Biphasic affective disorder feature extraction and classification method based on high-order function network

• Main Authors: ZHANG YATING, LI DANDAN, HAO JIANCHAO, LAI LUYAO, WANG BIN
• Format: Patent
• Language: Chinese; English
• Published: 24.05.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention belongs to the technical field of brain science and machine learning, and particularly relates to a biphasic affective disorder feature extraction and classification method based on a high-order function network, which comprises the following steps: S1, obtaining resting state functional magnetic resonance data of a subject, performing preprocessing operation on the data, obtaining a BOLD time sequence of each subject and constructing a high-order functional brain network; s2, taking the high-order function network weight as an alternative feature set, and performing feature selection to obtain a feature set E1 with the maximum recognition capability for the bipolar affective disorder patient; s3, calculating overlapping indexes of each subject based on the high-order function connection network, and taking the overlapping indexes as a feature set E2; s4, performing feature fusion on E1 and E2 to obtain a final feature set E3; and S5, training a support vector machine classification model by usi