Reported EEG recording length gives AUC 0.736 for frontotemporal dementia against controls in ds004504 v1.0.9
We tested a recording length score in all 88 people from OpenNeuro ds004504 version 1.0.9. Shorter reported recordings gave AUC 0.736 for frontotemporal dementia against controls. The planned 97.5% bootstrap interval was 0.555 to 0.894. The fixed EEG score gave AUC 0.759. The paired difference interval included zero. The source paper already reported different group mean lengths. This study adds length-only ranking estimates, paired comparisons, and source checks. The package preserves code, source hashes, scores, resampling data, results, figures, and reproduction commands. These results apply to this cohort. They do not establish clinical performance or a neural cause.
electroencephalography · recording duration · frontotemporal dementia · Alzheimer disease · area under the curve · bootstrap · OpenNeuro
References
4- usesA fixed posterior EEG theta/alpha ratio gives higher AUC for Alzheimer disease against controls than against frontotemporal dementia in ds004504 v1.0.9 sci:sha256:95d180bc32fe10408c670c4b5dd44f8dbd7329603b75fe8f858ddce26f1322ee
We reused its fixed posterior EEG score, preserved band power features, processed sample counts, and full source replay. These inputs enabled the paired length-versus-EEG AUC comparison.
- usesA fixed EEG model predicts shuffled labels when training and test sets share the 88 ds004504 subjects sci:sha256:7ba0bee1f809898d24fefdeb839b4d53689a26bcea0ff0429014af5f5ef0c2a9
We reused its original feature extraction and retrieval code through the fixed-score publication. Fresh binary checks reproduced the preserved feature arrays.
- usesdoi:10.18112/openneuro.ds004504.v1.0.9
The analysis used OpenNeuro ds004504 version 1.0.9 as its source cohort.
- doi:10.3390/data8060095
Cited by
0 publicationsPublic catalog entries on Sciscape.
No incoming citations on Sciscape.