Proof-of-concept: SCENTinel 1.1 rapidly discriminates COVID-19-related olfactory disorders

Abstract

It is estimated that 20%-67% of those with COVID-19 develop olfactory disorders, depending on the SARS-CoV-2 variant. However, there is an absence of quick, population-wide olfactory tests to screen for olfactory disorders. The purpose of this study was to provide a proof-of-concept that SCENTinel 1.1, a rapid, inexpensive, population-wide olfactory test, can discriminate between anosmia (total smell loss), hyposmia (reduced sense of smell), parosmia (distorted odor perception), and phantosmia (odor sensation without a source). Participants were mailed a SCENTinel 1.1 test, which measures odor detection, intensity, identification, and pleasantness, using one of 4 possible odors. Those who completed the test (N = 287) were divided into groups based on their self-reported olfactory function: quantitative olfactory disorder only (anosmia or hyposmia, N = 135), qualitative olfactory disorder only (parosmia and/or phantosmia; N = 86), and normosmia (normal sense of smell; N = 66). SCENTinel 1.1 accurately discriminates quantitative olfactory disorders, qualitative olfactory disorders, and normosmia groups. When olfactory disorders were assessed individually, SCENTinel 1.1 discriminates between hyposmia, parosmia, and anosmia. Participants with parosmia rated common odors less pleasant than those without parosmia. We provide proof-of-concept that SCENTinel 1.1, a rapid smell test, can discriminate quantitative and qualitative olfactory disorders, and is the only direct test to rapidly discriminate parosmia.

Keywords: anosmia; hyposmia; parosmia; phantosmia; prediction; smell test.

Fig. 1.

Validation of the original SCENTinel 1.0 classification model. SCENTinel 1.1-discriminated anosmia and normosmia in a COVID-19-related population (teal color; n = 51 with anosmia, 66 with normosmia) were well fitted to the original SCENTinel 1.0 classification model. Melon color refers to the model performance of SCENTinel 1.0 with the original sample (n = 111 with anosmia, 154 with normosmia). False- and true-positive rates correspond to the performance of the classification model to accurately predict an individual as someone with “anosmia” or someone with “normosmia” based on their SCENTinel results.

Fig. 2.

ROC curves and statistics on SCENTinel 1.1 scores overall and for single subtests across groups based on the linear discriminant analysis algorithm: A) individuals with normosmia (n = 66) versus quantitative dysfunction (n = 135); B) individuals with quantitative dysfunction versus qualitative dysfunction (n = 86); C) individuals with normosmia versus qualitative dysfunction. Quantitative dysfunction encompasses individuals with anosmia or hyposmia; qualitative dysfunction includes individuals with parosmia and/or phantosmia. Intensity and hedonics are continuous. D, DeLong’s test for 2 ROC curves; df, degrees of freedom.

Fig. 3.

Investigation of the hedonic score across individuals with or without parosmia. A) Comparison of average hedonic score across individual smell groups (n = 84 with hyposmia, 66 with normosmia, 66 with parosmia). B) Relationship between hedonic score and frequency of parosmia events (determined via participant’s response to “How often have you experienced smells being distorted or don’t smell like they used to?”; n = 66). C) Comparison of average hedonic score per odor across those with and without parosmia (n = 150 without parosmia, 66 with parosmia). D) Comparison of average hedonic rating and vomit rating across those with and without parosmia. Error bars indicate standard deviation.

Fig. 4.

Summary of participants in the current study. Final smell group classifications (quantitative, qualitative, mixed, and normosmia) were based on the self-report answers to the question stated. Quantitative smell disorders are classified as those with a change in the perceived intensity of odors. Qualitative smell disorders include those where the perceptual quality or identity of an odor has changed. Thick-lined and dashed boxes are used in the final analyses.