Artificial Intelligence in Healthcare: a Primer for Medical Education in Radiomics

Abstract

The application of artificial intelligence (AI) to healthcare has garnered significant enthusiasm in recent years. Despite the adoption of new analytic approaches, medical education on AI is lacking. We aim to create a usable AI primer for medical education. We discuss how to generate a clinical question involving AI, what data are suitable for AI research, how to prepare a dataset for training and how to determine if the output has clinical utility. To illustrate this process, we focused on an example of how medical imaging is employed in designing a machine learning model. Our proposed medical education curriculum addresses AI’s potential and limitations for enhancing clinicians’ skills in research, applied statistics and care delivery.

Radiomic Features Applied to Contrast Enhancement Spectral Mammography: Possibility to Predict Breast Cancer Molecular Subtypes in a Non-Invasive Manner

“…The application of radiomics to clinical practice, in particular the correlation with molecular biomarkers, represents one of the most interesting challenges for radiologists and clinicians in recent years [ 15 , 16 , 17 , 18 ]. The possibility of providing increasingly personalized and precise diagnostic and therapeutic pathways can be greatly assisted by the intrinsic radiological image information that radiomics is able to provide: radiomics is able to support the clinical decision-making process of the patient’s management.…”

Educating Medical Providers in the Era of Artificial Intelligence

“…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…”

“…Advocates for inclusion of multidimensional AI training in medical education suggest that practical skill acquisition through real-world use of the technology is a valuable method for teaching the theory and foundational principles of AI. 4 If true, in the context of incorporating diagnostic AI tools into medical education, the concept would theoretically also apply in the context of incorporating AI education tools such as intelligent tutoring into medical education methods; both facilitate real-world interaction with AI systems.…”

“…In summary, machine learning represents the subdomain of AI involving the use of computer algorithms that can essentially learn from a source of data through pattern recognition and prediction with the added ability to adapt based on what it has learned. 4 Deep learning is a further subdomain of machine learning that uses algorithms within artificial neural networks to enhance the ability to perform machine learning tasks and solve problems. 5 For simplicity and the purposes of this article, "AI" will be used as a general term to represent the field of AI including the subdomains mentioned above.…”

“…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…”