Desmoid tumours are a rare fibroblastic proliferation of monoclonal origin, arising in deep soft-tissues. Histologically, they are characterized by locally aggressive behaviour and an inability to metastasize, and clinically by a heterogeneous and unpredictable course. Desmoid tumours can occur in any anatomical site, but commonly arise in the limbs. Despite their benign nature, they can be extremely disabling and sometimes life-threatening, causing severe pain and functional limitations. Their surgical management is complex and challenging, due to uncertainties surrounding the biological and clinical behaviour, rarity, and limited available literature. Resection has been the first-line approach for patients with a desmoid tumour but, during the last few decades, a shift towards a more conservative approach has occurred, with an initial ‘wait and see’ policy. Many medical and regional forms of treatment are also available for the management of this condition, and others have recently emerged with promising results. However, many areas of controversy remain, and further studies and global collaboration are needed to obtain prospective and randomized data, in order to develop an appropriate shared stepwise approach. Cite this article:
Artificial intelligence and machine-learning analytics have gained extensive popularity in recent years due to their clinically relevant applications. A wide range of proof-of-concept studies have demonstrated the ability of these analyses to personalize risk prediction, detect implant specifics from imaging, and monitor and assess patient movement and recovery. Though these applications are exciting and could potentially influence practice, it is imperative to understand when these analyses are indicated and where the data are derived from, prior to investing resources and confidence into the results and conclusions. In this article, we review the current benefits and potential limitations of machine-learning for the orthopaedic surgeon with a specific emphasis on data quality.
