Publications

BibTex format

@article{Zhang:2022,
author = {Zhang, J and Budhdeo, S and William, W and Cerrato, P and Shuaib, H and Sood, H and Ashrafian, H and Halamka, J and Teo, J},
journal = {npj Digital Medicine},
pages = {1--9},
title = {Moving towards vertically integrated artificial intelligence development},
url = {https://www.nature.com/articles/s41746-022-00690-x},
volume = {5},
year = {2022}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Substantial interest and investment in clinical artificial intelligence (AI) research has not resulted in widespread translation to deployed AI solutions. Current attention has focused on bias and explainability in AI algorithm development, external validity and model generalisability, and lack of equity and representation in existing data. While of great importance, these considerations also reflect a model-centric approach seen in publishedclinical AI research, which focuses on optimising architecture and performance of an AI model on best available datasets. However, even robustly built models using state-of-the-art algorithms may fail once tested in realistic environments due to unpredictability of real-world conditions, out-of-dataset scenarios, characteristics of deployment infrastructure, and lack ofadded value to clinical workflows relative to cost and potential clinical risks. In this perspective, we define a vertically integrated approach to AI development that incorporates early, cross-disciplinary, consideration of impact evaluation, data lifecycles, and AI production, and explore its implementation in two contrasting AI development pipelines: a scalable “AI factory” (Mayo Clinic, Rochester, United States), and an end-to-end cervicalcancer screening platform for resource poor settings (Paps AI, Mbarara, Uganda). We provide practical recommendations for implementers, and discuss future challenges and novel approaches (including a decentralised federated architecture being developed in the NHS (AI4VBH, London, UK)). Growth in global clinical AI research continues unabated, and introduction of vertically integrated teams and development practices can increase thetranslational potential of future clinical AI projects.
AU  - Zhang,J
AU  - Budhdeo,S
AU  - William,W
AU  - Cerrato,P
AU  - Shuaib,H
AU  - Sood,H
AU  - Ashrafian,H
AU  - Halamka,J
AU  - Teo,J
EP  - 9
PY  - 2022///
SN  - 2398-6352
SP  - 1
TI  - Moving towards vertically integrated artificial intelligence development
T2  - npj Digital Medicine
UR  - https://www.nature.com/articles/s41746-022-00690-x
UR  - http://hdl.handle.net/10044/1/99563
VL  - 5
ER  -

Download

DrHutanAshrafian

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)