Integrating artificial intelligence into the clinical practice of radiology: challenges and recommendations

Abstract

Artificial intelligence (AI) has the potential to significantly disrupt the way radiology will be practiced in the near future, but several issues need to be resolved before AI can be widely implemented in daily practice. These include the role of the different stakeholders in the development of AI for imaging, the ethical development and use of AI in healthcare, the appropriate validation of each developed AI algorithm, the development of effective data sharing mechanisms, regulatory hurdles for the clearance of AI algorithms, and the development of AI educational resources for both practicing radiologists and radiology trainees. This paper details these issues and presents possible solutions based on discussions held at the 2019 meeting of the International Society for Strategic Studies in Radiology. Key Points • Radiologists should be aware of the different types of bias commonly encountered in AI studies, and understand their possible effects. • Methods for effective data sharing to train, validate, and test AI algorithms need to be developed.• It is essential for all radiologists to gain an understanding of the basic principles, potentials, and limits of AI.

Implementation of artificial intelligence (AI) applications in radiology: hindering and facilitating factors

“…Another implementation challenge we found, the role of evidence on innovation implementation, has been discussed extensively in the field of evidence-based healthcare [41]. Scientific evidence is an important determinant of innovation implementation for practitioners, a finding that also appears to hold for AI in radiology [8,21,41,42]. It thus follows that AI applications for radiology reflect a trend in the field of medical imaging to engage with technologies that have yet to prove their promises of contributing to the improvement of the quality or efficiency of healthcare [43].…”

“…The interviews showed that computer science and programming knowledge required in the development of AI algorithms are not present-day competencies of radiologists. However, some technical understanding is imperative for quality and safety assessment and therefore create trust in the AI application's reliability [8,21,30].…”

“…Technology implementation in hospital settings involves a large variety of stakeholders and organizational procedures, with strong routines and professional identities, as well as strict legal and regulatory standards [18][19][20]. Considering that AI applications in radiology are in an emerging phase, it is too early to evaluate their implementation [21]. However, in view of the unsuccessful widespread diffusion of earlier CAD systems, it can be assumed that AI applications will encounter barriers to implementation.…”

Promises of artificial intelligence in neuroradiology: a systematic technographic review

“…For radiologists, it is crucial to know the strength and weaknesses of the technology that they use to improve quality, ensure safety and understand artefacts [19,20]. Additionally, radiologists need to understand technical information about the applications [21] to recognize the strengths and pitfalls of AI applications [22]. Information about the training data of algorithms and whether external validation was performed helps radiologists assess the credibility and applicability of an AI application in their hospital [23].…”

Challenges and solutions for introducing artificial intelligence (AI) in daily clinical workflow

“…2. Technical validation: once the algorithm has been trained, it is difficult to prove its robustness and reliability as it works like a black box [3]. 3.…”