TWTimothy Wilton

Timothy Wilton

*This is an algorithmically generated author record based on publicly available information.

Timothy Wilton has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    An AI-Based Approach for the Automatic Classification and Labeling of Joint Implants Using Registry Taxonomy and Manufacturer Data: A PoC Study with an Application in a Real-World Framework

    by Tiziana Falcone, Enrico Ciminello, Mascia Masciocchi, Alessandro Mentuccia, Marco Davide Forlani, Martina Barral, Martina Zanforlini, Duilio Luca Bacocco, Eugenio Carrani, Fernanda Gellona, et al.

    Joint replacement registries are essential for post-market surveillance; however, medical device (MD) classification dictionaries often rely on manual processes and heterogeneous data sources, limiting efficiency and standardization. The aim of this study was to design and validate, as a proof of concept (PoC), an artificial intelligence (AI) classification system for hip and knee implants, leveraging registry taxonomies and manufacturer technical documents to overcome the above limitations. A PoC study was conducted using a custom-built dataset derived from the Italian Arthroplasty Registry (RIAP) MD-Dictionary, the UK National Joint Registry MD-Classification, and 49 manufacturer documents. A convolutional neural network (CNN) and a transformer-based model (BioBERT) were evaluated. Model performance was assessed on a validation dataset (49 documents) and an external test set (25 documents) using standard metrics and a comparison with manual extraction. BioBERT outperformed the CNN across main evaluation metrics (precision 94.62% vs. 67.18%, recall 88.45% vs. 75.82%, and F1-score 91.43% vs. 71.24%). Processing times were reduced from over 22 h for manual extraction to 4 min for CNN and 27 min for BioBERT. The results show that this AI module-PoC enables the extraction of structured data from technical documents and enhances data completeness and surveillance capabilities by integrating NLP-based automation into MD registries.

  • Camouflage uncovered: what should happen next?

    by Tim Wilton, John A. Skinner, Fares S. Haddad

    Recent publications have drawn attention to the fact that some brands of joint replacement may contain variants which perform significantly worse (or better) than their ‘siblings’. As a result, the National Joint Registry has performed much more detailed analysis on the larger families of knee arthroplasties in order to identify exactly where these differences may be present and may hitherto have remained hidden. The analysis of the Nexgen knee arthroplasty brand identified that some posterior-stabilized combinations have particularly high revision rates for aseptic loosening of the tibia, and consequently a medical device recall has been issued for the Nexgen ‘option’ tibial component which was implicated. More elaborate signal detection is required in order to identify such variation in results in a routine fashion if patients are to be protected from such variation in outcomes between closely related implant types.Cite this article: Bone Joint J 2023;105-B(3):221–226.


  • Open Access

    Implementing large-scale data quality validation in a national arthroplasty registry to improve compliance

    by Christopher Boulton, Carol Harrison, Timothy Wilton, Richard Armstrong, Elaine Young, Derek Pegg, J. Mark Wilkinson

    Data of high quality are critical for the meaningful interpretation of registry information. The National Joint Registry (NJR) was established in 2002 as the result of an unexpectedly high failure rate of a cemented total hip arthroplasty. The NJR began data collection in 2003. In this study we report on the outcomes following the establishment of a formal data quality (DQ) audit process within the NJR, within which each patient episode entry is validated against the hospital unit’s Patient Administration System and vice-versa. This process enables bidirectional validation of every NJR entry and retrospective correction of any errors in the dataset. In 2014/15 baseline average compliance was 92.6% and this increased year-on-year with repeated audit cycles to 96.0% in 2018/19, with 76.4% of units achieving > 95% compliance. Following the closure of the audit cycle, an overall compliance rate of 97.9% was achieved for the 2018/19 period. An automated system was initiated in 2018 to reduce administrative burden and to integrate the DQ process into standard workflows. Our processes and quality improvement results demonstrate that DQ may be implemented successfully at national level, while minimizing the burden on hospitals. Cite this article: Bone Jt Open 2022;3(9):716–725.