Beyond predictive performance: Interpretability challenges and feature importance bias in XGBoost-based readmission models.

Oka S, Suzuki M, Takefuji Y

Open source

DOI
10.1016/j.gerinurse.2026.104318
Published
2026 Aug 27
Container
Geriatric nursing (New York, N.Y.)
Publisher
Not recorded
Open access
no

Credibility signals

limited evidence Score 43/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.1016/j.gerinurse.2026.104318,
  title = {Beyond predictive performance: Interpretability challenges and feature importance bias in XGBoost-based readmission models.},
  author = {Oka S and Suzuki M and Takefuji Y},
  year = {2026},
  journal = {Geriatric nursing (New York, N.Y.)},
  doi = {10.1016/j.gerinurse.2026.104318},
  url = {https://doi.org/10.1016/j.gerinurse.2026.104318}
}

RIS

TY  - JOUR
TI  - Beyond predictive performance: Interpretability challenges and feature importance bias in XGBoost-based readmission models.
AU  - Oka S
AU  - Suzuki M
AU  - Takefuji Y
PY  - 2026
JO  - Geriatric nursing (New York, N.Y.)
DO  - 10.1016/j.gerinurse.2026.104318
UR  - https://doi.org/10.1016/j.gerinurse.2026.104318
ER  -

APA

S, O., M, S., & Y, T. (2026). Beyond predictive performance: Interpretability challenges and feature importance bias in XGBoost-based readmission models.. Geriatric nursing (New York, N.Y.). https://doi.org/10.1016/j.gerinurse.2026.104318

Source records