Skip to main content

Advertisement

SpringerLink
Log in

Deficit schizophrenia is a discrete diagnostic category defined by neuro-immune and neurocognitive features: results of supervised machine learning

  • Original Article
  • Published:
Metabolic Brain Disease Aims and scope Submit manuscript

Abstract

Deficit schizophrenia is characterized by neurocognitive impairments and changes in the patterning of IgA/IgM responses to plasma tryptophan catabolites (TRYCATs). In the current study, supervised pattern recognition methods, including logistic regression analysis (LRA), Support Vector Machine (SVM), and Soft Independent Modeling of Class Analogy (SIMCA), were used to examine whether deficit schizophrenia is a discrete diagnostic class with respect to Consortium To Establish a Registry for Alzheimer’s disease (CERAD) and Cambridge Neuropsychological Test Automated Battery (CANTAB) tests and IgA/IgM responses to noxious (NOX) and generally more protective (PRO) TRYCATs. We recruited patients with (n = 40) and without (n = 40) deficit schizophrenia and healthy volunteers (n = 40). The combined use of TRYCAT and CERAD features strongly segregates deficit from nondeficit schizophrenia and healthy controls. Three out of the top five most important features in LRA, SVM and SIMCA agreed, namely two different NOX/PRO TRYCAT ratios and false memory recall. SIMCA shows that deficit schizophrenia is significantly separated from nondeficit schizophrenia and controls with as top 6 features IgA responses to picolinic acid, IgM responses to 3-OH-kynurenine and kynurenic acid, and impairments in Word List Memory and Verbal Fluency Tests and Mini-Mental State Examination. Nevertheless, nondeficit schizophrenia was not significantly separated from controls. The results show that schizophrenia is not a unitary disease with mere continuous differences in severity of illness between apparent subtypes. Deficit schizophrenia is a qualitatively distinct class defined by neuroimmune (autoimmune responses to TRYCATs) and neurocognitive (episodic and semantic memory) features coupled or not with clinical (negative) symptoms.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

References

  • Ahmed AO, Strauss GP, Buchanan RW, Kirkpatrick B, Carpenter WT (2015) Are Negative Symptoms Dimensional or Categorical? Detection and Validation of Deficit Schizophrenia With Taxometric and Latent Variable Mixture Models. Schizophr Bull 41(4):879–891

    Article  PubMed  Google Scholar 

  • American Psychiatric Association (2000) Diagnostic and statistical manual of mental disorders: DSM-IV-TR. American Psychiatric Association, Washington, DC

    Google Scholar 

  • American Psychiatric Association (2013) Diagnostic and statistical manual of mental disorders (5th ed.). American Association, Arlington

  • Andreasen NC (1989) The Scale for the Assessment of Negative Symptoms (SANS): conceptual and theoretical foundations. Br J Psychiatry Suppl 7:49–58

    Article  Google Scholar 

  • Beeri MS, Schmeidler J, Sano M, Wang J, Lally R, Grossman H, Silverman JM (2006) Age, gender, and education norms on the CERAD neuropsychological battery in the oldest old. Neurology 67(6):1006–1010

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  • Benjamini Y, Hochberg Y (1995) Controlling the false discovery rate: a practical and powerful approach to multiple testing. J R Stat Soc Ser B Methodol 57:289–300

    Google Scholar 

  • Berrios GE, Luque RVJM (2003) "Schizophrenia: a conceptual history" (PDF). Int J Psychol Psychol Ther 3:111–140

    Google Scholar 

  • CANTAB (2017) Test-batteries/schizophrenia: http://www.cambridgecognition.com/cantab/test-batteries/schizophrenia. As accessed 5 Oct 2017

  • CERAD (1986) CERAD – An Overview: The Consortium to Establish a Registry for Alzheimer’s Disease. http://cerad.mc.duke.edu/

  • Cohen AS, Docherty NM (2004) Deficit versus negative syndrome in schizophrenia: prediction of attentional impairment. Schizophr Bull 30:827–835

    Article  PubMed  Google Scholar 

  • Cohen AS, Brown LA, Minor KS (2010) The psychiatric symptomatology of deficit schizophrenia: a meta-analysis. Schizophr Res 118(1–3):122–127

    Article  PubMed  Google Scholar 

  • Cuthbert BN, Insel TR (2013) Toward the future of psychiatric diagnosis: the seven pillars of RDoC. BMC Med 11:126

    Article  PubMed  PubMed Central  Google Scholar 

  • Derde M-P, Massart DL (1982) Extraction of information from large data sets by pattern recognition. Fresenius' Z Anal Chem 313:484–495

    Article  CAS  Google Scholar 

  • Derde M-P, Coomans D, Massart DL (1984) SIMCA (soft independent modeling of class analogy) demonstrated with characterization and classification of Italian olive oil. J Assoc Off Anal Chem 67:721–726

    CAS  Google Scholar 

  • Fervaha G, Takeuchi H, Foussias G, Agid O, Remington G (2016) Using poverty of speech as a case study to explore the overlap between negative symptoms and cognitive dysfunction. Schizophr Res 176:411–416

    Article  PubMed  Google Scholar 

  • Iwabuchi SJ, Liddle PF, Palaniyappan L (2013) Clinical utility of machine-learning approaches in schizophrenia: improving diagnostic confidence for translational neuroimaging. Front Psych 4:95

    Google Scholar 

  • Kaiser S, Heekeren K, Simon JJ (2011) The negative symptoms of schizophrenia: category or continuum? Psychopathology 44:345–353

    Article  PubMed  Google Scholar 

  • Kanchanatawan B, Hemrungrojn S, Thika S, Sirivichayakul S, Ruxrungtham K, Carvalho AF, Geffard M, Anderson G, Maes M (2017a) Changes in Tryptophan Catabolite (TRYCAT) Pathway Patterning Are Associated with Mild Impairments in Declarative Memory in Schizophrenia and Deficits in Semantic and Episodic Memory Coupled with Increased False-Memory Creation in Deficit Schizophrenia. Mol Neurobiol Sep 5. https://doi.org/10.1007/s12035-017-0751-8

  • Kanchanatawan B, Sirivichayakul S, Ruxrungtham K, Carvalho AF, Geffard M, Anderson G, Maes M (2017b) Deficit Schizophrenia Is Characterized by Defects in IgM-Mediated Responses to Tryptophan Catabolites (TRYCATs): a Paradigm Shift Towards Defects in Natural Self-Regulatory Immune Responses Coupled with Mucosa-Derived TRYCAT Pathway Activation. Mol Neurobiol Mar 14. https://doi.org/10.1007/s12035-017-0465-y

  • Kanchanatawan B, Sirivichayakul S, Ruxrungtham K, Carvalho AF, Geffard M, Ormstad H, Anderson G, Maes M (2017c) Deficit, but Not Nondeficit, Schizophrenia Is Characterized by Mucosa-Associated Activation of the Tryptophan Catabolite (TRYCAT) Pathway with Highly Specific Increases in IgA Responses Directed to Picolinic, Xanthurenic, and Quinolinic Acid. Mol Neurobiol. Feb 8. https://doi.org/10.1007/s12035-017-0417-6

  • Kaplan EF, Goodglass H, Weintraub S (1978) The Boston Naming Test. Veterans Administration Medical Center, Boston

    Google Scholar 

  • Kay SR, Fiszbein A, Opler LA (1987) The positive and negative syndrome scale (PANSS) for schizophrenia. Schizophr Bull 13:261–276

    Article  PubMed  CAS  Google Scholar 

  • Kirkpatrick B, Buchanan RW, McKenney PD, Alphs LD, Carpenter WT Jr (1989) The Schedule for the Deficit syndrome: an instrument for research in schizophrenia. Psychiatry Res 30:119–123

    Article  PubMed  CAS  Google Scholar 

  • Kita T, Morrison PF, Heyes MP, Markey SP (2002) Effects of systemic and central nervous system localized inflammation on the contributions of metabolic precursors to the L-kynurenine and quinolinic acid pools in brain. J Neurochem 82:258–268

    Article  PubMed  CAS  Google Scholar 

  • Kittirathanapaiboon P, Khamwongpin M (2005) The Validity of the Mini International Neuropsychiatric Interview (M.I.N.I.) Thai Version. Suanprung Hospital, Department of Mental Health

  • Kuhn R, Cahn CH (2004) Eugen Bleuler’s Concepts of Psychopathology. Hist Psychiatry 15:361–366

    Article  PubMed  Google Scholar 

  • Kyziridis TC (2005) Notes on the History of Schizophrenia. Ger J Psychol 8:42–48

    Google Scholar 

  • Lieberman JA, Jody D, Alvir MJ, Borenstein M, Mayerhoff DI, Geisler S, Szymanski S, Gonzales A, Bogerts B (1991) Negative Symptoms in Schizophrenia: Relationship to Positive Symptoms and Outcome. In: Marneros A, Andreasen N, Tsuang MT (eds) Negative Versus Positive Schizophrenia. Springer-Verlag, Berlin Heidelberg, pp 109–125

    Chapter  Google Scholar 

  • Maes M (2009) "Functional" or "psychosomatic" symptoms, e.g. a flu-like malaise, aches and pain and fatigue, are major features of major and in particular of melancholic depression. Neuro Endocrinol Lett 30:564–573

    PubMed  Google Scholar 

  • Maes M, Cosyns P, Maes L, D'Hondt P, Schotte C (1990a) Clinical subtypes of unipolar depression: Part I. A validation of the vital and nonvital clusters. Psychiatry Res 34:29–41

    Article  PubMed  CAS  Google Scholar 

  • Maes M, Schotte C, Maes L, Cosyns P (1990b) Clinical subtypes of unipolar depression: Part II. Quantitative and qualitative clinical differences between the vital and nonvital depression groups. Psychiatry Res 34:43–57

    Article  PubMed  CAS  Google Scholar 

  • Maes M, Maes L, Schotte C, Vandewoude M, Martin M, D'Hondt P, Blockx P, Scharpé S, Cosyns P (1990c) Clinical subtypes of unipolar depression: Part III. Quantitative differences in various biological markers between the cluster-analytically generated nonvital and vital depression classes. Psychiatry Res 34:59–75

    Article  PubMed  CAS  Google Scholar 

  • Maes M, Maes L, Schotte C, Cosyns P (1992) A clinical and biological validation of the DSM-III melancholia diagnosis in men: results of pattern recognition methods. J Psychiatr Res 26:183–196

    Article  PubMed  CAS  Google Scholar 

  • Maes M, Leonard BE, Myint AM, Kubera M, Verkerk R (2011) The new '5-HT' hypothesis of depression: cell-mediated immune activation induces indoleamine 2,3-dioxygenase, which leads to lower plasma tryptophan and an increased synthesis of detrimental tryptophan catabolites (TRYCATs), both of which contribute to the onset of depression. Prog Neuro-Psychopharmacol Biol Psychiatry 35:702–721

    Article  CAS  Google Scholar 

  • Maes M, Twisk FN, Johnson C (2012) Myalgic Encephalomyelitis (ME), Chronic Fatigue Syndrome (CFS), and Chronic Fatigue (CF) are distinguished accurately: results of supervised learning techniques applied on clinical and inflammatory data. Psychiatry Res 200(2-3):754–60

  • Maes M (2015) A new case definition of Neuro-Inflammatory and Oxidative Fatigue (NIOF), a neuroprogressive disorder, formerly known as chronic fatigue syndrome or Myalgic Encephalomyelitis: results of multivariate pattern recognition methods and external validation by neuro-immune biomarkers. Neuro Endocrinol Lett 36:320–329

    PubMed  CAS  Google Scholar 

  • Mak M, Misiak B, Frydecka D, Pełka-Wysiecka J, Kucharska-Mazur J, Samochowiec A, Bieńkowski P, Pawlak-Adamska E, Karabon L, Szmida E, Skiba P, Kotowicz K, Piotrowski P, Beszłej JA, Samochowiec J (2017) Polymorphisms in immune-inflammatory response genes and the risk of deficit schizophrenia. Schizophr Res. 2017 Jun 30. https://doi.org/10.1016/j.schres.2017.06.050

  • Marder SR, Galderisi S (2017) The current conceptualization of negative symptoms in schizophrenia. World Psychiatry 16(1):14–24

    Article  PubMed  PubMed Central  Google Scholar 

  • Marneros A, Deister A, Rohde A (1991) Long-Term Monomorphism of Negative and Positive Schizophrenic Episodes. In: Marneros A, Andreasen N, Tsuang MT (eds) Negative Versus Positive Schizophrenia. Springer-Verlag, Berlin Heidelberg, pp 183–196

    Chapter  Google Scholar 

  • Massart L, Kaufman L (1983) Nonhierarchical clustering methods. In: Elving PJ, Winefordner JD (eds) The Interpretation of Analytical Chemical Data by the Use of Cluster Analysis. Wiley, New York, pp 101–138

    Google Scholar 

  • Morris G, Maes M (2013) Case definitions and diagnostic criteria for Myalgic Encephalomyelitis and Chronic fatigue Syndrome: from clinical-consensus to evidence-based case definitions. Neuro Endocrinol Lett 34:185–199

    PubMed  Google Scholar 

  • Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830

    Google Scholar 

  • Sharaf MA, lllman DL, Kowalski BR (1986) Unsupervised learning. In: Chemometrics. Wiley, New York, pp. 219–228

  • Welsh KA, Butters N, Mohs RC, Beekly D, Edland S, Fillenbaum G, Heyman A (1994) The Consortium to Establish a Registry for Alzheimer's Disease (CERAD). Part V. A normative study of the neuropsychological battery. Neurology 44:609–614

    Article  PubMed  CAS  Google Scholar 

  • Wold S, Sjostrom M (1977) SIMCA: A method for analyzing chemical data in terms of similarity and analogy. In: Kowalski BR (ed) Chemometrics Theory and Application, American Chemical Society Symposium Series 52. American Chemical Society, Washington DC, pp 243–282

    Chapter  Google Scholar 

  • Yu M, Tang X, Wang X, Zhang X, Zhang X, Sha W, Yao S, Shu N, Zhang X, Zhang Z (2015) Neurocognitive Impairments in Deficit and Non-Deficit Schizophrenia and Their Relationships with Symptom Dimensions and Other Clinical Variables. PLoS One 10:e0138357

    Article  PubMed  PubMed Central  CAS  Google Scholar 

Download references

Acknowledgements

The study was supported by the Asahi Glass Foundation, Chulalongkorn University Centenary Academic Development Project.

Author information

Authors and Affiliations

  1. Department of Psychiatry, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand

    Buranee Kanchanatawan, Supaksorn Thika & Michael Maes

  2. Research Affairs, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand

    Sira Sriswasdi

  3. Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand

    Sunee Sirivichayakul

  4. Department of Clinical Medicine and Translational Psychiatry Research Group, Faculty of Medicine, Federal University of Ceará, Fortaleza, CE, Brazil

    André F. Carvalho

  5. Research Department, IDRPHT, Talence, France

    Michel Geffard

  6. GEMAC, Saint Jean d’Illac, France

    Michel Geffard

  7. Department of Experimental Neuroendocrinology, Institute of Pharmacology, Polish Academy of Sciences, Krakow, Poland

    Marta Kubera

  8. Department of Psychiatry, Medical University of Plovdiv, Plovdiv, Bulgaria

    Michael Maes

  9. IMPACT Strategic Research Center, Barwon Health, Deakin University, Geelong, Vic, Australia

    Michael Maes

Authors
  1. Buranee Kanchanatawan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sira Sriswasdi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Supaksorn Thika
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sunee Sirivichayakul
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. André F. Carvalho
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Michel Geffard
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Marta Kubera
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Michael Maes
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All the contributing authors have participated in the manuscript. MM and BK designed the study. BK recruited patients and completed diagnostic interviews and rating scale measurements. MM and SiSri carried out the statistical analyses. ST carried out the cognitive tests. SS and MG performed the TRYCAT assays. All authors (BK, SiSri, ST, SS, AC, MG, MK and MM) contributed to interpretation of the data and writing of the manuscript. All authors approved the final version of the manuscript.

Corresponding author

Correspondence to Michael Maes.

Ethics declarations

Conflict of interest

The authors have no conflict of interest with any commercial or other association in connection with the submitted article.

Electronic supplementary material

ESM 1

Electronic supplementary material showing four figures displaying the neuroimmune and cognitive differences between normal controls and participants with deficit and nondeficit schizophrenia. (PDF 486 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kanchanatawan, B., Sriswasdi, S., Thika, S. et al. Deficit schizophrenia is a discrete diagnostic category defined by neuro-immune and neurocognitive features: results of supervised machine learning. Metab Brain Dis 33, 1053–1067 (2018). https://doi.org/10.1007/s11011-018-0208-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11011-018-0208-4

Keywords

Search

Navigation