Decide Before You Record: Heterogeneity-Guided Pre-Acquisition Stimulus Selection for Cross-Day Neuroprostheses

Decoding language intentions from intracranial electroencephalography signals enables direct communication for patients with severe speech impairments. However, practical deployment remains severely limited by cross-day performance degradation caused by physiological and instrumental heterogeneity, requiring patients to record extensive calibration data daily to maintain decoding performance. Here we introduce Heterogeneity-Guided Data Acquisition and Adaptation (HeDA2), a novel calibration paradigm that determines which stimuli to record for optimal calibration before any neural data are acquired, fundamentally departing from existing methods that passively adapt to whatever data happen to be available. HeDA2 operates through three stages: it first quantifies cross-day neural heterogeneity with a proposed Sentence-level Heterogeneity via Alignment Path Entropy that captures how different phonetic phenomena exhibit varying degrees of heterogeneity; second, an estimator learns to predict this heterogeneity from historical patterns, enabling strategic selection of calibration sentences before any neural recording occurs; third, heterogeneity-aware adaptation updates the decoder using minimal acquired data. Extensive experiments on intracranial recordings across diverse recalibration settings demonstrate that, with merely 20% of conventionally required calibration data, HeDA2 achieves comparable or superior decoding accuracy, representing a critical step toward clinically viable speech prosthesis.