The joint research group at the University of Mannheim and the University Medical Center Mannheim is investigating the explainability of radiological decision support systems based on artificial intelligence (AI). Existing technologies for explaining AI advice were designed for AI developers but are not sufficiently meaningful for clinical decisions. Using a novel, hybrid AI approach, they have developed a new explanation method that takes into account radiology-informed diagnostic principles and thus improves the understandability and trustworthiness of automated diagnostic recommendations.
To gain further insights into our hybrid approach of radiology-based AI explanations, they kindly invite you as a resident, specialist, or senior physician in radiology to participate in a study. Your clinical background will help to better adapt the technologies to the actual working environment. At the same time, you can gain exciting insights into the development progress of AI systems.
The study is conducted as an online experiment and takes less than 15 minutes and is open until 30 September. It includes short questions on previous AI use, the detection of pulmonary nodules in CT imaging, and a final survey on the understandability of AI support.
Your answers will be treated anonymously and confidentially so that your identity cannot be traced. As a thank you for your time, they are giving away ten Amazon vouchers worth €50 each among all participants. If you are interested, they will also be pleased to send you the most important results afterwards. You can access the online experiment here:
If you have any further questions about the study or require additional information, please do not hesitate to contact them by e-mail (oberste@uni-mannheim.de) or phone (+49 (0) 151 7000 1994).
