Prediction of patient's response to OnabotulinumtoxinA treatment for migraine

Abstract

Migraine affects the daily life of millions of people around the world. The most well-known disabling symptom associated with this illness is the intense headache. Nowadays, there are treatments that can diminish the level of pain. OnabotulinumtoxinA (BoNT-A) has become a very popular medication for treating migraine headaches in those cases in which other medication is not working, typically in chronic migraines. Currently, the positive response to Botox treatment is not clearly understood, yet understanding the mechanisms that determine the effectiveness of the treatment could help with the development of more effective treatments. To solve this problem, this paper sets up a realistic scenario of electronic medical records of migraineurs under BoNT-A treatment where some clinical features from real patients are labeled by doctors. Medical registers have been preprocessed. A label encoding method based on simulated annealing has been proposed. Two methodologies for predicting the results of the first and the second infiltration of the BoNT-A based treatment are contempled. Firstly, a strategy based on the medical HIT6 metric is described, which achieves an accuracy over 91%. Secondly, when this value is not available, several classifiers and clustering methods have been performed in order to predict the reduction and adverse effects, obtaining an accuracy of 85%. Some clinical features as Greater occipital nerves (GON), chronic migraine time evolution and others have been detected as relevant features when examining the prediction models. The GON and the retroocular component have also been described as important features according to doctors.

SOFIA: Selection of Medical Features by Induced Alterations in Numeric Labels

“…It takes the value of 1 when the percentage reduction of days of migraine is less than or equal to 25%, 2 for the interval between 25% and 49%, 3 for the interval between 50% and 74% and 4 when the percentage is greater than or equal to 75%. A is equal to 1 when there are no adverse effects, 2 when there are mild adverse effects (easily tolerated), 3 when there are moderate adverse effects (interfere with usual activities and may require suspension of treatment) and 4 when there are serious adverse effects (incapacitate or disable usual activities, and require suspension of treatment as well as medical intervention) [2].…”

“…In fact, modern hospitals possess a wide variety of monitoring and data collection devices that provide relatively inexpensive means of collecting and storing data in inter and intrahospital information systems [1]. Hence, medicine has leveraged the availability of these EMRs to build predictive models for a given treatment [2]. Due to the economic cost of continuous treatments such as those of hepatitis C [3,4] or migraine [5], it is important for our methodology to be able to know in advance whether a treatment will be effective in patients with those diseases.…”

“…For example, Armañanzas et al [7] use the Feature Subset Selection (FSS) technique to reveal the most important factors when predicting the severity of symptoms in patients with Parkinson's disease [8] using non-motor symptoms. In other works [2,9], the authors propose a data transformation for carrying out the selection of relevant features while achieving high percentages of accuracy when predicting treatment responses in migraine. In these works, a single-objective Simulated Annealing (SA) [10] was applied to find that data transformation instead of employing a multi-objective optimization metaheuristic [9,11].…”

Individual differences of maladaptive brain changes in migraine and their relationship with differential effectiveness of treatments

“…After 3 months of therapy, decreased migraine attacks appeared in 62% of the subjects. Similarly, another research group utilized data mining techniques to predict Botox effectiveness in migraineurs based on different causal factors [145]. They were able to utilize certain classifiers and clustering methods to predict decreased migraine attack frequency and treatment side effects with a relatively high accuracy.…”

SMURF: Systematic Methodology for Unveiling Relevant Factors in Retrospective Data on Chronic Disease Treatments

“…For example, Armañanzas et al [12] use the Feature Subset Selection (FSS) technique to reveal the most important factors in predicting the severity of symptoms in a patient with Parkinson's disease [13] using non-motor symptoms. In [14], the authors propose the extraction of the most important attributes within a continuous CD treatment using a consensus tree. Hence, on the basis of the aforementioned works, it is desirable to incorporate the features of all these techniques into our methodology in order to be able to predict the response to several treatment stages as well as to reveal the reasons that make them effective.…”