The potential of GPT-4 advanced data analysis for radiomics-based machine learning models
GPT-4 can autonomously develop radiomics-based MLMs, achieving performance comparable to handcrafted MLMs. However, its poorer class-wise performance due to unbalanced datasets shows limitations in handling complete end-to-end ML pipelines.
Authors
- Gianluca Brugnara (ORCID: https://orcid.org/0000-0003-2461-1407)
- Martin Bendszus (ORCID: https://orcid.org/0000-0002-9094-6769)
- Philipp Kickingereder (ORCID: https://orcid.org/0000-0002-6224-0064)
- Martha Foltyn‐Dumitru (ORCID: https://orcid.org/0009-0005-2925-9176)
- Marianne Schell (ORCID: https://orcid.org/0000-0002-9754-1350)
- Felix Sahm (ORCID: https://orcid.org/0000-0001-5441-1962)
- Mustafa Ahmed Mahmutoglu (ORCID: https://orcid.org/0000-0002-4891-5547)
- Wolfgang Wick (ORCID: https://orcid.org/0000-0002-6171-634X)
- Aditya Rastogi (ORCID: https://orcid.org/0000-0001-6103-4886)
- Tobias Keßler (ORCID: https://orcid.org/0000-0001-8350-7074)
- Jae Young Cho
Institutions
- German Cancer Research Center (DE)
- Heidelberg University (DE)
- University Hospital Bonn (DE)
- University Hospital Heidelberg (DE)
- Cancer Research Center (US)
- Heidelberg University (US)
Publication Details
- Journal
- Neuro-Oncology Advances
- Published
- 2024-12-23
- DOI
- https://doi.org/10.1093/noajnl/vdae230
- Citations
- 3
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 1.21
Funders
- Deutsches Krebsforschungszentrum
- Deutsche Forschungsgemeinschaft
- Deutschen Konsortium für Translationale Krebsforschung
- Universitätsklinikum Heidelberg