1
|
Huang Z, Wang S, Zhou J, Chen H, Li Y. PD-L1 Scoring Models for Non-Small Cell Lung Cancer in China: Current Status, AI-Assisted Solutions and Future Perspectives. Thorac Cancer 2025; 16:e70042. [PMID: 40189932 PMCID: PMC11973252 DOI: 10.1111/1759-7714.70042] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2024] [Revised: 02/27/2025] [Accepted: 03/05/2025] [Indexed: 04/10/2025] Open
Abstract
Immunotherapy has revolutionized the diagnosis and treatment model for patients with advanced non-small cell lung cancer (NSCLC). Numerous clinical trials and real-world reports have confirmed that PD-L1 status is a key factor for the successful use of immunotherapy in NSCLC, by predicting clinical outcomes and identifying patients most likely to benefit from this treatment. Therefore, accurate and standardized evaluation of PD-L1 expression is crucial. Currently, PD-L1 testing in China faces several challenges, including a heavy pathologist workload, a shortage of highly trained pathologists plus the inadequate capacity of diagnostic laboratories, confusion around different scoring methods, cut-off values, and indications, and limited concordance between PD-L1 assays. In this review, we summarize the current status and limitations of PD-L1 testing for patients with NSCLC in China and discuss recent progress in artificial intelligence-assisted PD-L1 scoring. Our review aims to support improvements in clinical PD-L1 testing practice and optimization of the prognosis and outcomes of immunotherapy in this patient population.
Collapse
Affiliation(s)
- Ziling Huang
- Department of PathologyFudan University Shanghai Cancer CenterShanghaiChina
- Department of Oncology, Shanghai Medical CollegeFudan UniversityShanghaiChina
| | - Shen Wang
- School of Computer ScienceFudan UniversityShanghaiChina
| | - Jiansong Zhou
- Value & Implementation, Global Medical & Scientific Affairs, MSD ChinaShanghaiChina
| | - Haiquan Chen
- Department of Oncology, Shanghai Medical CollegeFudan UniversityShanghaiChina
- Department of Thoracic SurgeryFudan University Shanghai Cancer CenterShanghaiChina
| | - Yuan Li
- Department of PathologyFudan University Shanghai Cancer CenterShanghaiChina
- Department of Oncology, Shanghai Medical CollegeFudan UniversityShanghaiChina
| |
Collapse
|
2
|
Rui M, Wang Y, Li Y, Fei Z. Immunotherapy Guided by Immunohistochemistry PD-L1 Testing for Patients with NSCLC: A Microsimulation Model-Based Effectiveness and Cost-Effectiveness Analysis. BioDrugs 2024; 38:157-170. [PMID: 37792142 DOI: 10.1007/s40259-023-00628-z] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 09/18/2023] [Indexed: 10/05/2023]
Abstract
BACKGROUND On the basis of immunohistochemistry PD-L1 testing results, patients with advanced non-small cell lung cancer (NSCLC) are treated differently. Theoretically, patients with high PD-L1 expression (50% or 1%) should receive PD-1 monotherapy for fewer adverse reactions and cost savings from avoiding chemotherapy; however, there is controversy surrounding the cut-off criteria (1% or 50%) for immunohistochemistry testing and threshold for PD-1 monotherapy. OBJECTIVE This study aims to predict the effectiveness and cost-effectiveness of different immunotherapy strategies for patients with NSCLC in China from the healthcare system perspective. PATIENTS AND METHODS A microsimulation model was developed to evaluate the effectiveness and cost-effectiveness of three treatment strategies: PD-L1 testing (1%) (PD-1 monotherapy for those with PD-L1 expression at 1% threshold, and combination with chemotherapy for others with immunohistochemistry testing), PD-L1 testing (50%) (PD-1 monotherapy for those with PD-L1 expression at 50% threshold, and combination with chemotherapy for others with immunohistochemistry testing), and No PD-L1 testing (PD-1 combined with chemotherapy without immunohistochemistry testing). The model assumed 1000 patients per strategy, with each patient entering a unique clinical path prior to receiving treatment on the basis of PD-L1 test results. Clinical inputs were derived from clinical trials. Cost and utility parameters were obtained from the database and literature. One-way probabilistic sensitivity analyses (PSA) and six scenario analyses were used to test the model's robustness. RESULTS The study revealed a hierarchy of survival benefits across three strategies, with No PD-L1 testing demonstrating the most survival advantage, followed by PD-L1 testing (50%), and finally, PD-L1 testing (1%). The comparative analysis demonstrated that No PD-L1 testing significantly enhanced overall survival (OS) (HR 0.85, 95% CI 0.78-0.93), progression-free survival (HR 0.82, 95% CI 0.75-0.90), and progression-free2 survival (PFS2) (HR 0.91, 95% CI 0.83-0.99) when juxtaposed against PD-L1 testing (1%). However, these improvements were not as pronounced when compared with PD-L1 testing (50%), particularly in relation to PFS, PFS2, and OS. The cost-effectiveness analysis further unveiled incremental cost-utility ratios (ICUR), with No PD-L1 testing versus PD-L1 testing (50%) at $34,003 per quality-adjusted life year (QALY) and No PD-L1 testing versus PD-L1 testing (1%) at $34,804 per QALY. In parallel, the ICUR for PD-L1 testing (50%) versus PD-L1 testing (1%) stood at $35,713 per QALY. Remarkably, the PSA result under a willingness-to-pay (WTP) threshold of $10,144 per QALY, with a 100% probability, demonstrated PD-L1 testing (1%) as the most cost-effective option. CONCLUSIONS The survival benefits of PD-1 monotherapy for high expression with PD-L1 immunohistochemistry testing are inferior to those of PD-1 combined with chemotherapy without testing, but it is found to be more cost-effective at the WTP thresholds in China and holds great potential in increasing affordability and reducing the economic burden.
Collapse
Affiliation(s)
- Mingjun Rui
- School of Pharmacy, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong SAR, China.
| | - Yingcheng Wang
- School of Pharmacy, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Yunfei Li
- Institute for Global Health, Department of Population Health Sciences, University College London, London, UK
| | - Zhengyang Fei
- Center for Pharmacoeconomics and Outcomes Research, China Pharmaceutical University, Nanjing, China
- School of International Pharmaceutical Business, China Pharmaceutical University, Nanjing, Jiangsu, China
| |
Collapse
|
3
|
Yu Y, Bai Y, Zheng P, Wang N, Deng X, Ma H, Yu R, Ma C, Liu P, Xie Y, Wang C, Chen H. Radiomics-based prediction of response to immune checkpoint inhibitor treatment for solid cancers using computed tomography: a real-world study of two centers. BMC Cancer 2022; 22:1241. [PMID: 36451109 PMCID: PMC9710011 DOI: 10.1186/s12885-022-10344-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2022] [Accepted: 11/21/2022] [Indexed: 12/05/2022] Open
Abstract
BACKGROUND Immune checkpoint inhibitors (ICIs) represent an approved treatment for various cancers; however, only a small proportion of the population is responsive to such treatment. We aimed to develop and validate a plain CT-based tool for predicting the response to ICI treatment among cancer patients. METHODS Data for patients with solid cancers treated with ICIs at two centers from October 2019 to October 2021 were randomly divided into training and validation sets. Radiomic features were extracted from pretreatment CT images of the tumor of interest. After feature selection, a radiomics signature was constructed based on the least absolute shrinkage and selection operator regression model, and the signature and clinical factors were incorporated into a radiomics nomogram. Model performance was evaluated using the training and validation sets. The Kaplan-Meier method was used to visualize associations with survival. RESULTS Data for 122 and 30 patients were included in the training and validation sets, respectively. Both the radiomics signature (radscore) and nomogram exhibited good discrimination of response status, with areas under the curve (AUC) of 0.790 and 0.814 for the training set and 0.831 and 0.847 for the validation set, respectively. The calibration evaluation indicated goodness-of-fit for both models, while the decision curves indicated that clinical application was favorable. Both models were associated with the overall survival of patients in the validation set. CONCLUSIONS We developed a radiomics model for early prediction of the response to ICI treatment. This model may aid in identifying the patients most likely to benefit from immunotherapy.
Collapse
Affiliation(s)
- Yang Yu
- grid.411294.b0000 0004 1798 9345The Department of Tumor Surgery, Lanzhou University Second Hospital, Lanzhou, 730030 Gansu China ,grid.32566.340000 0000 8571 0482The Second Clinical Medical College, Lanzhou University, Lanzhou, 730000 Gansu China
| | - Yuping Bai
- grid.32566.340000 0000 8571 0482The Second Clinical Medical College, Lanzhou University, Lanzhou, 730000 Gansu China ,grid.411294.b0000 0004 1798 9345Department of MR, Lanzhou University Second Hospital, Lanzhou, 730030 Gansu China
| | - Peng Zheng
- grid.411294.b0000 0004 1798 9345The Department of Tumor Surgery, Lanzhou University Second Hospital, Lanzhou, 730030 Gansu China ,grid.32566.340000 0000 8571 0482The Second Clinical Medical College, Lanzhou University, Lanzhou, 730000 Gansu China
| | - Na Wang
- grid.411294.b0000 0004 1798 9345The Department of Tumor Surgery, Lanzhou University Second Hospital, Lanzhou, 730030 Gansu China ,grid.32566.340000 0000 8571 0482The Second Clinical Medical College, Lanzhou University, Lanzhou, 730000 Gansu China
| | - Xiaobo Deng
- grid.411294.b0000 0004 1798 9345The Department of Tumor Surgery, Lanzhou University Second Hospital, Lanzhou, 730030 Gansu China ,grid.32566.340000 0000 8571 0482The Second Clinical Medical College, Lanzhou University, Lanzhou, 730000 Gansu China
| | - Huanhuan Ma
- grid.411294.b0000 0004 1798 9345The Department of Tumor Surgery, Lanzhou University Second Hospital, Lanzhou, 730030 Gansu China ,grid.32566.340000 0000 8571 0482The Second Clinical Medical College, Lanzhou University, Lanzhou, 730000 Gansu China
| | - Rong Yu
- grid.411294.b0000 0004 1798 9345The Department of Tumor Surgery, Lanzhou University Second Hospital, Lanzhou, 730030 Gansu China ,grid.32566.340000 0000 8571 0482The Second Clinical Medical College, Lanzhou University, Lanzhou, 730000 Gansu China
| | - Chenhui Ma
- grid.411294.b0000 0004 1798 9345The Department of Tumor Surgery, Lanzhou University Second Hospital, Lanzhou, 730030 Gansu China ,grid.32566.340000 0000 8571 0482The Second Clinical Medical College, Lanzhou University, Lanzhou, 730000 Gansu China
| | - Peng Liu
- grid.461867.a0000 0004 1765 2646Department of Radiology, Gansu Provincial Cancer Hospital, Lanzhou, 730050 Gansu China
| | - Yijing Xie
- grid.411294.b0000 0004 1798 9345Department of Radiology, Lanzhou University Second Hospital, Lanzhou, 730030 Gansu China
| | - Chen Wang
- grid.411294.b0000 0004 1798 9345Department of General Surgery, Lanzhou University Second Hospital, Lanzhou, 730030 Gansu China
| | - Hao Chen
- grid.411294.b0000 0004 1798 9345The Department of Tumor Surgery, Lanzhou University Second Hospital, Lanzhou, 730030 Gansu China
| |
Collapse
|
4
|
Liu Q, Wang X, Yang Y, Wang C, Zou J, Lin J, Qiu L. Immuno-PET imaging of PD-L1 expression in patient-derived lung cancer xenografts with [ 68Ga]Ga-NOTA-Nb109. Quant Imaging Med Surg 2022; 12:3300-3313. [PMID: 35655844 PMCID: PMC9131318 DOI: 10.21037/qims-21-991] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2021] [Accepted: 01/17/2022] [Indexed: 09/17/2023]
Abstract
Background Accurate evaluation of programmed death-ligand 1 (PD-L1) expression levels in cancer patients may be useful in the identification of potential candidates for anti-programmed death-1/PD-L1 (anti-PD-1/PD-L1) immune checkpoint therapy to improve the response rate of immune checkpoint blockade therapy. This study evaluated the feasibility of the nanobody-based positron emission tomography (PET) tracer [68Ga]Ga-NOTA-Nb109 for immuno-PET imaging of PD-L1 in lung cancer patient-derived xenograft (PDX). Methods We constructed 2 PDXs of lung adenocarcinoma (ADC) and lung squamous cell carcinoma (SCC) and used them for immuno-PET imaging. A 2-hour dynamic PET scanning was performed on the samples and the in vivo biodistribution and metabolism of [68Ga]Ga-NOTA-Nb109 were investigated using region of interest (ROI) analysis. The ex vivo biodistribution of [68Ga]Ga-NOTA-Nb109 in the 2 PDXs was investigated by static PET scanning. In addition, tumor PD-L1 expression in the 2 PDXs was evaluated by autoradiography, western blot, and immunohistochemical (IHC) analysis. Results Noninvasive PET imaging showed that [68Ga]Ga-NOTA-Nb109 can accurately and sensitively assess the PD-L1 expression in non-small cell lung cancer (NSCLC) PDX models. The maximum [68Ga]Ga-NOTA-Nb109 uptake by the ADC PDX LU6424 and the SCC PDX LU6437 were 3.13%±0.35% and 2.60%±0.32% injected dose per milliliter of tissue volume (ID/mL), respectively, at 20 min post injection. In vivo and ex vivo biodistribution analysis showed that [68Ga]Ga-NOTA-Nb109 was rapidly cleared through renal excretion and an enhanced signal-to-noise ratio (SNR) was achieved. Ex vivo PD-L1 expression analysis showed good agreement with in vivo PET imaging results. Conclusions This study demonstrated that [68Ga]Ga-NOTA-Nb109 could be applied with PET imaging to noninvasively and accurately monitor PD-L1 expression in vivo for screening patients who may be responsive to immunotherapy and to guide the development of appropriate treatment strategies for such patients.
Collapse
Affiliation(s)
- Qingzhu Liu
- NHC Key Laboratory of Nuclear Medicine, Jiangsu Key Laboratory of Molecular Nuclear Medicine, Jiangsu Institute of Nuclear Medicine, Wuxi, China
| | - Xiaodan Wang
- Wuxi Second Hospital Affiliated to Nanjing Medical University, Wuxi, China
| | - Yanling Yang
- Suzhou Smart Nuclide Biopharmaceutical Co. Ltd., Suzhou Industrial Park, Suzhou, China
| | - Chao Wang
- Suzhou Smart Nuclide Biopharmaceutical Co. Ltd., Suzhou Industrial Park, Suzhou, China
| | - Jian Zou
- Center of Clinical Research, The Affiliated Wuxi People’s Hospital of Nanjing Medical University, Wuxi, China
| | - Jianguo Lin
- NHC Key Laboratory of Nuclear Medicine, Jiangsu Key Laboratory of Molecular Nuclear Medicine, Jiangsu Institute of Nuclear Medicine, Wuxi, China
- Department of Radiopharmaceuticals, School of Pharmacy, Nanjing Medical University, Nanjing, China
| | - Ling Qiu
- NHC Key Laboratory of Nuclear Medicine, Jiangsu Key Laboratory of Molecular Nuclear Medicine, Jiangsu Institute of Nuclear Medicine, Wuxi, China
- Department of Radiopharmaceuticals, School of Pharmacy, Nanjing Medical University, Nanjing, China
| |
Collapse
|
5
|
Xiong A, Wang J, Zhou C. Immunotherapy in the First-Line Treatment of NSCLC: Current Status and Future Directions in China. Front Oncol 2021; 11:757993. [PMID: 34900707 PMCID: PMC8654727 DOI: 10.3389/fonc.2021.757993] [Citation(s) in RCA: 22] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2021] [Accepted: 11/01/2021] [Indexed: 12/15/2022] Open
Abstract
Lung cancer causes significant morbidity and mortality in China and worldwide. In China, lung cancer accounts for nearly one-fourth of all cancer deaths. Non-small cell lung cancer (NSCLC) is the predominant type of lung cancer, accounting for approximately 80%–85% of all lung cancer cases. Immunotherapy with immune checkpoint inhibitors (ICIs) is revolutionizing the treatment of NSCLC. Immune checkpoint molecules, including PD-1/PD-L1 and CTLA-4, can suppress immune responses by delivering negative signals to T cells. By interfering with these immunosuppressive axes, ICIs unleash antitumor immune responses, ultimately eliminating cancer cells. ICIs have demonstrated promising antitumor efficacy in NSCLC, and mounting evidence supports the use of ICIs in treatment-naïve patients with advanced NSCLC. A comprehensive overview of current and emerging ICIs for the first-line treatment of NSCLC in China will facilitate a better understanding of NSCLC immunotherapy using ICIs and optimize the clinical use of ICIs in previously untreated Chinese patients with NSCLC. Herein, we review the efficacy and safety of currently approved and investigational ICIs as the first-line treatment of NSCLC in China. We also discuss the challenges limiting more widespread use of ICIs and future directions in the first-line treatment of NSCLC using ICIs.
Collapse
Affiliation(s)
- Anwen Xiong
- Department of Medical Oncology, Shanghai Pulmonary Hospital, Thoracic Cancer Institute, Tongji University School of Medicine, Shanghai, China
| | - Jiali Wang
- Medical Research Lab (MRL) Global Medical Affairs, MSD China, Shanghai, China
| | - Caicun Zhou
- Department of Medical Oncology, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai, China
| |
Collapse
|
6
|
Jiang L, Lin Z, Li N, Jiang J, Lu C, Du S, Zhang J, Wang Y, Chen J, Gong P. [Correlation Study on Expression of PD-1 and PD-L1 in Non-small Cell Lung Cancer and Epidermal Growth Factor Receptor Mutations]. ZHONGGUO FEI AI ZA ZHI = CHINESE JOURNAL OF LUNG CANCER 2021; 24:623-631. [PMID: 34455737 PMCID: PMC8503982 DOI: 10.3779/j.issn.1009-3419.2021.102.31] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 11/05/2022]
Abstract
BACKGROUND The treatment mode of lung cancer is epidermal growth factor receptor-tyrosine kinase inhibitors (EGFR-TKIs) as a first-line treatment for patients with EGFR mutant in non-small cell lung cancer (NSCLC). At the same time programmed death receptor 1 (PD-1) and its programmed death receptor ligand 1 (PD-L1) inhibitors therapy as the representative immune checkpoint inhibitors (ICIs) has a significant effect in the treatment of lung cancer. The aim of this study was to investigate the correlation between the expression of PD-1 and PD-L1 in NSCLC and clinicopathologic feature, EGFR gene mutation. METHODS The protein expression of PD-1 and PD-L1 was detected by immunohistochemistry from 127 patients with NSCLC and EGFR gene mutation was detected by quantitative polymerase chain reaction (qPCR) to analyze its relation with clinicopathologic feature. Also, the correlation between protein expression of PD-1 and PD-L1 and EGFR mutation. RESULTS The PD-1 positive expression in NSCLC tumor cells and tumor infiltrating immune cells is 53.5% (68/127), PD-L1 is 57.5% (73/127). The PD-1 and PD-L1 expression significantly higher in well-differentiated and moderately-differentiated carcinoma than poorly differentiated carcinoma, I+II than III+IV in clinical staging (P<0.05). The EGFR mutation rate was 46.5% (59/127), correlate with female, without smoking history, adenocarcinoma and well-differentiated and moderately-differentiated patients respectively higher than male, smoking history, squamous carcinoma and poorly differentiated patients (P<0.05). The protein expression of PD-L1 and PD-1 had the consistency in NSCLC patients (kappa=0.107,5, P=0.487). There was a negative correlation between the EGFR mutation and PD-1 and PD-L1 expression (Φ=-0.209, Φ=-0.221, P<0.05). Follow-up of NSCLC patients, the median total survival in under the age of 65, adenocarcinoma, well-differentiated and moderately-differentiated, with PD-L1 expression patients respectively higher than over the age of 65, squamous carcinoma, poorly differentiated, without PD-L1 expression patients (P<0.05). The median survival of hypo expression patients of PD-L1 significantly higher than hyper expression patient (P=0.04). CONCLUSIONS According to the Chinese Expert Consensus on Standards of PD-L1 immunohistochemistry testing for NSCLC, we tested the PD-L1 expression in NSCLC and then the dominant population of anti-PD-1/PD-L1 treatment was screened out. Patients with EGFR mutation were also detected and EGFR mutation was negatively correlated with the expression of PD-1 and PD-L1 as well. On the basis of PD-L1 expression and EGFR mutation status, it may benefit NSCLC patients from individualized treatment. Meanwhile, patients who were under the age of 65, adenocarcinoma, well-differentiated and moderately-differentiated, hypo expression of PD-L1 have a relatively good prognosis, to provide reference for the prognosis evaluation of NSCLC.
Collapse
Affiliation(s)
- Ling Jiang
- First Affiliated Hospital, School of Medicine, Shihezi University, Shihezi 832002, China
| | - Zhiyi Lin
- First Affiliated Hospital, School of Medicine, Shihezi University, Shihezi 832002, China
| | - Na Li
- Suining Central Hospital, Suining 629000, China
| | - Jinfang Jiang
- Clinical Medical School Shihezi University, Shihezi 832002, China
| | - Cengceng Lu
- First Affiliated Hospital, School of Medicine, Shihezi University, Shihezi 832002, China
| | - Shenghang Du
- Clinical Medical School Shihezi University, Shihezi 832002, China
| | - Jun Zhang
- Clinical Medical School Shihezi University, Shihezi 832002, China
| | - Yuanyuan Wang
- Clinical Medical School Shihezi University, Shihezi 832002, China
| | - Jun Chen
- Department of Lung Cancer Surgery, Tianjin Medical University General Hospital, Tianjin 300052, China
| | - Ping Gong
- First Affiliated Hospital, School of Medicine, Shihezi University, Shihezi 832002, China
| |
Collapse
|
7
|
Jiang Z, Dong Y, Yang L, Lv Y, Dong S, Yuan S, Li D, Liu L. CT-Based Hand-crafted Radiomic Signatures Can Predict PD-L1 Expression Levels in Non-small Cell Lung Cancer: a Two-Center Study. J Digit Imaging 2021; 34:1073-1085. [PMID: 34327623 DOI: 10.1007/s10278-021-00484-9] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/28/2020] [Revised: 05/27/2021] [Accepted: 06/21/2021] [Indexed: 12/01/2022] Open
Abstract
Here, we used pre-treatment CT images to develop and evaluate a radiomic signature that can predict the expression of programmed death ligand 1 (PD-L1) in non-small cell lung cancer (NSCLC). We then verified its predictive performance by cross-referencing its results with clinical characteristics. This two-center retrospective analysis included 125 patients with histologically confirmed NSCLC. A total of 1287 hand-crafted radiomic features were observed from manually determined tumor regions. Valuable features were then selected with a ridge regression-based recursive feature elimination approach. Machine learning-based prediction models were then built from this and compared each other. The final radiomic signature was built using logistic regression in the primary cohort, and then tested in a validation cohort. Finally, we compared the efficacy of the radiomic signature to the clinical model and the radiomic-clinical nomogram. Among the 125 patients, 89 were classified as having PD-L1 positive expression. However, there was no significant difference in PD-L1 expression levels determined by clinical characteristics (P = 0.109-0.955). Upon selecting 9 radiomic features, we found that the logistic regression-based prediction model performed the best (AUC = 0.96, P < 0.001). In the external cohort, our radiomic signature showed an AUC of 0.85, which outperformed both the clinical model (AUC = 0.38, P < 0.001) and the radiomics-nomogram model (AUC = 0.61, P < 0.001). Our CT-based hand-crafted radiomic signature model can effectively predict PD-L1 expression levels, providing a noninvasive means of better understanding PD-L1 expression in patients with NSCLC.
Collapse
Affiliation(s)
- Zekun Jiang
- Shandong Key Laboratory of Medical Physics and Image Processing, Shandong Institute of Industrial Technology for Health Sciences and Precision Medicine, School of Physics and Electronics, Shandong Normal University, Jinan, 250358, Shandong, China
| | - Yinjun Dong
- Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, 250117, Shandong, China.,Liaocheng People's Hospital, Liaocheng, 252002, Shandong, China.,Shandong University, Jinan, 250117, Shandong, China
| | - Linke Yang
- Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, 250117, Shandong, China
| | - Yunhong Lv
- Department of Mathematics and Information Technology, Xingtai University, Xingtai, 054001, Hebei, China.,Department of Mathematics and Statistics, University of Windsor, Windsor, ON, N9B 3P4, Canada
| | - Shuai Dong
- Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, 250117, Shandong, China
| | - Shuanghu Yuan
- Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, 250117, Shandong, China.
| | - Dengwang Li
- Shandong Key Laboratory of Medical Physics and Image Processing, Shandong Institute of Industrial Technology for Health Sciences and Precision Medicine, School of Physics and Electronics, Shandong Normal University, Jinan, 250358, Shandong, China.
| | - Liheng Liu
- Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, 200032, China.
| |
Collapse
|