Predicting fractures outcomes from clinical Registry data using Artificial Intelligence Supplemented models for Evidence-informed treatment (PRAISE) study

Project description: On behalf of the Victorian Orthopaedic Trauma Outcomes Registry (VOTOR), we will establish the role of artificial intelligence (AI) deep learning to improve the prediction of clinical and longer-term patient-reported outcomes following distal radius (wrist) fractures. The PRAISE study will, for the first time, use a flexible three-stage multimodal deep learning fracture reasoning system to unlock important information from unstructured data sources including X-ray images, surgical and radiology text reports. We will compare prediction models based on existing, routinely collected clinical registry data with registry data enhanced by findings from the deep learning system, using robust, novel and specialised analytical techniques, to enhance the capability of registries to generate predictive analytics capable of guiding personalised fracture care. The study will be conducted under the auspices of an experienced, multi-disciplinary team, including national and international experts in health “big data”, clinical registries, emergency medicine and orthopaedic trauma. We will leverage from VOTOR, the largest and most comprehensive orthopaedic trauma outcomes registry worldwide to ensure feasibility, and to facilitate the rapid translation of study findings into registry practice and health data environments.

Project goals: The aim of the project is to develop cutting-edge AI algorithms for identifying key distal radius fracture characteristics and treatment details using technologies invented in the joint area of NLP and CV, via bringing in the domain expertise.