Protecting patient privacy in healthcare records is a top priority, and redaction is a commonly used method for obscuring directly identifiable information in text. Rule-based methods have been widely used, but their precision is often low causing over-redaction of text and frequently not being adaptable enough for non-standardised or unconventional structures of personal health information. Deep learning techniques have emerged as a promising solution, but implementing them in real-world environments poses challenges due to the differences in patient record structure and language across different departments, hospitals, and countries. In this study, we present AnonCAT, a transformer-based model and a blueprint on how deidentification models can be deployed in real-world healthcare. AnonCAT was trained through a process involving manually annotated redactions of real-world documents from three UK hospitals with different electronic health record systems and 3116 documents. The model achieved high performance in all three hospitals with a Recall of 0.99, 0.99 and 0.96. Our findings demonstrate the potential of deep learning techniques for improving the efficiency and accuracy of redaction in global healthcare data and highlight the importance of building workflows which not just use these models but are also able to continually fine-tune and audit the performance of these algorithms to ensure continuing effectiveness in real-world settings. This approach provides a blueprint for the real-world use of de-identifying algorithms through fine-tuning and localisation, the code together with tutorials is available on GitHub (https://github.com/CogStack/MedCAT).

Several solutions exist for semantically describing Web Services (WSs) from the perspective of orchestration but little is known about how semantics benefit WS choreography. The most extreme example of a choreography problem occurs in peer-to-peer systems where shared semantics of data may need to be established via services interactions. We present a solution to this problem by sharing micro-data via interaction models. No pre-unified ontology is required in our approach so peers can make use of existing heterogeneous resources having been described in the RDF data model flexibly and compatibly. The experimental results indicate that our approach semantically enhances WS choreography in a lightweight way which complies with principles of Linked Data and republished Interaction Models (IMs) can further facilitate the progress of the Web of data as well as the formation of peer communities generated through peers' interactions.