Machine Learning-Based Classification of Jhana Advanced Concentrative Absorption Meditation (ACAM-J) using 7T fMRI

2026-02-16 · Source: cs.NE updates on arXiv.org · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Expert, quick

Summary

A study submitted on February 13, 2026, by Puneet Kumar and colleagues, investigates the neural correlates of Jhana advanced concentrative absorption meditation (ACAM-J) using 7T fMRI and machine learning. The research aimed to classify ACAM-J states from non-meditative states by analyzing regional homogeneity (ReHo) derived from fMRI data. Researchers collected fMRI data from 20 advanced meditators for classifier training and single-case data from one advanced practitioner for generalization evaluation. Features were extracted from predefined brain regions, and multiple machine learning classifiers were trained using stratified cross-validation. Ensemble models achieved 66.82% accuracy (p < 0.05) in distinguishing ACAM-J from control conditions. Feature importance analysis highlighted the prefrontal and anterior cingulate areas as key contributors to model decisions, consistent with their roles in attentional regulation and metacognition.

Key takeaway

For AI Researchers developing models for neurophysiological data, this study demonstrates the feasibility of classifying complex meditative states using fMRI and machine learning. You should consider incorporating regional homogeneity (ReHo) as a feature for distinguishing subtle brain states, particularly when investigating consciousness or cognitive processing, to inform future neuromodulation strategies or mechanistic models.

Key insights

Machine learning can classify advanced meditation states using fMRI-derived regional homogeneity patterns.

Principles

• Prefrontal and anterior cingulate areas are critical for attentional regulation.
• ReHo patterns can differentiate conscious states.

Method

The study computed ReHo maps from 7T fMRI data, extracted features from brain regions of interest, and trained ensemble machine learning classifiers with stratified cross-validation to distinguish ACAM-J from control states.

In practice

• Use 7T fMRI for high-resolution brain activity mapping.
• Apply ReHo analysis for functional brain connectivity.

Topics

• Machine Learning Classification
• Jhana Meditation
• 7T fMRI
• Regional Homogeneity
• Neuroimaging

Best for: AI Researcher, AI Scientist, Research Scientist

Related on AIssential

• Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging — Neuro-JEPA is a sparse multimodal neuroimaging foundation model using a latent predictive objective and Mixture-of-Experts.
• End-to-End Machine Learning for Depressive State Classification via EEG and fNIRS — Biological signal analysis via EEG and fNIRS offers an objective framework for depressive state classification.
• Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity Matrices Generative Replay — A continual learning framework uses generative replay and knowledge distillation to diagnose brain disorders from sequential fMRI data.
• Deep Sleep Classification via EEG Signal Criticality: A Passive BCI Approach for Sleep-Improvement Neurofeedback — High-accuracy passive BCI sensing is achievable via probabilistic decoding of EEG criticality.
• A Controlled Benchmark of Quantum-Latent GAN Augmentation for Brain MRI — Quantum-latent GAN augmentation for brain MRI offers no significant performance or diversity benefits over classical methods or real-data-only training.
• A Minimalist Brain-Computer Musical Interface for Real-Time Emotion-Driven Sonification: System Design and Preliminary Evaluation — Frontal alpha asymmetry proved unreliable for voluntary emotion control in a real-time brain-computer musical interface.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by cs.NE updates on arXiv.org.