In Pain practice : the official journal of World Institute of Pain ; h5-index 0.0
BACKGROUND : Migraine is a heterogeneous condition with multiple clinical manifestations. Machine-learning algorithms permit the identification of population groups providing analytical advantages over other modeling techniques.
OBJECTIVE : The aim of this study was to analyze critical features that permit to differentiate subgroups of patients with migraine according to the intensity and frequency of attacks by using machine-learning algorithms.
METHODS : Sixty-seven women with migraine participated. Clinical features of migraine, related-disability (MIDAS), anxiety/depressive levels (HADS), anxiety state/trait levels (STAI) and pressure pain thresholds (PPT) over the temporalis, neck, second metacarpal, and tibialis anterior were collected. Physical examination included the flexion-rotation test, cervical range of cervical motion, forward head position in sitting and standing, passive accessory intervertebral movements (PAIVMs) with headache reproduction, and joint positioning sense error. Subgrouping was based on machine-learning algorithms by using Nearest Neighbors algorithms, multisource variability assessment, and Random Forest.
RESULTS : For migraine intensity, group 2 (women with regular migraine headache intensity of 7) were younger, had lower joint positioning sense error in cervical rotation, greater cervical mobility in rotation and flexion, lower flexion-rotation test, positive PAIVMs reproducing migraine, normal PPTs over tibialis anterior, shorter migraine history, and lower cranio-vertebral angle in standing than the remaining migraine intensity subgroups. The most discriminative variable was the flexion-rotation test to the symptomatic side. For migraine frequency, no model was able to identify differences between groups, i.e. patients with episodic or chronic migraine.
CONCLUSIONS : A subgroup of women with migraine with common migraine intensity was identify with machine-learning algorithms.
Pérez-Benito Francisco J, Conejero J Alberto, Sáez Carlos, García-Gómez Juan M, Navarro-Pardo Esperanza, Florencio Lidiane L, Fernández-de-Las-Peñas César
Machine Learning, Migraine, Multisource variability, Random Forest