Abstract
Cluster headache is characterized by recurrent, unilateral attacks of excruciating pain associated with ipsilateral cranial autonomic symptoms. Although a wide array of clinical, anatomical, physiological, and genetic data have informed multiple theories about the underlying pathophysiology, the lack of a comprehensive mechanistic understanding has inhibited, on the one hand, the development of new treatments and, on the other, the identification of features predictive of response to established ones. The first-line drug, verapamil, is found to be effective in only half of all patients, and after several weeks of dose escalation, rendering therapeutic selection both uncertain and slow. Here we use high-dimensional modelling of routinely acquired phenotypic and MRI data to quantify the predictability of verapamil responsiveness and to illuminate its neural dependants, across a cohort of 708 patients evaluated for cluster headache at the National Hospital for Neurology and Neurosurgery between 2007 and 2017. We derive a succinct latent representation of cluster headache from non-linear dimensionality reduction of structured clinical features, revealing novel phenotypic clusters. In a subset of patients, we show that individually predictive models based on gradient boosting machines can predict verapamil responsiveness from clinical (410 patients) and imaging (194 patients) features. Models combining clinical and imaging data establish the first benchmark for predicting verapamil responsiveness, with an area under the receiver operating characteristic curve of 0.689 on cross-validation (95% confidence interval: 0.651 to 0.710) and 0.621 on held-out data. In the imaged patients, voxel-based morphometry revealed a grey matter cluster in lobule VI of the cerebellum (−4, −66, −20) exhibiting enhanced grey matter concentrations in verapamil non-responders compared with responders (familywise error-corrected P = 0.008, 29 voxels). We propose a mechanism for the therapeutic effect of verapamil that draws on the neuroanatomy and neurochemistry of the identified region. Our results reveal previously unrecognized high-dimensional structure within the phenotypic landscape of cluster headache that enables prediction of treatment response with modest fidelity. An analogous approach applied to larger, globally representative datasets could facilitate data-driven redefinition of diagnostic criteria and stronger, more generalizable predictive models of treatment responsiveness.
Highlights
Cluster headache is the most common type of trigeminal autonomic cephalalgia, a class of disorders characterized by recurrent, unilateral attacks of excruciating cranial pain accompanied by prominent, ipsilateral cranial autonomic symptoms [Headache Classification Committee of the International Headache Society (IHS), 2018]
The first-line therapy for cluster headache, demands a lengthy evaluation, for the risk of heart block mandates that the high doses typically necessary to produce an effect are reached in incremental steps of at least 14 days (Cohen et al, 2007)
At a significance threshold of P 5 0.007 (P 5 0.05 with Bonferroni correction for seven comparisons), verapamil responders differed from non-responders in chronicity only (P = 0.001)
Summary
Cluster headache is the most common type of trigeminal autonomic cephalalgia, a class of disorders characterized by recurrent, unilateral attacks of excruciating cranial pain accompanied by prominent, ipsilateral cranial autonomic symptoms [Headache Classification Committee of the International Headache Society (IHS), 2018]. As no treatment response has ever been robustly linked to any clinical or physiological parameter, treatment selection remains heuristic, executable no faster than the weeks-long period of dose escalation needed to evaluate each candidate agent. The first-line therapy for cluster headache, demands a lengthy evaluation, for the risk of heart block mandates that the high doses typically necessary to produce an effect are reached in incremental steps of at least 14 days (Cohen et al, 2007). Patients may endure many weeks of excruciating attacks until the dose reached is high enough to indicate an absence of response and another agent can be considered. The consequent obligation to explore a wide array of potential predictive factors has not been previously fulfilled for two reasons: first, because of the lack of mathematical techniques with the power to render the problem computationally tractable; and second, because of the lack of patient cohorts of sufficient size and data quality
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.