TY  - JOUR
AU  - Hamdan, Sami
AU  - More, Shammi
AU  - Sasse, Leonard
AU  - Komeyer, Vera
AU  - Patil, Kaustubh
AU  - Raimondo, Federico
TI  - Julearn: an easy-touse library for leakage-free evaluation and inspection of ML models
JO  - GigaByte
VL  -  
SN  - 2709-4715
CY  - [Erscheinungsort nicht ermittelbar]
PB  - GigaScience Press
M1  - FZJ-2024-01705
SP  -  
PY  - 2024
N1  - This work was partly supported by the Helmholtz-AI project DeGen (ZT-I-PF-5-078), the Helmholtz Portfolio Theme “Supercomputing and Modeling for the Human Brain” the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation), project PA 3634/1-1 and project-ID 431549029–SFB 1451 project B05, the Helmholtz Imaging Platform and eBRAIN Health (HORIZON-INFRA-2021-TECH-01).
AB  - The fast-paced development of machine learning (ML) and its increasing adoption in research challenge researchers without extensive training in ML. In neuroscience, ML can help understand brain-behavior relationships, diagnose diseases and develop biomarkers using data from sources like magnetic resonance imaging and electroencephalography. Primarily, ML builds models to make accurate predictions on unseen data. Researchers evaluate models' performance and generalizability using techniques such as cross-validation (CV). However, choosing a CV scheme and evaluating an ML pipeline is challenging and, if done improperly, can lead to overestimated results and incorrect interpretations. Here, we created julearn, an open-source Python library allowing researchers to design and evaluate complex ML pipelines without encountering common pitfalls. We present the rationale behind julearn’s design, its core features, and showcase three examples of previously-published research projects. Julearn simplifies the access to ML providing an easy-to-use environment. With its design, unique features, simple interface, and practical documentation, it poses as a useful Python-based library for research projects.
LB  - PUB:(DE-HGF)16
DO  - DOI:10.46471/gigabyte.113
UR  - https://juser.fz-juelich.de/record/1023472
ER  -