Antidepressant drug-specific prediction of depression treatment outcomes from genetic and clinical variables

Raquel Iniesta; Karen Hodgson; Daniel Richard Stahl; Karim Malki; Wolfgang Maier; Marcella Rietschel; Ole Mors; Joanna Hauser; Neven Henigsberg; Mojca Zvezdana Dernovšek; Daniel Souery; Richard Dobson; Katherine. J Aitchison; Anne  Farmer; Peter McGuffin; Cathryn M. Lewis; Rudolf Uher

doi:10.1038/s41598-018-23584-z

Antidepressant drug-specific prediction of depression treatment outcomes from genetic and clinical variables

Raquel Iniesta
, Karen Hodgson
, Daniel Richard Stahl
, Karim Malki
, Wolfgang Maier
, Marcella Rietschel
, Ole Mors
, Joanna Hauser
, Neven Henigsberg
, Mojca Zvezdana Dernovšek
, Daniel Souery
, Richard Dobson
, Katherine. J Aitchison
, Anne Farmer
, Peter McGuffin
, Cathryn M. Lewis
, Rudolf Uher

Research output: Contribution to journal › Article › peer-review

61 Citations (Scopus)

296 Downloads (Pure)

Abstract

Individuals with depression differ substantially in their response to treatment with antidepressants. Specific predictors explain only a small proportion of these differences. To meaningfully predict who will respond to which antidepressant, it may be necessary to combine multiple biomarkers and clinical variables. Using statistical learning on common genetic variants and clinical information in a training sample of 280 individuals randomly allocated to 12-week treatment with antidepressants escitalopram or nortriptyline, we derived models to predict remission with each antidepressant drug. We tested the reproducibility of each prediction in a validation set of 150 participants not used in model derivation. An elastic net logistic model based on eleven genetic and six clinical variables predicted remission with escitalopram in the validation dataset with area under the curve 0.77 (95%CI; 0.66-0.88; p = 0.004), explaining approximately 30% of variance in who achieves remission. A model derived from 20 genetic variables predicted remission with nortriptyline in the validation dataset with an area under the curve 0.77 (95%CI; 0.65-0.90; p < 0.001), explaining approximately 36% of variance in who achieves remission. The predictive models were antidepressant drug-specific. Validated drug-specific predictions suggest that a relatively small number of genetic and clinical variables can help select treatment between escitalopram and nortriptyline.

Original language	English
Article number	5530
Number of pages	9
Journal	Scientific Reports
Volume	8
Issue number	1
Early online date	3 Apr 2018
DOIs	https://doi.org/10.1038/s41598-018-23584-z
Publication status	Published - 3 Apr 2018

Access to Document

10.1038/s41598-018-23584-zLicence: CC BY

Antidepressant drug-specific prediction_INIESTA_Accepted14March2018_GOLD AAM (CC BY)Accepted author manuscript, 803 KBLicence: CC BY
Antidepressant drug-specifc_INIESTA_Accepted13March2018_GOLD VoR (CC BY)Final published version, 1.16 MBLicence: CC BY

Cite this

Iniesta, R., Hodgson, K., Stahl, D. R., Malki, K., Maier, W., Rietschel, M., Mors, O., Hauser, J., Henigsberg, N., Dernovšek, M. Z., Souery, D., Dobson, R., Aitchison , K. J., Farmer, A., McGuffin, P., Lewis, C. M., & Uher, R. (2018). Antidepressant drug-specific prediction of depression treatment outcomes from genetic and clinical variables. Scientific Reports, 8(1), Article 5530 . https://doi.org/10.1038/s41598-018-23584-z

@article{b2fbf38029b54ebd92c3a33361f46fe1,

title = "Antidepressant drug-specific prediction of depression treatment outcomes from genetic and clinical variables",

abstract = "Individuals with depression differ substantially in their response to treatment with antidepressants. Specific predictors explain only a small proportion of these differences. To meaningfully predict who will respond to which antidepressant, it may be necessary to combine multiple biomarkers and clinical variables. Using statistical learning on common genetic variants and clinical information in a training sample of 280 individuals randomly allocated to 12-week treatment with antidepressants escitalopram or nortriptyline, we derived models to predict remission with each antidepressant drug. We tested the reproducibility of each prediction in a validation set of 150 participants not used in model derivation. An elastic net logistic model based on eleven genetic and six clinical variables predicted remission with escitalopram in the validation dataset with area under the curve 0.77 (95\%CI; 0.66-0.88; p = 0.004), explaining approximately 30\% of variance in who achieves remission. A model derived from 20 genetic variables predicted remission with nortriptyline in the validation dataset with an area under the curve 0.77 (95\%CI; 0.65-0.90; p < 0.001), explaining approximately 36\% of variance in who achieves remission. The predictive models were antidepressant drug-specific. Validated drug-specific predictions suggest that a relatively small number of genetic and clinical variables can help select treatment between escitalopram and nortriptyline.",

author = "Raquel Iniesta and Karen Hodgson and Stahl, \{Daniel Richard\} and Karim Malki and Wolfgang Maier and Marcella Rietschel and Ole Mors and Joanna Hauser and Neven Henigsberg and Dernov{\v s}ek, \{Mojca Zvezdana\} and Daniel Souery and Richard Dobson and Aitchison, \{Katherine. J\} and Anne Farmer and Peter McGuffin and Lewis, \{Cathryn M.\} and Rudolf Uher",

year = "2018",

month = apr,

day = "3",

doi = "10.1038/s41598-018-23584-z",

language = "English",

volume = "8",

journal = "Scientific Reports",

issn = "2045-2322",

publisher = "Nature Publishing Group",

number = "1",

}

Iniesta, R , Hodgson, K , Stahl, DR , Malki, K, Maier, W, Rietschel, M, Mors, O, Hauser, J, Henigsberg, N, Dernovšek, MZ, Souery, D, Dobson, R, Aitchison , KJ, Farmer, A , McGuffin, P , Lewis, CM & Uher, R 2018, 'Antidepressant drug-specific prediction of depression treatment outcomes from genetic and clinical variables', Scientific Reports, vol. 8, no. 1, 5530 . https://doi.org/10.1038/s41598-018-23584-z

TY - JOUR

T1 - Antidepressant drug-specific prediction of depression treatment outcomes from genetic and clinical variables

AU - Iniesta, Raquel

AU - Hodgson, Karen

AU - Stahl, Daniel Richard

AU - Malki, Karim

AU - Maier, Wolfgang

AU - Rietschel, Marcella

AU - Mors, Ole

AU - Hauser, Joanna

AU - Henigsberg, Neven

AU - Dernovšek, Mojca Zvezdana

AU - Souery, Daniel

AU - Dobson, Richard

AU - Aitchison , Katherine. J

AU - Farmer, Anne

AU - McGuffin, Peter

AU - Lewis, Cathryn M.

AU - Uher, Rudolf

PY - 2018/4/3

Y1 - 2018/4/3

N2 - Individuals with depression differ substantially in their response to treatment with antidepressants. Specific predictors explain only a small proportion of these differences. To meaningfully predict who will respond to which antidepressant, it may be necessary to combine multiple biomarkers and clinical variables. Using statistical learning on common genetic variants and clinical information in a training sample of 280 individuals randomly allocated to 12-week treatment with antidepressants escitalopram or nortriptyline, we derived models to predict remission with each antidepressant drug. We tested the reproducibility of each prediction in a validation set of 150 participants not used in model derivation. An elastic net logistic model based on eleven genetic and six clinical variables predicted remission with escitalopram in the validation dataset with area under the curve 0.77 (95%CI; 0.66-0.88; p = 0.004), explaining approximately 30% of variance in who achieves remission. A model derived from 20 genetic variables predicted remission with nortriptyline in the validation dataset with an area under the curve 0.77 (95%CI; 0.65-0.90; p < 0.001), explaining approximately 36% of variance in who achieves remission. The predictive models were antidepressant drug-specific. Validated drug-specific predictions suggest that a relatively small number of genetic and clinical variables can help select treatment between escitalopram and nortriptyline.

AB - Individuals with depression differ substantially in their response to treatment with antidepressants. Specific predictors explain only a small proportion of these differences. To meaningfully predict who will respond to which antidepressant, it may be necessary to combine multiple biomarkers and clinical variables. Using statistical learning on common genetic variants and clinical information in a training sample of 280 individuals randomly allocated to 12-week treatment with antidepressants escitalopram or nortriptyline, we derived models to predict remission with each antidepressant drug. We tested the reproducibility of each prediction in a validation set of 150 participants not used in model derivation. An elastic net logistic model based on eleven genetic and six clinical variables predicted remission with escitalopram in the validation dataset with area under the curve 0.77 (95%CI; 0.66-0.88; p = 0.004), explaining approximately 30% of variance in who achieves remission. A model derived from 20 genetic variables predicted remission with nortriptyline in the validation dataset with an area under the curve 0.77 (95%CI; 0.65-0.90; p < 0.001), explaining approximately 36% of variance in who achieves remission. The predictive models were antidepressant drug-specific. Validated drug-specific predictions suggest that a relatively small number of genetic and clinical variables can help select treatment between escitalopram and nortriptyline.

UR - https://www.scopus.com/pages/publications/85044976298

U2 - 10.1038/s41598-018-23584-z

DO - 10.1038/s41598-018-23584-z

M3 - Article

SN - 2045-2322

VL - 8

JO - Scientific Reports

JF - Scientific Reports

IS - 1

M1 - 5530

ER -

Antidepressant drug-specific prediction of depression treatment outcomes from genetic and clinical variables

Abstract

Access to Document

Other files and links

Fingerprint

Cite this