Classifying Unconscious, Psychedelic, and Neuropsychiatric Brain States with Functional Connectivity, Graph Theory, and Cortical Gradient Analysis.

A machine learning model that combines functional connectivity, graph-theoretic metrics, and cortical gradient features can classify brain states—including unconsciousness (NREM2 sleep, propofol sedation and anesthesia), psychedelic states (ketamine, LSD, nitrous oxide), and neuropsychiatric disorders (ADHD, bipolar disorder, schizophrenia)—with an average balanced accuracy of 79% (range 62–98%). The ensemble model outperformed individual feature-based models (70–76%). Transferability across datasets varied, and feature importance analysis indicated that different brain states rely on distinct neural mechanisms, suggesting that tailored approaches are needed for accurate classification. The findings highlight the value of integrating multiple feature types for robust brain-state classification, though further work is needed for broader generalizability.

Study at a glance

Abstract

Accurate and generalizable classification of brain states is essential for understanding their neural underpinnings and improving clinical diagnostics. Traditionally, functional connectivity patterns and graph-theoretic metrics have been utilized. However, cortical gradient features, which reflect global brain organization, offer a complementary approach. We hypothesized that a machine learning model integrating these three feature sets would effectively discriminate between baseline and atypical brain states across a wide spectrum of conditions, even though the underlying neural mechanisms vary. To test this, we extracted features from brain states associated with three meta-conditions including unconsciousness (NREM2 sleep, propofol deep sedation, and propofol general anesthesia), psychedelic states induced by hallucinogens (subanesthetic ketamine, lysergic acid diethylamide, and nitrous oxide), and neuropsychiatric disorders (attention-deficit hyperactivity disorder, bipolar disorder, and schizophrenia). We used support vector machine with nested cross-validation to construct our models. The soft voting ensemble model marked the average balanced accuracy (average of specificity and sensitivity) of 79% (62-98% across all conditions), outperforming individual base models (70-76%). Notably, our models exhibited varying degrees of transferability across different datasets, with performance being dependent on the specific brain states and feature sets used. Feature importance analysis across meta-conditions suggests that the underlying neural mechanisms vary significantly, necessitating tailored approaches for accurate classification of specific brain states. This finding underscores the value of our feature-integrated ensemble models, which leverage the strengths of multiple feature types to achieve robust performance across a broader range of brain states. While our approach offers valuable insights into the neural signatures of different brain states, future work is needed to develop and validate even more generalizable models that can accurately classify brain states across a wider array of conditions.