Early delay high-power event fractions did not lower mean recall forecast error beyond SEEG power in fixed logistic models for 13 patients under source trial order
We tested whether early delay high-power events improve recall forecasts beyond mean SEEG power and task context. We used OpenNeuro ds006136 version 1.0.1: 13 patients, 14 recordings, 143 released bipolar channels, and 2134 matched trials. Forward filters and event thresholds used no test data for fitting. Models trained on the first 65 percent of matched trials and tested on 751 later trials. Mean patient Brier error was 0.179663 for power and 0.189751 for power plus eight event inputs. Gain was -0.010088; the patient bootstrap 95 percent interval was [-0.022143, -0.000679]. The exact patient sign-flip value was 0.100342. 4 of 13 patients had positive gain. The event model did not lower mean patient Brier error in this fixed test. The interval is below zero. We provide new event tables, fitted models, figures, source hashes, and code. This is an offline test in selected source data. It does not establish a live BCI or a stimulation benefit.
working memory · recall forecasting · stereoelectroencephalography · high-power events · Brier error · brain-computer interface
References
3- usesEarly delay SEEG power gave no mean Brier gain in later recall forecasts for 13 patients under source trial order sci:sha256:adbcbe06fcce87132c9633b5137a24af646e5c49afc3ac2d09469a1e05618474
We used its exact matched power tables, EDF reader, and retrieval code. We rebuilt both tables from the pinned source and checked baseline forecasts. We added new forward event features and a fixed incremental forecast test.
- usesdoi:10.18112/openneuro.ds006136.v1.0.1
The analysis used OpenNeuro ds006136 version 1.0.1; the archived source manifest records the source commit, URLs, byte counts, and SHA-256 hashes.
- doi:10.1016/j.neuroimage.2026.121718
Cited by
2 publicationsPublic catalog entries on Sciscape.
- usesAdded frontal and temporal power envelope correlations raised mean recall forecast error in fixed logistic readers for 11 SEEG patients under assumed source trial order
Its preserved package supplied the parent files and baseline forecasts. Its known event result helped define a different question before the fixed envelope plan. We did not use its event features. The patients and later trials are reused.
- usesEarly delay burst rate and occupancy did not lower mean recall forecast error beyond power from the same causal filters in 13 patients under source trial order
Read its related event-occupancy forecast evidence after fixing this protocol and before computing new scores. It provides a same-cohort reference. This test holds the power and burst signal estimate equal and includes burst rate. No code or result file from that publication enters this calculation.