Machine Learning for Precision Psychiatry: Opportunities and Challenges

  • Danilo Bzdok
    Correspondence
    Address correspondence to Danilo Bzdok, M.D., Ph.D., Research Center Jülich, Institute of Neuroscience and Medicine 1, Pauwelsstraße 30, Aachen 52074, Germany.
    Affiliations
    Department of Psychiatry, Psychotherapy and Psychosomatics, RWTH Aachen University, Aachen, Germany

    JARA-BRAIN, Jülich-Aachen Research Alliance, Aachen, Germany

    Parietal team, INRIA, Neurospin, Gif-sur-Yvette, France
    Search for articles by this author
  • Andreas Meyer-Lindenberg
    Affiliations
    Department of Psychiatry and Psychotherapy, Central Institute of Mental Health, Medical Faculty Mannheim, University of Heidelberg, Mannheim, Germany

    Bernstein Center for Computational Neuroscience Heidelberg-Mannheim, Central Institute of Mental Health, Medical Faculty Mannheim, University of Heidelberg, Mannheim, Germany
    Search for articles by this author
Published:December 05, 2017DOI:https://doi.org/10.1016/j.bpsc.2017.11.007

      Abstract

      The nature of mental illness remains a conundrum. Traditional disease categories are increasingly suspected to misrepresent the causes underlying mental disturbance. Yet psychiatrists and investigators now have an unprecedented opportunity to benefit from complex patterns in brain, behavior, and genes using methods from machine learning (e.g., support vector machines, modern neural-network algorithms, cross-validation procedures). Combining these analysis techniques with a wealth of data from consortia and repositories has the potential to advance a biologically grounded redefinition of major psychiatric disorders. Increasing evidence suggests that data-derived subgroups of psychiatric patients can better predict treatment outcomes than DSM/ICD diagnoses can. In a new era of evidence-based psychiatry tailored to single patients, objectively measurable endophenotypes could allow for early disease detection, individualized treatment selection, and dosage adjustment to reduce the burden of disease. This primer aims to introduce clinicians and researchers to the opportunities and challenges in bringing machine intelligence into psychiatric practice.

      Keywords

      To read this article in full you will need to make a payment

      References

        • Hyman S.E.
        Can neuroscience be integrated into the DSM-V?.
        Nat Rev Neurosci. 2007; 8: 725-732
        • Insel T.R.
        • Cuthbert B.N.
        Brain disorders?.
        Precisely. Science. 2015; 348: 499-500
        • Stephan K.E.
        • Schlagenhauf F.
        • Huys Q.J.M.
        • Raman S.
        • Aponte E.A.
        • Brodersen K.H.
        • et al.
        Computational neuroimaging strategies for single patient predictions.
        Neuroimage. 2017; 145: 189-199
        • Arbabshirani M.R.
        • Plis S.
        • Sui J.
        • Calhoun V.D.
        Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls.
        Neuroimage. 2017; 145: 137-165
        • Huys Q.J.M.
        • Maia T.V.
        • Frank M.J.
        Computational psychiatry as a bridge from neuroscience to clinical applications.
        Nat Neurosci. 2016; 19: 404-413
        • Woo C.-W.
        • Chang L.J.
        • Lindquist M.A.
        • Wager T.D.
        Building better biomarkers: Brain models in translational neuroimaging.
        Nat Neurosci. 2017; 20: 365-377
        • Goodfellow I.J.
        • Bengio Y.
        • Courville A.
        Deep Learning.
        MIT Press, Cambridge, MA2016
        • Breiman L.
        Statistical modeling: The two cultures.
        Stat Sci. 2001; 16: 199-231
        • Bzdok D.
        Classical statistics and statistical learning in imaging neuroscience.
        Front Neurosci. 2017; 11: 543
        • Hastie T.
        • Tibshirani R.
        • Friedman J.
        The Elements of Statistical Learning. Springer Series in Statistics.
        Springer, Heidelberg, Germany2001
        • Manyika J.
        • Chui M.
        • Brown B.
        • Bughin J.
        • Dobbs R.
        • Roxburgh C.
        • et al.
        Big data: The next frontier for innovation, competition, and productivity. Technical report.
        McKinsey Global Institute, Washington, DC2011
        • Efron B.
        • Hastie T.
        Computer-Age Statistical Inference.
        Cambridge University Press, Cambridge, UK2016
        • Shalev-Shwartz S.
        • Ben-David S.
        Understanding Machine Learning: From Theory to Algorithms.
        Cambridge University Press, Cambridge, UK2014
        • Wong E.H.F.
        • Yocca F.
        • Smith M.A.
        • Lee C.-M.
        Challenges and opportunities for drug discovery in psychiatric disorders: The drug hunters' perspective.
        Int J Neuropsychopharmacol. 2010; 13: 1269-1284
        • Hofmann S.G.
        • Asnaani A.
        • Vonk I.J.
        • Sawyer A.T.
        • Fang A.
        The efficacy of cognitive behavioral therapy: A review of meta-analyses.
        Cognit Ther Res. 2012; 36: 427-440
        • Perna G.
        • Nemeroff C.B.
        Personalized medicine in psychiatry: Back to the future.
        Pers Med Psychiatry. 2017; 1: 1
        • Rush A.J.
        • Trivedi M.H.
        • Wisniewski S.R.
        • Nierenberg A.A.
        • Stewart J.W.
        • Warden D.
        • et al.
        Acute and longer-term outcomes in depressed outpatients requiring one or several treatment steps: A STAR* D report.
        Am J Psychiatry. 2006; 163: 1905-1917
        • Gabrieli J.D.
        • Ghosh S.S.
        • Whitfield-Gabrieli S.
        Prediction as a humanitarian and pragmatic contribution from human cognitive neuroscience.
        Neuron. 2015; 85: 11-26
        • Drysdale A.T.
        • Grosenick L.
        • Downar J.
        • Dunlop K.
        • Mansouri F.
        • Meng Y.
        • et al.
        Resting-state connectivity biomarkers define neurophysiological subtypes of depression.
        Nat Med. 2017; 23: 28-38
        • Bzdok D.
        • Yeo B.T.T.
        Inference in the age of big data: Future perspectives on neuroscience.
        Neuroimage. 2017; 155: 549-564
        • Shmueli G.
        To explain or to predict?.
        Stat Sci. 2010; 25: 289-310
        • Zhang X.
        • Mormino E.C.
        • Sun N.
        • Sperling R.A.
        • Sabuncu M.R.
        • Yeo B.T.T.
        Bayesian model reveals latent atrophy factors with dissociable cognitive trajectories in Alzheimer’s disease.
        Proc Natl Acad Sci U S A. 2016; 113: E6535-E6544
        • Esteva A.
        • Kuprel B.
        • Novoa R.A.
        • Ko J.
        • Swetter S.M.
        • Blau H.M.
        • et al.
        Dermatologist-level classification of skin cancer with deep neural networks.
        Nature. 2017; 542: 115-118
        • Wasserstein R.L.
        • Lazar N.A.
        The ASA's statement on p-values: Context, process, and purpose.
        Am Stat. 2016; 70: 129-133
        • Breiman L.
        • Friedman J.H.
        Predicting multivariate responses in multiple linear regression.
        J R Stat Soc Ser B Stat Methodol. 1997; 59: 3-54
        • Caruana R.
        Multitask Learning: Learning to Learn.
        Springer, New York1998: 95-133
        • Caruana R.A.
        Multitask connectionist learning.
        in: Proceedings of the 1993 Connectionist Models Summer School. Lawrence Erlbaum, Hillsdale, NJ1993: 372-379
        • Ransohoff D.F.
        • Feinstein A.R.
        Problems of spectrum and bias in evaluating the efficacy of diagnostic tests.
        N Engl J Med. 1978; 299: 926-930
        • Perlis R.H.
        Translating biomarkers to clinical practice.
        Mol Psychiatr. 2011; 16: 1076-1087
        • Cuthbert B.N.
        • Insel T.R.
        Toward the future of psychiatric diagnosis: The seven pillars of RDoC.
        BMC Med. 2013; 11: 126
        • Van Os J.
        “Schizophrenia” does not exist.
        BMJ. 2016; 352: i375
        • Insel T.
        • Cuthbert B.
        • Garvey M.
        • Heinssen R.
        • Pine D.S.
        • Quinn K.
        • et al.
        Research domain criteria (RDoC): Toward a new classification framework for research on mental disorders.
        Am J Psychiatry. 2010; 167: 748-751
        • Cross-Disorder Group of the Psychiatric Genomics C
        Identification of risk loci with shared effects on five major psychiatric disorders: A genome-wide analysis.
        Lancet. 2013; 381: 1371-1379
        • Ehrenreich H.
        • Mitjans M.
        • Van der Auwera S.
        • Centeno T.P.
        • Begemann M.
        • Grabe H.J.
        • et al.
        OTTO: a new strategy to extract mental disease-relevant combinations of GWAS hits from individuals.
        Mol Psychiatry. 2018; 23: 476-486
        • Bengio Y.
        • Courville A.
        • Vincent P.
        Representation learning: A review and new perspectives.
        IEEE Trans Pattern Anal Mach Intell. 2013; 35: 1798-1828
        • Hinton G.E.
        • Salakhutdinov R.R.
        Reducing the dimensionality of data with neural networks.
        Science. 2006; 313: 504-507
        • James G.
        • Witten D.
        • Hastie T.
        • Tibshirani R.
        An Introduction to Statistical Learning.
        Springer, New York2013
        • Domingos P.
        A few useful things to know about machine learning.
        Commun ACM. 2012; 55: 78-87
        • Pereira F.
        • Mitchell T.
        • Botvinick M.
        Machine learning classifiers and fMRI: A tutorial overview.
        Neuroimage. 2009; 45: 199-209
        • Haynes J.-D.
        A primer on pattern-based approaches to fMRI: Principles, pitfalls, and perspectives.
        Neuron. 2015; 87: 257-270
        • Mur M.
        • Bandettini P.A.
        • Kriegeskorte N.
        Revealing representational content with pattern-information fMRI—an introductory guide.
        Soc Cogn Affect Neurosci. 2009; 4: 101-109
        • Squeglia L.M.
        • Ball T.M.
        • Jacobus J.
        • Brumback T.
        • McKenna B.S.
        • Nguyen-Louie T.T.
        • et al.
        Neural predictors of initiating alcohol use during adolescence.
        Am J Psychiatry. 2017; 174: 172-185
        • Eyre H.A.
        • Singh A.B.
        • Reynolds C.
        Tech giants enter mental health.
        World Psychiatry. 2016; 15: 21-22
        • Varoquaux G.
        Cross-validation failure: Small sample sizes lead to large error bars.
        Neuroimage. 2017; ([published online ahead of print Jun 24])
        • Longo D.L.
        • Drazen J.M.
        Data sharing.
        N Engl J Med. 2016; 374: 276-277
        • Poldrack R.A.
        • Gorgolewski K.J.
        Making big data open: Data sharing in neuroimaging.
        Nat Neurosci. 2014; 17: 1510-1517
        • Gorgolewski K.J.
        • Auer T.
        • Calhoun V.D.
        • Craddock R.C.
        • Das S.
        • Duff E.P.
        • et al.
        The brain imaging data structure, a format for organizing and describing outputs of neuroimaging experiments.
        Scientific Data 3,. 2016; : 160044
        • Manyika J.
        • Chui M.
        • Bisson P.
        • Woetzel J.
        • Dobbs R.
        • Bughin J.
        • et al.
        Unlocking the Potential of the Internet of Things.
        McKinsey Global Institute, Washington, DC2015
        • Weinberger D.R.
        • Radulescu E.
        Finding the elusive psychiatric “lesion” with 21st-century neuroanatomy: A note of caution.
        Am J Psychiatry. 2015; 173: 27-33
        • O'Neil C.
        Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy.
        Crown, New York2016
        • Gustavsson A.
        • Svensson M.
        • Jacobi F.
        • Allgulander C.
        • Alonso J.
        • Beghi E.
        • et al.
        Cost of disorders of the brain in Europe 2010.
        Eur Neuropsychopharmacol. 2011; 21: 718-779