You are here

Article Text

Article menu
Download PDFPDF
Analysis
Implementing AI models in clinical workflows: a roadmap
  1. Fei Wang1,
  2. Ashley Beecy1,2
  1. 1Weill Cornell Medical College, New York, New York, USA
  2. 2NewYork-Presbyterian Hospital, New York, New York, USA
  1. Correspondence to Dr Fei Wang, Weill Cornell Medical College, New York, New York, USA; few2001{at}med.cornell.edu

https://doi.org/10.1136/bmjebm-2023-112727

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    Artificial Intelligence (AI) aims at mimicking human intelligence through computer programmes. Machine learning (ML), especially deep learning technologies, aiming at inferring insights from complex data through mathematical modelling, offers an effective way of achieving AI and has achieved great success in many disciplines, such as computer vision and natural language processing. Over the past decade, many ML models have also been developed with the goal of improving healthcare, such as predicting the risk of sepsis shock for patients in critical care,1 identifying patients who are at high risk of developing postpartum depression from their historical clinical records2 and screening patients who are infected by SARS-CoV-2 according to their routine blood test results.3

    Real-world clinical trials are essential for proving that AI applications are safe, effective and fit for use in healthcare by assessing their performance across diverse conditions and populations, ensuring regulatory compliance and addressing ethical concerns. Despite the need for clinical trials and the promising results reported in research papers, the ratio of these models that have been implemented in real-world clinical workflows is relatively small. One of the inherent reasons is the complex interactions among multiple stakeholders in the healthcare system including patients, providers, policymakers and insurance companies. In a recent review, Li et al4 identified 19 technical/algorithm, stakeholder and social levels barriers to the application of AI in healthcare and called for future endeavours to address them. With this demand, there has been more and more efforts focusing on particular aspects of these barriers5 6 or exemplar implementations in different disease contexts,1 2 7 but guidelines for the holistic process of implementating AI models in clinical workflows are still sporadic.

    To fill in this gap, in this perspective, we provide an AI model implementation roadmap in clinical workflows, including three main …

    View Full Text

    Footnotes

    • Contributors FW conceptualised the manuscript. FW and AB drafted and proofread the whole manuscript.

    • Funding FW would like to acknowledge the support from NIH awards R01MH124740, RF1AG072449, R01AG080991, R01AG080624, R01AG076448, R01AG076234 and NSF award 1750326 and 2212175.

    • Competing interests None declared.

    • Provenance and peer review Commissioned; externally peer reviewed.