AI for Doctors-A Course to Educate Medical Professionals in Artificial Intelligence for Medical Imaging.

Dennis M Hedderich,Judith E Spiro,Daniel Rückert,Dominik Heim,Tobias Czempiel,Martin J Gruber,Daniel Pinto Dos Santos,Florian Hinterwimmer,Nassir Navab,Claus Zimmer,Matthias Keicher,Benedikt Wiestler,Jan S Kirschke,Hendrik Burwinkel

doi:10.3390/healthcare9101278

Abstract

Successful adoption of artificial intelligence (AI) in medical imaging requires medical professionals to understand underlying principles and techniques. However, educational offerings tailored to the need of medical professionals are scarce. To fill this gap, we created the course “AI for Doctors: Medical Imaging”. An analysis of participants’ opinions on AI and self-perceived skills rated on a five-point Likert scale was conducted before and after the course. The participants’ attitude towards AI in medical imaging was very optimistic before and after the course. However, deeper knowledge of AI and the process for validating and deploying it resulted in significantly less overoptimism with respect to perceivable patient benefits through AI (p = 0.020). Self-assessed skill ratings significantly improved after the course, and the appreciation of the course content was very positive. However, we observed a substantial drop-out rate, mostly attributed to the lack of time of medical professionals. There is a high demand for educational offerings regarding AI in medical imaging among medical professionals, and better education may lead to a more realistic appreciation of clinical adoption. However, time constraints imposed by a busy clinical schedule need to be taken into account for successful education of medical professionals.

Highlights

Artificial intelligence (AI) has become one of the dominant topics in medical research, especially in processing and analysis of medical imaging data [1,2]
The group of participants consisted of 40 medical doctors (MDs) (43.0%), 35 medical students (37.6%), 7 PhD students (7.5%), and 11 postgraduate researchers without an MD
The majority of participants stated that they currently do not use AI in their daily work (77; 82.8%) and half of them had previous programming experience (46; 49.5%); 36 participants (39.2%) stated that they had no previous education in the field of artificial intelligence, while 40 (43.0%)

Summary

Introduction

Artificial intelligence (AI) has become one of the dominant topics in medical research, especially in processing and analysis of medical imaging data [1,2]. Clinical adoption of AI algorithms for medical imaging is lagging behind for various reasons, such as a lack of clinical validation of AI algorithms, regulatory burdens, hesitance of patients to accept AI for individual clinical decisions, and as of yet, often unsatisfactory reimbursement for AI algorithms [3,4,5,6] Another important reason may be that educational programs on AI in medical imaging tailored to the needs of medical professionals are lacking, which may lead to hesitance to use new algorithmic tools in clinical practice [7,8]. Educational programs, which are open to a broader audience of medical professionals working with medical-imaging data, such as ophthalmologists or pathologists, are very rare

Methods

Results

Discussion

Conclusion