View in EDS

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

Saved in:
Bibliographic Details
Title: Large language model vs. traditional machine learning: Evaluating predictive models for early detection of tumor relapse.
Authors: Timilsina, Mohan1 (AUTHOR) mohan.timilsina@insight-centre.org, Buosi, Samuele1 (AUTHOR) samuele.buosi@insight-centre.org, Torrente, Maria2 (AUTHOR), Provencio, Mariano2 (AUTHOR) mariano.provencio@salud.madrid.org, Cobo, Manuel3 (AUTHOR) manuelcobodols@yahoo.es, Rodrıguez Abreu, Delvys4 (AUTHOR) drodabr@gobiernodecanarias.org, López Castro, Rafael5 (AUTHOR) rafalopezcastro@yahoo.es, Carcereny, Enric6 (AUTHOR) ecarcereny@iconcologia.net, Curry, Edward1 (AUTHOR) edward.curry@insight-centre.org, Nováček, Vít1,7,8 (AUTHOR) vit.novacek@insight-centre.org
Source: Expert Systems with Applications. Jul2025, Vol. 283, pN.PAG-N.PAG. 1p.
Subjects: Language models, Lung cancer, Non-small-cell lung carcinoma, Cancer relapse, Early detection of cancer
Abstract: 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. • Study contrasts AI and traditional methods for NSCLC relapse prediction. • Early, accurate predictions are crucial for NSCLC patient care. • Analysis includes 1,348 NSCLC patient data points. • Random Forest edges out Mistral-7B in precision–recall. • Both models show potential for early detection of lung cancer recurrence. [ABSTRACT FROM AUTHOR]
Copyright of Expert Systems with Applications is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 185443527
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Large language model vs. traditional machine learning: Evaluating predictive models for early detection of tumor relapse.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Timilsina%2C+Mohan%22">Timilsina, Mohan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> mohan.timilsina@insight-centre.org</i><br /><searchLink fieldCode="AR" term="%22Buosi%2C+Samuele%22">Buosi, Samuele</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> samuele.buosi@insight-centre.org</i><br /><searchLink fieldCode="AR" term="%22Torrente%2C+Maria%22">Torrente, Maria</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Provencio%2C+Mariano%22">Provencio, Mariano</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> mariano.provencio@salud.madrid.org</i><br /><searchLink fieldCode="AR" term="%22Cobo%2C+Manuel%22">Cobo, Manuel</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> manuelcobodols@yahoo.es</i><br /><searchLink fieldCode="AR" term="%22Rodrıguez+Abreu%2C+Delvys%22">Rodrıguez Abreu, Delvys</searchLink><relatesTo>4</relatesTo> (AUTHOR)<i> drodabr@gobiernodecanarias.org</i><br /><searchLink fieldCode="AR" term="%22López+Castro%2C+Rafael%22">López Castro, Rafael</searchLink><relatesTo>5</relatesTo> (AUTHOR)<i> rafalopezcastro@yahoo.es</i><br /><searchLink fieldCode="AR" term="%22Carcereny%2C+Enric%22">Carcereny, Enric</searchLink><relatesTo>6</relatesTo> (AUTHOR)<i> ecarcereny@iconcologia.net</i><br /><searchLink fieldCode="AR" term="%22Curry%2C+Edward%22">Curry, Edward</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> edward.curry@insight-centre.org</i><br /><searchLink fieldCode="AR" term="%22Nováček%2C+Vít%22">Nováček, Vít</searchLink><relatesTo>1,7,8</relatesTo> (AUTHOR)<i> vit.novacek@insight-centre.org</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Expert+Systems+with+Applications%22">Expert Systems with Applications</searchLink>. Jul2025, Vol. 283, pN.PAG-N.PAG. 1p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Language+models%22">Language models</searchLink><br /><searchLink fieldCode="DE" term="%22Lung+cancer%22">Lung cancer</searchLink><br /><searchLink fieldCode="DE" term="%22Non-small-cell+lung+carcinoma%22">Non-small-cell lung carcinoma</searchLink><br /><searchLink fieldCode="DE" term="%22Cancer+relapse%22">Cancer relapse</searchLink><br /><searchLink fieldCode="DE" term="%22Early+detection+of+cancer%22">Early detection of cancer</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: 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. • Study contrasts AI and traditional methods for NSCLC relapse prediction. • Early, accurate predictions are crucial for NSCLC patient care. • Analysis includes 1,348 NSCLC patient data points. • Random Forest edges out Mistral-7B in precision–recall. • Both models show potential for early detection of lung cancer recurrence. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Expert Systems with Applications is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=185443527
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.eswa.2025.127641
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: N.PAG
    Subjects:
      – SubjectFull: Language models
        Type: general
      – SubjectFull: Lung cancer
        Type: general
      – SubjectFull: Non-small-cell lung carcinoma
        Type: general
      – SubjectFull: Cancer relapse
        Type: general
      – SubjectFull: Early detection of cancer
        Type: general
    Titles:
      – TitleFull: Large language model vs. traditional machine learning: Evaluating predictive models for early detection of tumor relapse.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Timilsina, Mohan
      – PersonEntity:
          Name:
            NameFull: Buosi, Samuele
      – PersonEntity:
          Name:
            NameFull: Torrente, Maria
      – PersonEntity:
          Name:
            NameFull: Provencio, Mariano
      – PersonEntity:
          Name:
            NameFull: Cobo, Manuel
      – PersonEntity:
          Name:
            NameFull: Rodrıguez Abreu, Delvys
      – PersonEntity:
          Name:
            NameFull: López Castro, Rafael
      – PersonEntity:
          Name:
            NameFull: Carcereny, Enric
      – PersonEntity:
          Name:
            NameFull: Curry, Edward
      – PersonEntity:
          Name:
            NameFull: Nováček, Vít
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 07
              Text: Jul2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 09574174
          Numbering:
            – Type: volume
              Value: 283
          Titles:
            – TitleFull: Expert Systems with Applications
              Type: main
ResultId 1