4.0; I.5.0

Access to Document

2309.12325v1

Cite this

Lekadir, K., Feragen, A., Fofanah, A. J., Frangi, A. F., Buyx, A., Emelie, A., Lara, A., Porras, A. R., Chan, A.-W., Navarro, A., Glocker, B., Botwe, B. O., Khanal, B., Beger, B., Wu, C. C., Cintas, C., Langlotz, C. P., Rueckert, D., Mzurikwao, D., ... Starmans, M. P. A. (2023). Future-ai: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare.

@techreport{3e62c962aa8846b2b0a9b893de13774c,

title = "Future-ai: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare",

abstract = " Despite major advances in artificial intelligence (AI) for medicine and healthcare, the deployment and adoption of AI technologies remain limited in real-world clinical practice. In recent years, concerns have been raised about the technical, clinical, ethical and legal risks associated with medical AI. To increase real world adoption, it is essential that medical AI tools are trusted and accepted by patients, clinicians, health organisations and authorities. This work describes the FUTURE-AI guideline as the first international consensus framework for guiding the development and deployment of trustworthy AI tools in healthcare. The FUTURE-AI consortium was founded in 2021 and currently comprises 118 inter-disciplinary experts from 51 countries representing all continents, including AI scientists, clinicians, ethicists, and social scientists. Over a two-year period, the consortium defined guiding principles and best practices for trustworthy AI through an iterative process comprising an in-depth literature review, a modified Delphi survey, and online consensus meetings. The FUTURE-AI framework was established based on 6 guiding principles for trustworthy AI in healthcare, i.e. Fairness, Universality, Traceability, Usability, Robustness and Explainability. Through consensus, a set of 28 best practices were defined, addressing technical, clinical, legal and socio-ethical dimensions. The recommendations cover the entire lifecycle of medical AI, from design, development and validation to regulation, deployment, and monitoring. FUTURE-AI is a risk-informed, assumption-free guideline which provides a structured approach for constructing medical AI tools that will be trusted, deployed and adopted in real-world practice. Researchers are encouraged to take the recommendations into account in proof-of-concept stages to facilitate future translation towards clinical practice of medical AI. ",

keywords = "cs.CY, cs.AI, cs.CV, cs.LG, I.2.0; I.4.0; I.5.0",

author = "Karim Lekadir and Aasa Feragen and Fofanah, {Abdul Joseph} and Frangi, {Alejandro F} and Alena Buyx and Anais Emelie and Andrea Lara and Porras, {Antonio R} and An-Wen Chan and Arcadi Navarro and Ben Glocker and Botwe, {Benard O} and Bishesh Khanal and Brigit Beger and Wu, {Carol C} and Celia Cintas and Langlotz, {Curtis P} and Daniel Rueckert and Deogratias Mzurikwao and Fotiadis, {Dimitrios I} and Doszhan Zhussupov and Enzo Ferrante and Erik Meijering and Eva Weicken and Gonz{\'a}lez, {Fabio A} and Asselbergs, {Folkert W} and Fred Prior and Krestin, {Gabriel P} and Gary Collins and Tegenaw, {Geletaw S} and Georgios Kaissis and Gianluca Misuraca and Gianna Tsakou and Girish Dwivedi and Haridimos Kondylakis and Harsha Jayakody and Woodruf, {Henry C} and Aerts, {Hugo JWL} and Ian Walsh and Ioanna Chouvarda and Ir{\`e}ne Buvat and Islem Rekik and James Duncan and Jayashree Kalpathy-Cramer and Jihad Zahir and Jinah Park and John Mongan and Gichoya, {Judy W} and Schnabel, {Julia A} and Kaisar Kushibar and Katrine Riklund and Kensaku Mori and Kostas Marias and Amugongo, {Lameck M} and Fromont, {Lauren A} and Lena Maier-Hein and Alberich, {Leonor Cerd{\'a}} and Leticia Rittner and Lighton Phiri and Linda Marrakchi-Kacem and Llu{\'i}s Donoso-Bach and Luis Mart{\'i}-Bonmat{\'i} and Cardoso, {M Jorge} and Maciej Bobowicz and Mahsa Shabani and Manolis Tsiknakis and Zuluaga, {Maria A} and Maria Bielikova and Marie-Christine Fritzsche and Linguraru, {Marius George} and Markus Wenzel and Bruijne, {Marleen De} and Tolsgaard, {Martin G} and Marzyeh Ghassemi and Md Ashrafuzzaman and Melanie Goisauf and Mohammad Yaqub and Mohammed Ammar and Abad{\'i}a, {M{\'o}nica Cano} and Mahmoud, {Mukhtar M E} and Mustafa Elattar and Nicola Rieke and Nikolaos Papanikolaou and Noussair Lazrak and Oliver D{\'i}az and Olivier Salvado and Oriol Pujol and Ousmane Sall and Pamela Guevara and Peter Gordebeke and Philippe Lambin and Pieta Brown and Purang Abolmaesumi and Qi Dou and Qinghua Lu and Richard Osuala and Rose Nakasi and Zhou, {S Kevin} and Sandy Napel and Sara Colantonio and Shadi Albarqouni and Smriti Joshi and Stacy Carter and Stefan Klein and Petersen, {Steffen E} and Susanna Auss{\'o} and Suyash Awate and Raviv, {Tammy Riklin} and Tessa Cook and Mutsvangwa, {Tinashe E M} and Rogers, {Wendy A} and Niessen, {Wiro J} and X{\`e}nia Puig-Bosch and Yi Zeng and Mohammed, {Yunusa G} and Aquino, {Yves Saint James} and Zohaib Salahuddin and Starmans, {Martijn P A}",

year = "2023",

month = aug,

day = "11",

language = "English",

type = "WorkingPaper",

}

Lekadir, K, Feragen, A, Fofanah, AJ, Frangi, AF, Buyx, A, Emelie, A, Lara, A, Porras, AR, Chan, A-W, Navarro, A, Glocker, B, Botwe, BO, Khanal, B, Beger, B, Wu, CC, Cintas, C, Langlotz, CP, Rueckert, D, Mzurikwao, D, Fotiadis, DI, Zhussupov, D, Ferrante, E, Meijering, E, Weicken, E, González, FA, Asselbergs, FW, Prior, F, Krestin, GP, Collins, G, Tegenaw, GS, Kaissis, G, Misuraca, G, Tsakou, G, Dwivedi, G, Kondylakis, H, Jayakody, H, Woodruf, HC, Aerts, HJWL, Walsh, I, Chouvarda, I, Buvat, I, Rekik, I, Duncan, J, Kalpathy-Cramer, J, Zahir, J, Park, J, Mongan, J, Gichoya, JW, Schnabel, JA, Kushibar, K, Riklund, K, Mori, K, Marias, K, Amugongo, LM, Fromont, LA, Maier-Hein, L, Alberich, LC, Rittner, L, Phiri, L, Marrakchi-Kacem, L, Donoso-Bach, L, Martí-Bonmatí, L, Cardoso, MJ, Bobowicz, M, Shabani, M, Tsiknakis, M, Zuluaga, MA, Bielikova, M, Fritzsche, M-C, Linguraru, MG, Wenzel, M, Bruijne, MD, Tolsgaard, MG, Ghassemi, M, Ashrafuzzaman, M, Goisauf, M, Yaqub, M, Ammar, M, Abadía, MC, Mahmoud, MME, Elattar, M, Rieke, N, Papanikolaou, N, Lazrak, N, Díaz, O, Salvado, O, Pujol, O, Sall, O, Guevara, P, Gordebeke, P, Lambin, P, Brown, P, Abolmaesumi, P, Dou, Q, Lu, Q, Osuala, R, Nakasi, R, Zhou, SK, Napel, S, Colantonio, S, Albarqouni, S, Joshi, S, Carter, S, Klein, S, Petersen, SE, Aussó, S, Awate, S, Raviv, TR, Cook, T, Mutsvangwa, TEM, Rogers, WA, Niessen, WJ, Puig-Bosch, X, Zeng, Y, Mohammed, YG, Aquino, YSJ, Salahuddin, Z & Starmans, MPA 2023 'Future-ai: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare'.

TY - UNPB

T1 - Future-ai

T2 - International consensus guideline for trustworthy and deployable artificial intelligence in healthcare

AU - Lekadir, Karim

AU - Feragen, Aasa

AU - Fofanah, Abdul Joseph

AU - Frangi, Alejandro F

AU - Buyx, Alena

AU - Emelie, Anais

AU - Lara, Andrea

AU - Porras, Antonio R

AU - Chan, An-Wen

AU - Navarro, Arcadi

AU - Glocker, Ben

AU - Botwe, Benard O

AU - Khanal, Bishesh

AU - Beger, Brigit

AU - Wu, Carol C

AU - Cintas, Celia

AU - Langlotz, Curtis P

AU - Rueckert, Daniel

AU - Mzurikwao, Deogratias

AU - Fotiadis, Dimitrios I

AU - Zhussupov, Doszhan

AU - Ferrante, Enzo

AU - Meijering, Erik

AU - Weicken, Eva

AU - González, Fabio A

AU - Asselbergs, Folkert W

AU - Prior, Fred

AU - Krestin, Gabriel P

AU - Collins, Gary

AU - Tegenaw, Geletaw S

AU - Kaissis, Georgios

AU - Misuraca, Gianluca

AU - Tsakou, Gianna

AU - Dwivedi, Girish

AU - Kondylakis, Haridimos

AU - Jayakody, Harsha

AU - Woodruf, Henry C

AU - Aerts, Hugo JWL

AU - Walsh, Ian

AU - Chouvarda, Ioanna

AU - Buvat, Irène

AU - Rekik, Islem

AU - Duncan, James

AU - Kalpathy-Cramer, Jayashree

AU - Zahir, Jihad

AU - Park, Jinah

AU - Mongan, John

AU - Gichoya, Judy W

AU - Schnabel, Julia A

AU - Kushibar, Kaisar

AU - Riklund, Katrine

AU - Mori, Kensaku

AU - Marias, Kostas

AU - Amugongo, Lameck M

AU - Fromont, Lauren A

AU - Maier-Hein, Lena

AU - Alberich, Leonor Cerdá

AU - Rittner, Leticia

AU - Phiri, Lighton

AU - Marrakchi-Kacem, Linda

AU - Donoso-Bach, Lluís

AU - Martí-Bonmatí, Luis

AU - Cardoso, M Jorge

AU - Bobowicz, Maciej

AU - Shabani, Mahsa

AU - Tsiknakis, Manolis

AU - Zuluaga, Maria A

AU - Bielikova, Maria

AU - Fritzsche, Marie-Christine

AU - Linguraru, Marius George

AU - Wenzel, Markus

AU - Bruijne, Marleen De

AU - Tolsgaard, Martin G

AU - Ghassemi, Marzyeh

AU - Ashrafuzzaman, Md

AU - Goisauf, Melanie

AU - Yaqub, Mohammad

AU - Ammar, Mohammed

AU - Abadía, Mónica Cano

AU - Mahmoud, Mukhtar M E

AU - Elattar, Mustafa

AU - Rieke, Nicola

AU - Papanikolaou, Nikolaos

AU - Lazrak, Noussair

AU - Díaz, Oliver

AU - Salvado, Olivier

AU - Pujol, Oriol

AU - Sall, Ousmane

AU - Guevara, Pamela

AU - Gordebeke, Peter

AU - Lambin, Philippe

AU - Brown, Pieta

AU - Abolmaesumi, Purang

AU - Dou, Qi

AU - Lu, Qinghua

AU - Osuala, Richard

AU - Nakasi, Rose

AU - Zhou, S Kevin

AU - Napel, Sandy

AU - Colantonio, Sara

AU - Albarqouni, Shadi

AU - Joshi, Smriti

AU - Carter, Stacy

AU - Klein, Stefan

AU - Petersen, Steffen E

AU - Aussó, Susanna

AU - Awate, Suyash

AU - Raviv, Tammy Riklin

AU - Cook, Tessa

AU - Mutsvangwa, Tinashe E M

AU - Rogers, Wendy A

AU - Niessen, Wiro J

AU - Puig-Bosch, Xènia

AU - Zeng, Yi

AU - Mohammed, Yunusa G

AU - Aquino, Yves Saint James

AU - Salahuddin, Zohaib

AU - Starmans, Martijn P A

PY - 2023/8/11

Y1 - 2023/8/11

N2 - Despite major advances in artificial intelligence (AI) for medicine and healthcare, the deployment and adoption of AI technologies remain limited in real-world clinical practice. In recent years, concerns have been raised about the technical, clinical, ethical and legal risks associated with medical AI. To increase real world adoption, it is essential that medical AI tools are trusted and accepted by patients, clinicians, health organisations and authorities. This work describes the FUTURE-AI guideline as the first international consensus framework for guiding the development and deployment of trustworthy AI tools in healthcare. The FUTURE-AI consortium was founded in 2021 and currently comprises 118 inter-disciplinary experts from 51 countries representing all continents, including AI scientists, clinicians, ethicists, and social scientists. Over a two-year period, the consortium defined guiding principles and best practices for trustworthy AI through an iterative process comprising an in-depth literature review, a modified Delphi survey, and online consensus meetings. The FUTURE-AI framework was established based on 6 guiding principles for trustworthy AI in healthcare, i.e. Fairness, Universality, Traceability, Usability, Robustness and Explainability. Through consensus, a set of 28 best practices were defined, addressing technical, clinical, legal and socio-ethical dimensions. The recommendations cover the entire lifecycle of medical AI, from design, development and validation to regulation, deployment, and monitoring. FUTURE-AI is a risk-informed, assumption-free guideline which provides a structured approach for constructing medical AI tools that will be trusted, deployed and adopted in real-world practice. Researchers are encouraged to take the recommendations into account in proof-of-concept stages to facilitate future translation towards clinical practice of medical AI.

AB - Despite major advances in artificial intelligence (AI) for medicine and healthcare, the deployment and adoption of AI technologies remain limited in real-world clinical practice. In recent years, concerns have been raised about the technical, clinical, ethical and legal risks associated with medical AI. To increase real world adoption, it is essential that medical AI tools are trusted and accepted by patients, clinicians, health organisations and authorities. This work describes the FUTURE-AI guideline as the first international consensus framework for guiding the development and deployment of trustworthy AI tools in healthcare. The FUTURE-AI consortium was founded in 2021 and currently comprises 118 inter-disciplinary experts from 51 countries representing all continents, including AI scientists, clinicians, ethicists, and social scientists. Over a two-year period, the consortium defined guiding principles and best practices for trustworthy AI through an iterative process comprising an in-depth literature review, a modified Delphi survey, and online consensus meetings. The FUTURE-AI framework was established based on 6 guiding principles for trustworthy AI in healthcare, i.e. Fairness, Universality, Traceability, Usability, Robustness and Explainability. Through consensus, a set of 28 best practices were defined, addressing technical, clinical, legal and socio-ethical dimensions. The recommendations cover the entire lifecycle of medical AI, from design, development and validation to regulation, deployment, and monitoring. FUTURE-AI is a risk-informed, assumption-free guideline which provides a structured approach for constructing medical AI tools that will be trusted, deployed and adopted in real-world practice. Researchers are encouraged to take the recommendations into account in proof-of-concept stages to facilitate future translation towards clinical practice of medical AI.

KW - cs.CY

KW - cs.AI

KW - cs.CV

KW - cs.LG

KW - I.2.0; I.4.0; I.5.0

M3 - Preprint

BT - Future-ai

ER -

Future-ai: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare

Abstract

Keywords

Access to Document

Fingerprint

Cite this