Your browser doesn't support javascript.
loading
Prediction of depression treatment outcome from multimodal data: a CAN-BIND-1 report.
Sajjadian, Mehri; Uher, Rudolf; Ho, Keith; Hassel, Stefanie; Milev, Roumen; Frey, Benicio N; Farzan, Faranak; Blier, Pierre; Foster, Jane A; Parikh, Sagar V; Müller, Daniel J; Rotzinger, Susan; Soares, Claudio N; Turecki, Gustavo; Taylor, Valerie H; Lam, Raymond W; Strother, Stephen C; Kennedy, Sidney H.
Afiliação
  • Sajjadian M; Department of Psychiatry, Dalhousie University, Halifax, NS, Canada.
  • Uher R; Department of Psychiatry, Dalhousie University, Halifax, NS, Canada.
  • Ho K; University Health Network, 399 Bathurst Street, Toronto, ON, M5T 2S8, Canada.
  • Hassel S; Unity Health Toronto, St. Michael's Hospital, 193 Yonge Street, 6th floor, Toronto, ON, M5B 1M4, Canada.
  • Milev R; Department of Psychiatry and Mathison Centre for Mental Health Research and Education, Cumming School of Medicine, University of Calgary, 3330 Hospital Dr NW, Calgary, AB, T2N 4N1, Canada.
  • Frey BN; Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada.
  • Farzan F; Departments of Psychiatry and Psychology, Queen's University, Providence Care Hospital, Kingston, ON, Canada.
  • Blier P; Department of Psychiatry and Behavioural Neurosciences, McMaster University, Hamilton, ON, Canada.
  • Foster JA; Mood Disorders Program and Women's Health Concerns Clinic, St. Joseph's Healthcare Hamilton, Hamilton, ON, Canada.
  • Parikh SV; eBrain Lab, School of Mechatronic Systems Engineering, Simon Fraser University, Surrey, BC, Canada.
  • Müller DJ; The Royal's Institute of Mental Health Research, 1145 Carling Avenue, Ottawa, ON, K1Z 7K4, Canada.
  • Rotzinger S; Department of Cellular and Molecular Medicine, University of Ottawa, 451 Smyth Road, Ottawa, ON, K1H 8M5, Canada.
  • Soares CN; Department of Psychiatry, University of Ottawa, 1145 Carling Avenue, Ottawa, ON, K1Z 7K4, Canada.
  • Turecki G; Department of Psychiatry & Behavioural Neurosciences, St Joseph's Healthcare, Hamilton, ON, Canada.
  • Taylor VH; Department of Psychiatry, University of Michigan, Ann Arbor, MI, USA.
  • Lam RW; Campbell Family Mental Health Research Institute, Center for Addiction and Mental Health, Toronto, ON, Canada.
  • Strother SC; Department of Psychiatry, University of Toronto, Toronto, ON, Canada.
  • Kennedy SH; Department of Psychiatry, University of Toronto, Toronto, ON, Canada.
Psychol Med ; 53(12): 5374-5384, 2023 09.
Article em En | MEDLINE | ID: mdl-36004538
ABSTRACT

BACKGROUND:

Prediction of treatment outcomes is a key step in improving the treatment of major depressive disorder (MDD). The Canadian Biomarker Integration Network in Depression (CAN-BIND) aims to predict antidepressant treatment outcomes through analyses of clinical assessment, neuroimaging, and blood biomarkers.

METHODS:

In the CAN-BIND-1 dataset of 192 adults with MDD and outcomes of treatment with escitalopram, we applied machine learning models in a nested cross-validation framework. Across 210 analyses, we examined combinations of predictive variables from three modalities, measured at baseline and after 2 weeks of treatment, and five machine learning methods with and without feature selection. To optimize the predictors-to-observations ratio, we followed a tiered approach with 134 and 1152 variables in tier 1 and tier 2 respectively.

RESULTS:

A combination of baseline tier 1 clinical, neuroimaging, and molecular variables predicted response with a mean balanced accuracy of 0.57 (best model mean 0.62) compared to 0.54 (best model mean 0.61) in single modality models. Adding week 2 predictors improved the prediction of response to a mean balanced accuracy of 0.59 (best model mean 0.66). Adding tier 2 features did not improve prediction.

CONCLUSIONS:

A combination of clinical, neuroimaging, and molecular data improves the prediction of treatment outcomes over single modality measurement. The addition of measurements from the early stages of treatment adds precision. Present results are limited by lack of external validation. To achieve clinically meaningful prediction, the multimodal measurement should be scaled up to larger samples and the robustness of prediction tested in an external validation dataset.
Assuntos
Palavras-chave

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Transtorno Depressivo Maior Tipo de estudo: Prognostic_studies / Risk_factors_studies Limite: Adult / Humans País como assunto: America do norte Idioma: En Ano de publicação: 2023 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Transtorno Depressivo Maior Tipo de estudo: Prognostic_studies / Risk_factors_studies Limite: Adult / Humans País como assunto: America do norte Idioma: En Ano de publicação: 2023 Tipo de documento: Article