Artificial Intelligence and Deep Learning for Rheumatologists

Abstract

Deep learning has emerged as the leading method in machine learning, spawning a rapidly growing field of academic research and commercial applications across medicine. Deep learning could have particular relevance to rheumatology if correctly utilized. The greatest benefits of deep learning methods are seen with unstructured data frequently found in rheumatology, such as images and text, where traditional machine learning methods have struggled to unlock the trove of information held within these data formats. The basis for this success comes from the ability of deep learning to learn the structure of the underlying data. It is no surprise that the first areas of medicine that have started to experience impact from deep learning heavily rely on interpreting visual data, such as triaging radiology workflows and computer-assisted colonoscopy. Applications in rheumatology are beginning to emerge, with recent successes in areas as diverse as detecting joint erosions on plain radiography, predicting future rheumatoid arthritis disease activity, and identifying halo sign on temporal artery ultrasound. Given the important role deep learning methods are likely to play in the future of rheumatology, it is imperative that rheumatologists understand the methods and assumptions that underlie the deep learning algorithms in widespread use today, their limitations and the landscape of deep learning research that will inform algorithm development, and clinical decision support tools of the future. The best applications of deep learning in rheumatology must be informed by the clinical experience of rheumatologists, so that algorithms can be developed to tackle the most relevant clinical problems.

Educating Medical Providers in the Era of Artificial Intelligence

“…New foundations of knowledge will be required of future medical providers, including an understanding of the methodology and limitations involved in advanced AI such as machine learning and deep learning. 5 This knowledge should encourage the acquisition of new skillsets that equip medical providers with the required ability to critically examine AI systems. 1 While equipping medical providers with knowledge and skills for their eventual interaction with AI systems is of value, there appears to be less discussion on how AI itself can and will impact methodology, pedagogy, engagement with students, assessment, and curriculum design as it relates to medical education.…”

“…Any data used in machine learning training containing intentional or inadvertent biases could theoretically influence the AI model generated. 4,5 Evolving Medical Provider Role…”

“…12 To prevent a "black box" effect, where the technology behind the AI decision-making processes is not understood, medical providers will need to be able to provide critical appraisal of AI decision-making processes as discussed earlier. 1,5 In addition to the critical appraisal of AI systems, medical providers will likely play a central role in maintaining the humanistic aspects of medical care through the expression of empathy and compassion and as communicators of AI-guided medical decisions to patients. 1,2 Both aspects of this role evolution will require modification of medical education curricula to support them.…”

“…The deep learning systems that support natural language processing applications like ChatGPT also demonstrate success in application to the complex data associated with the field of medicine, including radiology, dermatology, and pathology. 3,5 Through such applications in medicine, advanced data analytics can identify novel patterns of disease, develop enhanced diagnostic models, and predict disease and treatment outcomes. 4…”

Understanding the role and adoption of artificial intelligence techniques in rheumatology research: an in-depth review of the literature

“…Furthermore, another narrative review [44] covered the applications of ML in systemic sclerosis (SS). A review of AI and deep learning (DL) [45] attempted to highlight the relevance of these techniques in the near future of the field of rheumatology. Finally, a review explored the opportunities and challenges of using RWD data focusing mainly on the electronic health record (EHR) data to advance clinical research in rheumatology [5].…”