Revisiting the Endoscopic Third Ventriculostomy Success Score using machine learning: can we do better?
This is the largest external validation of the ETVSS, and it confirms modest performance. More sophisticated ML algorithms do not meaningfully improve predictive performance compared to ETVSS; this underscores the need for higher utility, novelty, and dimensionality of input data rather than changes in modeling strategies.
Authors
- Syed M. Adil (ORCID: https://orcid.org/0000-0002-2322-5478)
- Matthew L. Vestal (ORCID: https://orcid.org/0009-0004-1788-2326)
- Gerald A. Grant (ORCID: https://orcid.org/0000-0002-2651-4603)
- Kennedy Carpenter (ORCID: https://orcid.org/0000-0001-6633-5266)
- Brad J. Kolls (ORCID: https://orcid.org/0000-0002-8704-8749)
- Benjamin D. Wissel (ORCID: https://orcid.org/0000-0002-8967-9296)
- Timothy Dunn (ORCID: https://orcid.org/0000-0002-9381-4630)
- Pranav Warman (ORCID: https://orcid.org/0000-0001-5199-2474)
- Andreas Seas (ORCID: https://orcid.org/0000-0003-0624-1254)
- Anthony T. Fuller (ORCID: https://orcid.org/0000-0001-8841-6948)
- Lacey Carter
- Shivanand P. Lad (ORCID: https://orcid.org/0000-0003-4991-5319)
- Daniel Sexton (ORCID: https://orcid.org/0000-0002-0403-2574)
- Herbert E. Fuchs
Institutions
- Prisma Health (US)
- Duke University (US)
- Greenville Memorial Hospital (US)
- Duke Medical Center (US)
- Duke University Hospital (US)
Publication Details
- Journal
- Journal of Neurosurgery Pediatrics
- Published
- 2024-12-01
- DOI
- https://doi.org/10.3171/2024.9.peds24146
- Primary Topic
- Cerebrospinal fluid and hydrocephalus
- Type
- article
- Field-Weighted Citation Impact
- 0.00