Predicting Depression Risk in Patients with Cancer Using Multimodal Data
Publication date
2023-05-18
Authors
de Hond, Anne A.H.
Van Buchem, Marieke
Fanconi, Claudio
Roy, Mohana
Blayney, Douglas
Kant, Ilse M J
Steyerberg, Ewout W
Hernandez-Boussard, Tina
Editors
Hagglund, Maria
Blusi, Madeleine
Bonacina, Stefano
Nilsson, Lina
Madsen, Inge Cort
Pelayo, Sylvia
Moen, Anne
Benis, Arriel
Lindskold, Lars
Gallos, Parisis
Advisors
Supervisors
Document Type
Part of book
Metadata
Show full item recordCollections
License
cc_by_nc
Abstract
When patients with cancer develop depression, it is often left untreated. We developed a prediction model for depression risk within the first month after starting cancer treatment using machine learning and Natural Language Processing (NLP) models. The LASSO logistic regression model based on structured data performed well, whereas the NLP model based on only clinician notes did poorly. After further validation, prediction models for depression risk could lead to earlier identification and treatment of vulnerable patients, ultimately improving cancer care and treatment adherence.
Keywords
depression, machine learning, Natural Language Processing, oncology, Biomedical Engineering, Health Informatics, Health Information Management
Citation
De Hond, A, Van Buchem, M, Fanconi, C, Roy, M, Blayney, D, Kant, I, Steyerberg, E & Hernandez-Boussard, T 2023, Predicting Depression Risk in Patients with Cancer Using Multimodal Data. in M Hagglund, M Blusi, S Bonacina, L Nilsson, I C Madsen, S Pelayo, A Moen, A Benis, L Lindskold & P Gallos (eds), Caring is Sharing - Exploiting the Value in Data for Health and Innovation - Proceedings of MIE 2023. vol. 302, Studies in Health Technology and Informatics, vol. 302, IOS Press, pp. 817-818, 33rd Medical Informatics Europe Conference: Caring is Sharing - Exploiting the Value in Data for Health and Innovation, MIE2023, Gothenburg, Sweden, 22/05/23. https://doi.org/10.3233/SHTI230274, conference