Machine learning could help predict migraine sufferers’ response to NSAIDs

Using machine learning (ML), researchers were able to determine that disrupted functional connectivity (FC) of the amygdala can predict the effectiveness of nonsteroidal anti-inflammatory drugs (NSAIDs) in patients with migraine. without aura (MwoA). The results of the study were published in Frontiers in molecular neuroscience.

Although opioids and sedatives are often used to treat migraine, NSAIDs are considered first-line treatment for the condition. However, due to interindividual variability, NSAIDs may have unsatisfactory treatment outcomes in a considerable percentage of migraine sufferers, the authors explained.

Some patients who abuse NSAIDs may experience treatment-resistant headaches and develop cognitive decline or depression.

In order to better understand the interindividual variability affecting responses to NSAIDs and to optimize treatment delivery, the researchers decided to use ML algorithms to predict the efficacy of this class of drugs in patients with MwoA.

Previous research has implicated the amygdala in the analgesic response to NSAIDs and noted that antinociceptive tolerance to NSAIDs is associated with disrupted amygdala-related FC patterns, they said.

The 70 patients included in the study all had MwoA, had been medication-free for at least 1 month prior to enrollment, and had no headaches for at least 3 days before and after the examination. Thirty-three healthy controls matched by age, sex and level of education were also recruited.

Patients were required to keep a headache diary, undergo cognitive impairment screening, and complete the Visual Analogue Scale (VAS), the 6-item Headache Impact Test Scale (HIT-6) and the Migraine Disability Assessment (MIDAS). Imaging data was collected via functional MRIs.

Using these data, the researchers developed multivariate logistic regression (MLR) and support vector machine (SVM) models, with 80% of migraine sufferers assigned to the training group and the remaining 20% ​​to the training group. of testing.

A total of 35 migraine patients effectively managed with NSAIDs (M-eNSAID), 35 MwoA patients with an ineffective response to NSAIDs (M-ieNSAID), and 33 healthy participants were evaluated.

The analyzes revealed:

  • The M-eNSAIDs group showed improved FC with an ipsilateral calcarine sulcus (CAL), superior parietal gyrus, paracentral lobule, and contralateral superior frontal gyrus (SFG) in the left amygdala
  • The M-eNSAIDs group showed a decrease in HR with the ipsilateral caudate nucleus (CAU) compared to the M-ieNSAIDs group
  • M-eNSAIDs group showed higher HR with left precentral gyrus and postcentral gyrus compared to controls
  • M-ieNSAIDs group showed lower HR with left anterior cingulate cortex and right GFS
  • Patients with MwoA showed increased HR with left middle frontal gyrus in right amygdala compared to controls
  • FC patterns related to the disrupted left amygdala showed significant correlations with migraine characteristics in the M-ieNSAIDs group

“The MLR and SVM models discriminated the clinical efficacy of NSAIDs with an area under the curve of 0.891 and 0.896, a sensitivity of 0.971 and 0.833, and a specificity of 0.629 and 0.875, respectively,” the authors wrote.

The data also showed a significant correlation between the FC of the left amygdala-CAL and MIDAS scores, and the FC of the amygdala-CAU and VAS scores in the M-ieNSAIDs group, with no significant correlation between the FC of the right amygdala and characteristics clinics.

“These results suggest that neural function in the left amygdala plays an important role in determining the effectiveness of NSAIDs,” while the results provide insight into the neurophysiological mechanisms underlying migraine, the researchers said.

Since the MLR model revealed amygdala-visual FCs, which have been shown to positively affect the efficacy of NSAIDs, they hypothesized that this finding may indicate that dysfunctional amygdala-visual patterns could affect the response of migraine sufferers to the class of drugs.

Due to the cross-sectional nature of the study, causality cannot be proven, while longitudinal investigations are warranted to verify any causal mechanism. These studies should also include patients with different migraine subtypes and a larger sample size.

“Altered FC patterns related to the amygdala with higher-level sensory cortex and prefrontal cortex were important central pathological features in distinguishing MwoA patients likely to have an effective response to NSAIDs from MwoA patients likely to have an ineffective response to NSAIDs,” the authors concluded. “These results may help to further elucidate the functional characteristics of migraine and predict individualized response to NSAIDs.”

Reference

Wei H, Xu C, Wang J, et al. Disrupted functional connectivity of the amygdala predicts the efficacy of nonsteroidal anti-inflammatory drugs in migraineurs without aura. Before Mol Neurosci. Published online February 24, 2022. doi:10.3389/fnmol.2022.819507

Sherry J. Basler