Co-Design of a Trustworthy AI System in Healthcare: Deep Learning Based Skin Lesion Classifier

Roberto V. Zicari; Sheraz Ahmed; Julia Amann; Stephan Alexander Braun; John Brodersen; Frédérick Bruneault; James Brusseau; Erik Campano; Megan Coffee; Andreas Dengel; Boris Düdder; Alessio Gallucci; Thomas Krendl Gilbert; Philippe Gottfrois; Emmanuel Goffi; Christoffer Bjerre Haase; Thilo Hagendorff; Eleanore Hickman; Elisabeth Hildt; Sune Holm; Pedro Kringen; Ulrich Kühne; Adriano Lucieri; Vince I. Madai; Pedro A. Moreno-Sánchez; Oriana Medlicott; Matiss Ozols; Eberhard Schnebel; Andy Spezzatti; Jesmin Jahan Tithi; Steven Umbrello; Dennis Vetter; Holger Volland; Magnus Westerlund; Renee Wurth

doi:10.3389/fhumd.2021.688152

Co-Design of a Trustworthy AI System in Healthcare: Deep Learning Based Skin Lesion Classifier

Roberto V. Zicari (Corresponding author)
, Sheraz Ahmed
, Julia Amann
, Stephan Alexander Braun
, John Brodersen
, Frédérick Bruneault
, James Brusseau
, Erik Campano
, Megan Coffee
, Andreas Dengel
, Boris Düdder
, Alessio Gallucci
, Thomas Krendl Gilbert
, Philippe Gottfrois
, Emmanuel Goffi
, Christoffer Bjerre Haase
, Thilo Hagendorff
, Eleanore Hickman
, Elisabeth Hildt
, Sune Holm

Pedro Kringen, Ulrich Kühne, Adriano Lucieri, Vince I. Madai, Pedro A. Moreno-Sánchez, Oriana Medlicott, Matiss Ozols, Eberhard Schnebel, Andy Spezzatti, Jesmin Jahan Tithi, Steven Umbrello, Dennis Vetter, Holger Volland, Magnus Westerlund, Renee Wurth

Eindhoven MedTech Innovation Center

Onderzoeksoutput: Bijdrage aan tijdschrift › Tijdschriftartikel › Academic › peer review

53 Citaten (Scopus)

273 Downloads (Pure)

Samenvatting

This paper documents how an ethically aligned co-design methodology ensures trustworthiness in the early design phase of an artificial intelligence (AI) system component for healthcare. The system explains decisions made by deep learning networks analyzing images of skin lesions. The co-design of trustworthy AI developed here used a holistic approach rather than a static ethical checklist and required a multidisciplinary team of experts working with the AI designers and their managers. Ethical, legal, and technical issues potentially arising from the future use of the AI system were investigated. This paper is a first report on co-designing in the early design phase. Our results can also serve as guidance for other early-phase AI-similar tool developments

Originele taal-2	Engels
Artikelnummer	688152
Aantal pagina's	21
Tijdschrift	Frontiers in Human Dynamics
Volume	3
DOI's	https://doi.org/10.3389/fhumd.2021.688152
Status	Gepubliceerd - 13 jul. 2021

Financiering

DV received funding from the European Union’s Horizon 2020 Research and Innovation Program “PERISCOPE: Pan European Response to the ImpactS of COvid-19 and future Pandemics and Epidemics” under grant agreement no. 101016233, H2020-SC1-PHE-CORONAVIRUS-2020-2-RTD. TH was supported by the Cluster of Excellence “Machine Learning—New Perspectives for Science” funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy—Reference Number EXC 2064/1—Project ID 390727645

Financiers	Financiernummer
European Union’s Horizon Europe research and innovation programme
Deutsche Forschungsgemeinschaft	390727645, EXC 2064/1

Duurzame ontwikkelingsdoelstellingen van de VN

Deze output draagt bij aan de volgende duurzame ontwikkelingsdoelstelling(en)

SDG 3 – Goede gezondheid en welzijn

Trefwoorden

artificial intelligence
healthcare
trustworthy AI
ethics
malignant melanoma
Z-inspection®1
Social Sciences
H

Toegang tot document

10.3389/fhumd.2021.688152

478757871.pdfDefinitieve gepubliceerde versie, 1,09 MB

Andere bestanden en links

Link naar publicatie in Scopus

Citeer dit

Zicari, R. V., Ahmed, S., Amann, J., Braun, S. A., Brodersen, J., Bruneault, F., Brusseau, J., Campano, E., Coffee, M., Dengel, A., Düdder, B., Gallucci, A., Gilbert, T. K., Gottfrois, P., Goffi, E., Haase, C. B., Hagendorff, T., Hickman, E., Hildt, E., ... Wurth, R. (2021). Co-Design of a Trustworthy AI System in Healthcare: Deep Learning Based Skin Lesion Classifier. Frontiers in Human Dynamics, 3, Artikel 688152. https://doi.org/10.3389/fhumd.2021.688152

@article{f96bb5ef0a474208bf90ec0ae47307eb,

title = "Co-Design of a Trustworthy AI System in Healthcare: Deep Learning Based Skin Lesion Classifier",

abstract = "This paper documents how an ethically aligned co-design methodology ensures trustworthiness in the early design phase of an artificial intelligence (AI) system component for healthcare. The system explains decisions made by deep learning networks analyzing images of skin lesions. The co-design of trustworthy AI developed here used a holistic approach rather than a static ethical checklist and required a multidisciplinary team of experts working with the AI designers and their managers. Ethical, legal, and technical issues potentially arising from the future use of the AI system were investigated. This paper is a first report on co-designing in the early design phase. Our results can also serve as guidance for other early-phase AI-similar tool developments",

keywords = "artificial intelligence, healthcare, trustworthy AI, ethics, malignant melanoma, Z-inspection{\textregistered}1, Social Sciences, H, artificial intelligence, ethical co-design, ethics, healthcare, malignant melanoma, trustworthy AI, trustworthy AI Co-design, Z-inspection",

author = "Zicari, \{Roberto V.\} and Sheraz Ahmed and Julia Amann and Braun, \{Stephan Alexander\} and John Brodersen and Fr{\'e}d{\'e}rick Bruneault and James Brusseau and Erik Campano and Megan Coffee and Andreas Dengel and Boris D{\"u}dder and Alessio Gallucci and Gilbert, \{Thomas Krendl\} and Philippe Gottfrois and Emmanuel Goffi and Haase, \{Christoffer Bjerre\} and Thilo Hagendorff and Eleanore Hickman and Elisabeth Hildt and Sune Holm and Pedro Kringen and Ulrich K{\"u}hne and Adriano Lucieri and Madai, \{Vince I.\} and Moreno-S{\'a}nchez, \{Pedro A.\} and Oriana Medlicott and Matiss Ozols and Eberhard Schnebel and Andy Spezzatti and Tithi, \{Jesmin Jahan\} and Steven Umbrello and Dennis Vetter and Holger Volland and Magnus Westerlund and Renee Wurth",

year = "2021",

month = jul,

day = "13",

doi = "10.3389/fhumd.2021.688152",

language = "English",

volume = "3",

journal = "Frontiers in Human Dynamics",

issn = "2673-2726",

publisher = "Frontiers Media S.A.",

}

Zicari, RV, Ahmed, S, Amann, J, Braun, SA, Brodersen, J, Bruneault, F, Brusseau, J, Campano, E, Coffee, M, Dengel, A, Düdder, B, Gallucci, A, Gilbert, TK, Gottfrois, P, Goffi, E, Haase, CB, Hagendorff, T, Hickman, E, Hildt, E, Holm, S, Kringen, P, Kühne, U, Lucieri, A, Madai, VI, Moreno-Sánchez, PA, Medlicott, O, Ozols, M, Schnebel, E, Spezzatti, A, Tithi, JJ, Umbrello, S, Vetter, D, Volland, H, Westerlund, M & Wurth, R 2021, 'Co-Design of a Trustworthy AI System in Healthcare: Deep Learning Based Skin Lesion Classifier', Frontiers in Human Dynamics, vol. 3, 688152. https://doi.org/10.3389/fhumd.2021.688152

TY - JOUR

T1 - Co-Design of a Trustworthy AI System in Healthcare: Deep Learning Based Skin Lesion Classifier

AU - Zicari, Roberto V.

AU - Ahmed, Sheraz

AU - Amann, Julia

AU - Braun, Stephan Alexander

AU - Brodersen, John

AU - Bruneault, Frédérick

AU - Brusseau, James

AU - Campano, Erik

AU - Coffee, Megan

AU - Dengel, Andreas

AU - Düdder, Boris

AU - Gallucci, Alessio

AU - Gilbert, Thomas Krendl

AU - Gottfrois, Philippe

AU - Goffi, Emmanuel

AU - Haase, Christoffer Bjerre

AU - Hagendorff, Thilo

AU - Hickman, Eleanore

AU - Hildt, Elisabeth

AU - Holm, Sune

AU - Kringen, Pedro

AU - Kühne, Ulrich

AU - Lucieri, Adriano

AU - Madai, Vince I.

AU - Moreno-Sánchez, Pedro A.

AU - Medlicott, Oriana

AU - Ozols, Matiss

AU - Schnebel, Eberhard

AU - Spezzatti, Andy

AU - Tithi, Jesmin Jahan

AU - Umbrello, Steven

AU - Vetter, Dennis

AU - Volland, Holger

AU - Westerlund, Magnus

AU - Wurth, Renee

PY - 2021/7/13

Y1 - 2021/7/13

N2 - This paper documents how an ethically aligned co-design methodology ensures trustworthiness in the early design phase of an artificial intelligence (AI) system component for healthcare. The system explains decisions made by deep learning networks analyzing images of skin lesions. The co-design of trustworthy AI developed here used a holistic approach rather than a static ethical checklist and required a multidisciplinary team of experts working with the AI designers and their managers. Ethical, legal, and technical issues potentially arising from the future use of the AI system were investigated. This paper is a first report on co-designing in the early design phase. Our results can also serve as guidance for other early-phase AI-similar tool developments

AB - This paper documents how an ethically aligned co-design methodology ensures trustworthiness in the early design phase of an artificial intelligence (AI) system component for healthcare. The system explains decisions made by deep learning networks analyzing images of skin lesions. The co-design of trustworthy AI developed here used a holistic approach rather than a static ethical checklist and required a multidisciplinary team of experts working with the AI designers and their managers. Ethical, legal, and technical issues potentially arising from the future use of the AI system were investigated. This paper is a first report on co-designing in the early design phase. Our results can also serve as guidance for other early-phase AI-similar tool developments

KW - artificial intelligence

KW - healthcare

KW - trustworthy AI

KW - ethics

KW - malignant melanoma

KW - Z-inspection®1

KW - Social Sciences

KW - H

KW - artificial intelligence

KW - ethical co-design

KW - ethics

KW - healthcare

KW - malignant melanoma

KW - trustworthy AI

KW - trustworthy AI Co-design

KW - Z-inspection

UR - https://www.scopus.com/pages/publications/85121899656

U2 - 10.3389/fhumd.2021.688152

DO - 10.3389/fhumd.2021.688152

M3 - Article

SN - 2673-2726

VL - 3

JO - Frontiers in Human Dynamics

JF - Frontiers in Human Dynamics

M1 - 688152

ER -

Co-Design of a Trustworthy AI System in Healthcare: Deep Learning Based Skin Lesion Classifier

Samenvatting

Financiering

Duurzame ontwikkelingsdoelstellingen van de VN

Trefwoorden

Toegang tot document

Andere bestanden en links

Vingerafdruk

Citeer dit