Artificial intelligence in general, and machine learning(ML)-based applications in particular, have the potential to change the scope of Orthopaedic surgery. According the technology hype cycle, we are currently coming to realize that incorporating these algorithms into the clinical workflows and electronic health record will be critical for unlocking these algorithms’ potential.
Ongoing projects include clinical applications and scenarios using ML-derived clinical decision support tools, deep learning-based computer vision and natural language processing:
- Feasibility of Machine Learning and Logistic Regression Algorithms to Predict Outcome in Orthopaedic Trauma Surgery
- Development of machine learning algorithms for preoperative prediction of postoperative delirium in geriatric hip fracture patients
- What is the impact of predictor heterogeneity on external validation of machine learning algorithms? A case study of hip fracture patients from two continents
- Surgical decision-making and implant choice: development of clinical prediction tools to predict 90 day and 2 year mortality in elderly femoral neck fracture patients
- Can we develop a sustainable human-artificial intelligence assisted strategy for fracture annotation? A machine learning approach for body part recognition, hardware detection, fracture detection and classification.
- International examination of the translational capacity of natural language processing algorithms for incidental durotomy
- What is the Difference in Survival and Complication Profile Between Patients Undergoing Surgery for an Impending versus a Pathologic Fracture in Metastatic Bone Disease?
