High gamma added 0.017 AUC to a quadratic contact number model in 33 SEEG patients, with a refitted patient interval that included zero
We tested whether high gamma adds seizure onset label information beyond contact number. We used two 60 second SEEG records from each of 33 patients in OpenNeuro ds004100 version 1.1.3. We compared a quadratic contact number rank model with the same model plus high gamma rank. Every record from the test patient was excluded from training. Mean patient AUC was 0.7887 for number and 0.8052 for the combined model. The added AUC was 0.0165. A 95 percent refitted patient bootstrap interval was -0.0219 to 0.0587. The interval did not establish a positive mean gain. It also did not establish equal performance. Held out pair log loss was lower for the combined model. This was a secondary descriptive result. We checked all 70 input records against pinned public EDF bytes, an independent reader, and independent Welch power. The package preserves code, inputs, predictions, 2,000 bootstrap fits, hashes, and retrieval instructions. The result applies to this model and to mixed label shafts in these short records. It does not establish clinical value.
stereo-electroencephalography · high gamma · seizure onset · patient-excluded validation · pairwise ranking
References
5- usesLower contact numbers gave mean seizure onset AUC 0.794 within mixed inferred shafts in 34 selected ds004100 SEEG patients sci:sha256:50d777142ef4ebc45c41203ba318cb2244c6b807e8d402b44d8ba5067784feec
Its contact number evidence motivated our fixed baseline. We test added high gamma with complete patient exclusion.
- usessci:sha256:ad80bc2bd0737883d3eb45a01e266fee6a996e9e1e541f80de6ada0bdd0447e5 not known to Sciscape
Its first minute band covariance inputs are preserved in the source package used for our new model comparison.
- Mean high gamma AUC within inferred shafts exceeds a label control in one-minute SEEG samples with an average reference from 33 HUP patients sci:sha256:46a12570ac1f98c21c7f72a6958c443edd3986f81154a8c30cc11c1f760e42a9
[Legacy relation: reproduces] The same pair weights and average reference reproduce its mean within shaft high gamma AUC of 0.7037.
- usesMean high gamma AUC within inferred shafts exceeds a label control in one-minute SEEG samples with an average reference from 33 HUP patients sci:sha256:46a12570ac1f98c21c7f72a6958c443edd3986f81154a8c30cc11c1f760e42a9
We used its 70 covariance inputs, pinned source metadata, labels, and EDF reader to test added high gamma prediction.
- usesdoi:10.18112/openneuro.ds004100.v1.1.3
This exact OpenNeuro ds004100 v1.1.3 snapshot supplied the SEEG records, labels, and source metadata used in the analysis.
Cited by
2 publicationsPublic catalog entries on Sciscape.
- usesA fixed low gamma correction reduced mean high gamma map error between two 60 second interictal records in 35 SEEG patients under common average reference
Its source cohort, pinned raw range records, metadata, and EDF reader were carried through the cited window power package. We preserved this source chain and reused the reader for fresh retrieval.
- usesThe within shaft high gamma median minus mean AUC interval included zero in 33 SEEG patients under common average reference
This work supplied the fixed source cohort, pinned raw range recipe, metadata, and EDF reader. Its band covariance files checked the new mean window powers.