Literature DB >> 31676975

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

Jörn Lötsch1,2, Antje Haehner3, Thomas Hummel3.   

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.

Entities:  

Keywords:  Data science; Decision trees; Machine-learning; Olfaction; Parkinson’s disease

Mesh:

Year:  2019        PMID: 31676975     DOI: 10.1007/s00415-019-09604-6

Source DB:  PubMed          Journal:  J Neurol        ISSN: 0340-5354            Impact factor:   4.849


  32 in total

1.  Olfactory function in patients with Parkinson's disease.

Authors:  K A Ansari; A Johnson
Journal:  J Chronic Dis       Date:  1975-10

2.  'Sniffin' sticks': olfactory performance assessed by the combined testing of odor identification, odor discrimination and olfactory threshold.

Authors:  T Hummel; B Sekinger; S R Wolf; E Pauli; G Kobal
Journal:  Chem Senses       Date:  1997-02       Impact factor: 3.160

3.  Parkinson risk in idiopathic REM sleep behavior disorder: preparing for neuroprotective trials.

Authors:  Ronald B Postuma; Jean-Francois Gagnon; Josie-Anne Bertrand; Daphné Génier Marchand; Jacques Y Montplaisir
Journal:  Neurology       Date:  2015-02-13       Impact factor: 9.910

4.  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.

Authors:  T Hummel; G Kobal; H Gudziol; A Mackay-Sim
Journal:  Eur Arch Otorhinolaryngol       Date:  2006-09-23       Impact factor: 2.503

5.  Diagnostic tests 2: Predictive values.

Authors:  D G Altman; J M Bland
Journal:  BMJ       Date:  1994-07-09

6.  Frequency of bowel movements and the future risk of Parkinson's disease.

Authors:  R D Abbott; H Petrovitch; L R White; K H Masaki; C M Tanner; J D Curb; A Grandinetti; P L Blanchette; J S Popper; G W Ross
Journal:  Neurology       Date:  2001-08-14       Impact factor: 9.910

7.  Olfaction and color vision identify impending neurodegeneration in rapid eye movement sleep behavior disorder.

Authors:  Ronald B Postuma; Jean-François Gagnon; Mélanie Vendette; Catherine Desjardins; Jacques Y Montplaisir
Journal:  Ann Neurol       Date:  2011-01-18       Impact factor: 10.422

8.  Different odor tests contribute differently to the evaluation of olfactory loss.

Authors:  Jörn Lötsch; Heinz Reichmann; Thomas Hummel
Journal:  Chem Senses       Date:  2007-08-30       Impact factor: 3.160

9.  "Taste Strips" - a rapid, lateralized, gustatory bedside identification test based on impregnated filter papers.

Authors:  Basile Nicolas Landis; Antje Welge-Luessen; Annika Brämerson; Mats Bende; Christian Albert Mueller; Steven Nordin; Thomas Hummel
Journal:  J Neurol       Date:  2009-02-07       Impact factor: 4.849

10.  Local and systemic administration of corticosteroids in the treatment of olfactory loss.

Authors:  Stefan Heilmann; Karl-Bernd Huettenbrink; Thomas Hummel
Journal:  Am J Rhinol       Date:  2004 Jan-Feb
View more
  1 in total

Review 1.  Olfactory-Trigeminal Interactions in Patients with Parkinson's Disease.

Authors:  Cécilia Tremblay; Johannes Frasnelli
Journal:  Chem Senses       Date:  2021-01-01       Impact factor: 3.160

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.