IMPROVING EARLY DIAGNOSIS AND PREDICTION OF PREMENSTRUAL HEADACHES BASED ON DIGITAL MONITORING OF CLINICAL AND NEUROVEGETATIVE PARAMETERS

Premenstrual headaches represent a significant clinical and neurological problem characterized by the onset or exacerbation of headache on specific days of the menstrual cycle. Their etiology may be associated with hormonal fluctuations, alterations in neurotransmitter systems, autonomic dysfunction, sleep disturbances, and stress-related conditions.

Objective: To improve methods for the early diagnosis and prediction of premenstrual headaches in women of reproductive age. This will be achieved through comprehensive digital monitoring of clinical and neurovegetative parameters, identification of key factors contributing to headache occurrence, and development of a personalized prediction algorithm.

Materials and Methods: A prospective clinical and neurological study involving women of reproductive age with recurrent headaches associated with the menstrual cycle is planned. The collected data will be analyzed using descriptive statistics, correlation analysis, and multivariable analysis. The predictive accuracy of the developed model will be evaluated using receiver operating characteristic (ROC) analysis, including the determination of sensitivity, specificity, and the area under the ROC curve (AUC).

Expected Results: The study is expected to identify the main clinical and neurological characteristics of pre­menstrual headaches, including their intensity, duration, and frequency during different phases of the menstrual cycle. Potential correlations between headache severity, sleep disturbances, psycho-emotional stress, and neurovegetative status are expected to be identified.

Conclusion: The comprehensive use of digital monitoring of clinical and neurovegetative parameters repre­sents a promising approach to improving the early diagnosis and prediction of premenstrual headaches