scholarly journals Machine Learning Incorporating Host Factors for Predicting Survival in Head and Neck Squamous Cell Carcinoma Patients

Cancers ◽  
2021 ◽  
Vol 13 (18) ◽  
pp. 4559
Author(s):  
Han Yu ◽  
Sung Jun Ma ◽  
Mark Farrugia ◽  
Austin J. Iovoli ◽  
Kimberly E. Wooten ◽  
...  
Keyword(s):  
Machine Learning ◽  
Overall Survival ◽  
Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Head And Neck ◽  
Risk Group ◽  
Host Factors ◽  
Learning Models ◽  
Random Survival Forest ◽  
Machine Learning Models

Prognostication for cancer patients is integral for patient counseling and treatment planning, yet providing accurate prediction can be challenging using existing patient-specific clinical indicators and host factors. In this work, we evaluated common machine learning models in predicting head and neck squamous cell carcinoma (HNSCC) patients’ overall survival based on demographic, clinical features and host factors. We found random survival forest had best performance among the models evaluated, which achieved a C-index of 0.729 and AUROC of 0.792 in predicting two-year overall survival. In addition, we verified that host factors are independently predictive of HNSCC overall survival, which improved the C-index by a margin of 0.026 and the AUROC by 0.034. Due to the strong correlation among host factors, we showed that proper dimension reduction is an important step before their incorporation into the machine learning models, which provides a host factor score reflecting the patients’ nutrition and inflammation status. The score by itself showed excellent discriminating capacity with the high-risk group having a hazard ratio of 3.76 (1.93–7.32, p < 0.0001) over the low-risk group. The hazard ratios were further improved to 7.41 (3.66–14.98, p < 0.0001) by the random survival forest model after including demographic and clinical features.

scholarly journals Comparisons of forecasting for Survival Outcome for Head and Neck Squamous Cell Carcinoma by using Six Machine Learning Models Based on Multi-Omics

2021 ◽  
Author(s):  
Liying Mo ◽  
Yuangang Su ◽  
Jianhui Yuan ◽  
Zhiwei Xiao ◽  
Ziyan Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Head And Neck ◽  
Squamous Cell ◽  
Survival Outcome ◽  
Learning Models ◽  
Machine Learning Methods ◽  
Machine Learning Models ◽  
Better Than

Abstract Background: Machine learning methods showed excellent predictive ability in a wide range of fields. For the survival of head and neck squamous cell carcinoma (HNSC), its multi-omics influence is crucial. This study attempts to establish a variety of machine learning multi-omics models to predict the survival of HNSC and find the most suitable machine learning prediction method. Results: For omics of HNSC, the results of the six models all showed that the performance of multi-omics was better than each single-omic alone. Results were presented which showed that the BN model played a good prediction performance (area under the curve [AUC] 0.8250) in HNSC multi-omics data. The other machine learning models RF (AUC = 0.8002), NN (AUC = 0.7200), and GLM (AUC = 0.7145) also showed high predictive performance except for DT(AUC = 0.5149) and SVM(AUC = 0.6981). And the results of a vitro qPCR were consistent with the Random forest algorithm. Conclusion: Machine learning methods could better forecast the survival outcome of HNSC. Meanwhile, this study found that the Bayesian network was the most superior. Moreover, the forecast result of multi-omics was better than single-omic alone in HNSC.

scholarly journals A key genomic signature associated with lymphovascular invasion in head and neck squamous cell carcinoma

2020 ◽  
Author(s):  
Jian Zhang ◽  
Huaming Lin ◽  
Huali Jiang ◽  
Hualong Jiang ◽  
Tao Xie ◽  
...  
Keyword(s):  
Overall Survival ◽  
Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Head And Neck ◽  
Lymphovascular Invasion ◽  
Kegg Pathway ◽  
Risk Group ◽  
Functional Enrichment ◽  
Hub Genes ◽  
Risk Formula

Abstract Background: Lymphovascular invasion (LOI), a key pathological feature of head and neck squamous cell carcinoma (HNSCC), is predictive of poor survival; however, the associated clinical characteristics and underlying molecular mechanisms remain largely unknown. Methods: We performed weighted gene co-expression network analysis to construct gene co-expression networks and investigate the relationship between key modules and the LOI clinical phenotype. Functional enrichment and KEGG pathway analyses were performed with differentially expressed genes. A protein–protein interaction network was constructed using Cytoscape, and module analysis was performed using MCODE. Prognostic value, expression analysis, and survival analysis were conducted using hub genes; GEPIA and the Human Protein Atlas database were used to determine the mRNA and protein expression levels of hub genes, respectively. Multivariable Cox regression analysis was used to establish a prognostic risk formula and the areas under the receiver operating characteristic curve (AUCs) were used to evaluate prediction efficiency. Finally, potential small molecular agents that could target LOI were identified with DrugBank. Results: Ten co-expression modules in two key modules (turquoise and pink) associated with LOI were identified. Functional enrichment and KEGG pathway analysis revealed that turquoise and pink modules played significant roles in HNSCC progression. Seven hub genes (CNFN, KIF18B, KIF23, PRC1, CCNA2, DEPDC1, and TTK) in the two modules were identified and validated by survival and expression analyses, and the following prognostic risk formula was established: [risk score = EXP DEPDC1 * 0.32636 + EXP CNFN * (−0.07544)]. The low-risk group showed better overall survival than the high-risk group ( P < 0.0001), and the AUCs for 1-, 3-, and 5-year overall survival were 0.582, 0.634, and 0.636, respectively. Eight small molecular agents, namely XL844, AT7519, AT9283, alvocidib, nelarabine, benzamidine, L-glutamine, and zinc, were identified as novel candidates for controlling LOI in HNSCC ( P < 0.05). Conclusions: The two-mRNA signature (CNFN and DEPDC1) could serve as an independent biomarker to predict LOI risk and provide new insights into the mechanisms underlying LOI in HNSCC. In addition, the small molecular agents appear promising for LOI treatment.

scholarly journals The Prognostic Value and Immune Landscapes of a m6A/m5C/m1A-Related LncRNAs Signature in Head and Neck Squamous Cell Carcinoma

2021 ◽  
Vol 9 ◽  
Author(s):  
Enhao Wang ◽  
Yang Li ◽  
Ruijie Ming ◽  
Jiahui Wei ◽  
Peiyu Du ◽  
...  
Keyword(s):  
Overall Survival ◽  
Squamous Cell Carcinoma ◽  
High Risk ◽  
Cell Carcinoma ◽  
Head And Neck ◽  
Squamous Cell ◽  
Risk Group ◽  
Prognostic Signature ◽  
Mutational Burden ◽  
Tumor Mutational Burden

Background: N6-methyladenosine (m6A), 5-methylcytosine (m5C) and N1-methyladenosine (m1A) are the main RNA methylation modifications involved in the progression of cancer. However, it is still unclear whether m6A/m5C/m1A-related long non-coding RNAs (lncRNAs) affect the prognosis of head and neck squamous cell carcinoma (HNSCC).Methods: We summarized 52 m6A/m5C/m1A-related genes, downloaded 44 normal samples and 501 HNSCC tumor samples with RNA-seq data and clinical information from The Cancer Genome Atlas (TCGA) database, and then searched for m6A/m5C/m1A-related genes co-expressed lncRNAs. We adopt the least absolute shrinkage and selection operator (LASSO) Cox regression to obtain m6A/m5C/m1A-related lncRNAs to construct a prognostic signature of HNSCC.Results: This prognostic signature is based on six m6A/m5C/m1A-related lncRNAs (AL035587.1, AC009121.3, AF131215.5, FMR1-IT1, AC106820.5, PTOV1-AS2). It was found that the high-risk subgroup has worse overall survival (OS) than the low-risk subgroup. Moreover, the results showed that most immune checkpoint genes were significantly different between the two risk groups (p &lt; 0.05). Immunity microenvironment analysis showed that the contents of NK cell resting, macrophages M2, and neutrophils in samples of low-risk group were significantly lower than those of high-risk group (p &lt; 0.05), while the contents of B cells navie, plasma cells, and T cells regulatory (Tregs) were on the contrary (p &lt; 0.05). In addition, patients with high tumor mutational burden (TMB) had the worse overall survival than those with low tumor mutational burden.Conclusion: Our study elucidated how m6A/m5C/m1A-related lncRNAs are related to the prognosis, immune microenvironment, and TMB of HNSCC. In the future, these m6A/m5C/m1A-related lncRNAs may become a new choice for immunotherapy of HNSCC.

scholarly journals Phase II Evaluation of Sorafenib in Advanced and Metastatic Squamous Cell Carcinoma of the Head and Neck: Southwest Oncology Group Study S0420

2010 ◽  
Vol 28 (20) ◽  
pp. 3330-3335 ◽  
Author(s):  
Stephen K. Williamson ◽  
James Moon ◽  
Chao H. Huang ◽  
Perry P. Guaglianone ◽  
Michael LeBlanc ◽  
...  
Keyword(s):  
Overall Survival ◽  
Squamous Cell Carcinoma ◽  
Adverse Events ◽  
Cell Carcinoma ◽  
Head And Neck ◽  
Phase Ii ◽  
Single Agent ◽  
Response Probability ◽  
Oncology Group ◽  
Southwest Oncology Group

Purpose We conducted a phase II trial to evaluate the efficacy and safety of single-agent sorafenib in chemotherapy-naïve patients with metastatic or recurrent squamous cell carcinoma of the head and neck (SCCHN). The primary end point was response probability (ie, confirmed complete and partial response [PR]). Patients and Methods Chemotherapy-naïve patients with metastatic, persistent, or recurrent SCCHN who received one induction or fewer or received an adjuvant chemotherapy regimen, who had adequate organ function, and who had a performance status ≤ 1 were eligible. Sorafenib was administered orally at 400 mg twice daily on a continuous basis in 28-day cycles. Responses were evaluated according to RECIST (Response Evaluation Criteria in Solid Tumors). Results Sorafenib was generally well tolerated. Of the 41 eligible patients assessed for adverse events, one experienced a grade 4 adverse event as a result of an asymptomatic pulmonary embolus. The most common grades 2 to 3 adverse events were fatigue, anorexia, stomatitis/oral pain, abdominal pain, hand-foot syndrome, weight loss, and hypertension. There was one confirmed PR and two unconfirmed PRs. The estimated confirmed response probability was 2% (95% CI, 0% to 13%). The estimated median progression-free survival was 4 months (95% CI, 2 to 4 months), and the estimated median overall survival was 9 months (95% CI, 7 to 14 months). Conclusion Sorafenib was well tolerated. Although response was poor, progression-free and overall survival times compare favorably with previous Southwest Oncology Group, phase II, single-agent trials.

scholarly journals A TP53 mutation model for the prediction of prognosis and therapeutic responses in head and neck squamous cell carcinoma

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Congyu Shi ◽  
Shan Liu ◽  
Xudong Tian ◽  
Xiaoyi Wang ◽  
Pan Gao
Keyword(s):  
Squamous Cell Carcinoma ◽  
High Risk ◽  
Cell Carcinoma ◽  
Head And Neck ◽  
Risk Score ◽  
Squamous Cell ◽  
Risk Group ◽  
High Risk Group ◽  
Mutation Model ◽  
Therapeutic Responses

Abstract Background Tumor protein p53 (TP53) is the most frequently mutated gene in head and neck squamous cell carcinoma (HNSC), and TP53 mutations are associated with inhibited immune signatures and poor prognosis. We established a TP53 mutation associated risk score model to evaluate the prognosis and therapeutic responses of patients with HNSC. Methods Differentially expressed genes between patients with and without TP53 mutations were determined by using data from the HNSC cohort in The Cancer Genome Atlas database. Patients with HNSC were divided into high- and low-risk groups based on a prognostic risk score that was generated from ten TP53 mutation associated genes via the multivariate Cox regression model. Results TP53 was the most common mutant gene in HNSC, and TP53 mutations were associated with immunogenic signatures, including the infiltration of immune cells and expression of immune-associated genes. Patients in the high-risk group had significantly poorer overall survival than those in the low-risk group. The high-risk group showed less response to anti-programmed cell death protein 1 (PD-1) therapy but high sensitivity to some chemotherapies. Conclusion The risk score based on our TP53 mutation model was associated with poorer survival and could act as a specific predictor for assessing prognosis and therapeutic response in patients with HNSC.

scholarly journals Expression of the Extracellular Sulfatase SULF2 Affects Survival of Head and Neck Squamous Cell Carcinoma Patients

2021 ◽  
Vol 10 ◽  
Author(s):  
Yang Yang ◽  
Jaeil Ahn ◽  
Rekha Raghunathan ◽  
Bhaskar V. Kallakury ◽  
Bruce Davidson ◽  
...  
Keyword(s):  
Overall Survival ◽  
Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Head And Neck ◽  
Squamous Cell ◽  
Hpv Infection ◽  
Neck Squamous Cell Carcinoma ◽  
Therapeutic Interventions ◽  
Tumor Tissues ◽  
Significant Difference

Sulfation of heparan sulfate proteoglycans (HSPG) regulates signaling of growth factor receptors via specific interactions with the sulfate groups. 6-O-Sulfation of HSPG is an impactful modification regulated by the activities of dedicated extracellular endosulfatases. Specifically, extracellular sulfatase Sulf-2 (SULF2) removes 6-O-sulfate from HS chains, modulates affinity of carrier HSPG to their ligands, and thereby influences activity of the downstream signaling pathway. In this study, we explored the effect of SULF2 expression on HSPG sulfation and its relationship to clinical outcomes of patients with head and neck squamous cell carcinoma (HNSCC). We found a significant overexpression of SULF2 in HNSCC tumor tissues which differs by tumor location and etiology. Expression of SULF2 mRNA in tumors associated with human papillomavirus (HPV) infection was two-fold lower than in tumors associated with a history of tobacco and alcohol consumption. High SULF2 mRNA expression is significantly correlated with poor progression-free interval and overall survival of patients (n = 499). Among all HS-related enzymes, SULF2 expression had the highest hazard ratio in overall survival after adjusting for clinical characteristics. SULF2 protein expression (n = 124), determined by immunohistochemical analysis, showed a similar trend. The content of 6-O-sulfated HSPG, measured by staining with the HS3A8 antibody, was higher in adjacent mucosa compared to tumor tissue but revealed no difference based on SULF2 staining. LC-MS/MS analysis showed low abundance of N-sulfation and O-sulfation in HS but no significant difference between SULF2-positive and SULF2-negative tumors. Levels of enzymes modifying 6-O-sulfation, measured by RT-qPCR in HNSCC tumor tissues, suggest that HSPG sulfation is carried out by the co-regulated activities of multiple genes. Imbalance of the HS modifying enzymes in HNSCC tumors modifies the overall sulfation pattern, but the alteration of 6-O-sulfate is likely non-uniform and occurs in specific domains of the HS chains. These findings demonstrate that SULF2 expression correlates with survival of HNSCC patients and could potentially serve as a prognostic factor or target of therapeutic interventions.

Sign in / Sign up

Export Citation Format

Share Document