Data from: Olfactory testing in Parkinson’s disease & REM behavior disorder: a machine learning approach

Objective: We sought to identify an abbreviated test of impaired
olfaction, amenable for use in busy clinical environments in prodromal
(isolated REM sleep Behavior Disorder (iRBD)) and manifest Parkinson’s.
Methods: 890 PD and 313 control participants in the Discovery
cohort study underwent Sniffin’ stick odour identification assessment.
Random forests were initially trained to distinguish individuals with poor
(functional anosmia/hyposmia) and good (normosmia/super-smeller) smell
ability using all 16 Sniffin’ sticks. Models were retrained using the top
3 sticks ranked by order of predictor importance. One randomly selected
3-stick model was tested in a second independent Parkinson’s dataset
(n=452) and in two iRBD datasets (Discovery n=241;
Marburg  n=37) before being compared to previously
described abbreviated Sniffin’ stick combinations. Results: In
differentiating poor from good smell ability, the overall area under the
curve (AUC) value associated with the top 3 sticks (Anise, Licorice and
Banana) was 0.95 in the development dataset (sensitivity:90%,
specificity:92%, PPV:92%, NPV:90%). Internal and external validation
confirmed AUCs≥0.90. The combination of 3-stick model determined poor
smell and an RBD screening questionnaire score of ≥5, separated iRBD from
controls with a sensitivity, specificity, PPV and NPV of 65%, 100%, 100%
and 30%.  Conclusions: Our 3-Sniffin’-stick model holds
potential utility as a brief screening test in the stratification of
individuals with Parkinson’s and iRBD according to olfactory dysfunction.
Classification of Evidence: This study provides Class III
evidence that a 3-Sniffin’-stick model distinguishes individuals with poor
and good smell ability and can be used to screen for individuals with
iRBD.