Classification of odors associated with migraine attacks: a cross-sectional study

Abstract

Migraine, a common primary headache disorder, is associated with various factors such as stress, hormones in women, fasting, weather, and sleep disturbance as well as odors. We aimed to categorize odors associated with migraine and explore their relationships with clinical characteristics. A total of 101 migraineurs answered a questionnaire to determine the odors associated with migraine attacks. We performed factor analysis to explore the common factors of the odors and the relationship between these factors and the clinical characteristics. The factor analysis estimated six common factors: factor 1, fetid odor; factor 2, cooking products; factor 3, oil derivatives and others; factor 4, shampoo and conditioner; factor 5, cleaning products; factor 6, perfumes, insecticides, and rose. Factor 5 also included hair styling preparations, laundry detergent, and fabric softener, usually those with floral fragrances, and factor 5 was more likely to be associated with migraine attacks in patients with chronic migraine than in those with episodic migraine (P = 0.037). Our study showed that odors associated with migraine attacks could be categorized into six groups and suggested that some chemicals were more likely associated with migraine attacks in patients with chronic migraine than in those with episodic migraine.

Figure 1

Elbow chart and factor structure matrix. (A) Six common factors estimated through factor analysis using the elbow chart. (B) Factor structure matrix and factor loading values of the six factors. Factor loading values > 0.400 are in bold. The correlations between the factors were all < 0.388. Factor 1, fetid odor; factor 2, cooking products; factor 3, oil derivatives and others; factor 4, shampoo and conditioner; factor 5, cleaning products; factor 6, perfumes, insecticides, and rose.

Figure 2

Clustering results and their barycenters. (A) Clusters plotted in three-dimensional space; axes were calculated using principal component analysis. Cluster 1, 76 individuals (blue); cluster 2, 18 individuals (green); cluster 3, 7 individuals (orange). (B) The sensitivities against the common factors were statistically analyzed. Cluster 1 had a slightly stronger sensitivity than cluster 2 to factor 1 and than cluster 3 to factor 4. Cluster 2 had a strong sensitivity to factors 4, 5, and 6. Cluster 3 had a strong sensitivity to factors 1, 2, 3, 5, and 6. *P < 0.050, **P < 0.010, ***P < 0.001.

Figure 3

Summary of this study.