diff --git a/content/authors/admin/_index.md b/content/authors/admin/_index.md index 313a3a9..69f459b 100644 --- a/content/authors/admin/_index.md +++ b/content/authors/admin/_index.md @@ -6,28 +6,31 @@ title: Filippo Corponi superuser: true # Role/position/tagline -role: MD, MSc, PhD student +role: MD, MScR, PhD # Organizations/Affiliations to show in About widget -organizations: -- name: The University of Edinburgh - url: https://www.ucl.ac.uk/ +# organizations: +# - name: The University of Edinburgh +# url: https://www.ed.ac.uk/ # Short bio (displayed in user profile at end of posts) bio: # Interests to show in About widget interests: - - Artificial Intelligence - Mental health - Wearables - - Digital Psychiatry + - Machine Learning + - Precision Psychiatry # Education to show in About widget education: courses: + - course: PhD in Biomedical AI + institution: University of Edinburgh, School of Informatics + year: 2024 - course: MSc by Research in Biomedical AI - institution: University of Edinburgh + institution: University of Edinburgh, School of Informatics year: 2021 - course: Specialty in Psychiatry institution: University of Bologna @@ -77,12 +80,12 @@ social: # link: uploads/resume.pdf # Enter email to display Gravatar (if Gravatar enabled in Config) -email: "filippo.corponi@ed.ac.uk" +email: "filippo.corponi@gmail.com" # Highlight the author in author lists? (true/false) highlight_name: true --- -I am a medical consultant in General Adult Psychiatry at NHS Lothian and a UKRI-funded PhD student in Biomedical Artificial Intelligence at the University of Edinburgh, School of Informatics. I am a member of the [Centre for Doctoral Training in Biomedical AI](https://web.inf.ed.ac.uk/cdt/biomedical-ai) and part of the [APRIL research lab](https://april-tools.github.io/), supervised by [Dr. Antonio Vergari](http://nolovedeeplearning.com/), [Prof. Stephen Lawrie](https://www.ed.ac.uk/profile/professor-stephen-lawrie), and [Prof. Heather Whalley](https://www.ed.ac.uk/profile/dr-heather-whalley). +I am a medical consultant in General Adult Psychiatry at NHS Lothian and former member of the [Centre for Doctoral Training in Biomedical AI](https://web.inf.ed.ac.uk/cdt/biomedical-ai) at the University of Edinburgh, School of Informatics. I am interested in developing personalized, scalable, and trustworthy approaches to improving patients' lives through Artificial Intelligence. diff --git a/content/home/experience.md b/content/home/experience.md index 2d85f72..576ae68 100644 --- a/content/home/experience.md +++ b/content/home/experience.md @@ -30,18 +30,6 @@ experience: date_start: '2022-05-01' date_end: '' description: |2- - - - title: PhD student in Biomedical AI - company: University of Edinburgh - company_url: '' - company_logo: org-uoe - location: Edinburgh, UK - date_start: '2021-09-01' - date_end: '' - description: |2- - Supervised by [Dr. Antonio Vergari](http://nolovedeeplearning.com/) - * Fully funded by [UKRI](https://www.ukri.org/). - * Research topics: 1) digital phenotyping; 2) machine learning for mental healthcare. - title: Visiting Research Assistant company: King's College London, UK diff --git a/content/publication/corponi-mario-2023/cite.bib b/content/publication/corponi-mario-2023/cite.bib deleted file mode 100644 index d652091..0000000 --- a/content/publication/corponi-mario-2023/cite.bib +++ /dev/null @@ -1,16 +0,0 @@ - -@misc{corponi_wearable_2023, - title = {Wearable data from subjects playing Super Mario, sitting university exams, or performing physical exercise help detect acute mood episodes via self-supervised learning}, - url = {http://arxiv.org/abs/2311.04215}, - doi = {10.48550/arXiv.2311.04215}, - abstract = {Personal sensing, leveraging data passively and near-continuously collected with wearables from patients in their ecological environment, is a promising paradigm to monitor mood disorders ({MDs}), a major determinant of worldwide disease burden. However, collecting and annotating wearable data is very resource-intensive. Studies of this kind can thus typically afford to recruit only a couple dozens of patients. This constitutes one of the major obstacles to applying modern supervised machine learning techniques to {MDs} detection. In this paper, we overcome this data bottleneck and advance the detection of {MDs} acute episode vs stable state from wearables data on the back of recent advances in self-supervised learning ({SSL}). This leverages unlabelled data to learn representations during pre-training, subsequently exploited for a supervised task. First, we collected open-access datasets recording with an Empatica E4 spanning different, unrelated to {MD} monitoring, personal sensing tasks -- from emotion recognition in Super Mario players to stress detection in undergraduates -- and devised a pre-processing pipeline performing on-/off-body detection, sleep-wake detection, segmentation, and (optionally) feature extraction. With 161 E4-recorded subjects, we introduce E4SelfLearning, the largest to date open access collection, and its pre-processing pipeline. Second, we show that {SSL} confidently outperforms fully-supervised pipelines using either our novel E4-tailored Transformer architecture (E4mer) or classical baseline {XGBoost}: 81.23\% against 75.35\% (E4mer) and 72.02\% ({XGBoost}) correctly classified recording segments from 64 (half acute, half stable) patients. Lastly, we illustrate that {SSL} performance is strongly associated with the specific surrogate task employed for pre-training as well as with unlabelled data availability.}, - number = {{arXiv}:2311.04215}, - publisher = {{arXiv}}, - author = {Corponi, Filippo and Li, Bryan M. and Anmella, Gerard and Valenzuela-Pascual, Clàudia and Mas, Ariadna and Pacchiarotti, Isabella and Valentí, Marc and Grande, Iria and Benabarre, Antonio and Garriga, Marina and Vieta, Eduard and Young, Allan H. and Lawrie, Stephen M. and Whalley, Heather C. and Hidalgo-Mazzei, Diego and Vergari, Antonio}, - urldate = {2024-06-11}, - date = {2023-11-07}, - eprinttype = {arxiv}, - eprint = {2311.04215 [cs, eess]}, - keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Signal Processing}, - file = {arXiv Fulltext PDF:/Users/filippo/Zotero/storage/UJ8V7XPV/Corponi et al. - 2023 - Wearable data from subjects playing Super Mario, s.pdf:application/pdf;arXiv.org Snapshot:/Users/filippo/Zotero/storage/2AGGEQX4/2311.html:text/html}, -} diff --git a/content/publication/corponi-mario-2023/index.md b/content/publication/corponi-mario-2023/index.md index ddbb592..5a1d628 100644 --- a/content/publication/corponi-mario-2023/index.md +++ b/content/publication/corponi-mario-2023/index.md @@ -1,5 +1,5 @@ --- -title: 'Wearable data from students, teachers or subjects with alcohol use disorder help detect acute mood episodes via self-supervised learning' +title: 'Wearable Data From Subjects Playing Super Mario, Taking University Exams, or Performing Physical Exercise Help Detect Acute Mood Disorder Episodes via Self-Supervised Learning: Prospective, Exploratory, Observational Study' authors: - admin - Bryan M Li @@ -17,11 +17,11 @@ authors: - Heather C Whalley - Diego Hidalgo-Mazzei - Antonio Vergari -date: '2024-05-26' -publishDate: '2023-11-07T22:13:28.838395Z' +date: '2024-07-17' +publishDate: '2024-07-07T22:13:28.838395Z' publication_types: - '3' featured: true publication: 'JMIR mHealth and uHealth' -url_pdf: "https://arxiv.org/abs/2311.04215" +url_pdf: https://mhealth.jmir.org/2024/1/e55094" --- diff --git a/static/uploads/resume.pdf b/static/uploads/resume.pdf index 5058d13..0fe52c7 100644 Binary files a/static/uploads/resume.pdf and b/static/uploads/resume.pdf differ