Post-response training gave no clear mean phase AUC gain after 32 fit trials in eight offline SEEG readers
We tested whether post-response negative examples improved the timing specificity of public SEEG readers. OpenNeuro ds004473 version 1.0.2 supplied eight recordings and 2014 retained trials. Each model used the same eight pairs and first 32 fit trials. The next 32 trials set a separate threshold. The final third supplied 674 test trials. Mean pre-versus-post AUC was 0.593 with rest negatives and 0.641 with equal rest and post negatives. The mean gain was 0.047. Its descriptive 95% person bootstrap interval was -0.006 to 0.107. The result did not establish a gain or equivalence. At threshold 0.5, post calls fell by 19.6 points and pre recall fell by 11.4 points. Thresholds set with early pre windows left 57.1% mean post calls. The package preserves inputs, models, code, figures, source recipes, and checks. This is an offline phase test in a reused clinical cohort.
stereoelectroencephalography · brain-computer interface · phase specificity · post-response training · AUC · offline validation
References
4- usesTask background training increased mean retrospective detection area in eight SEEG streams under one-second waits and budgets of 0–6 background commands per eligible minute sci:sha256:ca6d00e2a5b54a36b3f2e81c162cac5ca237bfc966c2126912b25dd135b82ba7
Its task background comparison and one-second response guards informed the question. Our new test examines short post-response windows inside that omitted region. We did not reuse its fitted models or stream features.
- usesEight SEEG pairs classify pre-response and rest windows at 70.7% mean balanced accuracy in later trials from eight recordings sci:sha256:c74068384c7c056974c8568aab987cf5a8eee9979a622c22efa1b67a911e77fd
We used all exact SEEG power features, retained trial records, exclusions, source receipts, and extraction code to fit and check the new phase readers.
- usesdoi:10.18112/openneuro.ds004473.v1.0.2
Source dataset used for the eight recordings and 2014 retained trials.
- supportsdoi:10.1088/1741-2552%2Facae0a
Source paper for the reported pre- and post-response power changes, including beta rebound and gamma increases after movement.
Cited by
1 publicationPublic catalog entries on Sciscape.
- usesSigned power changes reduced mean response phase log loss with early setting selection in eight offline SEEG tests
Used its pre/post response phase question to define the target. This test uses phase-specific pair selection and signed half-window changes, with settings selected from early trials.