← Back to research

CatBoost with physics-based metaheuristics for thyroid cancer recurrence prediction

Thyroid risk returns
Physics guides machine learning—
Recurrence revealed.
Machine learning
Cancer prediction
Bioinformatics
CatBoost
Metaheuristics

P. Sarker, K. Choi, A. A. Nahid, M. A. Samad, et al., “CatBoost with physics-based metaheuristics for thyroid cancer recurrence prediction,” BioData Mining 18:84 (2025), doi: 10.1186/s13040-025-00494-1

Authors
Affiliations

P. Sarker

K. Choi

A. A. Nahid

M. A. Samad

Published

January 2025

Doi

10.1186/s13040-025-00494-1

Abstract

Thyroid cancer recurrence prediction remains challenging due to complex nonlinear relationships in clinical and pathological data. This study proposes a hybrid modeling framework that integrates CatBoost with physics-based metaheuristic optimization algorithms to enhance predictive accuracy and robustness. Experimental results demonstrate that the proposed approach outperforms conventional machine learning models, offering a reliable decision-support tool for identifying patients at high risk of thyroid cancer recurrence.

Important figures

Figure 2a: Predicted effects of imposing specific emergency public health measures over first 15 months of the COVID pandemic, split by whether states formally derogated from the ICCPR

Figure 3a: Predicted effects of imposing specific emergency public health measures over first 15 months of the COVID pandemic, split by whether states formally derogated from the ICCPR

Citation

 Add to Zotero

```bibtex (article?){SarkerEtAl:2025, Author = {Sarker, P. and Choi, K. and Nahid, A. A. and Samad, M. A. and others}, Title = {CatBoost with physics-based metaheuristics for thyroid cancer recurrence prediction}, Journal = {BioData Mining}, Volume = {18}, Pages = {84}, Year = {2025}, Doi = {10.1186/s13040-025-00494-1} }