Advanced diagnostic strategies for wrist trauma

We investigated clinical applications of artificial intelligence and advanced 3D imaging strategies for patients with sustained wrist trauma. In part I, we developed an online machine-learning based decision tool that can accurately predict the probability of a fracture of the distal radius after injury to the wrist. Clinicians could use the generated low and high probabilities to identify distal radius fractures. In part II, the utility of a deep learning algorithm for scaphoid fractures was tested. Initial experience with our deep learning algorithm suggests that it has trouble identifying scaphoid fractures that are obvious to human observers. In part III, a global collaborative of surgeons was surveyed. The observation that—other than age—personal factors have limited influence on surgeon recommendations for operative treatment of distal radius fractures may reflect how surgeon cognitive biases, personal preferences, different perspectives, and incentives may contribute to variations in care. Part IV determined whether the reliability of assessing specific fracture characteristics as well as classification that guide surgical decision-making for distal radius fractures improve with 3-D printed handheld models? We found that intersurgeon reliability for evaluating the characteristics of and classifying intraarticular distal radius fractures did not improve with an additional 3-D model. Part V investigated whether intraoperative 3D fluoroscopic imaging outperforms dorsal tangential views in the detection of dorsal cortex screw penetration after volar plating of an intra-articular distal radial fracture, as identified on postoperative CT imaging. One cannot conclude that 3D fluoroscopy outperforms dorsal tangential views when used for this purpose.