Reddy Anusha, Reddy Ajit
San Juan Bautista School of Medicine, Caguas, Puerto Rico, United States.
Independent Researcher, Monmouth County, NJ, United States.
Front Neurol. 2025 May 9;16:1555215. doi: 10.3389/fneur.2025.1555215. eCollection 2025.
In many countries, patients with headache disorders such as migraine remain under-recognized and under-diagnosed. Patients affected by these disorders are often unaware of the seriousness of their conditions, as headaches are neither fatal nor contagious. In many cases, patients with migraine are often misdiagnosed as regular headaches.
In this article, we present a study on migraine, covering known triggers, different phases, classification of migraine into different types based on clinical studies, and the use of various machine learning algorithms such as logistic regression (LR), support vector machine (SVM), random forest (RF), and artificial neural network (ANN) to learn and classify different migraine types. This study will only consider using these methods for diagnostic purposes. Models based on these algorithms are then trained using the dataset, which includes a compilation of the types of migraine experienced by various patients. These models are then used to classify the types of migraines, and the results are analyzed.
The results of the machine learning models trained on the dataset are verified for their performance. The results are further evaluated by selective sampling and tuning, and improved performance is observed. The precision and accuracy obtained by the support vector machine and artificial neural network are 91% compared to logistic regression (90%) and random forest (87%). These models are run with the dataset without optimal tuning across the entire dataset for different migraine types; which is further improved with selective sampling and optimal tuning. These results indicate that the discussed models are relatively good and can be used with high precision and accuracy for diagnosing different types of migraine.
Our study presents a realistic assessment of promising models that are dependable in aiding physicians. The study shows the performance of various models based on the classification metrics computed for each model. It is evident from the results that the artificial neural network (ANN) performs better, irrespective of the sampling techniques used. With these machine learning models, types of migraines can be classified with high accuracy and reliability, enabling physicians to make timely clinical diagnoses of patients.
在许多国家，偏头痛等头痛疾病患者仍未得到充分认识和诊断。受这些疾病影响的患者往往没有意识到自身病情的严重性，因为头痛既不致命也不具传染性。在许多情况下，偏头痛患者常被误诊为普通头痛。
在本文中，我们展示了一项关于偏头痛的研究，内容涵盖已知诱因、不同阶段、基于临床研究将偏头痛分为不同类型，以及使用各种机器学习算法，如逻辑回归（LR）、支持向量机（SVM）、随机森林（RF）和人工神经网络（ANN）来学习和分类不同的偏头痛类型。本研究仅考虑将这些方法用于诊断目的。然后使用包含各种患者所经历偏头痛类型汇编的数据集对基于这些算法的模型进行训练。接着使用这些模型对偏头痛类型进行分类，并分析结果。
在数据集上训练的机器学习模型的性能得到验证。通过选择性采样和调优对结果进行进一步评估，观察到性能有所提升。支持向量机和人工神经网络获得的精度和准确率为91%，而逻辑回归为90%，随机森林为87%。这些模型在整个数据集上针对不同偏头痛类型未进行最优调优的情况下运行；通过选择性采样和最优调优进一步得到改进。这些结果表明所讨论的模型相对较好，可高精度、准确地用于诊断不同类型的偏头痛。
我们的研究对有助于医生的有前景的模型进行了实际评估。该研究展示了基于为每个模型计算的分类指标的各种模型的性能。从结果中可以明显看出，无论使用何种采样技术，人工神经网络（ANN）的表现都更好。借助这些机器学习模型，可以高精度、可靠地对偏头痛类型进行分类，使医生能够及时对患者进行临床诊断。
