The last decade has seen a huge surge in interest surrounding artificial intelligence (AI). AI has been around since the 1950s, although technological limitations in the early days meant performance was initially inferior compared to humans. 1 With rapid progression of algorithm design, growth of vast digital datasets and development of powerful computing power, AI now has the capability to outperform humans. Consequently, the integration of AI into the modern world is skyrocketing. This review article will give an overview of the use of AI in the modern world and discuss current and potential uses in healthcare, with a particular focus on its applications and likely impact in medical imaging. We will discuss the consequences and challenges of AI integration into healthcare.
Telemedicine is an innovative, rapidly evolving method of care delivery in the National Health Service. The main long-term benefit of teledermatology triage is to ensure that patients receive timely care in the most appropriate setting, and to increase capacity in secondary care for patients who need face-to-face referrals. However, the diagnosis made and the advice given may vary depending on the experience and knowledge of the person triaging. The aim of this study was to evaluate how the interpretation of the information/images by different clinicians can affect the outcome of a teledermatology referral. The data collected in this project are expected to provide knowledge about the concordance between dermatology doctors in their approach to teledermatology referrals and to evaluate the impact on quality of care. The teledermatology service referrals to our dermatology department are made through the national electronic Referral Service, with the option to attach images or to refer patients to an image-taking clinic based at the hospital. Dermatology consultants will then review referrals virtually, relaying advice back to the referrer. We provided a mixture of 10 teledermatology referrals who had attended the image-taking clinic to dermatology consultants and dermatology trainees. The dermatology doctors were asked to complete an outcome template for each referral based on the information/images provided. The study was completed by nine consultants and four trainees. Only three consultants (33%) and no trainees had previous experience of the teledermatology service. The respondents evaluated the clinical information provided in the referrals as good (41%), satisfactory (47%) and poor (12%). The clinicians evaluated the quality of images taken following the referral as good (68%), satisfactory (28%) and poor (4%). Overall, 90% of the consultants and 72% of the trainees agreed with the final diagnosis/outcome of the teledermatology referral. The benign skin lesions had the least consistency between the clinicians in terms of the diagnosis and type of the follow-up arranged. The follow-ups arranged after a referral included routine referral to clinic (consultants 30%, trainees 32%), urgent referral to clinic (consultants 25%, trainees 40%), referral to clinic if not improved (consultants 21%, trainees 17%) and discharge (consultants 23%, trainees 10%). In conclusion, there was satisfactory concordance between clinicians in responding to the majority of the teledermatology referrals. Trainees have shown to agree with the final diagnosis in the majority of cases; however, they still need more training in this area, particularly on how to gain confidence in arranging an appropriate follow-up plan after the advice given.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.