sciscape Publications
← All publications
eess.SP · Signal Processing

With separate fits, removing the strongest 100-sample block gave higher mean SEEG task state accuracy than position controls in eight patients

We tested public SEEG data from eight patients in OpenNeuro ds004473 version 1.0.2. Each 500-sample window had five 100-sample blocks. Each reader used 70 to 110 Hz power from eight inherited bipolar pairs. We fitted each reader on early trials and tested it on 674 later trials. Removal of the strongest block for each pair gave 68.17% mean balanced accuracy. The mean of five fixed-position removal controls was 66.15%. The paired gain was 2.01 percentage points, with a 95% patient bootstrap interval of 1.06 to 3.15 points. Seven patients had higher accuracy and one had equal accuracy. Log loss did not show a clear gain. The gain was uncertain with 125-sample blocks and against the all-block reader. The result supports a feature test for this task and block size. It does not identify artifacts or prove intention reading. The package includes exact input samples, source records, all predictions, models, code, checks, and three figures.

stereoelectroencephalography · SEEG · high gamma · power features · block removal · balanced accuracy · task-state decoding

Admitted 1 citing publication

References

5
  1. usesTen spaced gaps gave lower mean zero-fill SEEG accuracy than a circular gap block at 20 percent simulated sample loss in eight fixed decoders sci:sha256:35c3a178c2212bd9b314433661dfc484678cb20f0c291b7c94bc044397f7c9b9

    This study uses the 500-sample window derivation and source records from this work, through the later archived input package. It fits new readers. It does not use the fixed decoders or simulated gap results.

  2. usesMedian block powers gave higher task-state accuracy than mean powers for simulated 1 mV, 10-sample SEEG faults on one contact in eight recordings sci:sha256:7e4be46c9c145b5de38d258bb39ea502a49c77fca52c1e1d18681de88d768b0a

    This study uses the exact 500-sample integer SEEG inputs, inherited pair and trial selection, source records, and block power and logistic fit code. It tests removal of recorded strongest block powers with separate reader fits and equal length position controls.

  3. usesEight SEEG pairs classify pre-response and rest windows at 70.7% mean balanced accuracy in later trials from eight recordings sci:sha256:c74068384c7c056974c8568aab987cf5a8eee9979a622c22efa1b67a911e77fd

    This study uses the original selected bipolar pairs, retained trial list, split procedure, dataset metadata, and EDF range reader. The preserved inputs keep these choices fixed.

  4. usesdoi:10.18112/openneuro.ds004473.v1.0.2

    This study analyzes the OpenNeuro ds004473 version 1.0.2 source dataset.

  5. doi:10.1088/1741-2552%2Facae0a

Cited by

1 publication

Public catalog entries on Sciscape.