Your Location：
Home >
Browse articles >
PRIME: an interpretable artificial intelligence model based on liquid biopsy improves prediction of progression risk in non-small cell lung cancer
RESEARCH | Updated：2026-06-10
Previous|Next

    • PRIME: an interpretable artificial intelligence model based on liquid biopsy improves prediction of progression risk in non-small cell lung cancer

    • “Researchers developed PRIME, an interpretable AI model integrating ctDNA-MRD, mutations and clinical features to predict treatment failure risk in early-stage NSCLC. The neural network achieved AUCs of 0.85 and 0.82 in training and validation sets, outperforming single biomarkers and enabling personalized adjuvant therapy decisions.”
    • Yu Wang , Yong-Bo Xiang , Xiao-Wei Chen , Tao Zhang , Jian-Yang Wang , Wen-Yang Liu , Lei Deng , Lu-Hua Wang , Shu-Geng Gao , Nan Bi
    • Military Medical Research Vol. 13, Issue 5, Pages: 747-765(2026)

    • DOI： 10.1186/s40779-025-00679-z     

      CLC：

    • Accepted：25 November 2025 ，

    Scan QR Code

  •  
  •  

  • AI Introduction

  • Full Text(HTML)

  • Figs( 6 ) Tabs( 0 )

  • References

  • Publication Info

  • Metrics

56

Views

59

Downloads

0

CSCD

Alert me when the article has been cited
Submit
Tools
  • BibTeXDownload
  • EndnoteDownload
  • RefMan Download
  • NoteExpressDownload
  • NoteFirstDownload

Related Articles

Enhancing the clinical relevance of haemorrhage prediction models in trauma
Artificial intelligence and machine learning for hemorrhagic trauma care
Sepsis in burns: lessons learned, challenges remain
Endothelial barrier and sepsis: mechanisms and potential therapeutic strategies
Bridging the lung cancer screening eligibility gap: evaluation of guideline applicability in asymptomatic patients

Related Author

Sankalp Tandle
Jared M. Wohlgemut
Max E. R. Marsden
Erhan Pisirir
Evangelia Kyrimi
Rebecca S. Stoner
William Marsh
Zane B. Perkins

Related Institution

Centre for Trauma Sciences, Blizard Institute, Queen Mary University of London
The Royal London Hospital, Barts Health NHS Trust
Academic Department of Military Surgery and Trauma, Research and Clinical Innovation, The Royal Centre for Defence Medicine
Department of Electronic Engineering and Computer Science, Queen Mary University of London
Sunnybrook Health Sciences Centre