Clinical trials

Objective: To evaluate the impact of real-time AI feedback on fetal biometry accuracy and investigate the Expertise Reversal Effect-whether AI benefits diminish as user experience increases. Design: A stratified randomized trial of 75 participants (25 Novices, 25 Intermediates, 25 Experts). Users are randomized 1:1 to either AI-assisted or manual measurement groups. Outcomes: * Primary: EFW accuracy (MAPE) compared to actual birthweight. * Secondary: Procedure time, image quality, error relative to baseline scans, and cognitive workload (NASA-TLX).

The goal of this randomized controlled study is to compare the effect of a new, personalized uncertainty-aware decision model (FDM) to a standard image recognition model in improving the diagnostic accuracy while reducing diagnostic uncertainty in experienced dermatologists tasked with differentiating between melanomas, moles and other benign skin lesions. The main question it aims to answer: Is the FDM a feasible method for an improved human AI partnership in which trust is build, misdiagnoses are avoided, and uncertainty is duly introduced or reduced. The investigators expect to see only a slight increase in collective diagnostic accuracy for both interventions as the the human participants are skilled dermatologist and thus have high accuracies pre-intervention. The investigators expect to see a higher increase in diagnostic certainty for the FDM intervention compared to the diagnostic certainty in the Base Model intervention. The investigators expect to see a higher amount of diagnosis changes from incorrect to correct in the FDM group compared to the Base Model group. The investigators do not expect any learning effect during the study. Participants will start by answering a series of training cases consisting of images of skin lesions. These are used to train their individual FDM (only for the FDM-intervention group). From here, the participants will be randomized into two arms determining which of the two interventions they are exposed to. The participants will solve each case withouth any intervention first, and this reply will act as a control.

The training of orthopedic surgeons has historically relied heavily on an apprenticeship model as the primary way of teaching the various procedures an aspiring surgeon needs to master. However, due to work-hour restrictions, demand for operating room efficiency, lack of supervisors and a growing focus and concern for patient safety, this model is challenged. As the importance of proper education and supervision of surgeons in training is still monumental, simulation-based training (SBT) has gained popularity within most medical specialties, as it provides a safe, and realistic room for training, where surgeons can effectively enhance their operating technique without posing a threat to patient safety. Techniques within orthopedic surgery are no exception to this tendency, and several virtual reality simulators and SBT courses has been developed. This includes the well-established SBT course in proximal femoral fracture (PFF) osteosynthesis, where evidence supported mastery standards for antegrade nailing, dynamic hip screw, Hansson pins and canulated screws have been established. A course that is recommended in the national curriculum for Danish orthopedic surgeons in training. This change into a more technology- and simulation-based training does however pose challenges, that needs to be acknowledged and addressed to ensure the quality of the education and clinical skills of the orthopedic surgeons. A key challenge is the limited resource of qualified instructors. These instructors are mainly experienced surgeons with a demanding and busy schedule, who teach part time in addition to their clinical work. It has previously been shown that teaching skills are to be taught by doctors and that good clinicians are not automatically good educators. With the burden of a busy clinical schedule, these experienced surgeons have difficulties finding the time to learn teaching skills. It can therefore be challenging to educate enough qualified instructors. This poses a rising concern as the field of SBT is only expected to grow, with more courses in continuous development. Thus, potentially limiting the accessibility to orthopedic SBT courses, including the PFF course. A possible solution for this challenge is dyad introductions. By converting one-on-one introduction to SBT for trainees into one-on-two introduction, it is possible to double the number of participants getting introductions without increasing the teaching load or expenses. This could significantly reduce the needed faculty time per trainee. Several studies have shown beneficial learning outcomes of dyad training. However, it seems, that the positive effects of dyad training cannot be translated into all types of medical simulations, and some studies suggests that the complexity and nature of the simulation defines whether dyad training is beneficial . It is theorized, that the effect of dyad training is caused by the learning of motor skills through mirror neurons during observation, and the distribution of knowledge during complex simulations according to the cognitive load theory. This suggests, that dyad training may be most beneficial in complex simulations requiring high levels of motor skills such as complex surgical procedures. To our knowledge, no studies exist that examines whether dyad introduction can be equally used in the simulations of orthopedic procedures in general or PFF surgery specifically. The aim of this study was to examine whether dyad introduction is non-inferior to the current one-on- one student introduction.