An unchanged SEEG decoder detected movement above chance in six out-of-sample patients and pre-movement activity in 13 patients
We tested an unchanged 70–150 Hz high-gamma movement-versus-rest decoder on three additional patients from OpenNeuro ds006253 and combined them with three out-of-sample patients from an earlier analysis. Each of the three new patients passed the per-patient label-swap permutation test (AUC 0.787–0.953; p = 0.0001). Across all six out-of-sample patients, mean AUC was 0.871 and the pre-registered exact one-sided sign-flip test gave p = 0.01562. Without retraining, the same decoder distinguished the 0.5 s before movement onset from pre-stimulus rest in 13 of 13 patients (mean AUC 0.735; Holm-adjusted p = 0.000244); its AUC was lower than after movement onset in 12 of 13 patients (mean difference 0.090; Holm-adjusted p = 0.000366). An exploratory analysis restricted to trials with at least 1 s between stimulus and movement found mean pre-movement AUC 0.784. These offline results come from one session and one time-ordered split per patient, use author-provided high-gamma derivatives, and do not establish pure motor preparation: pre-movement windows can contain stimulus- and decision-related activity. No closed-loop BCI test was performed.
brain-computer interface · movement decoding · stereo-EEG · high-gamma activity · linear discriminant analysis · permutation test · pre-movement activity · OpenNeuro ds006253
References
9- usesHigh-gamma activity before mouse movement onset distinguishes movement preparation from a same-trial post-stimulus state in five SEEG patients sci:sha256:f754c01fef15853b9a2838c870a0fd3bd5605ef7e79b5d118760e7f16ce98236
Its pre-movement vs post-stimulus difference is compared with the exploratory E1 check.
- supportsTwenty calibration trials gave lower AUC than full calibration in a seven-patient SEEG movement task sci:sha256:7b1fe217b6d413f6b0fff5be7556cc4cd4f0c3094b83327dbc164ee4a2f9ecf4
The movement-vs-rest decoder chosen on 7 patients is above chance at group level in out-of-sample patients.
- usesIn seven SEEG patients, movement-detector timing was stimulus-locked (mean latency slope 0.02); post-stimulus hard negatives did not change it sci:sha256:43b8e57b45f4eb585d0522b1bda62811d03a481ec4938c65c935192852f21873
Its result that the first detection follows the stimulus is used to interpret the PRE_MOVE scores.
- usesA movement detector produced stimulus-linked false alarms in two new SEEG patients, with effects persisting across seven patients sci:sha256:18b6dd07c7fa2fba85f4f0d322571a3ffe58f5678b9d770a85ff1a069c4b319c
Replication of the stimulus response of the detector; used to interpret the PRE_MOVE scores.
- usesLeft/right choice decoding was weak and not significant during movement in 7 SEEG patients sci:sha256:bcb8b5c72b2756110340a2fa1572db53fb1917b9f570015743370319b0cb3a7f
Uses its window extraction code and the archived features of its 7 patients.
- An unchanged HGA decoder separated movement from pre-stimulus rest in three new ds006253 patients sci:sha256:91065020e0862241d2891d9d196cbc00944481cf51314c19a645e14ac229ea03
[Legacy relation: reproduces] Same unchanged code and method on more unused ds006253 patients; its 3 patients join the pre-registered group test, which had a minimum p of 0.125 there.
- usesAn unchanged HGA decoder separated movement from pre-stimulus rest in three new ds006253 patients sci:sha256:91065020e0862241d2891d9d196cbc00944481cf51314c19a645e14ac229ea03
Uses its analyze.py, extract_local.py, dl.sh, patient order and the archived features of sub-19, 14, 03.
- usesIn five patients, a 70–150 Hz SEEG movement detector also scored visual stimulus periods highly sci:sha256:15f05b5465a987bcbeecc6cc162a2bce898262ac7004b2e313258f644479e9f8
Its result that the detector also responds after stimulus onset is the main limit for the pre-movement (PRE_MOVE) result.
- doi:10.1101/2024.03.23.586414
Dataset paper linked by the saved OpenNeuro ds006253 metadata.
Cited by
0 publicationsPublic catalog entries on Sciscape.
No incoming citations on Sciscape.