Scientists at the University of Liverpool have presented a model for applying artificial intelligence (AI) to enhance the utilization of antimicrobial agents and improve infection care.
Image Credit: University of Liverpool.
This initiative aims to contribute to mitigating the worldwide antimicrobial resistance (AMR) issue.
Their blueprint is detailed in a research study published recently in The Lancet Digital Health journal on December 18th, 2023.
Different forms of AI bring many opportunities to improve healthcare. AIs can harness complex evolving data, inform and augment human actions, and learn from outcomes. The global public health challenge of AMR needs large-scale optimization of antimicrobial use and wider infection care, which can be enabled by carefully constructed AIs.
Dr. Alex Howard, Study Lead Author, University of Liverpool
The researchers observed that despite the growing utility and resilience of AIs, their integration into healthcare systems presents considerable challenges. There exists a gap between the potential of AIs and their actual implementation in patient and population care.
Keeping this in consideration, the team has proposed an adaptive framework for the implementation and maintenance of AIs as a learning system. This framework addresses the identification of AMR issues, legal and regulatory considerations, organizational support, and data processing concerning the development, evaluation, maintenance, and scalability of AI systems targeting AMR.
Bridging the implementation gap between AI innovation and tackling AMR presents technical, regulatory, organizational, and human challenges. Learning systems built on integrated dataflows, governance, and technologies have the potential to close this gap.
Dr. Alex Howard, Study Lead Author, University of Liverpool
Howard added, “Translational expertise between AMR and AI fields will be essential to appropriately design, maintain, normalize, and globalize AMR-AIs in infection care and realize the potential for AIs to support clinician-driven AMR minimization strategies.”
The study outlines a perspective on utilizing data science to combat antimicrobial resistance within the framework of the Centres for Antimicrobial Optimisation Network program.
This global collaboration unites multidisciplinary expertise in infection and health informatics to address the challenge of antimicrobial resistance.
Journal Reference:
Howard, A., et al. (2023) Antimicrobial learning systems: an implementation blueprint for artificial intelligence to tackle antimicrobial resistance. The Lancet Digital Health. doi.org/10.1016/S2589-7500(23)00221-2