[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123034-en":3,"doc-seo-123034-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123034,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Machine learning identifies prognostic subtypes of the tumor microenvironment of NSCLC","Tumor microenvironment heterogeneity across patients limits efficient drug development in non-small-cell lung cancer (NSCLC). This study applies recent machine-learning advances for survival analysis to retrospective NSCLC cohorts treated with definitive surgical resection, integrating immune pathology after surgery. Six survival models, including Cox regression and five survival ML methods, are calibrated using PD-L1 expression, CD3 expression, and ten baseline patient characteristics. Using synthetic data augmentation, biomarker subregions are delineated for overall survival concordance, achieving highest predictive accuracy with random survival forest.","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nMachine learning identifies prognostic subtypes of the tumor microenvironment of NSCLC  \nDuo Yu1, Michael J. Kane2, Eugene J. Koay 3, Ignacio I. Wistuba4 & Brian P. Hobbs 5*  \nThe tumor microenvironment (TME) plays a fundamental role in tumorigenesis, tumor progression, and anti-cancer immunity potential of emerging cancer therapeutics. Understanding inter-patient TME heterogeneity, however, remains a challenge to efficient drug development. This article applies recent advances in machine learning (ML) for survival analysis to a retrospective study of NSCLC patients who received definitive surgical resection and immune pathology following surgery. ML methods are compared for their effectiveness in identifying prognostic subtypes. Six survival models, including Cox regression and five survival machine learning methods, were calibrated and applied to predict survival for NSCLC patients based on PD-L1 expression, CD3 expression, and ten baseline patient characteristics. Prognostic subregions ofthe biomarker space are delineated for each method using synthetic patient data augmentation and compared between models for overall survival concordance. A total of 423 NSCLC patients (46% female; median age [inter quantile range]: 67 [60–73]) treated with definite surgical resection were included in the study. And 219 (52%) patients experienced events during the observation period consisting of a maximum follow-up of 10 years and median follow up  \n78 months. The random survival forest (RSF) achieved the highest predictive accuracy, with a C-indexof 0.84. The resultant biomarker subtypes demonstrate that patients with high PD-L1 expression combined with low CD3 counts experience higher risk of death within five-years of surgical resection.  \nKeywords Precision oncology, Thoracic tumor, Biomarkers, Cancer immunity, Survival prediction  \nNon–Small-Cell Lung Cancer (NSCLC) is a common subtype of lung cancer that accounts for 76% of all lung cancer cases in the United States1,2, and 85% of all lung malignancies worldwide3. With the advent of targeted therapy and immunotherapies, especially FDA-approved therapies for stage IV EGFR-positive NSCLC, a rapid decline in mortality from NSCLC has been observed in recent decades4,5. Nevertheless, the survival rate of NSCLC remains low, with a 5-year survival rate of less than 25%6. Furthermore, more than 75% of NSCLC cases are diagnosed in advanced stages (IIIA-IV), which results in an even lower survival rate7,8. Precise characterization of prognosis is pivotal to optimal patient management.  \nIn addition to the commonly known factors that are associated with prognosis, such as stage of the disease, age, and sex9, recent advances in immunology have revealed prognostic biomarkers that describe the tumor microenvironment (TME) 10. Programmed Death-Ligand 1 (PD-L1) has been recognized as a type of immunosuppressive checkpoint protein on tumor cell11, 12. The binding of PD-L1 to programmed cell death 1 (PD- 1) reduces the proliferation of CD8+ and CD4+ cells and induces apoptosis13. The antibody-mediated blockade of PD-L1 can result in durable tumor regression and can prolong stabilization of disease in patients with advanced cancers, including non–small-cell lung cancer (NSCLC), melanoma, and renal-cell cancer12, 14. However, the prognostic role of PD-L1 expression in NSCLC remains contentious as conflicting results have been obtained from various studies. The variability in study results regarding PD-L1’s prognostic role could be attributed to multiple factors, such as differences in subtypes (i.e., squamous cell carcinoma [SCC] and adenocarcinoma [AC])15, heterogeneity in clinical studies on NSCLC (where clinicopathological factors may vary), the use of diverse scoring methods, and different cutoff levels (details of which are discussed in the next paragraph)16. For instance, the association between PD-L1 expression and ov","cbCaimXA8RQ8kRFt","https://ap.wps.com/l/cbCaimXA8RQ8kRFt","pdf",375289,1,9,"English","en",105,"# Introduction\n## Tumor microenvironment and survival challenges\n## Prognostic biomarkers and PD-L1 controversy\n## Study objective and approach\n# Methods\n## Cohort and clinical variables\n## Survival models and calibration\n## Biomarker subregion identification\n# Results\n## Predictive performance and concordance\n## PD-L1/CD3-defined risk patterns","[{\"question\":\"What data and biomarkers are used to predict NSCLC survival in this study?\",\"answer\":\"The models use PD-L1 expression, CD3 expression, and ten baseline patient characteristics from NSCLC patients treated with definitive surgical resection.\"},{\"question\":\"How many survival models are compared, and which one performs best?\",\"answer\":\"Six models are compared, including Cox regression and five survival machine learning methods. Random survival forest (RSF) achieves the highest predictive accuracy with a C-index of 0.84.\"},{\"question\":\"What biomarker subtype is associated with higher five-year mortality risk?\",\"answer\":\"Patients with high PD-L1 expression combined with low CD3 counts show higher risk of death within five years after surgical resection.\"}]","Machine learning identifies prognostic subtypes of the tumor microenvironment of NSCLC | PDF",1785814294,23,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-identifies-prognostic-subtypes-of-the-tumor-microenvironment-of-nsclc","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-identifies-prognostic-subtypes-of-the-tumor-microenvironment-of-nsclc/123034/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data and biomarkers are used to predict NSCLC survival in this study?","Question",{"text":75,"@type":76},"The models use PD-L1 expression, CD3 expression, and ten baseline patient characteristics from NSCLC patients treated with definitive surgical resection.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How many survival models are compared, and which one performs best?",{"text":80,"@type":76},"Six models are compared, including Cox regression and five survival machine learning methods. Random survival forest (RSF) achieves the highest predictive accuracy with a C-index of 0.84.",{"name":82,"@type":73,"acceptedAnswer":83},"What biomarker subtype is associated with higher five-year mortality risk?",{"text":84,"@type":76},"Patients with high PD-L1 expression combined with low CD3 counts show higher risk of death within five years after surgical resection.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]