Background:White matter lesion(WML)is common in aging brain and is associated with cognitive impairment and dementia.However,recent studies reported an association between patent foramen ovale(PFO)and WML in migraineu...Background:White matter lesion(WML)is common in aging brain and is associated with cognitive impairment and dementia.However,recent studies reported an association between patent foramen ovale(PFO)and WML in migraineurs,especially in young,middle-aged migraineurs.Our retrospective,case-control study aims to describe the clinical characteristics of WML in this population and to explore potential risk factors.Methods:226 patients with migraine and PFO were consecutively initially screened.Relevant factors were selected by the least absolute shrinkage and selection operator(LASSO)regression and multivariable logistic regression model.A Nomogram was employed to visualize the prediction model conveniently.The discrimination and calibration abilities were evaluated using the Receiver Operating Characteristic(ROC)curve,the Hosmer-Lemeshow test,and calibration curves.Results:One hundred and nineteen participants were ultimately enrolled in our study,with a median age of 36.9±12.7 years and 80.7%of females.Brain magnetic resonance imaging MRI showed 67(56.3%)patients had WML,whereas 52(43.7%)patients were categorized into the non-WML group.LASSO regression screened out potential variables and subsequent multivariate analysisfinally identified age,mean platelet volume,andfibri-nogen(FIB)as independent predictive factors of WML.The area under the ROC curve(AUC)was 0.807.Hos-mer-Lemeshow test and calibration curve verified a consistency between the predicted and actual probability.Conclusion:The predictive nomogram established and validated in our study may assist clinicians in screening WML among young middle-aged migraineurs with PFO and developing individualized preventive and treatment strategies.展开更多
文摘Background:White matter lesion(WML)is common in aging brain and is associated with cognitive impairment and dementia.However,recent studies reported an association between patent foramen ovale(PFO)and WML in migraineurs,especially in young,middle-aged migraineurs.Our retrospective,case-control study aims to describe the clinical characteristics of WML in this population and to explore potential risk factors.Methods:226 patients with migraine and PFO were consecutively initially screened.Relevant factors were selected by the least absolute shrinkage and selection operator(LASSO)regression and multivariable logistic regression model.A Nomogram was employed to visualize the prediction model conveniently.The discrimination and calibration abilities were evaluated using the Receiver Operating Characteristic(ROC)curve,the Hosmer-Lemeshow test,and calibration curves.Results:One hundred and nineteen participants were ultimately enrolled in our study,with a median age of 36.9±12.7 years and 80.7%of females.Brain magnetic resonance imaging MRI showed 67(56.3%)patients had WML,whereas 52(43.7%)patients were categorized into the non-WML group.LASSO regression screened out potential variables and subsequent multivariate analysisfinally identified age,mean platelet volume,andfibri-nogen(FIB)as independent predictive factors of WML.The area under the ROC curve(AUC)was 0.807.Hos-mer-Lemeshow test and calibration curve verified a consistency between the predicted and actual probability.Conclusion:The predictive nomogram established and validated in our study may assist clinicians in screening WML among young middle-aged migraineurs with PFO and developing individualized preventive and treatment strategies.
