Abstract
Rationale
The impact of neuroscience-based approaches for psychiatry on pragmatic clinical decision-making has been limited. Although neuroscience has provided insights into basic mechanisms of neural function, these insights have not improved the ability to generate better assessments, prognoses, diagnoses, or treatment of psychiatric conditions.
Objectives
To integrate the emerging findings in machine learning and computational psychiatry to address the question: what measures that are not derived from the patient’s self-assessment or the assessment by a trained professional can be used to make more precise predictions about the individual’s current state, the individual’s future disease trajectory, or the probability to respond to a particular intervention?
Results
Currently, the ability to use individual differences to predict differential outcomes is very modest possibly related to the fact that the effect sizes of interventions are small. There is emerging evidence of genetic and neuroimaging-based heterogeneity of psychiatric disorders, which contributes to imprecise predictions. Although the use of machine learning tools to generate clinically actionable predictions is still in its infancy, these approaches may identify subgroups enabling more precise predictions. In addition, computational psychiatry might provide explanatory disease models based on faulty updating of internal values or beliefs.
Conclusions
There is a need for larger studies, clinical trials using machine learning, or computational psychiatry model parameters predictions as actionable outcomes, comparing alternative explanatory computational models, and using translational approaches that apply similar paradigms and models in humans and animals.
Similar content being viewed by others
References
Bach DR (2017) The cognitive architecture of anxiety-like behavioral inhibition. J Exp Psychol Hum Percept Perform 43:18–29
Baker TE, Zeighami Y, Dagher A, Holroyd CB (2018) Smoking decisions: Altered reinforcement learning signals induced by nicotine state. Nicotine Tob Res https://doi.org/10.1093/ntr/nty136
Bernardini F, Attademo L, Cleary SD, Luther C, Shim RS, Quartesan R, Compton MT (2017) Risk prediction models in psychiatry: toward a new frontier for the prevention of mental illnesses. J Clin Psychiatry 78:572–583
Bosco FA, Aguinis H, Singh K, Field JG, Pierce CA (2015) Correlational effect size benchmarks. J Appl Psychol 100:431–449
Brendel DH (2003) Reductionism, eclecticism, and pragmatism in psychiatry: the dialectic of clinical explanation. J Med Philos 28:563–580
Brown VM, Zhu L, Wang JM, Frueh BC, King-Casas B, Chiu PH (2018) Associability-modulated loss learning is increased in posttraumatic stress disorder. eLife 7 https://doi.org/10.7554/eLife.30150.001
Browning M, Behrens TE, Jocham G, O’Reilly JX, Bishop SJ (2015) Anxious individuals have difficulty learning the causal statistics of aversive environments. Nat Neurosci 18:590–596
Busch Y, Menke A (2019) Blood-based biomarkers predicting response to antidepressants. J Neural Transm (Vienna Austria) 1996(126):47–63
Casey BJ, Craddock N, Cuthbert BN, Hyman SE, Lee FS, Ressler KJ (2013) DSM-5 and RDoC: progress in psychiatry research? Nat Rev Neurosci 14:810–814
Channa R, Siddiqi M (2008) What do patients want from their psychiatrist? A cross-sectional questionnaire based exploratory study from Karachi. BMC Psychiatry 8:14
Cook NR (2007) Use and misuse of the receiver operating characteristic curve in risk prediction. Circulation 115:928–935
Daw ND, Doya K (2006) The computational neurobiology of learning and reward. Curr Opin Neurobiol 16:199–204
Dion PA, Daoud H, Rouleau GA (2009) Genetics of motor neuron disorders: new insights into pathogenic mechanisms. Nat Rev Genet 10:769–782
Durstewitz D, Koppe G, Meyer-Lindenberg A (2019) Deep neural networks in psychiatry. Mol Psychiatry https://doi.org/10.1038/s41380-019-0365-9
Friston KJ, Stephan KE, Montague R, Dolan RJ (2014) Computational psychiatry: the brain as a phantastic organ. Lancet Psychiatry 1:148–158
Friston K, FitzGerald T, Rigoli F, Schwartenbeck P, Pezzulo G (2017a) Active inference: a process theory. Neural Comput 29:1–49
Friston KJ, Redish AD, Gordon JA (2017b) Computational nosology and precision psychiatry. Comput Psychiatr (Cambridge, Mass) 1:2–23
Gerds TA, Cai T, Schumacher M (2008) The performance of risk prediction models. Biom J 50:457–479
Gignac GE, Szodorai ET (2016) Effect size guidelines for individual differences researchers. Personal Individ Differ 102:74–78
Hall LS, Adams MJ, Arnau-Soler A, Clarke TK, Howard DM, Zeng Y, Davies G, Hagenaars SP, Maria Fernandez-Pujals A, Gibson J, Wigmore EM, Boutin TS, Hayward C, Scotland G, Porteous DJ, Deary IJ, Thomson PA, Haley CS, McIntosh AM (2018) Genome-wide meta-analyses of stratified depression in generation Scotland and UK Biobank. Transl Psychiatry 8:9
Hernaus D, Gold JM, Waltz JA, Frank MJ (2018) Impaired expected value computations coupled with overreliance on stimulus-response learning in schizophrenia. Biol Psychiatry 3:916–926
Huys QJM, Guitart-Masip M, Dolan RJ, Dayan P (2015) Decision-theoretic psychiatry. Clin Psychol Sci 3:400–421
Huys QJ, Maia TV, Frank MJ (2016) Computational psychiatry as a bridge from neuroscience to clinical applications. Nat Neurosci 19:404–413
Janssen RJ, Mourao-Miranda J, Schnack HG (2018) Making individual prognoses in psychiatry using neuroimaging and machine learning. Biol Psychiatry 3:798–808
Johansson FD, Shalit U, Sontag D (2016) Learning representations for counterfactual inference. eprint arXiv:160503661: arXiv:1605.03661
Johnson BT, Scott-Sheldon LAJ, Carey MP (2010) Meta-synthesis of health behavior change meta-analyses. Am J Public Health 100:2193–2198
Joyner MA, Gearhardt AN, Flagel SB (2018) A translational model to assess sign-tracking and goal-tracking behavior in children. Neuropsychopharmacology 43:228–229
Karvelis P, Seitz AR, Lawrie SM, Series P (2018) Autistic traits, but not schizotypy, predict increased weighting of sensory information in Bayesian visual integration. eLife 7 https://doi.org/10.7554/eLife.34115.001
Kendler KS (2005) Toward a philosophical structure for psychiatry. Am J Psychiatry 162:433–440
Kendler KS (2008) Explanatory models for psychiatric illness. Am J Psychiatry 165:695–702
Kendler KS (2012) Levels of explanation in psychiatric and substance use disorders: implications for the development of an etiologically based nosology. Mol Psychiatry 17:11–21
Kendler KS (2014) The structure of psychiatric science. Am J Psychiatry 171:931–938
Kendler KS (2017a) David Skae and his nineteenth century etiologic psychiatric diagnostic system: looking forward by looking back. Mol Psychiatry 22:802–807
Kendler KS (2017b) DSM disorders and their criteria: how should they inter-relate? Psychol Med 47: 2054-2060
Kendler KS, Engstrom EJ (2017) Kahlbaum, Hecker, and Kraepelin and the transition from psychiatric symptom complexes to empirical disease forms. Am J Psychiatry 174:102–109
Kessler RC, van Loo HM, Wardenaar KJ, Bossarte RM, Brenner LA, Ebert DD, de Jonge P, Nierenberg AA, Rosellini AJ, Sampson NA, Schoevers RA, Wilcox MA, Zaslavsky AM (2017) Using patient self-reports to study heterogeneity of treatment effects in major depressive disorder. Epidemiol Psychiatr Sci 26:22–36
Kingslake J, Dias R, Dawson GR, Simon J, Goodwin GM, Harmer CJ, Morriss R, Brown S, Guo B, Dourish CT, Ruhe HG, Lever AG, Veltman DJ, van Schaik A, Deckert J, Reif A, Stablein M, Menke A, Gorwood P, Voegeli G, Perez V, Browning M (2017) The effects of using the PReDicT test to guide the antidepressant treatment of depressed patients: study protocol for a randomised controlled trial. Trials 18:558
Kohler CA, Evangelou E, Stubbs B, Solmi M, Veronese N, Belbasis L, Bortolato B, Melo MCA, Coelho CA, Fernandes BS, Olfson M, Ioannidis JPA, Carvalho AF (2018) Mapping risk factors for depression across the lifespan: an umbrella review of evidence from meta-analyses and Mendelian randomization studies. J Psychiatr Res 103:189–207
Marr D (1982) Vision: a computational investigation into the human representation and processing of visual information. WH Freeman, San Francisco
Martin AR, Daly MJ, Robinson EB, Hyman SE, Neale BM (2018) Predicting polygenic risk of psychiatric disorders. Biol Psychiatry https://doi.org/10.1016/j.biopsych.2018.12.015
Matsumori K, Koike Y, Matsumoto K (2018) A biased Bayesian inference for decision-making and cognitive control. Front Neurosci 12:734
Menzies P (2012) The causal structure of mechanisms. Stud Hist Phil Biol Biomed Sci 43:796–805
Millner AJ, Gershman SJ, Nock MK, den Ouden HEM (2017) Pavlovian control of escape and avoidance. J Cogn Neurosci 30: 1379-1390
Mkrtchian A, Aylward J, Dayan P, Roiser JP, Robinson OJ (2017a) Modeling avoidance in mood and anxiety disorders using reinforcement learning. Biol Psychiatry 82:532–539
Mkrtchian A, Roiser JP, Robinson OJ (2017b) Threat of shock and aversive inhibition: induced anxiety modulates Pavlovian-instrumental interactions. J Exp Psychol Gen 146:1694–1704
Moons KG, Kengne AP, Grobbee DE, Royston P, Vergouwe Y, Altman DG, Woodward M (2012a) Risk prediction models: II. External validation, model updating, and impact assessment. Heart 98:691–698
Moons KG, Kengne AP, Woodward M, Royston P, Vergouwe Y, Altman DG, Grobbee DE (2012b) Risk prediction models: I. Development, internal validation, and assessing the incremental value of a new (bio)marker. Heart 98:683–690
Moutoussis M, Shahar N, Hauser TU, Dolan RJ (2018) Computation in psychotherapy, or how computational psychiatry can aid learning-based psychological therapies. Comput Psychiatry (Cambridge, Mass) 2:50–73
Nagel M, Watanabe K, Stringer S, Posthuma D, van der Sluis S (2018) Item-level analyses reveal genetic heterogeneity in neuroticism. Nat Commun 9:905
Palminteri S, Wyart V, Koechlin E (2017) The importance of falsification in computational cognitive modeling. Trends Cogn Sci 21:425–433
Papini S, Pisner D, Shumake J, Powers MB, Beevers CG, Rainey EE, Smits JAJ, Warren AM (2018) Ensemble machine learning prediction of posttraumatic stress disorder screening status after emergency room hospitalization. J Anxiety Disord 60:35–42
Paulus MP (2017) Evidence-based pragmatic psychiatry-a call to action. JAMA Psychiatry 74:1185
Paulus MP, Huys QJ, Maia TV (2016) A roadmap for the development of applied computational psychiatry. Biol Psychiatry 1:386–392
Pencina MJ, D’Agostino RB Sr (2012) Thoroughly modern risk prediction? Sci Transl Med 4:131fs10
Powers AR, Mathys C, Corlett PR (2017) Pavlovian conditioning-induced hallucinations result from overweighting of perceptual priors. Science 357:596–600
Price RB, Brown V, Siegle GJ (2019) Computational modeling applied to the dot-probe task yields improved reliability and mechanistic insights. Biol Psychiatry 85:606–612
Rector TS, Taylor BC, Wilt TJ (2012) Chapter 12: systematic review of prognostic tests. J Gen Intern Med 27(Suppl 1):S94–S101
Roberts JA, Friston KJ, Breakspear M (2017a) Clinical applications of stochastic dynamic models of the brain, part I: a primer. Biol Psychiatry 2:216–224
Roberts JA, Friston KJ, Breakspear M (2017b) Clinical applications of stochastic dynamic models of the brain, part II: a review. Biol Psychiatry 2:225–234
Ross CA, Aylward EH, Wild EJ, Langbehn DR, Long JD, Warner JH, Scahill RI, Leavitt BR, Stout JC, Paulsen JS, Reilmann R, Unschuld PG, Wexler A, Margolis RL, Tabrizi SJ (2014) Huntington disease: natural history, biomarkers and prospects for therapeutics. Nat Rev Neurol 10:204–216
Rothman KJ, Greenland S (2005) Causation and causal inference in epidemiology. Am J Public Health 95(Suppl 1):S144–S150
Schnack HG (2017) Improving individual predictions: machine learning approaches for detecting and attacking heterogeneity in schizophrenia (and other psychiatric diseases). Schizophr Res https://doi.org/10.1016/j.schres.2017.10.023
Schnack HG, Kahn RS (2016) Detecting neuroimaging biomarkers for psychiatric disorders: sample size matters. Front Psych 7:50
Schork AJ, Won H, Appadurai V, Nudel R, Gandal M, Delaneau O, Revsbech Christiansen M, Hougaard DM, Baekved-Hansen M, Bybjerg-Grauholm J, Giortz Pedersen M, Agerbo E, Bocker Pedersen C, Neale BM, Daly MJ, Wray NR, Nordentoft M, Mors O, Borglum AD, Bo Mortensen P, Buil A, Thompson WK, Geschwind DH, Werge T (2019) A genome-wide association study of shared risk across psychiatric disorders implicates gene regulation during fetal neurodevelopment. Nat Neurosci 22:353–361
Schultz W, Dayan P, Montague PR (1997) A neural substrate of prediction and reward. Science 275:1593–1599
Scott IA, Greenberg PB (2010) Cautionary tales in the interpretation of studies of tools for predicting risk and prognosis. Intern Med J 40:803–812
Smith DJ, Escott-Price V, Davies G, Bailey ME, Colodro-Conde L, Ward J, Vedernikov A, Marioni R, Cullen B, Lyall D, Hagenaars SP, Liewald DC, Luciano M, Gale CR, Ritchie SJ, Hayward C, Nicholl B, Bulik-Sullivan B, Adams M, Couvy-Duchesne B, Graham N, Mackay D, Evans J, Smith BH, Porteous DJ, Medland SE, Martin NG, Holmans P, McIntosh AM, Pell JP, Deary IJ, O'Donovan MC (2016) Genome-wide analysis of over 106 000 individuals identifies 9 neuroticism-associated loci. Mol Psychiatry 21:749–757
Stephan KE, Mathys C (2014) Computational approaches to psychiatry. Curr Opin Neurobiol 25:85–92
Stephan KE, Schlagenhauf F, Huys QJM, Raman S, Aponte EA, Brodersen KH, Rigoux L, Moran RJ, Daunizeau J, Dolan RJ, Friston KJ, Heinz A (2017) Computational neuroimaging strategies for single patient predictions. Neuroimage 145:180–199
Torkamani A, Wineinger NE, Topol EJ (2018) The personal and clinical utility of polygenic risk scores. Nat Rev Genet 19:581–590
Vaghi MM, Luyckx F, Sule A, Fineberg NA, Robbins TW, De Martino B (2017) Compulsivity reveals a novel dissociation between action and confidence. Neuron 96:348–354.e4
Wager S, Athey S (2018) Estimation and inference of heterogeneous treatment effects using random forests. J Am Stat Assoc 113:1228–1242
Wang JM, Zhu L, Brown VM, De La Garza R 2nd, Newton T, King-Casas B, Chiu PH (2019) In cocaine dependence, neural prediction errors during loss avoidance are increased with cocaine deprivation and predict drug use. Biol Psychiatry: cognitive neuroscience and neuroimaging 4: 291-299
Will GJ, Rutledge RB, Moutoussis M, Dolan RJ (2017) Neural and computational processes underlying dynamic changes in self-esteem. eLife 6 https://doi.org/10.7554/eLife.28098.001
Wolfers T, Doan NT, Kaufmann T, Alnaes D, Moberget T, Agartz I, Buitelaar JK, Ueland T, Melle I, Franke B, Andreassen OA, Beckmann CF, Westlye LT, Marquand AF (2018) Mapping the heterogeneous phenotype of schizophrenia and bipolar disorder using normative models. JAMA Psychiatry (Chicago, Ill) 75:1146–1155
Wolfers T, Beckmann CF, Hoogman M, Buitelaar JK, Franke B, Marquand AF (2019) Individual differences v. the average patient: mapping the heterogeneity in ADHD using normative models. Psychol Med:1–10
Zachar P, Kendler KS (2017) The philosophy of nosology. Annu Rev Clin Psychol 13:49–71
Funding
This research was supported by the Laureate Institute for Brain Research and the National Institute of General Medical Sciences (P20GM121312, Paulus).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Additional information
This article belongs to a Special Issue on Imaging for CNS drug development and biomarkers. Editors O Howes and M Mehta.
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Paulus, M.P., Thompson, W.K. Computational approaches and machine learning for individual-level treatment predictions. Psychopharmacology 238, 1231–1239 (2021). https://doi.org/10.1007/s00213-019-05282-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00213-019-05282-4