Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Jun 14, 2023
Date Accepted: Sep 13, 2023
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Democratising artificial intelligence imaging analysis with automated machine learning
ABSTRACT
Background:
Artificial intelligence (AI) has produced impressive results across medicine. In particular, deep learning-based clinical imaging analysis underlies diagnostic models which often match or even exceed the performance of clinical experts, with potential to revolutionise clinical practice. A wide variety of automated machine learning (autoML) platforms lower the technical barrier to entry to deep learning, extending AI capabilities to clinicians with limited technical expertise, and even autonomous foundation models such as emerging large language models.
Objective:
Here, we provide a technical overview of autoML with descriptions of how autoML may be applied in education, research, and clinical practice.
Methods:
Each stage of the process of conducting an autoML project is outlined, with an emphasis on ethical and technical best-practice. Specifically, data acquisition, data partitioning, model training, model validation, analysis, and model deployment are considered. The strengths and limitations of the variety of available code-free, code-minimal, and code-intensive autoML platforms is considered.
Results:
-
Conclusions:
AutoML has great potential to democratise AI in medicine, improving AI-literacy by enabling ‘hands-on’ education. AutoML may serve as a useful adjunct in research by facilitating rapid testing and benchmarking before significant computational resources are committed. AutoML may also be applied in clinical contexts, provided regulatory requirements are met. The abstraction by autoML of arduous aspects of AI engineering promotes prioritisation of dataset curation, supporting the transition from conventional model-driven approaches to data-centric development. To fulfil its potential, clinicians must be educated in how to apply these technologies ethically, rigorously, and effectively: this review represents a comprehensive summary of relevant considerations.
Citation
