Predictive value of machine learning for PD-L1 expression in NSCLC: a systematic review and meta-analysis

Abstract Background As machine learning (ML) continuously develops in cancer diagnosis and treatment, some researchers have attempted to predict the expression of programmed death ligand-1 (PD-L1) in non-small cell lung cancer (NSCLC) by ML. However, there is a lack of systematic evidence on the eff...

Full description

Saved in:
Bibliographic Details
Main Authors: Ting Zheng, Xingxing Li, Li Zhou, Jianjiang Jin
Format: Article
Language:English
Published: BMC 2025-05-01
Series:World Journal of Surgical Oncology
Subjects:
Online Access:https://doi.org/10.1186/s12957-025-03847-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850268945874944000
author Ting Zheng
Xingxing Li
Li Zhou
Jianjiang Jin
author_facet Ting Zheng
Xingxing Li
Li Zhou
Jianjiang Jin
author_sort Ting Zheng
collection DOAJ
description Abstract Background As machine learning (ML) continuously develops in cancer diagnosis and treatment, some researchers have attempted to predict the expression of programmed death ligand-1 (PD-L1) in non-small cell lung cancer (NSCLC) by ML. However, there is a lack of systematic evidence on the effectiveness of ML. Methods We conducted a thorough search across Embase, PubMed, the Cochrane Library, and Web of Science from inception to December 14th, 2023.A systematic review and meta-analysis was conducted to assess the value of ML for predicting PD-L1 expression in NSCLC. Results Totally 30 studies with 12,898 NSCLC patients were included. The thresholds of PD-L1 expression level were < 1%, 1–49%, and ≥ 50%. In the validation set, in the binary classification for PD-L1 ≥ 1%, the pooled C-index was 0.646 (95%CI: 0.587–0.705), 0.799 (95%CI: 0.782–0.817), 0.806 (95%CI: 0.753–0.858), and 0.800 (95%CI: 0.717–0.883), respectively, for the clinical feature-, radiomics-, radiomics + clinical feature-, and pathomics-based ML models; in the binary classification for PD-L1 ≥ 50%, the pooled C-index was 0.649 (95%CI: 0.553–0.744), 0.771 (95%CI: 0.728–0.814), and 0.826 (95%CI: 0.783–0.869), respectively, for the clinical feature-, radiomics-, and radiomics + clinical feature-based ML models. Conclusions At present, radiomics- or pathomics-based ML methods are applied for the prediction of PD-L1 expression in NSCLC, which both achieve satisfactory accuracy. In particular, the radiomics-based ML method seems to have wider clinical applicability as a non-invasive diagnostic tool. Both radiomics and pathomics serve as processing methods for medical images. In the future, we expect to develop medical image-based DL methods for intelligently predicting PD-L1 expression.
format Article
id doaj-art-54b1bfdee12c4136a2ce83e267555b8f
institution OA Journals
issn 1477-7819
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series World Journal of Surgical Oncology
spelling doaj-art-54b1bfdee12c4136a2ce83e267555b8f2025-08-20T01:53:19ZengBMCWorld Journal of Surgical Oncology1477-78192025-05-0123111610.1186/s12957-025-03847-6Predictive value of machine learning for PD-L1 expression in NSCLC: a systematic review and meta-analysisTing Zheng0Xingxing Li1Li Zhou2Jianjiang Jin3Department of Medical Oncology, The First People’s Hospital of Linping DistrictDepartment of Medical Oncology, The First People’s Hospital of Linping DistrictDepartment of Medical Oncology, The First People’s Hospital of Linping DistrictDepartment of Medical Oncology, The First People’s Hospital of Linping DistrictAbstract Background As machine learning (ML) continuously develops in cancer diagnosis and treatment, some researchers have attempted to predict the expression of programmed death ligand-1 (PD-L1) in non-small cell lung cancer (NSCLC) by ML. However, there is a lack of systematic evidence on the effectiveness of ML. Methods We conducted a thorough search across Embase, PubMed, the Cochrane Library, and Web of Science from inception to December 14th, 2023.A systematic review and meta-analysis was conducted to assess the value of ML for predicting PD-L1 expression in NSCLC. Results Totally 30 studies with 12,898 NSCLC patients were included. The thresholds of PD-L1 expression level were < 1%, 1–49%, and ≥ 50%. In the validation set, in the binary classification for PD-L1 ≥ 1%, the pooled C-index was 0.646 (95%CI: 0.587–0.705), 0.799 (95%CI: 0.782–0.817), 0.806 (95%CI: 0.753–0.858), and 0.800 (95%CI: 0.717–0.883), respectively, for the clinical feature-, radiomics-, radiomics + clinical feature-, and pathomics-based ML models; in the binary classification for PD-L1 ≥ 50%, the pooled C-index was 0.649 (95%CI: 0.553–0.744), 0.771 (95%CI: 0.728–0.814), and 0.826 (95%CI: 0.783–0.869), respectively, for the clinical feature-, radiomics-, and radiomics + clinical feature-based ML models. Conclusions At present, radiomics- or pathomics-based ML methods are applied for the prediction of PD-L1 expression in NSCLC, which both achieve satisfactory accuracy. In particular, the radiomics-based ML method seems to have wider clinical applicability as a non-invasive diagnostic tool. Both radiomics and pathomics serve as processing methods for medical images. In the future, we expect to develop medical image-based DL methods for intelligently predicting PD-L1 expression.https://doi.org/10.1186/s12957-025-03847-6Lung cancerPD-L1Machine learningMeta-analysisRadiomics
spellingShingle Ting Zheng
Xingxing Li
Li Zhou
Jianjiang Jin
Predictive value of machine learning for PD-L1 expression in NSCLC: a systematic review and meta-analysis
World Journal of Surgical Oncology
Lung cancer
PD-L1
Machine learning
Meta-analysis
Radiomics
title Predictive value of machine learning for PD-L1 expression in NSCLC: a systematic review and meta-analysis
title_full Predictive value of machine learning for PD-L1 expression in NSCLC: a systematic review and meta-analysis
title_fullStr Predictive value of machine learning for PD-L1 expression in NSCLC: a systematic review and meta-analysis
title_full_unstemmed Predictive value of machine learning for PD-L1 expression in NSCLC: a systematic review and meta-analysis
title_short Predictive value of machine learning for PD-L1 expression in NSCLC: a systematic review and meta-analysis
title_sort predictive value of machine learning for pd l1 expression in nsclc a systematic review and meta analysis
topic Lung cancer
PD-L1
Machine learning
Meta-analysis
Radiomics
url https://doi.org/10.1186/s12957-025-03847-6
work_keys_str_mv AT tingzheng predictivevalueofmachinelearningforpdl1expressioninnsclcasystematicreviewandmetaanalysis
AT xingxingli predictivevalueofmachinelearningforpdl1expressioninnsclcasystematicreviewandmetaanalysis
AT lizhou predictivevalueofmachinelearningforpdl1expressioninnsclcasystematicreviewandmetaanalysis
AT jianjiangjin predictivevalueofmachinelearningforpdl1expressioninnsclcasystematicreviewandmetaanalysis