Screening, Prediction and Remission of Depressive Disorder Using the Fuzzy Probability Function and Petri Net

DepressionDepression affects the individual's quality of life and work performance and increases stress on families and society. Early detection and treatment of depressionDepression can significantly improve treatment outcomes while reducing costs. However, such detection typically requires a professional diagnosis, and thus, early symptoms are often overlooked, raising the need for new methods for early diagnosis and preventive healthcareHealthcare. Past studies on depression have often relied on questionnaire-based assessments, which are not only time-intensive to conduct and evaluate but are also prone to subjective assessment error and cannot directly evaluate depressive state. Electroencephalography (EEG)Electroencephalography (EEG) can indicate an individual's mental and physical condition and identify specific changes in physiological characteristics, making it a crucial tool for the early detection of depressionDepression. However, physiological signals are susceptible to external interference and individual physiological differences, which can lead to distortion. This study uses the Fast Fourier Transform, Correlation Petri Nets, Chebyshev's theorem, and Fuzzy TheoryFuzzy theory to develop an early diagnosis model for depression. Using Fuzzy TheoryFuzzy theory, the probability distributions of brainwave characteristics were separately calculated for two normal samples and two subjects with a tendency towards depressionDepression. Subsequently, by constructing trapezoidal membership functions for normal and depression tendencies and analyzing the differential changes in EEG features between normal and depression-prone individuals, the study aims to predict the likelihood of individuals developing depressionDepression. The results could serve as a useful reference for early clinical diagnosis, aiding in the timely detection of depression and potentially arresting the progression of the illness.