ABSTRACT
Fieldwork is a pedagogical cornerstone of many geoscience degrees. During the academic years 2019–20 and 2020–21, the worldwide COVID-19 pandemic made outdoors fieldwork difficult, resulting in an urgent need to develop virtual alternatives. However, there is still more to learn about the impact of teaching fieldwork virtually on the student learning experience. This study aims to assess the student learning experience during immersive and interactive three-dimensional virtual fieldwork and establish the value of digital techniques to improve the inclusivity of geosciences degrees. Quantitative and qualitative data were collected to assess students' attitudes to virtual fieldwork in comparison to outdoor fieldwork in terms of accessibility, inclusivity and their learning experience. Our results show overall positive student responses to virtual fieldwork, with over half stating it adequately replicated the learning experience of outdoor fieldwork. Students also value outdoor fieldwork for the degree of autonomy it provides, and idea-sharing with peers;yet simultaneously the majority believed outdoor fieldwork is inherently exclusionary. This study concludes that virtual fieldwork, taught using interactive 3D virtual outcrops set within virtual worlds, replicates the outdoor fieldwork learning experience as closely as possible. However, students missed some fundamental and important aspects of outdoor fieldwork, as being outside and the social interactions with peers and staff that are specific to on-location fieldwork. This study recommends the use of virtual fieldwork in addition to residential on-location fieldwork, as for a significant number of students virtual fieldwork may be a better way of accessing this valued pedagogy of the geosciences. Furthermore, virtual fieldwork has the potential to make geosciences more inclusive and attractive to a wider range of students. © 2023 The Author(s). Published with license by Taylor & Francis Group, LLC.
ABSTRACT
INTRODUCTION: Adverse drug reaction reports are usually manually assessed by pharmacovigilance experts to detect safety signals associated with drugs. With the recent extension of reporting to patients and the emergence of mass media-related sanitary crises, adverse drug reaction reports currently frequently overwhelm pharmacovigilance networks. Artificial intelligence could help support the work of pharmacovigilance experts during such crises, by automatically coding reports, allowing them to prioritise or accelerate their manual assessment. After a previous study showing first results, we developed and compared state-of-the-art machine learning models using a larger nationwide dataset, aiming to automatically pre-code patients' adverse drug reaction reports. OBJECTIVES: We aimed to determine the best artificial intelligence model identifying adverse drug reactions and assessing seriousness in patients reports from the French national pharmacovigilance web portal. METHODS: Reports coded by 27 Pharmacovigilance Centres between March 2017 and December 2020 were selected (n = 11,633). For each report, the Portable Document Format form containing free-text information filled by the patient, and the corresponding encodings of adverse event symptoms (in Medical Dictionary for Regulatory Activities Preferred Terms) and seriousness were obtained. This encoding by experts was used as the reference to train and evaluate models, which contained input data processing and machine-learning natural language processing to learn and predict encodings. We developed and compared different approaches for data processing and classifiers. Performance was evaluated using receiver operating characteristic area under the curve (AUC), F-measure, sensitivity, specificity and positive predictive value. We used data from 26 Pharmacovigilance Centres for training and internal validation. External validation was performed using data from the remaining Pharmacovigilance Centres during the same period. RESULTS: Internal validation: for adverse drug reaction identification, Term Frequency-Inverse Document Frequency (TF-IDF) + Light Gradient Boosted Machine (LGBM) achieved an AUC of 0.97 and an F-measure of 0.80. The Cross-lingual Language Model (XLM) [transformer] obtained an AUC of 0.97 and an F-measure of 0.78. For seriousness assessment, FastText + LGBM achieved an AUC of 0.85 and an F-measure of 0.63. CamemBERT (transformer) + Light Gradient Boosted Machine obtained an AUC of 0.84 and an F-measure of 0.63. External validation for both adverse drug reaction identification and seriousness assessment tasks yielded consistent and robust results. CONCLUSIONS: Our artificial intelligence models showed promising performance to automatically code patient adverse drug reaction reports, with very similar results across approaches. Our system has been deployed by national health authorities in France since January 2021 to facilitate pharmacovigilance of COVID-19 vaccines. Further studies will be needed to validate the performance of the tool in real-life settings.