Machine Learning-Based Classification of Jhana Advanced Concentrative Absorption Meditation Using 7 Tesla Functional Magnetic Resonance Imaging
Puneet Kumar, Winson F.z. Yang, Alakhsimar Singh, Xiaobai Li, Matthew D. Sacchet
arXiv Preprint Archive February 13, 2026 preprint
Study at a glance
AI-extracted from the abstract| Characteristics | Machine learning classification study using 7T fMRI data |
|---|---|
| Sample size | 20 |
| Population | Advanced meditators progressing through their standard ACAM-J sequence, plus one case-study participant |
| Intervention | Jhana advanced concentrative absorption meditation (ACAM-J) |
| Measures | regional homogeneity (ReHo) |
| Topics | Meditation |
| Keywords | Cs.lg Cs.ne |
| Key points | ReHo patterns at 7T allowed machine learning models to distinguish ACAM-J from control states and, more modestly, from one another, with average accuracy of 65.87% (66.82% after regressing out phenomenology-related variance) and average kappa of 0.2443 across 19 binary comparisons. Discrimination was strongest for the most separated states (ACAM-J1 vs ACAM-J6: 74.33%, kappa = 0.5158) and weaker for adjacent states. Prefrontal and anterior cingulate areas contributed most to model decisions. |
Abstract
Introduction: Jhana advanced concentrative absorption meditation (ACAM-J) involves profound changes in consciousness, making its neural correlates important for understanding consciousness and well-being. Prior neuroimaging has relied on univariate, group-level contrasts, leaving open whether ACAM-J carries distributed neural signatures decodable from individual scans. This study evaluates whether fMRI-derived regional homogeneity (ReHo) can classify ACAM-J using machine learning.
Methods: We analysed 7T fMRI data from 20 advanced meditators who progressed through their standard ACAM-J sequence and two matched control tasks, plus intensive data from one case-study participant held out for final evaluation. ReHo maps were computed per segment and parcellated into 498 regions spanning cortex, subcortex, brainstem, and cerebellum. Within subject-wise stratified cross-validation, feature ranking, recursive feature elimination, and class balancing were applied to training data only; six classifier families were fitted, and the top three per contrast were combined by probability averaging.
Results: Across 19 binary comparisons, the ensemble reached an overall average accuracy of 65.87% before and 66.82% after regressing out phenomenology-related variance, with an average Cohen's \k{appa} of 0.2443. Discrimination was strongest for the most separated states (ACAM-J1 vs ACAM-J6, 74.33% accuracy, \k{appa} = 0.5158), while adjacent states were harder to separate. Prefrontal and anterior cingulate areas contributed most to model decisions.
Conclusion: ReHo patterns measured at 7T carry information distinguishing ACAM-J from control states and, more modestly, from one another, supporting the feasibility of multivariate decoding of advanced meditation and informing future work on its mechanisms and neuromodulation.