Deep Learning Applications in Orthopaedics: A Systematic Review and Future Directions

Abstract

Introduction: Artificial intelligence and deep learning in orthopaedics had gained mass interest over the last years. In prior studies, researchers have demonstrated different applications, from radiographic assessment to bone tumor diagnosis. The purpose of this review is to provide an analysis of the current literature for AI and deep learning tools to identify the most used application in risk assessment, outcomes assessment, imaging, and basic science fields. Method: Searches were conducted in Pubmed, EMBASE and Google scholar up to October 31st, 2023. We identified 717 studies, of which 595 were included in the systematic review. 281 studies about radiographic assessment, 102 about spine-oriented surgery, 95 about outcomes assessment 84 about fundamental AI orthopedic education, and 33 about basic science application were included for review. Primary outcomes were measures of diagnostic accuracy, study design and reporting standards in the literature. Estimates were pooled using random-effects meta-analysis. Results: 153 different imagenology measurements for radiographic aspects were identified. 185 different machine learning algorithms were used, being the convolutional neural network architecture the most common one (73%). To improve diagnostic accuracy and speed were the most commonly used (62%). Conclusion: Heterogeneity was high between studies and extensive variation in methodology, terminology and outcome measures were noted. This can lead to an overestimation of the diagnostic accuracy of DL algorithms on medical imaging. There is an immediate need for the development of artificial intelligence-specific guidelines, to provide guidance around key issues in this field.