Skip to main content
SpringerLink
Log in

Machine-learning-derived rules set excludes risk of Parkinson’s disease in patients with olfactory or gustatory symptoms with high accuracy

  • Original Communication
  • Published:
Journal of Neurology Aims and scope Submit manuscript

Abstract

Background

Chemosensory loss is a symptom of Parkinson’s disease starting already at preclinical stages. Their appearance without an identifiable etiology therefore indicates a possible early symptom of Parkinson’s disease. Supervised machine-learning was used to identify parameters that predict Parkinson’s disease among patients having sought medical advice for chemosensory symptoms.

Methods

Olfactory, gustatory and demographic parameters were analyzed in 247 patients who had reported for chemosensory symptoms. Unsupervised machine-learning, implanted as so-called fast and frugal decision trees, was applied to map these parameters to a diagnosis of Parkinson’s disease queried for in median 9 years after the first interview.

Results

A symbolic hierarchical decision rule-based classifier was created that comprised d = 5 parameters, including scores in tests of odor discrimination, odor identification and olfactory thresholds, the age at which the chemosensory loss has been noticed, and a familial history of Parkinson’s disease. The rule set provided a cross-validated negative predictive performance of Parkinson’s disease of 94.1%; however, its balanced accuracy to predict the disease was only 58.9% while robustly above guessing.

Conclusions

Applying machine-learning techniques, a classifier was developed that took the shape of a set of six hierarchical rules with binary decisions about olfaction-related features or a familial burden of Parkinson’s disease. Its main clinical strength lies in the exclusion of the possibility of developing Parkinson’s disease in a patient with olfactory or gustatory loss.

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.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Ansari KA, Johnson A (1975) Olfactory function in patients with Parkinson's disease. J Chron Dis. 28:493–497

    CAS  PubMed  Google Scholar 

  2. Korten J, Meulstee J (1980) Olfactory disturbances in parkinsonism. Clin Neurol Neurosurg 82:113–118

    CAS  PubMed  Google Scholar 

  3. Ward CD, Hess WA, Calne DB (1983) Olfactory impairment in Parkinson's disease. Neurology 33:943–946

    CAS  PubMed  Google Scholar 

  4. Serby M, Corwin J, Conrad P, Rotrosen J (1985) Olfactory dysfunction in Alzheimer's disease and Parkinson's disease [letter]. Am J Psychiatry 142(6):781–782

    CAS  PubMed  Google Scholar 

  5. Doty RL, Deems D, Steller S (1988) Olfactory dysfunction in Parkinson's disease: a general deficit unrelated to neurologic signs, disease stage, or disease duration. Neurology 38:1237–1244

    CAS  PubMed  Google Scholar 

  6. Haehner A, Masala C, Walter S, Reichmann H, Hummel T (2019) Incidence of Parkinson's disease in a large patient cohort with idiopathic smell and taste loss. J Neurol 266(2):339–345

    PubMed  Google Scholar 

  7. Heilmann S, Hüttenbrink KB, Hummel T (2004) Local and systemic administration of corticosteroids in the treatment of olfactory loss. Am J Rhinol 18:29–33

    PubMed  Google Scholar 

  8. Lötsch J, Hummel T (2019) A machine-learned analysis suggests non-redundant diagnostic information in olfactory subtests. IBRO Rep 6:64–73

    PubMed  PubMed Central  Google Scholar 

  9. Kobal G, Hummel T, Sekinger B, Barz S, Roscher S, Wolf SR (1996) "Sniffin' Sticks": screening of olfactory performance. Rhinology 34:222–226

    CAS  PubMed  Google Scholar 

  10. Hummel T, Sekinger B, Wolf SR, Pauli E, Kobal G (1997) 'Sniffin' sticks': olfactory performance assessed by the combined testing of odor identification, odor discrimination and olfactory threshold. Chem Senses 22(1):39–52

    CAS  PubMed  Google Scholar 

  11. Hummel T, Kobal G, Gudziol H, Mackay-Sim A (2007) Normative data for the "Sniffin' Sticks" including tests of odor identification, odor discrimination, and olfactory thresholds: an upgrade based on a group of more than 3,000 subjects. Eur Arch Otorhinolaryngol 264(3):237–243

    CAS  PubMed  Google Scholar 

  12. Frasnelli J, Landis BN, Heilmann S, Hauswald B, Huttenbrink KB, Lacroix JS et al (2003) Clinical presentation of qualitative olfactory dysfunction. Eur Arch Otorhinolaryngol 11:11–13

    Google Scholar 

  13. Landis BN, Welge-Luessen A, Bramerson A, Bende M, Mueller CA, Nordin S et al (2009) "Taste Strips"—a rapid, lateralized, gustatory bedside identification test based on impregnated filter papers. J Neurol 256(2):242–248

    PubMed  Google Scholar 

  14. Hummel T, Hummel C, Welge-Luessen A (2013) Assessment of olfaction and gustation. In: Hummel T, Welge-Luessen A (eds) Management of smell and taste disorders: a practical guide for clinicians. Thieme, Stuttgart, pp 58–75

    Google Scholar 

  15. R Development Core Team. R: a language and environment for statistical computing. 2008.

  16. Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theor 13(1):21–27

    Google Scholar 

  17. Torgo L (2010) Data mining with R: learning with case studies. Chapman & Hall, London

    Google Scholar 

  18. Rosenbaum PR, Rubin DB (1983) The central role of the propensity score in observational studies for causal effects. Biometrika 70(1):41–55

    Google Scholar 

  19. Student (1908) The probable error of a mean. Biometrika 6(1):1–25

    Google Scholar 

  20. Wilcoxon F (1945) Individual comparisons by ranking methods. Biometrics 1:80–83

    Google Scholar 

  21. Pearson K (1900) On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling. Philos Mag Ser 5(50):157–175

    Google Scholar 

  22. Newell A, Simon HA (1976) Computer science as empirical inquiry: symbols and search. Commun ACM 19(3):113–126

    Google Scholar 

  23. Gigerenzer G, Todd PM (1999) Fast and frugal heuristics: the adaptive toolbox. Simple heuristics that make us smart. Evolution and cognition. Oxford University Press, New York, pp 3–34

    Google Scholar 

  24. Martignon L, Katsikopoulos KV, Woike JK (2008) Categorization with limited resources: a family of simple heuristics. J Math Psychol 52(6):352–361

    Google Scholar 

  25. Marewski JN, Gigerenzer G (2012) Heuristic decision making in medicine. Dialogues Clin Neurosci 14(1):77–89

    PubMed  PubMed Central  Google Scholar 

  26. Gigerenzer G, Czerlinski J, Martignon L. How good are fast and frugal heuristics? In: Shanteau J, Mellers BA, Schum DA, editors. Decision science and technology: reflections on the contributions of ward edwards. Boston: Springer US; 1999. p. 81–103.

    Google Scholar 

  27. Phillips N, Neth H, Woike J, Gaissmaer W. FFTrees: generate, visualise, and evaluate fast-and-frugal decision trees. R package version 1.4.0. 2018.

  28. Phillips ND, Neth H, Woike JK, Gaissmaier W (2017) FFTrees: a toolbox to create, visualize, and evaluate fast-and-frugal decision trees. Judgm Decis Mak 12(4):344–368

    Google Scholar 

  29. Tillé Y, Matei A (2016) Sampling: survey sampling. R package version 2.8. https://CRAN.R-project.org/package=sampling

  30. Ultsch A, Lötsch J (2015) Computed ABC analysis for rational selection of most informative variables in multivariate data. PLoS ONE 10(6):e0129767

    PubMed  PubMed Central  Google Scholar 

  31. Wild A (1997) Best practice in inventory management. Wiley, New York

    Google Scholar 

  32. Altman DG, Bland JM (1994) Diagnostic tests 2: predictive values. BMJ 309(6947):102

    CAS  PubMed  PubMed Central  Google Scholar 

  33. Altman DG, Bland JM (1994) Diagnostic tests. 1: sensitivity and specificity. BMJ 308(6943):1552

    CAS  PubMed  PubMed Central  Google Scholar 

  34. Martignon L, Vitouch O, Takezawa M, Forster M, Hardman D, Macchi L. Thinking: psychological perspective on reasoning, judgment, and decision making. In: Hardman D, Macchi L, editors. 2003. pp.189–211.

  35. Martignon L, Katsikopoulos KV, Woike JK, editors. Categorization with limited resources: a family of simple heuristics. 2008.

  36. Lotsch J, Kringel D, Hummel T. Machine learning in human olfactory research. Chem Senses. 2018.

  37. Ross GW, Petrovitch H, Abbott RD, Tanner CM, Popper J, Masaki K et al (2008) Association of olfactory dysfunction with risk for future Parkinson's disease. Ann Neurol 63(2):167–173

    PubMed  Google Scholar 

  38. Postuma RB, Gagnon JF, Vendette M, Desjardins C, Montplaisir JY (2011) Olfaction and color vision identify impending neurodegeneration in rapid eye movement sleep behavior disorder. Ann Neurol 69(5):811–818

    PubMed  Google Scholar 

  39. Ponsen MM, Stoffers D, Twisk JW, Wolters E, Berendse HW (2009) Hyposmia and executive dysfunction as predictors of future Parkinson's disease: a prospective study. Mov Disord 24(7):1060–1065

    PubMed  Google Scholar 

  40. Cox D (1972) Regression models and life tables. J R Stat Soc B 34:187–220

    Google Scholar 

  41. Lötsch J, Reichmann H, Hummel T (2008) Different odor tests contribute differently to the evaluation of olfactory loss. Chem Senses 33(1):17–21

    PubMed  Google Scholar 

  42. Hedner M, Larsson M, Arnold N, Zucco GM, Hummel T (2010) Cognitive factors in odor detection, odor discrimination, and odor identification tasks. J Clin Exp Neuropsychol 32(10):1062–1067

    PubMed  Google Scholar 

  43. Mahlknecht P, Iranzo A, Hogl B, Frauscher B, Muller C, Santamaria J et al (2015) Olfactory dysfunction predicts early transition to a Lewy body disease in idiopathic RBD. Neurology 84(7):654–658

    PubMed  Google Scholar 

  44. Mogensen UB, Ishwaran H, Gerds TA (2012) Evaluating random forests for survival analysis using prediction error curves. J Stat Softw 50(11):1–23

    PubMed  PubMed Central  Google Scholar 

  45. Berg D, Postuma RB, Adler CH, Bloem BR, Chan P, Dubois B et al (2015) MDS research criteria for prodromal Parkinson's disease. Mov Disord 30(12):1600–1611

    PubMed  Google Scholar 

  46. Postuma RB, Gagnon JF, Bertrand JA, Genier Marchand D, Montplaisir JY (2015) Parkinson risk in idiopathic REM sleep behavior disorder: preparing for neuroprotective trials. Neurology 84(11):1104–1113

    PubMed  PubMed Central  Google Scholar 

  47. Gustafsson H, Nordstrom A, Nordstrom P (2015) Depression and subsequent risk of Parkinson disease: a nationwide cohort study. Neurology 84(24):2422–2429

    PubMed  PubMed Central  Google Scholar 

  48. Abbott RD, Petrovitch H, White LR, Masaki KH, Tanner CM, Curb JD et al (2001) Frequency of bowel movements and the future risk of Parkinson's disease. Neurology 57(3):456–462

    CAS  PubMed  Google Scholar 

  49. Schrag A, Horsfall L, Walters K, Noyce A, Petersen I (2015) Prediagnostic presentations of Parkinson's disease in primary care: a case-control study. Lancet Neurol 14(1):57–64

    PubMed  Google Scholar 

  50. Postuma RB, Lang AE, Gagnon JF, Pelletier A, Montplaisir JY (2012) How does parkinsonism start? Prodromal parkinsonism motor changes in idiopathic REM sleep behaviour disorder. Brain 135(Pt 6):1860–1870

    CAS  PubMed  Google Scholar 

  51. Iranzo A, Lomena F, Stockner H, Valldeoriola F, Vilaseca I, Salamero M et al (2010) Decreased striatal dopamine transporter uptake and substantia nigra hyperechogenicity as risk markers of synucleinopathy in patients with idiopathic rapid-eye-movement sleep behaviour disorder: a prospective study [corrected]. Lancet Neurol 9(11):1070–1077

    CAS  PubMed  Google Scholar 

  52. Tremblay C, Durand Martel P, Frasnelli J (2017) Trigeminal system in Parkinson's disease: a potential avenue to detect Parkinson-specific olfactory dysfunction. Parkinsonism Relat Disord 44:85–90

    PubMed  Google Scholar 

  53. Lötsch J, Lerch F, Djaldetti R, Tegeder I, Ultsch A (2018) Identification of disease-distinct complex biomarker patterns by means of unsupervised machine-learning using an interactive R toolbox (Umatrix). BMC Big Data Anal. https://doi.org/10.1186/s41044-018-0032-1

    Article  Google Scholar 

  54. Pearson K (1904) Report on certain enteric fever inoculation statistics. BMJ 3:1243–1246

    Google Scholar 

  55. Ultsch A, editor. Pareto density estimation: a density estimation for knowledge discovery. Innovations in classification, data science, and information systems. In: Proceedings 27th annual conference of the German Classification Society (GfKL). Berlin: Springer; 2003.

Download references

Funding

This work has been funded by the Landesoffensive zur Entwicklung wissenschaftlich-ökonomischer Exzellenz (LOEWE), LOEWE-Zentrum für Translationale Medizin und Pharmakologie (JL). We also would like to thank the Deutsche Forschungsgemeinschaft for support (DFG HU 441/18-1 to TH). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Author information

Authors and Affiliations

  1. Institute of Clinical Pharmacology, Goethe-University, Theodor Stern Kai 7, 60590, Frankfurt am Main, Germany

    Jörn Lötsch

  2. Fraunhofer Institute of Molecular Biology and Applied Ecology-Project Group Translational Medicine and Pharmacology (IME-TMP), Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany

    Jörn Lötsch

  3. Department of Otorhinolaryngology, Smell and Taste Clinic, TU Dresden, Fetscherstrasse 74, 01307, Dresden, Germany

    Antje Haehner & Thomas Hummel

Authors
  1. Jörn Lötsch
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Antje Haehner
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Thomas Hummel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jörn Lötsch.

Ethics declarations

Conflicts of interest

The authors have declared that no competing interests exist.

Ethical approval

The study has been approved by the Ethics Committee of the Medical Faculty of the Technical University of Dresden, Germany and has therefore been performed in accordance with the ethical standards laid down in the 1964 Declaration of Helsinki and its later amendments.

Informed consent

All persons gave their informed consent prior to their inclusion in the study. Details that might disclose the identity of the subjects under study are omitted.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lötsch, J., Haehner, A. & Hummel, T. Machine-learning-derived rules set excludes risk of Parkinson’s disease in patients with olfactory or gustatory symptoms with high accuracy. J Neurol 267, 469–478 (2020). https://doi.org/10.1007/s00415-019-09604-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00415-019-09604-6

Keywords

Search

Navigation