The journal of headache and pain · 2025
The association between social factors and migraine or severe headache in men: a secondary analysis of national population-based studies with machine learning models.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Yu Zhe, Zhang Jiaxin, He Mianwang, Liu Ruozhuo, Yu Shengyuan
Аннотация
BACKGROUND: Migraine is recognized as a global public health issue. It is more prevalent among women; therefore, studies focusing solely on migraine in men are scarce. We aimed to investigate the relationship between social factors and migraine or severe headache in men, based on a Chinese national population study and the National Health and Nutrition Examination Survey (NHANES).
METHOD: In 2009, we conducted a population-based survey on headaches, for which 5,041 unrelated individuals were randomly selected and visited in all regions of China. A secondary analysis was performed on the data pertaining to men. Data retrieved from the NHANES between 1999 and 2004 were analyzed alongside the same social factors. Logistic regression was used to analyze the factors affecting men. We compared the predictive performance of six machine learning models: XGBoost, Random Forest, Decision Tree, Logistic Regression, Support Vector Machine, and K-Nearest Neighbors.
RESULTS: Of 2,496 male Chinese participants, 236 (9.5%) were diagnosed with migraine or severe headache. According to the NHANES data, 714 (16.6%) of 4,303 male participants reported migraine or severe headache. Logistic regression of the two studies consistently revealed a positive association between obesity and migraine or severe headache (Chinese participants: odds ratio [OR] = 2.017, p = 0.020; NHANES sample: OR = 1.256, p = 0.038) as well as a negative correlation between increased income and the same condition. Occupation was related to migraine or severe headache in the Chinese population, and races were associated with headaches in the NHANES data. The five-fold cross-validation results demonstrated that the logistic regression model was the most stable and generalizable classifier. The SHAP analysis clarifies that significant differences existed in the contribution of individual factors to migraine or severe headache between the two studies.
CONCLUSION: Obesity and high income were found to be associated with migraine or severe headache in men. Given the discrepancies observed between the two studies, further exploration of these factors across different countries may be warranted.
METHOD: In 2009, we conducted a population-based survey on headaches, for which 5,041 unrelated individuals were randomly selected and visited in all regions of China. A secondary analysis was performed on the data pertaining to men. Data retrieved from the NHANES between 1999 and 2004 were analyzed alongside the same social factors. Logistic regression was used to analyze the factors affecting men. We compared the predictive performance of six machine learning models: XGBoost, Random Forest, Decision Tree, Logistic Regression, Support Vector Machine, and K-Nearest Neighbors.
RESULTS: Of 2,496 male Chinese participants, 236 (9.5%) were diagnosed with migraine or severe headache. According to the NHANES data, 714 (16.6%) of 4,303 male participants reported migraine or severe headache. Logistic regression of the two studies consistently revealed a positive association between obesity and migraine or severe headache (Chinese participants: odds ratio [OR] = 2.017, p = 0.020; NHANES sample: OR = 1.256, p = 0.038) as well as a negative correlation between increased income and the same condition. Occupation was related to migraine or severe headache in the Chinese population, and races were associated with headaches in the NHANES data. The five-fold cross-validation results demonstrated that the logistic regression model was the most stable and generalizable classifier. The SHAP analysis clarifies that significant differences existed in the contribution of individual factors to migraine or severe headache between the two studies.
CONCLUSION: Obesity and high income were found to be associated with migraine or severe headache in men. Given the discrepancies observed between the two studies, further exploration of these factors across different countries may be warranted.