Image recognition AI has the potential to significantly enhance the diagnostic process by assisting healthcare providers in identifying and distinguishing imaging patterns associated with rare bone diseases.
In 2024, we conducted a global survey to evaluate healthcare providers' interest in using an AI-based assistant to support the differential diagnosis of these conditions. We sincerely thank the community for participating in the survey and sharing valuable feedback. As promised, we are now sharing the aggregated results through the following (mostly interactive) visualisations. A detailed report of the findings has been submitted to the Orphanet Journal of Rare Diseases and is currently under review.
What is your primary role in or related to healthcare?
Which title best describes your position (please check if you have a dual function)?
Are you involved in teaching or training other healthcare professionals?
How many years of experience do you have in the healthcare field?
Which type of healthcare facility best describes where you primarily work (i.e., where do you work most often)?
Please enter the country where you primarily work.
What age group(s) of the patients do you work with (check all that apply)?
Approximately, how many patients with known or suspected rare bone diseases (or conditions where skeletal anomalies and related findings are an important feature) does your entire facility see per month?
According to the 2023 revision of the nosology of genetic skeletal disorders (Unger et al.), there are 41 different groups of skeletal disorders. Please SELECT ALL of the groups that represent the patients for which you, your clinic, and/or your institution provide care.
In your opinion, how important are medical images (i.e., x-rays, MRI, etc.) in the diagnosis of rare bone diseases?
Which imaging type do you think is the most important modality for the postnatal diagnosis of rare bone diseases?
How difficult do you think it is to delineate between different rare bone diseases based on visual inspection of patients’ radiographs? (for answering this question you may exclude the disorders with highly characteristic features such as achondroplasia).
What regulatory considerations or ethical concerns do you foresee in implementing image recognition AI for rare bone disease diagnosis? Select all that apply.
How concerned are you about the potential for AI-related errors in the diagnosis of rare bone diseases?
As long as the image recognition AI algorithms are confirmed (through trial studies) to perform their tasks accurately, how important to you is the explainability of these algorithms?
Would you be willing to do additional training to learn to utilize an image recognition AI tool for rare bone disease diagnosis?
If an image recognition AI is developed that provides you with a prioritized list of syndromes based on a radiograph, how likely are you to consider integrating it into your current diagnostic workflow?