Clinical translation of computational brain models: understanding the salience of trust in clinician–researcher relationships

ABSTRACT

Computational brain models use machine learning, algorithms and statistical models to harness big data for delivering disease-specific diagnosis or prognosis for individuals. While intended to support clinical decision-making, their translation into clinical practice remains challenging despite efforts to improve implementation through training clinicians and clinical staff in their use and benefits. Drawing on the specific case of neurology, we argue that existing implementation efforts are insufficient for the responsible translation of computational models. Our research based on a collective seven-year engagement with the Human Brain Project, participant observation at workshops and conferences, and expert interviews, suggests that relationships of trust between clinicians and researchers (modellers, data scientists) are essential to the meaningful translation of computational models. In particular, efforts to increase model transparency, strengthen upstream collaboration, and integrate clinicians' perspectives and tacit knowledge have the potential to reinforce trust building and increase translation of technologies that are beneficial to patients.

KEYWORDS:

• Human Brain Project
• Artificial Intelligence
• machine learning
• neurology
• neuroscience
• clinical prediction models; big data
• data driven health

Acknowledgements

We would like to convey our special thanks to Dr Edison Bicudo (University of Sussex, UK), Professor Alex Faulkner (University of Sussex, UK), and to all who participated in this research. The authors acknowledge support from the European Union’s Horizon 2020 Research and Innovation Programme funding for the Human Brain Project (Special Grant Agreement 2 number 785907).

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes

1 In this paper, ‘researchers’ refer to modellers neuroscientists and data scientists involved with the development of computational models and data analysis tools.

2 Covering all areas of use from process optimisation to patient-facing applications and notably applications integrated in clinical pathways, which encompass among other techniques machine learning and data-driven computational models.

3 see analysis by researchers at Johns Hopkins https://www.hopkinsmedicine.org/news/media/releases/diagnostic_errors_more_common_costly_and_harmful_than_treatment_mistakes

4 https://www.fda.gov/NewsEvents/Newsroom/PressAnnouncements/ucm596575.htm

5 http://www.fatml.org/

Additional information

Funding

The authors acknowledge support from the European Union's Horizon 2020 Research and Innovation Framework Programme funding for the Human Brain Project (Special Grant Agreement 2 number 785907); and the United Kingdom Engineering and Physical Sciences Research Council grant for the PETRAS-2 project (grant number EP/S03562/1).

Notes on contributors

S. Datta Burton

S. Datta Burton is a Research Fellow at the Department of Science, Technology, Engineering and Public Policy, University College London. She is the Principal Investigator for the Petras project Building Evidence for CoP Legislation (BECL), a Visiting Research Fellow at the Department of Politics, University of Vienna, and a member of the Ethics and Society subproject of the Human Brain Project from 2017 till 2020. Saheli is interested in the international political economy of emerging technologies with a focus on data-driven health and medicine.

T. Mahfoud

T. Mahfoud is a Lecturer in the Department of Sociology at the University of Essex. Before that, she was a Research Associate in the Department of Global Health and Social Medicine at King's College London and a member of the Human Brain Project Foresight Lab.

C. Aicardi

C. Aicardi is senior research fellow in King's College London Foresight Laboratory, Department of Global Health & Social Medicine. Christine worked for many years in the Information and Communication Technologies industry before returning to higher education to pursue a PhD in Science and Technology Studies at University College London. She joined the Ethics and Society subproject of the Human Brain Project in 2014.

N. Rose

N. Rose is Professor of Sociology at King's College London, and Co-Director of King's ESRC Centre for Society and Mental Health. He was the Principal Investigator and Director of the Foresight Lab at King's for the Human Brain Project and a member of the Steering Committee of the Ethics and Society Division of the HBP from its inception until 2020.