Currently, depression diagnosis relies primarily on behavioral symptoms and signs, and treatment is guided by trial and error instead of evaluating associated underlying brain characteristics. Unlike past studies, we attempted to estimate accurate prediction models for late-life depression diagnosis and treatment response using multiple machine learning methods with inputs of multi-modal imaging and non-imaging whole brain and network-based features.

Methods

Late-life depression patients (medicated post-recruitment) (n = 33) and older non-depressed individuals (n = 35) were recruited. Their demographics and cognitive ability scores were recorded, and brain characteristics were acquired using multi-modal magnetic resonance imaging pretreatment. Linear and nonlinear learning methods were tested for estimating accurate prediction models.

Results

A learning method called alternating decision trees estimated the most accurate prediction models for late-life depression diagnosis (87.27% accuracy) and treatment response (89.47% accuracy). The diagnosis model included measures of age, Mini-mental state examination score, and structural imaging (e.g. whole brain atrophy and global white mater hyperintensity burden). The treatment response model included measures of structural and functional connectivity.

Conclusions

Combinations of multi-modal imaging and/or non-imaging measures may help better predict late-life depression diagnosis and treatment response. As a preliminary observation, we speculate that the results may also suggest that different underlying brain characteristics defined by multi-modal imaging measures—rather than region-based differences—are associated with depression versus depression recovery because to our knowledge this is the first depression study to accurately predict both using the same approach. These findings may help better understand late-life depression and identify preliminary steps toward personalized late-life depression treatment. Copyright © 2015 John Wiley & Sons, Ltd.

Supporting Information

References

Aizenstein HJ, Andreescu C, Edelman KL, et al. 2011. fMRI correlates of white matter hyperintensities in late-life depression. Am J Psychiatry 168(10): 1075–1082.
10.1176/appi.ajp.2011.10060853
PubMed Web of Science® Google Scholar
Aizenstein HJ, Khalaf A, Walker SE, Andreescu C. 2014. Magnetic resonance imaging predictors of treatment response in late-life depression. J Geriatr Psychiatry Neurol 27(1): 24–32.
10.1177/0891988713516541
PubMed Web of Science® Google Scholar
Ajilore O, Lamar M, Leow A, et al. 2014. Graph theory analysis of cortical-subcortical networks in late-life depression. Am J Geriatr Psychiatry: Off J Am Assoc Geriatr Psychiatry 22(2): 195–206.
10.1016/j.jagp.2013.03.005
PubMed Web of Science® Google Scholar
Alalade E, Denny K, Potter G, Steffens D, Wang L. 2011. Altered cerebellar-cerebral functional connectivity in geriatric depression. PLoS One 6(5): e20035.
10.1371/journal.pone.0020035
CAS PubMed Web of Science® Google Scholar
Alexopoulos GS, Murphy CF, Gunning-Dixon FM, et al. 2008. Microstructural white matter abnormalities and remission of geriatric depression. Am J Psychiatry 165(2): 238–244.
10.1176/appi.ajp.2007.07050744
PubMed Web of Science® Google Scholar
Alexopoulos GS, Hoptman MJ, Kanellopoulos D, et al. 2012. Functional connectivity in the cognitive control network and the default mode network in late-life depression. J Affect Disord 139(1): 56–65.
10.1016/j.jad.2011.12.002
PubMed Web of Science® Google Scholar
Andreescu C, Reynolds CF, 3rd. 2011. Late-life depression: evidence-based treatment and promising new directions for research and clinical practice. Psychiatr Clin North Am 34(2): 335–355, vii-iii.
10.1016/j.psc.2011.02.005
PubMed Web of Science® Google Scholar
Andreescu C, Mulsant BH, Houck PR, et al. (2008). Empirically derived decision trees for the treatment of late-life depression. Am J Psychiatry 165(7): 855–862.
10.1176/appi.ajp.2008.07081340
PubMed Web of Science® Google Scholar
Andreescu C, Wu M, Butters MA, et al. 2011. The default mode network in late-life anxious depression. Am J Geriatr Psychiatry: Off J Am Assoc Geriatr Psychiatry 19(11): 980–983.
10.1097/JGP.0b013e318227f4f9
Web of Science® Google Scholar
Andreescu C, Tudorascu DL, Butters MA, et al. 2013. Resting state functional connectivity and treatment response in late-life depression. Psychiatry Res 214(3): 313–321.
10.1016/j.pscychresns.2013.08.007
PubMed Web of Science® Google Scholar
Bhalla RK, Butters MA, Zmuda MD, et al. 2005. Does education moderate neuropsychological impairment in late-life depression? Int J Geriatr Psychiatry 20(5): 413–417.
10.1002/gps.1296
PubMed Web of Science® Google Scholar
Blazer DG. 2012. Review: antidepressants are effective for the treatment of major depressive disorder in individuals aged 55 years or older. Evid Based Ment Health 15(3): 72.
10.1136/ebmental-2012-100629
PubMed Google Scholar
Bohr IJ, Kenny E, Blamire A, et al. 2012. Resting-state functional connectivity in late-life depression: higher global connectivity and more long distance connections. Frontiers in psychiatry 3: 116.
PubMed Google Scholar
Chang CC, Yu SC, McQuoid DR, et al. 2011. Reduction of dorsolateral prefrontal cortex gray matter in late-life depression. Psychiatry Res 193(1): 1–6.
10.1016/j.pscychresns.2011.01.003
PubMed Web of Science® Google Scholar
Chang-Quan H, Zheng-Rong W, Yong-Hong L, Yi-Zhou X, Qing-Xiu L. 2010. Education and risk for late life depression: a meta-analysis of published literature. Int J Psychiatry Med 40(1): 109–124.
10.2190/PM.40.1.i
PubMed Web of Science® Google Scholar
Colloby SJ, Firbank MJ, Thomas AJ, et al. 2011. White matter changes in late-life depression: a diffusion tensor imaging study. J Affect Disord 135(1-3): 216–220.
10.1016/j.jad.2011.07.025
PubMed Web of Science® Google Scholar
Colloby SJ, Firbank MJ, He J, et al. 2012. Regional cerebral blood flow in late-life depression: arterial spin labelling magnetic resonance study. Br J Psychiatry: J Ment Sci 200(2): 150–155.
10.1192/bjp.bp.111.092387
Web of Science® Google Scholar
Cortes C, Vapnik V. 1995. Support-vector networks. Mach Learn 20(3): 273–297.
10.1023/A:1022627411411
Web of Science® Google Scholar
Costafreda SG, Chu C, Ashburner J, Fu CH. 2009. Prognostic and diagnostic potential of the structural neuroanatomy of depression. PLoS One 4(7): e6353.
10.1371/journal.pone.0006353
CAS PubMed Web of Science® Google Scholar
Crocco EA, Castro K, Loewenstein DA. 2010. How late-life depression affects cognition: neural mechanisms. Curr Psychiatry Rep 12(1): 34–38.
10.1007/s11920-009-0081-2
PubMed Web of Science® Google Scholar
Disabato BM, Sheline YI. 2012. Biological basis of late life depression. Curr Psychiatry Rep 14(4): 273–279.
10.1007/s11920-012-0279-6
PubMed Web of Science® Google Scholar
Firbank MJ, Teodorczuk A, van der Flier WM, et al. 2012. Relationship between progression of brain white matter changes and late-life depression: 3-year results from the LADIS study. Br J Psychiatry: J Ment Sci 201(1): 40–45.
10.1192/bjp.bp.111.098897
Web of Science® Google Scholar
First M, Spitzer R, Williams J, Gibbons M. 1995. Structured Clinical Interview for DSM-IV-Patient Version. Biometrics Research Department, New York State Psychiatric Institute: New York.
Google Scholar
Forlani C, Morri M, Ferrari B, et al. 2013. Prevalence and gender differences in late-life depression: a population-based study. Am J Geriatr Psychiatry: Off J Am Assoc Geriatr Psychiatry 22(4): 370–380.
10.1016/j.jagp.2012.08.015
Web of Science® Google Scholar
Fu CH, Mourao-Miranda J, Costafreda SG, et al. 2008. Pattern classification of sad facial processing: toward the development of neurobiological markers in depression. Biol Psychiatry 63(7): 656–662.
10.1016/j.biopsych.2007.08.020
PubMed Web of Science® Google Scholar
Ganguli M, Du Y, Dodge HH, Ratcliff GG, Chang CC. 2006. Depressive symptoms and cognitive decline in late life: a prospective epidemiological study. Arch Gen Psychiatry 63(2): 153–160.
10.1001/archpsyc.63.2.153
PubMed Web of Science® Google Scholar
Greenwald BS, Kramer-Ginsberg E, Krishnan KR, et al. 1998. Neuroanatomic localization of magnetic resonance imaging signal hyperintensities in geriatric depression. Stroke; J Cerebr Circ 29(3): 613–617.
10.1161/01.STR.29.3.613
CAS PubMed Web of Science® Google Scholar
Gunning FM, Cheng J, Murphy CF, et al. 2009. Anterior cingulate cortical volumes and treatment remission of geriatric depression. Int J Geriatr Psychiatry 24(8): 829–836.
10.1002/gps.2290
PubMed Web of Science® Google Scholar
Gunning-Dixon FM, Walton M, Cheng J, et al. 2010. MRI signal hyperintensities and treatment remission of geriatric depression. J Affect Disord 126(3): 395–401.
10.1016/j.jad.2010.04.004
PubMed Web of Science® Google Scholar
Hahn T, Marquand AF, Ehlis AC, et al. 2011. Integrating neurobiological markers of depression. Arch Gen Psychiatry 68(4): 361–368.
10.1001/archgenpsychiatry.2010.178
PubMed Web of Science® Google Scholar
Jenkinson M, Beckmann CF, Behrens TE, Woolrich MW, Smith SM. 2012. FSL. Neuroimage 62(2): 782–790.
10.1016/j.neuroimage.2011.09.015
PubMed Web of Science® Google Scholar
Katon W, Unutzer J, Russo J. 2010. Major depression: the importance of clinical characteristics and treatment response to prognosis. Depress Anxiety 27(1): 19–26.
10.1002/da.20613
CAS PubMed Web of Science® Google Scholar
Kohler S, Thomas AJ, Barnett NA, O'Brien JT. 2010a. The pattern and course of cognitive impairment in late-life depression. Psychol Med 40(4): 591–602.
10.1017/S0033291709990833
CAS PubMed Web of Science® Google Scholar
Kohler S, Thomas AJ, Lloyd A, et al. 2010b. White matter hyperintensities, cortisol levels, brain atrophy and continuing cognitive deficits in late-life depression. Br J Psychiatry: J Ment Sci 196(2): 143–149.
10.1192/bjp.bp.109.071399
PubMed Web of Science® Google Scholar
Liu F, Hu M, Wang S, et al. 2012a. Abnormal regional spontaneous neural activity in first-episode, treatment-naive patients with late-life depression: a resting-state fMRI study. Prog Neuropsychopharmacol Biol Psychiatry 39(2): 326–331.
10.1016/j.pnpbp.2012.07.004
PubMed Web of Science® Google Scholar
Liu F, Guo W, Yu D, et al. 2012b. Classification of different therapeutic responses of major depressive disorder with multivariate pattern analysis method based on structural MR scans. PLoS One 7(7): e40968.
10.1371/journal.pone.0040968
CAS PubMed Web of Science® Google Scholar
Luppa M, Sikorski C, Luck T, et al. 2012. Age- and gender-specific prevalence of depression in latest-life–systematic review and meta-analysis. J Affect Disord 136(3): 212–221.
10.1016/j.jad.2010.11.033
CAS PubMed Web of Science® Google Scholar
Marquand AF, Mourao-Miranda J, Brammer MJ, Cleare AJ, Fu CH. 2008. Neuroanatomy of verbal working memory as a diagnostic biomarker for depression. Neuroreport 19(15): 1507–1511.
10.1097/WNR.0b013e328310425e
PubMed Web of Science® Google Scholar
Mental Health America. Depression in older adults. http://www.mentalhealthamerica.net/conditions/depression-older-adults#2. Retrieved 2014.
Google Scholar
Mettenburg JM, Benzinger TL, Shimony JS, Snyder AZ, Sheline YI. 2012. Diminished performance on neuropsychological testing in late life depression is correlated with microstructural white matter abnormalities. Neuroimage 60(4): 2182–2190.
10.1016/j.neuroimage.2012.02.044
PubMed Web of Science® Google Scholar
Mwangi B, Ebmeier KP, Matthews K, Steele JD. 2012a. Multi-centre diagnostic classification of individual structural neuroimaging scans from patients with major depressive disorder. Brain: J Neurol 135(Pt 5): 1508–1521.
10.1093/brain/aws084
PubMed Web of Science® Google Scholar
Mwangi B, Matthews K, Steele JD. 2012b. Prediction of illness severity in patients with major depression using structural MR brain scans. J Magn Reson Imag: JMRI 35(1): 64–71.
10.1002/jmri.22806
CAS PubMed Web of Science® Google Scholar
Nieto-Castanon A, Ghosh SS, Tourville JA, Guenther FH. 2003. Region of interest based analysis of functional imaging data. Neuroimage ( 4): 1303–1316.
10.1016/S1053-8119(03)00188-5
Web of Science® Google Scholar
Nouretdinov I, Costafreda SG, Gammerman A, et al. 2011. Machine learning classification with confidence: application of transductive conformal predictors to MRI-based diagnostic and prognostic markers in depression. Neuroimage 56(2): 809–813.
10.1016/j.neuroimage.2010.05.023
PubMed Web of Science® Google Scholar
Papakostas GI, Thase ME, Fava M, Nelson JC, Shelton RC. 2007. Are antidepressant drugs that combine serotonergic and noradrenergic mechanisms of action more effective than the selective serotonin reuptake inhibitors in treating major depressive disorder? A meta-analysis of studies of newer agents. Biol Psychiatry 62(11): 1217–1227.
10.1016/j.biopsych.2007.03.027
CAS PubMed Web of Science® Google Scholar
Pedregosa F, Varoquaux G, Gramfort A, et al. 2011. Scikit-learn: machine learning in Python. J Mach Learn Res 12: 2825–2830.
Web of Science® Google Scholar
Pfahringer B, Holmes G, Kirkby R. 2001. Optimizing the induction of alternating decision trees. In Advances in Knowledge Discovery and Data Mining, edn, Vol. 2035, D Cheung, G Williams, Q Li (eds). Springer: Berlin Heidelberg; 477–487.
10.1007/3-540-45357-1_50
Google Scholar
Ribeiz SR, Duran F, Oliveira MC, et al. 2013. Structural brain changes as biomarkers and outcome predictors in patients with late-life depression: a cross-sectional and prospective study. PLoS One 8(11): e80049.
10.1371/journal.pone.0080049
PubMed Google Scholar
Roose SP, Glassman AH, Attia E, Woodring S. 1994. Comparative efficacy of selective serotonin reuptake inhibitors and tricyclics in the treatment of melancholia. Am J Psychiatry 151(12): 1735–1739.
10.1176/ajp.151.12.1735
PubMed Web of Science® Google Scholar
Sexton CE, Mackay CE, Ebmeier KP. 2013. A systematic review and meta-analysis of magnetic resonance imaging studies in late-life depression. Am J Geriatr Psychiatry 21(2): 184–195.
10.1016/j.jagp.2012.10.019
PubMed Web of Science® Google Scholar
Shimony JS, Sheline YI, D'Angelo G, et al. 2009. Diffuse microstructural abnormalities of normal-appearing white matter in late life depression: a diffusion tensor imaging study. Biol Psychiatry 66(3): 245–252.
10.1016/j.biopsych.2009.02.032
PubMed Web of Science® Google Scholar
Shirer WR, Ryali S, Rykhlevskaia E, Menon V, Greicius MD. 2012. Decoding subject-driven cognitive states with whole-brain connectivity patterns. Cereb Cortex 22(1): 158–165.
10.1093/cercor/bhr099
CAS PubMed Web of Science® Google Scholar
Steffens DC, Taylor WD, Denny KL, Bergman SR, Wang L. 2011. Structural integrity of the uncinate fasciculus and resting state functional connectivity of the ventral prefrontal cortex in late life depression. PLoS One 6(7): e22697.
10.1371/journal.pone.0022697
CAS PubMed Web of Science® Google Scholar
Stern Y. 2003. The concept of cognitive reserve: a catalyst for research. J Clin Exp Neuropsychol 25(5): 589–593.
PubMed Web of Science® Google Scholar
Tadayonnejad R, Ajilore O. 2014. Brain network dysfunction in late-life depression: a literature review. J Geriatr Psychiatry Neurol 27(1): 5–12.
10.1177/0891988713516539
PubMed Web of Science® Google Scholar
Taylor WD, Doraiswamy PM. 2004. A systematic review of antidepressant placebo-controlled trials for geriatric depression: limitations of current data and directions for the future. Neuropsychoph: Off Publ Am Coll Neuropsychoph 29(12): 2285–2299.
10.1038/sj.npp.1300550
CAS PubMed Web of Science® Google Scholar
Taylor MJ, Freemantle N, Geddes JR, Bhagwagar Z. 2006. Early onset of selective serotonin reuptake inhibitor antidepressant action: systematic review and meta-analysis. Arch Gen Psychiatry 63(11): 1217–1223.
10.1001/archpsyc.63.11.1217
CAS PubMed Web of Science® Google Scholar
Taylor WD, Kuchibhatla M, Payne ME, et al. 2008. Frontal white matter anisotropy and antidepressant remission in late-life depression. PLoS One 3(9): e3267.
10.1371/journal.pone.0003267
CAS PubMed Web of Science® Google Scholar
Taylor WD, Macfall JR, Boyd B, et al. 2011. One-year change in anterior cingulate cortex white matter microstructure: relationship with late-life depression outcomes. Am J Geriatr Psychiatry: Off J Am Assoc Geriatr Psychiatry 19(1): 43–52.
10.1097/JGP.0b013e3181e70cec
PubMed Web of Science® Google Scholar
Teodorczuk A, Firbank MJ, Pantoni L, et al. 2010. Relationship between baseline white-matter changes and development of late-life depressive symptoms: 3-year results from the LADIS study. Psychol Med 40(4): 603–610.
10.1017/S0033291709990857
CAS PubMed Web of Science® Google Scholar
Thase ME, Ninan PT, Musgnung JJ, Trivedi MH. 2011. Remission with venlafaxine extended release or selective serotonin reuptake inhibitors in depressed patients: a randomized, open-label study. Prim Care Companion J Clin Psychiatry 13(1): e1-e9.
Google Scholar
Wang L, Krishnan KR, Steffens DC, et al. 2008. Depressive state- and disease-related alterations in neural responses to affective and executive challenges in geriatric depression. Am J Psychiatry 165(7): 863–871.
10.1176/appi.ajp.2008.07101590
PubMed Web of Science® Google Scholar
Whitfield-Gabrieli S, Nieto-Castanon A. 2012. Conn: a functional connectivity toolbox for correlated and anticorrelated brain networks. Brain connectivity 2(3): 125–141.
10.1089/brain.2012.0073
PubMed Google Scholar
Wild B, Herzog W, Schellberg D, et al. 2012. Association between the prevalence of depression and age in a large representative German sample of people aged 53 to 80 years. Int J Geriatr Psychiatry 27(4): 375–381.
10.1002/gps.2728
PubMed Web of Science® Google Scholar
Wilkins CH, Mathews J, Sheline YI. 2009. Late life depression with cognitive impairment: evaluation and treatment. Clin Interv Aging 4: 51–57.
PubMed Web of Science® Google Scholar
Wu M, Rosano C, Butters M, et al. 2006. A fully automated method for quantifying and localizing white matter hyperintensities on MR images. Psychiatry Res 148(2-3): 133–142.
10.1016/j.pscychresns.2006.09.003
PubMed Web of Science® Google Scholar
Wu M, Andreescu C, Butters MA, et al. 2011. Default-mode network connectivity and white matter burden in late-life depression. Psychiatry Res 194(1): 39–46.
10.1016/j.pscychresns.2011.04.003
PubMed Web of Science® Google Scholar
Wu Z, Schimmele CM, Chappell NL. 2012. Aging and late-life depression. J Aging Health 24(1): 3–28.
10.1177/0898264311422599
Web of Science® Google Scholar
Yuan G-X, Chang K-W, Hsieh C-J, Lin C-J. 2010. A comparison of optimization methods and software for large-scale L1-regularized linear classification. J Mach Learn Res 11: 3183–3234.
Web of Science® Google Scholar
Zeng LL, Shen H, Liu L, et al. 2012. Identifying major depression using whole-brain functional connectivity: a multivariate pattern analysis. Brain: J Neurol 135(Pt 5): 1498–1507.
10.1093/brain/aws059
PubMed Web of Science® Google Scholar

Citing Literature

Volume30, Issue10

October 2015

Pages 1056-1067

Machine learning approaches for integrating clinical and imaging features in late-life depression classification and response prediction

Abstract

Objective

Methods

Results

Conclusions

Supporting Information

References

Citing Literature

References

Information

About Wiley Online Library

Help & Support

Opportunities

Connect with Wiley

Machine learning approaches for integrating clinical and imaging features in late-life depression classification and response prediction

Abstract

Objective

Methods

Results

Conclusions

Supporting Information

References

Citing Literature

References

Related

Information