Stelios Georgiou

Joshua Harris, Timothy Laurence, Leo Loman et al.

Advances in Large Language Models (LLMs) have led to significant interest in their potential to support human experts across a range of domains, including public health. In this work we present automated evaluations of LLMs for public health tasks involving the classification and extraction of free text. We combine six externally annotated datasets with seven new internally annotated datasets to evaluate LLMs for processing text related to: health burden, epidemiological risk factors, and public health interventions. We evaluate eleven open-weight LLMs (7-123 billion parameters) across all tasks using zero-shot in-context learning. We find that Llama-3.3-70B-Instruct is the highest performing model, achieving the best results on 8/16 tasks (using micro-F1 scores). We see significant variation across tasks with all open-weight LLMs scoring below 60% micro-F1 on some challenging tasks, such as Contact Classification, while all LLMs achieve greater than 80% micro-F1 on others, such as GI Illness Classification. For a subset of 11 tasks, we also evaluate three GPT-4 and GPT-4o series models and find comparable results to Llama-3.3-70B-Instruct. Overall, based on these initial results we find promising signs that LLMs may be useful tools for public health experts to extract information from a wide variety of free text sources, and support public health surveillance, research, and interventions.

Ian Miles, Mayumi Wakimoto, Wagner Meira et al.

This review explores the integration of Artificial Intelligence into Horizon Scanning, focusing on identifying and responding to emerging threats and opportunities linked to Infectious Diseases. We examine how AI tools can enhance signal detection, data monitoring, scenario analysis, and decision support. We also address the risks associated with AI adoption and propose strategies for effective implementation and governance. The findings contribute to the growing body of Foresight literature by demonstrating the potential and limitations of AI in Public Health preparedness.

Georgia Frantzeskou, Stephen G. MacDonell, Efstathios Stamatatos et al.

When writing source code, programmers have varying levels of freedom when it comes to the creation and use of identifiers. Do they habitually use the same identifiers, names that are different to those used by others? Is it then possible to tell who the author of a piece of code is by examining these identifiers? If so, can we use the presence or absence of identifiers to assist in correctly classifying programs to authors? Is it possible to hide the provenance of programs by identifier renaming? In this study, we assess the importance of three types of identifiers in source code author classification for two different Java program data sets. We do this through a sequence of experiments in which we disguise one type of identifier at a time. These experiments are performed using as a tool the Source Code Author Profiles (SCAP) method. The results show that, although identifiers when examined as a whole do not seem to reflect program authorship for these data sets, when examined separately there is evidence that class names do signal the author of the program. In contrast, simple variables and method names used in Java programs do not appear to reflect program authorship. On the contrary, our analysis suggests that such identifiers are so common as to mask authorship. We believe that these results have applicability in relation to the robustness of code plagiarism analysis and that the underlying methods could be valuable in cases of litigation arising from disputes over program authorship.

Efstratios Geronikolakis, Paul Zikas, Steve Kateros et al.

In this work, a new and innovative way of spatial computing that appeared recently in the bibliography called True Augmented Reality (AR), is employed in cultural heritage preservation. This innovation could be adapted by the Virtual Museums of the future to enhance the quality of experience. It emphasises, the fact that a visitor will not be able to tell, at a first glance, if the artefact that he/she is looking at is real or not and it is expected to draw the visitors' interest. True AR is not limited to artefacts but extends even to buildings or life-sized character simulations of statues. It provides the best visual quality possible so that the users will not be able to tell the real objects from the augmented ones. Such applications can be beneficial for future museums, as with True AR, 3D models of various exhibits, monuments, statues, characters and buildings can be reconstructed and presented to the visitors in a realistic and innovative way. We also propose our Virtual Reality Sample application, a True AR playground featuring basic components and tools for generating interactive Virtual Museum applications, alongside a 3D reconstructed character (the priest of Asinou church) facilitating the storyteller of the augmented experience.