Naturalistic acute pain states decoded from neural and facial dynamics

Pain remains poorly understood in task-free contexts, limiting our understanding of its neurobehavioral basis in naturalistic settings. Here, we use a multimodal, data-driven approach with intracranial electroencephalography, pain self-reports, and facial expression analysis to study acute pain in twelve epilepsy patients under continuous neural and audiovisual monitoring. Using machine learning, we successfully decode individual participants' high versus low pain states from distributed neural activity, involving mesolimbic regions, striatum, and temporoparietal cortex. Neural representation of pain remains stable for hours and is modulated by pain onset and relief. Objective facial expressions also classify pain states, concordant with neural findings. Importantly, we identify transient periods of momentary pain as a distinct naturalistic acute pain measure, which can be reliably discriminated from affect-neutral periods using neural and facial features. These findings reveal reliable neurobehavioral markers of acute pain across naturalistic contexts, underscoring the potential for monitoring and personalizing pain interventions in real-world settings.