Mr David Owen
Teams and roles for David Owen
CUBRIC Data Engineer
Research student
Overview
I am Data Engineer in the Compute and Data Team at CUBRIC in the School of Psychology, Cardiff University.
My duties include the design, implementation, and maintenance of CUBRIC data pipelines. Typical pipelines may capture image data and metadata recorded during MRI sessions. This data may then be transformed according to the requirements of research staff prior to them receiving it.
I am also responsible for the administration of database systems underpinning CUBRIC's imaging informatics, High Performance Computing, and resource management software. We currently support XNAT, Slurm, and Calpendo respectively. These data sources support the centre's Business Intelligence reporting platform, which uses Elastic Stack.
Further, I am a PhD candidate in the CardiffNLP Research Group, School of Computer Science and Informatics. I am exploring the opportunities offered by NLP (Natural Language Processing) in helping to provide early healthcare intervention in occurrences of mental illness. Supervision is provided by Jose Camacho Collados and Antonio Pardiñas.
Publication
2025
- McNabb, C. B. et al. 2025. WAND: A multi-modal dataset integrating advanced MRI, MEG, and TMS for multi-scale brain analysis. Scientific Data 12, article number: 220. (10.1038/s41597-024-04154-7)
2024
- Owen, D., Lynham, A. J., Smart, S. E., Pardiñas, A. F. and Camacho Collados, J. 2024. AI for analyzing mental health disorders among social media users: Quarter-century narrative review of progress and challenges. Journal of Medical Internet Research 26, article number: e59225. (10.2196/59225)
2023
- Owen, D., Antypas, D., Hassoulas, A., Pardinas, A., Espinosa-Anke, L. and Camacho Collados, J. 2023. Enabling early health care intervention by detecting depression in users of web-based forums using Language models: longitudinal analysis and evaluation. JMIR AI 2, article number: e41205. (10.2196/41205)
2021
- Koller, K. et al. 2021. MICRA: Microstructural Image Compilation with Repeated Acquisitions. NeuroImage 225, article number: 117406. (10.1016/j.neuroimage.2020.117406)
2020
- Owen, D., Camacho Collados, J. and Espinosa-Anke, L. 2020. Towards preemptive detection of depression and anxiety in Twitter. Presented at: Social Media Mining for Health Applications Workshop & Shared Task 2020, Barcelona, Spain, 8-13 December 2020 Presented at Gonzalez-Hernandez, G. et al. eds.Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task. Association for Computational Linguistics pp. 82-89.
- Owen, D. et al. 2020. Towards a scientific workflow featuring Natural Language Processing for the digitisation of natural history collections.[Version 2]. Research Ideas and Outcomes 6, article number: e58030. (10.3897/rio.6.e58030)
- Owen, D. et al. 2020. Towards a scientific workflow featuring Natural Language Processing for the digitisation of natural history collections [Version 1]. Research Ideas and Outcomes 6, article number: e55789. (10.3897/rio.6.e55789)
- Button, K., Spasic, I., Playle, R., Owen, D., Lau, M., Hannaway, L. and Jones, S. 2020. Using routine referral data for patients with knee and hip pain to improve access to specialist care. BMC Musculoskeletal Disorders 21, article number: 66. (10.1186/s12891-020-3087-x)
2019
- Spasic, I., Owen, D., Smith, A. and Button, K. 2019. KLOSURE: Closing in on open–ended patient questionnaires with text mining. Journal of Biomedical Semantics 10(S1), article number: 24. (10.1186/s13326-019-0215-3)
- Spasic, I., Owen, D., Knight, D. and Artemiou, A. 2019. Unsupervised multi-word term recognition in Welsh. Presented at: Celtic Language Technology Workshop 2019, Dublin, Ireland, 19 August 2019 Presented at Lynn, T. et al. eds.Proceedings of the Celtic Language Technology Workshop. European Association for Machine Translation
- Nieva De La Hidalga, A., Owen, D., Spasic, I., Rosin, P. and Sun, X. 2019. Use of semantic segmentation for increasing the throughput of digitisation workflows for natural history collections. Presented at: Biodiversity_Next 2019, Leiden, The Netherlands, 21-25 October 2019Biodiversity Information Science and Standards, Vol. 3. Vol. e37161. Pensoft, (10.3897/biss.3.37161)
2018
- Spasic, I., Owen, D., Smith, A. and Button, K. 2018. Closing in on open-ended patient questionnaires with text mining. Presented at: UK Healthcare Text Analytics Conference (HealTAC), Manchester, UK, 18-19 April 2018.
- Button, K., Owen, D., Lau, T., Spasic, I., Playle, R., Hannaway, L. and Jones, S. 2018. Improving access to care and treatment for patients with hip and knee pain at the interface between primary and secondary care. Presented at: OARSI 2018 World Congress on Osteoarthritis, Liverpool, UK, 26-29 April 2018.
Articles
- McNabb, C. B. et al. 2025. WAND: A multi-modal dataset integrating advanced MRI, MEG, and TMS for multi-scale brain analysis. Scientific Data 12, article number: 220. (10.1038/s41597-024-04154-7)
- Owen, D., Lynham, A. J., Smart, S. E., Pardiñas, A. F. and Camacho Collados, J. 2024. AI for analyzing mental health disorders among social media users: Quarter-century narrative review of progress and challenges. Journal of Medical Internet Research 26, article number: e59225. (10.2196/59225)
- Owen, D., Antypas, D., Hassoulas, A., Pardinas, A., Espinosa-Anke, L. and Camacho Collados, J. 2023. Enabling early health care intervention by detecting depression in users of web-based forums using Language models: longitudinal analysis and evaluation. JMIR AI 2, article number: e41205. (10.2196/41205)
- Koller, K. et al. 2021. MICRA: Microstructural Image Compilation with Repeated Acquisitions. NeuroImage 225, article number: 117406. (10.1016/j.neuroimage.2020.117406)
- Owen, D. et al. 2020. Towards a scientific workflow featuring Natural Language Processing for the digitisation of natural history collections.[Version 2]. Research Ideas and Outcomes 6, article number: e58030. (10.3897/rio.6.e58030)
- Owen, D. et al. 2020. Towards a scientific workflow featuring Natural Language Processing for the digitisation of natural history collections [Version 1]. Research Ideas and Outcomes 6, article number: e55789. (10.3897/rio.6.e55789)
- Button, K., Spasic, I., Playle, R., Owen, D., Lau, M., Hannaway, L. and Jones, S. 2020. Using routine referral data for patients with knee and hip pain to improve access to specialist care. BMC Musculoskeletal Disorders 21, article number: 66. (10.1186/s12891-020-3087-x)
- Spasic, I., Owen, D., Smith, A. and Button, K. 2019. KLOSURE: Closing in on open–ended patient questionnaires with text mining. Journal of Biomedical Semantics 10(S1), article number: 24. (10.1186/s13326-019-0215-3)
Conferences
- Owen, D., Camacho Collados, J. and Espinosa-Anke, L. 2020. Towards preemptive detection of depression and anxiety in Twitter. Presented at: Social Media Mining for Health Applications Workshop & Shared Task 2020, Barcelona, Spain, 8-13 December 2020 Presented at Gonzalez-Hernandez, G. et al. eds.Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task. Association for Computational Linguistics pp. 82-89.
- Spasic, I., Owen, D., Knight, D. and Artemiou, A. 2019. Unsupervised multi-word term recognition in Welsh. Presented at: Celtic Language Technology Workshop 2019, Dublin, Ireland, 19 August 2019 Presented at Lynn, T. et al. eds.Proceedings of the Celtic Language Technology Workshop. European Association for Machine Translation
- Nieva De La Hidalga, A., Owen, D., Spasic, I., Rosin, P. and Sun, X. 2019. Use of semantic segmentation for increasing the throughput of digitisation workflows for natural history collections. Presented at: Biodiversity_Next 2019, Leiden, The Netherlands, 21-25 October 2019Biodiversity Information Science and Standards, Vol. 3. Vol. e37161. Pensoft, (10.3897/biss.3.37161)
- Spasic, I., Owen, D., Smith, A. and Button, K. 2018. Closing in on open-ended patient questionnaires with text mining. Presented at: UK Healthcare Text Analytics Conference (HealTAC), Manchester, UK, 18-19 April 2018.
- Button, K., Owen, D., Lau, T., Spasic, I., Playle, R., Hannaway, L. and Jones, S. 2018. Improving access to care and treatment for patients with hip and knee pain at the interface between primary and secondary care. Presented at: OARSI 2018 World Congress on Osteoarthritis, Liverpool, UK, 26-29 April 2018.
Biography
Education and qualifications
In progress: PhD Computer Science and Informatics, Cardiff University
2015: MSc Advanced Computer Science, Cardiff University
2005: BSc Computer Science, Swansea University
Career overview
2019 - present: Data Engineer, CUBRIC (Cardiff University Brain Research Imaging Centre), Cardiff University
2016 - 2019: Research Associate, School of Computer Science and Informatics, Cardiff University
Between 2006 and 2014 I held a series of developer analyst and application support analyst positions at non-profit organisations and private enterprises.
Speaking engagements
- Publication video: "Predicting Mental Health with AI: The Future of Social Media and Well-being" for JMIR Publications, 16th December 2024
- Article presentation: "Towards Preemptive Detection of Depression and Anxiety in Twitter" at Social Media Mining for Health Applications Workshop & Shared Task 2020 | COLING 2020, Barcelona, Spain, 12th December 2020
- Poster presentation: "KneeQApp: Supporting self-management of knee conditions with question answering" at UK Healthcare Text Analytics Conference (HealTAC), Manchester, UK, 18th-19th April 2018
- Invited talk: "FlexiTerm Cymraeg - A flexible term recognition method for the Welsh language" at the Dissemination event for the Welsh Natural Language Toolkit, University of South Wales, Treforest, UK, 25th May 2017
Committees and reviewing
- Program committee, International AAAI Conference on Web and Social Media (ICWSM) 2025 (2025)
- Journal reviewer, Social Network Analysis and Mining (2025)
- Journal reviewer, The Journal of Supercomputing (2025)
- Journal reviewer, Discover Mental Health (2024)
- Journal reviewer, Information Fusion (2024)
- Conference reviewer, International AAAI Conference on Web and Social Media (ICWSM) 2024 (2023)
- Journal reviewer, International Journal of Medical Informatics (2018, 2021-2023)
- Journal reviewer, Digital Health (2023)
- Journal reviewer, Biodiversity Data Journal (2018)
- Athena SWAN Self-Assessment Team member, School of Computer Science and Informatics (2017-2019)
Contact Details
+44 29208 70090
Cardiff University Brain Research Imaging Centre, Maindy Road, Cardiff, CF24 4HQ
Research themes
Specialisms
- Health informatics and information systems
- Natural language processing
- Data mining and knowledge discovery
- Machine learning