Identifying psychosis spectrum disorder from experience sampling data using machine learning approaches
- Submitting institution
-
Goldsmiths' College
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 3077
- Type
- D - Journal article
- DOI
-
10.1016/j.schres.2019.04.028
- Title of journal
- Schizophrenia Research
- Article number
- -
- First page
- 156
- Volume
- 209
- Issue
- -
- ISSN
- 0920-9964
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2019
- URL
-
http://research.gold.ac.uk/id/eprint/26340/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
6
- Research group(s)
-
-
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The work introduces for the first time a highly accurate machine learning and mobile-health approach to predicting risk of mental health - psychosis, which contributes to optimal medical interventions. Preliminary results were presented at the very selective IEEE Machine Learning and Applications Conference. The work contributed to establishing high profile collaborations in AI/ ML prediction modelling in mental-health with Oxford, UCL, KCL, and to securing a £240,000 grant with the University of Manchester, www.alzheimersresearchuk.org/leading-charity-2-million-boost-dementia-prevention-research/ featured on BBC, which now employs the ML methods developed in this paper.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -