Mean seizure onset label AUC was 0.795 without 80 to 150 Hz time concentration and 0.804 with it in fixed logistic model tests of 34 SEEG patient holdouts with two 60 s clips each
We tested whether 80 to 150 Hz power concentration added seizure onset label prediction beyond mean power. The sample had 34 SEEG patients, two 60-second clips each, and 3,325 selected bipolar pairs from OpenNeuro ds004100 version 1.1.3. Every test patient was absent from training. Fixed logistic models used high mean power, beta mean power, and contact number. Adding high band concentration changed mean patient AUC from 0.79485 to 0.80419. The mean change was 0.00934, with a descriptive 95 percent interval of -0.00156 to 0.02150. Adding concentration to a baseline that also had beta concentration gave a mean change of 0.00118. The intervals resample saved patient results and omit model refitting uncertainty. The package includes all 68 input files, features, models, predictions, source identities, code, and commands. New signal downloads reproduced all input power values. Independent fits gave the same primary AUCs. An offline run reproduced all 31 analysis files byte for byte. The result applies to the fixed models and selected clinical labels. It does not establish a population gain or clinical use.
stereoelectroencephalography · SEEG · epilepsy · seizure onset zone · high-frequency power · time concentration · patient holdout · logistic regression · area under the curve
References
3- usesTime concentration of 80–150 Hz SEEG power gave a mean AUC of 0.706 for seizure-onset labels in 34 patients with two 60 s clips each sci:sha256:1f5be9e5c88e4ff8065fcb38d242d64e32c8801f49e8f30af1fa36489bb1cf50
We use its 68 window-power files, clinical label and pair rules, source metadata, and signal retrieval code. We rebuilt all input arrays and test whether high band concentration adds information in combined models with every test patient absent from training.
- usesReference choice changed relative 30–55 Hz power AUROC by 0.111 on average in two 60 s clips from 35 SEEG patients sci:sha256:d441c426f62a09b3b78933ca35f4c191a45f8076d63d922c1013d1d697a54791
The source decoder, metadata preparation, and pair selection modules originated in this publication. The unchanged modules are preserved in the cited window-power package and are used to retrieve and rebuild the present inputs.
- usesdoi:10.18112/openneuro.ds004100.v1.1.3
This exact OpenNeuro ds004100 version supplied the recordings, clinical labels, metadata, and source identities used in the study.
Cited by
0 publicationsPublic catalog entries on Sciscape.
No incoming citations on Sciscape.