Large language model vs. traditional machine learning:
Evaluating predictive models for early detection of tumor
relapse

J 2025

Large language model vs. traditional machine learning: Evaluating predictive models for early detection of tumor relapse

TIMILSINA, Mohan; Samuele BUOSI; Maria TORRENTE; Mariano PROVENCIO; Manuel COBO et al.

Základní údaje

Originální název

Large language model vs. traditional machine learning: Evaluating predictive models for early detection of tumor relapse

Autoři

TIMILSINA, Mohan; Samuele BUOSI; Maria TORRENTE; Mariano PROVENCIO; Manuel COBO; Delvys Rodriguez ABREU; Rafael Lopez CASTRO; Enric CARCERENY; Edward CURRY a Vít NOVACEK

Vydání

EXPERT SYSTEMS WITH APPLICATIONS, OXFORD, PERGAMON-ELSEVIER SCIENCE LTD, 2025, 0957-4174

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Nizozemské království

Utajení

není předmětem státního či obchodního tajemství

Odkazy

Link to the paper on ScienceDirect

Impakt faktor

Impact factor: 7.500 v roce 2024

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14330/25:00144043

Organizační jednotka

Fakulta informatiky

Klíčová slova anglicky

Classification; Tabular data; Foundation model; Cancer; Relapse

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 1. 4. 2026 21:23, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

In this study, we evaluate the effectiveness of foundational artificial intelligence (AI) models, particularly large language models (LLMs), in comparison to traditional machine learning methods for predicting tumor relapse in patients with non-small-cell lung cancer (NSCLC). With a high recurrence risk in NSCLC, early and accurate prediction is essential for improving patient outcomes and guiding treatment decisions. Our analysis utilizes a dataset of 1,348 patients, examining the performance of traditional machine learning models such as Random Forest, alongside cutting-edge LLMs like Mistral-7B, LLaMA-7B, Falcon-7B, and GPT-based models. While the Random Forest model slightly outperforms Mistral-7B in precision-recall for relapse prediction, the comparable results suggest that both approaches offer valuable insights for early relapse detection. This study underscores the potential of integrating classical machine learning with foundational AI models to enhance predictive accuracy in cancer prognosis, providing pathways for more personalized medical interventions.

Citovat

TIMILSINA, Mohan; Samuele BUOSI; Maria TORRENTE; Mariano PROVENCIO; Manuel COBO; Delvys Rodriguez ABREU; Rafael Lopez CASTRO; Enric CARCERENY; Edward CURRY a Vít NOVACEK. Large language model vs. traditional machine learning: Evaluating predictive models for early detection of tumor relapse. EXPERT SYSTEMS WITH APPLICATIONS. OXFORD: PERGAMON-ELSEVIER SCIENCE LTD, 2025, roč. 283, č. 127641, s. 1-13. ISSN 0957-4174. Dostupné z: https://doi.org/10.1016/j.eswa.2025.127641.

@article{2562659,
   author = {Timilsina, Mohan and Buosi, Samuele and Torrente, Maria and Provencio, Mariano and Cobo, Manuel and Abreu, Delvys Rodriguez and Castro, Rafael Lopez and Carcereny, Enric and Curry, Edward and Novacek, Vít},
   article_location = {OXFORD},
   article_number = {127641},
   doi = {https://doi.org/10.1016/j.eswa.2025.127641},
   keywords = {Classification; Tabular data; Foundation model; Cancer; Relapse},
   language = {eng},
   issn = {0957-4174},
   journal = {EXPERT SYSTEMS WITH APPLICATIONS},
   title = {Large language model vs. traditional machine learning: Evaluating predictive models for early detection of tumor relapse},
   url = {https://doi.org/10.1016/j.eswa.2025.127641},
   volume = {283},
   year = {2025}
}

TY  - JOUR
ID  - 2562659
AU  - Timilsina, Mohan - Buosi, Samuele - Torrente, Maria - Provencio, Mariano - Cobo, Manuel - Abreu, Delvys Rodriguez - Castro, Rafael Lopez - Carcereny, Enric - Curry, Edward - Novacek, Vít
PY  - 2025
TI  - Large language model vs. traditional machine learning: Evaluating predictive models for early detection of tumor relapse
JF  - EXPERT SYSTEMS WITH APPLICATIONS
VL  - 283
IS  - 127641
SP  - 1-13
EP  - 1-13
PB  - PERGAMON-ELSEVIER SCIENCE LTD
SN  - 09574174
KW  - Classification
KW  - Tabular data
KW  - Foundation model
KW  - Cancer
KW  - Relapse
UR  - https://doi.org/10.1016/j.eswa.2025.127641
N2  - In this study, we evaluate the effectiveness of foundational artificial intelligence (AI) models, particularly large language models (LLMs), in comparison to traditional machine learning methods for predicting tumor relapse in patients with non-small-cell lung cancer (NSCLC). With a high recurrence risk in NSCLC, early and accurate prediction is essential for improving patient outcomes and guiding treatment decisions. Our analysis utilizes a dataset of 1,348 patients, examining the performance of traditional machine learning models such as Random Forest, alongside cutting-edge LLMs like Mistral-7B, LLaMA-7B, Falcon-7B, and GPT-based models. While the Random Forest model slightly outperforms Mistral-7B in precision-recall for relapse prediction, the comparable results suggest that both approaches offer valuable insights for early relapse detection. This study underscores the potential of integrating classical machine learning with foundational AI models to enhance predictive accuracy in cancer prognosis, providing pathways for more personalized medical interventions.
ER  -

TIMILSINA, Mohan; Samuele BUOSI; Maria TORRENTE; Mariano PROVENCIO; Manuel COBO; Delvys Rodriguez ABREU; Rafael Lopez CASTRO; Enric CARCERENY; Edward CURRY a Vít NOVACEK. Large language model vs. traditional machine learning: Evaluating predictive models for early detection of tumor relapse. \textit{EXPERT SYSTEMS WITH APPLICATIONS}. OXFORD: PERGAMON-ELSEVIER SCIENCE LTD, 2025, roč.~283, č.~127641, s.~1-13. ISSN~0957-4174. Dostupné z: https://doi.org/10.1016/j.eswa.2025.127641.

Přehled o publikaci