Machine-learning derived identification of prognostic signature to forecast head and neck squamous cell carcinoma prognosis and drug response

IntroductionHead and neck squamous cell carcinoma (HNSCC), a highly heterogeneous malignancy is often associated with unfavorable prognosis. Due to its unique anatomical position and the absence of effective early inspection methods, surgical intervention alone is frequently inadequate for achieving...

Full description

Saved in:
Bibliographic Details
Main Authors: Sha-Zhou Li, Hai-Ying Sun, Yuan Tian, Liu-Qing Zhou, Tao Zhou
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-12-01
Series:Frontiers in Immunology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fimmu.2024.1469895/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850054172558229504
author Sha-Zhou Li
Hai-Ying Sun
Yuan Tian
Liu-Qing Zhou
Tao Zhou
author_facet Sha-Zhou Li
Hai-Ying Sun
Yuan Tian
Liu-Qing Zhou
Tao Zhou
author_sort Sha-Zhou Li
collection DOAJ
description IntroductionHead and neck squamous cell carcinoma (HNSCC), a highly heterogeneous malignancy is often associated with unfavorable prognosis. Due to its unique anatomical position and the absence of effective early inspection methods, surgical intervention alone is frequently inadequate for achieving complete remission. Therefore, the identification of reliable biomarker is crucial to enhance the accuracy of screening and treatment strategies for HNSCC.MethodTo develop and identify a machine learning-derived prognostic model (MLDPM) for HNSCC, ten machine learning algorithms, namely CoxBoost, elastic network (Enet), generalized boosted regression modeling (GBM), Lasso, Ridge, partial least squares regression for Cox (plsRcox), random survival forest (RSF), stepwise Cox, supervised principal components (SuperPC), and survival support vector machine (survival-SVM), along with 81 algorithm combinations were utilized. Time-dependent receiver operating characteristics (ROC) curves and Kaplan-Meier analysis can effectively assess the model’s predictive performance. Validation was performed through a nomogram, calibration curves, univariate and multivariate Cox analysis. Further analyses included immunological profiling and gene set enrichment analyses (GSEA). Additionally, the prediction of 50% inhibitory concentration (IC50) of potential drugs between groups was determined.ResultsFrom analyses in the HNSCC tissues and normal tissues, we found 536 differentially expressed genes (DEGs). Subsequent univariate-cox regression analysis narrowed this list to 18 genes. A robust risk model, outperforming other clinical signatures, was then constructed using machine learning techniques. The MLDPM indicated that high-risk scores showed a greater propensity for immune escape and reduced survival rates. Dasatinib and 7 medicine showed the superior sensitivity to the high-risk NHSCC, which had potential to the clinical.ConclusionsThe construction of MLDPM effectively eliminated artificial bias by utilizing 101 algorithm combinations. This model demonstrated high accuracy in predicting HNSCC outcomes and has the potential to identify novel therapeutic targets for HNSCC patients, thus offering significant advancements in personalized treatment strategies.
format Article
id doaj-art-d1fd34047f4b4c09b7af1d021a68d018
institution DOAJ
issn 1664-3224
language English
publishDate 2024-12-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Immunology
spelling doaj-art-d1fd34047f4b4c09b7af1d021a68d0182025-08-20T02:52:20ZengFrontiers Media S.A.Frontiers in Immunology1664-32242024-12-011510.3389/fimmu.2024.14698951469895Machine-learning derived identification of prognostic signature to forecast head and neck squamous cell carcinoma prognosis and drug responseSha-Zhou Li0Hai-Ying Sun1Yuan Tian2Liu-Qing Zhou3Tao Zhou4Department of Otorhinolaryngology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, ChinaDepartment of Otorhinolaryngology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, ChinaDepartment of Geriatrics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, ChinaDepartment of Otorhinolaryngology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, ChinaDepartment of Otorhinolaryngology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, ChinaIntroductionHead and neck squamous cell carcinoma (HNSCC), a highly heterogeneous malignancy is often associated with unfavorable prognosis. Due to its unique anatomical position and the absence of effective early inspection methods, surgical intervention alone is frequently inadequate for achieving complete remission. Therefore, the identification of reliable biomarker is crucial to enhance the accuracy of screening and treatment strategies for HNSCC.MethodTo develop and identify a machine learning-derived prognostic model (MLDPM) for HNSCC, ten machine learning algorithms, namely CoxBoost, elastic network (Enet), generalized boosted regression modeling (GBM), Lasso, Ridge, partial least squares regression for Cox (plsRcox), random survival forest (RSF), stepwise Cox, supervised principal components (SuperPC), and survival support vector machine (survival-SVM), along with 81 algorithm combinations were utilized. Time-dependent receiver operating characteristics (ROC) curves and Kaplan-Meier analysis can effectively assess the model’s predictive performance. Validation was performed through a nomogram, calibration curves, univariate and multivariate Cox analysis. Further analyses included immunological profiling and gene set enrichment analyses (GSEA). Additionally, the prediction of 50% inhibitory concentration (IC50) of potential drugs between groups was determined.ResultsFrom analyses in the HNSCC tissues and normal tissues, we found 536 differentially expressed genes (DEGs). Subsequent univariate-cox regression analysis narrowed this list to 18 genes. A robust risk model, outperforming other clinical signatures, was then constructed using machine learning techniques. The MLDPM indicated that high-risk scores showed a greater propensity for immune escape and reduced survival rates. Dasatinib and 7 medicine showed the superior sensitivity to the high-risk NHSCC, which had potential to the clinical.ConclusionsThe construction of MLDPM effectively eliminated artificial bias by utilizing 101 algorithm combinations. This model demonstrated high accuracy in predicting HNSCC outcomes and has the potential to identify novel therapeutic targets for HNSCC patients, thus offering significant advancements in personalized treatment strategies.https://www.frontiersin.org/articles/10.3389/fimmu.2024.1469895/fullmachine learningHNSCCDEGstumor microenvironmentimmunotherapy
spellingShingle Sha-Zhou Li
Hai-Ying Sun
Yuan Tian
Liu-Qing Zhou
Tao Zhou
Machine-learning derived identification of prognostic signature to forecast head and neck squamous cell carcinoma prognosis and drug response
Frontiers in Immunology
machine learning
HNSCC
DEGs
tumor microenvironment
immunotherapy
title Machine-learning derived identification of prognostic signature to forecast head and neck squamous cell carcinoma prognosis and drug response
title_full Machine-learning derived identification of prognostic signature to forecast head and neck squamous cell carcinoma prognosis and drug response
title_fullStr Machine-learning derived identification of prognostic signature to forecast head and neck squamous cell carcinoma prognosis and drug response
title_full_unstemmed Machine-learning derived identification of prognostic signature to forecast head and neck squamous cell carcinoma prognosis and drug response
title_short Machine-learning derived identification of prognostic signature to forecast head and neck squamous cell carcinoma prognosis and drug response
title_sort machine learning derived identification of prognostic signature to forecast head and neck squamous cell carcinoma prognosis and drug response
topic machine learning
HNSCC
DEGs
tumor microenvironment
immunotherapy
url https://www.frontiersin.org/articles/10.3389/fimmu.2024.1469895/full
work_keys_str_mv AT shazhouli machinelearningderivedidentificationofprognosticsignaturetoforecastheadandnecksquamouscellcarcinomaprognosisanddrugresponse
AT haiyingsun machinelearningderivedidentificationofprognosticsignaturetoforecastheadandnecksquamouscellcarcinomaprognosisanddrugresponse
AT yuantian machinelearningderivedidentificationofprognosticsignaturetoforecastheadandnecksquamouscellcarcinomaprognosisanddrugresponse
AT liuqingzhou machinelearningderivedidentificationofprognosticsignaturetoforecastheadandnecksquamouscellcarcinomaprognosisanddrugresponse
AT taozhou machinelearningderivedidentificationofprognosticsignaturetoforecastheadandnecksquamouscellcarcinomaprognosisanddrugresponse