Artificial intelligence and machine learning are increasingly being applied to medical imaging, with the goal of improving diagnostic accuracy and efficiency. However, the adoption and use of these tools in practice can be influenced by clinicians' perceptions and attitudes toward them.
Therefore, we have three questions to cover these concerns:
1. Do you have any experience with artificial intelligence and machine learning in medical imaging?
2. How have your perceptions and attitudes towards these technologies affected your adoption and use of them in practice?
3. What factors do you think contribute to positive or negative perceptions and attitudes toward these technologies?
We invite researchers and practitioners with experience in this area to share their insights and experiences and to discuss the ways in which clinicians' perceptions and attitudes towards artificial intelligence and machine learning in medical imaging may influence their adoption and use of these tools.
Dear Francisco,
The questions are well asked, but finding the right answers that would capture the general global trend will not be easy. Nevertheless, I will try to offer at least our perspective, which may reflect the situation in Eastern Europe.
1. In Carebot, we have practical experience in implementing computer-aided-diagnosis (CAD) systems for the analysis of medical imaging data (primarily chest X-ray and mammography) in clinical practice. However, the rate of adoption and willingness to use these systems depends on many factors that do not only vary across regions (e.g., US vs. Eastern Europe), but even vary across hospitals in the same city.
2. I cannot speak directly for the medical staff, however, our experience to date suggests that communication is one of the keys to successful implementation. It is important to think about the specific benefits that AI can offer in clinical practice. For example, young radiologists would welcome a decision-support system when they are unsure of a finding and need to reach out to a more experienced colleague. For those more experienced, triage of images and prioritisation of patients with more acute findings, for example, can be a benefit. However, it is important to be honest about the benefits.
3. I definitely rank direct integration into existing medical workflow as one of the primary factors. Standalone applications have a huge disadvantage over CAD implemented in PACS. Although some commercial companies sometimes complain that physicians are conservative about their work habits, it cannot be viewed that way. In the end, the user is always the one who decides the success of the adoption.
Hopefully this brief summary has answered some of your questions at least a little.
I agree that communication and integration into existing medical workflow are important factors that can influence the adoption and usage of artificial intelligence, as well as machine learning in medical imaging. In my experience, it is crucial to clearly articulate the benefits that these technologies can bring and demonstrate how they can support and enhance clinical practice rather than replace it. This can help to build trust and acceptance among clinicians.
Another factor that can impact adoption is the level of training and support provided. Ensuring that clinicians have access to adequate training and support can help them feel confident in using the technology and can encourage more widespread adoption.
Finally, the reliability and accuracy of the technology are also important. Clinicians are likely to be more willing to adopt and use AI and machine learning tools if they have confidence in the results they produce. Ensuring that the technology has been adequately tested and validated can help to build this confidence.
You can also see some of our findings from an international study of adoption and acceptance that we recently published:
Francisco Maria Calisto, Nuno Nunes, Jacinto C. Nascimento, Modeling adoption of intelligent agents in medical imaging, International Journal of Human-Computer Studies, Volume 168, 2022, 102922, ISSN 1071-5819, https://doi.org/10.1016/j.ijhcs.2022.102922
Overall, it is important to approach the adoption and use of AI and machine learning in medical imaging with a collaborative and transparent mindset and to consider the needs and concerns of clinicians in order to facilitate successful implementation and use.
Francisco Maria Calisto Clinicians' perspectives and attitudes regarding artificial intelligence (AI) in medical imaging can influence their acceptance and usage of these tools significantly. Clinicians who are suspicious about the accuracy or use of AI in medical imaging may be less inclined to employ these technologies in their practice. Clinicians, on the other hand, maybe more willing to accept and apply AI in medical imaging if they are confident in its dependability and understand the potential benefits of adopting it.
Several factors, including clinicians' past experiences with these tools, their degree of knowledge with AI technology, and the quality of assistance and training they receive in utilizing these tools, might impact clinicians' views and attitudes regarding AI in medical imaging. It is also critical for AI in medical imaging developers and providers to properly convey the capabilities and limits of these technologies to doctors in order to guarantee that they are utilized appropriately and successfully.
- Badges
- Science topic
- Similar topics
- Social Psychology
- Attitude