Devising novel imaging biomarkers for Human Papillomavirus (HPV) status in oropharyngeal squamous cell carcinoma (OPSCC): applying radiomics and machine learning algorithms

Abstract Background The incidence of oropharyngeal squamous cell carcinoma (OPSCC) in the US is rapidly increasing, driven largely by the epidemic of human papillomavirus (HPV)-mediated OPSCC. Although survival for patients with HPV mediated OPSCC (HPV+ OPSCC) is generally better than that of patients with non-virally mediated OPSCC, this effect is not uniform. We hypothesized that tobacco exposure remains a critical modifier of survival for HPV+ OPSCC patients. Methods We conducted a retrospective analysis of 611 OPSCC patients with concordant p16 and HPV testing treated at a single institute (2002–2013). Survival analysis was performed using Kaplan-Meier analysis and Cox regression. Recursive partitioning analysis (RPA) was used to define tobacco exposure associated with survival (p < 0.05). Results Tobacco exposure impacted overall survival (OS) for HPV+ patients on univariate and multivariate analysis (p = 0.002, p = 0.003 respectively). RPA identified 30 pack-years (PY) as a threshold at which survival became significantly worse in HPV+ patients. OS and disease-free survival (DFS) for HPV+ > 30 PY patients didn’t differ significantly from HPV- patients (p = 0.72, p = 0.27, respectively). HPV+ > 30 PY patients had substantially lower 5-year OS when compared to their ≤30 PYs counterparts: 78.4% vs 91.6%; p = 0.03, 76% vs 88.3%; p = 0.07, and 52.3% vs 74%; p = 0.05, for stages I, II, and III (AJCC 8th Edition Manual), respectively. Conclusions Tobacco exposure can eliminate the survival benefit associated with HPV+ status in OPSCC patients. Until this effect can be clearly quantified using prospective datasets, de-escalation of treatment for HPV + OPSCC smokers should be avoided.

Download Full-text

Oropharyngeal squamous cell carcinoma: radiomic machine-learning classifiers from multiparametric MR images for determination of HPV infection status

Scientific Reports ◽

10.1038/s41598-020-74479-x ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Chong Hyun Suh ◽

Kyung Hwa Lee ◽

Young Jun Choi ◽

Sae Rom Chung ◽

Jung Hwan Baek ◽

...

Keyword(s):

Machine Learning ◽

Squamous Cell Carcinoma ◽

Logistic Regression ◽

Random Forest ◽

Cell Carcinoma ◽

Squamous Cell ◽

Oropharyngeal Squamous Cell Carcinoma ◽

Machine Learning Classifiers ◽

Learning Classifiers ◽

Hpv Status

Abstract We investigated the ability of machine-learning classifiers on radiomics from pre-treatment multiparametric magnetic resonance imaging (MRI) to accurately predict human papillomavirus (HPV) status in patients with oropharyngeal squamous cell carcinoma (OPSCC). This retrospective study collected data of 60 patients (48 HPV-positive and 12 HPV-negative) with newly diagnosed histopathologically proved OPSCC, who underwent head and neck MRIs consisting of axial T1WI, T2WI, CE-T1WI, and apparent diffusion coefficient (ADC) maps from diffusion-weighted imaging (DWI). The median age was 59 years (the range being 35 to 85 years), and 83.3% of patients were male. The imaging data were randomised into a training set (32 HPV-positive and 8 HPV-negative OPSCC) and a test set (16 HPV-positive and 4 HPV-negative OPSCC) in each fold. 1618 quantitative features were extracted from manually delineated regions-of-interest of primary tumour and one definite lymph node in each sequence. After feature selection by using the least absolute shrinkage and selection operator (LASSO), three different machine-learning classifiers (logistic regression, random forest, and XG boost) were trained and compared in the setting of various combinations between four sequences. The highest diagnostic accuracies were achieved when using all sequences, and the difference was significant only when the combination did not include the ADC map. Using all sequences, logistic regression and the random forest classifier yielded higher accuracy compared with the that of the XG boost classifier, with mean area under curve (AUC) values of 0.77, 0.76, and 0.71, respectively. The machine-learning classifier of non-invasive and quantitative radiomics signature could guide the classification of the HPV status.

Download Full-text

Socioeconomic and Racial Disparities and Survival of Human Papillomavirus–Associated Oropharyngeal Squamous Cell Carcinoma

Otolaryngology ◽

10.1177/0194599820935853 ◽

2020 ◽

pp. 019459982093585

Author(s):

Janine M. Rotsides ◽

Jamie R. Oliver ◽

Lindsey E. Moses ◽

Moses Tam ◽

Zujun Li ◽

...

Keyword(s):

Squamous Cell Carcinoma ◽

Human Papillomavirus ◽

Cell Carcinoma ◽

Squamous Cell ◽

Cox Regression ◽

Population Based ◽

Oropharyngeal Squamous Cell Carcinoma ◽

Median Income ◽

Racial Groups ◽

Hpv Status

Objective To investigate differences in epidemiology of oropharyngeal squamous cell carcinoma (OPSCC) with regards to human papillomavirus (HPV), race, and socioeconomic status (SES) using the National Cancer Database (NCDB). Study Design Population-based cohort study. Setting Racial and socioeconomic disparities in survival of OPSCC have been previously acknowledged. However, the distribution of HPV-related cancers and its influence on survival in conjunction with race and SES remain unclear. Subjects and Methods All patients with OPSCC in the NCDB with known HPV status from 2010 to 2016 were included. Differences in presentation, HPV status, treatment, and outcomes were compared along racial and socioeconomic lines. Univariable and multivariable Cox regression survival analyses were performed. Results In total, 45,940 patients met criteria. Most were male (38,038, 82.8%), older than 60 years (23,456, 51.5%), and white (40,156, 87.4%), and lived in higher median income areas (>$48,000, 28,587, 62.2%). Two-thirds were HPV positive (31,007, 67.5%). HPV-negative disease was significantly more common in lower SES (<$38,000, 2937, 41.5%, P < .001) and among blacks (1784, 55.3%, P < .001). Median follow-up was 33 months. Five-year overall survival was 81.3% (95% CI, 80.5%-82.1%) and 59.6% (95% CI, 58.2%-61.0%) in HPV-positive and HPV-negative groups, respectively. In univariable and multivariable analyses controlling for HPV status, age, stage, and treatment, black race (hazard ratio [HR], 1.22; 95% CI, 1.11-1.34; P < .001) and low SES (HR, 1.58; 95% CI, 1.45-1.72; P < .001) were associated with worse survival. Conclusion Significant differences in HPV status exist between socioeconomic and racial groups, with HPV-negative disease more common among blacks and lower SES. When controlling for HPV status, race and SES still influence outcomes in oropharyngeal cancers.

Download Full-text

Machine learning–based CT texture analysis to predict HPV status in oropharyngeal squamous cell carcinoma: comparison of 2D and 3D segmentation

European Radiology ◽

10.1007/s00330-020-07011-4 ◽

2020 ◽

Vol 30 (12) ◽

pp. 6858-6866 ◽

Cited By ~ 1

Author(s):

Jiliang Ren ◽

Ying Yuan ◽

Meng Qi ◽

Xiaofeng Tao

Keyword(s):

Machine Learning ◽

Squamous Cell Carcinoma ◽

Cell Carcinoma ◽

Texture Analysis ◽

Squamous Cell ◽

Oropharyngeal Squamous Cell Carcinoma ◽

3D Segmentation ◽

Hpv Status ◽

Ct Texture Analysis ◽

2D And 3D

Download Full-text

Tobacco exposure as a major modifier of oncologic outcomes in Human PapillomaVirus (HPV) associated oropharyngeal squamous cell carcinoma

10.21203/rs.2.22588/v2 ◽

2020 ◽

Author(s):

Hesham Elhalawani ◽

Abdallah S.R. Mo ◽

Baher Elgohari ◽

Timothy A. Lin ◽

Andrew G. Sikora ◽

...

Keyword(s):

Squamous Cell Carcinoma ◽

Human Papillomavirus ◽

Cell Carcinoma ◽

Squamous Cell ◽

Cox Regression ◽

Disease Free Survival ◽

Oropharyngeal Squamous Cell Carcinoma ◽

Oncologic Outcomes ◽

Tobacco Exposure ◽

Hpv Status

Abstract Background: The incidence of oropharyngeal squamous cell carcinoma (OPSCC) in the US is rapidly increasing, driven largely by the epidemic of human papillomavirus (HPV)-mediated OPSCC. Although survival for patients with HPV mediated OPSCC (HPV+ OPSCC) is generally better than that of patients with non-viral HPV+ OPSCC, the improvement is not uniform. We hypothesized that tobacco exposure remains a critical modifier of survival for HPV+ OPSCC patients. Methods: We conducted a retrospective analysis of 611 OPSCC patients with concordant p16 and HPV testing treated at a single institute (2002-2013). Survival analysis was performed using Kaplan-Meier analysis and Cox regression. Recursive partitioning analysis (RPA) was used to define tobacco exposure associated with survival (p<0.05). Results: Tobacco exposure impacted overall survival (OS) for HPV+ patients on univariate and multivariate analysis (p=0.002, p=0.003 respectively). RPA identified 30 pack-years (PY) as a threshold at which survival became significantly worse in HPV+ patients. OS and disease-free survival (DFS) for HPV+ >30 PY patients didn’t differ significantly from HPV- group (p= 0.72, p= 0.27, respectively). HPV+ >30 PY patients had substantially lower 5-year OS when compared to their ≤30 PYs counterparts: 78.4% vs 91.6%; p= 0.03, 76% vs 88.3%; p= 0.07, and 52.3% vs 74%; p= 0.05, for stages I, II, and III (AJCC 8 th Edition Manual), respectively. Conclusions: Tobacco exposure can eliminate the survival benefit associated with HPV+ status in OPSCC patients. Until this effect can be clearly quantified using prospective datasets, de-escalation of treatment for HPV+OPSCC smokers should be avoided.

Download Full-text

Review for "Comparison of machine learning algorithms for the prediction of five‐year survival in oral squamous cell carcinoma"

10.1111/jop.13135/v2/review1 ◽

2020 ◽

Keyword(s):

Machine Learning ◽

Squamous Cell Carcinoma ◽

Oral Squamous Cell Carcinoma ◽

Cell Carcinoma ◽

Squamous Cell ◽

Learning Algorithms ◽

Machine Learning Algorithms

Download Full-text

Tobacco exposure as a major modifier of oncologic outcomes in Human PapillomaVirus (HPV) associated oropharyngeal squamous cell carcinoma

10.21203/rs.2.22588/v4 ◽

2020 ◽

Author(s):

Hesham Elhalawani ◽

Abdallah S.R. Mo ◽

Baher Elgohari ◽

Timothy A. Lin ◽

Andrew G. Sikora ◽

...

Keyword(s):

Squamous Cell Carcinoma ◽

Human Papillomavirus ◽

Cell Carcinoma ◽

Squamous Cell ◽

Cox Regression ◽

Disease Free Survival ◽

Oropharyngeal Squamous Cell Carcinoma ◽

Oncologic Outcomes ◽

Tobacco Exposure ◽

Hpv Status

Abstract Background: The incidence of oropharyngeal squamous cell carcinoma (OPSCC) in the US is rapidly increasing, driven largely by the epidemic of human papillomavirus (HPV)-mediated OPSCC. Although survival for patients with HPV mediated OPSCC (HPV+ OPSCC) is generally better than that of patients with non-viral HPV+ OPSCC, this effect is not uniform. We hypothesized that tobacco exposure remains a critical modifier of survival for HPV+ OPSCC patients.Methods: We conducted a retrospective analysis of 611 OPSCC patients with concordant p16 and HPV testing treated at a single institute (2002-2013). Survival analysis was performed using Kaplan-Meier analysis and Cox regression. Recursive partitioning analysis (RPA) was used to define tobacco exposure associated with survival (p<0.05). Results: Tobacco exposure impacted overall survival (OS) for HPV+ patients on univariate and multivariate analysis (p=0.002, p=0.003 respectively). RPA identified 30 pack-years (PY) as a threshold at which survival became significantly worse in HPV+ patients. OS and disease-free survival (DFS) for HPV+ >30 PY patients didn’t differ significantly from HPV- patients (p= 0.72, p= 0.27, respectively). HPV+ >30 PY patients had substantially lower 5-year OS when compared to their ≤30 PYs counterparts: 78.4% vs 91.6%; p= 0.03, 76% vs 88.3%; p= 0.07, and 52.3% vs 74%; p= 0.05, for stages I, II, and III (AJCC 8th Edition Manual), respectively.Conclusions: Tobacco exposure can eliminate the survival benefit associated with HPV+ status in OPSCC patients. Until this effect can be clearly quantified using prospective datasets, de-escalation of treatment for HPV+OPSCC smokers should be avoided.

Download Full-text

Tobacco exposure as a major modifier of oncologic outcomes in Human PapillomaVirus (HPV) associated oropharyngeal squamous cell carcinoma

10.21203/rs.2.22588/v1 ◽

2020 ◽

Author(s):

Hesham Elhalawani ◽

Abdallah S.R. Mo ◽

Baher Elgohari ◽

Timothy A. Lin ◽

Andrew G. Sikora ◽

...

Keyword(s):

Squamous Cell Carcinoma ◽

Human Papillomavirus ◽

Cell Carcinoma ◽

Squamous Cell ◽

Cox Regression ◽

Disease Free Survival ◽

Oropharyngeal Squamous Cell Carcinoma ◽

Oncologic Outcomes ◽

Tobacco Exposure ◽

Hpv Status

Abstract Background The incidence of oropharyngeal squamous cell carcinoma (OPSCC) in the US is rapidly increasing, driven largely by the epidemic of human papillomavirus (HPV)-mediated OPSCC. Although survival for patients with HPV mediated OPSCC (HPV+ OPSCC) is generally better than that of patients with non-viral HPV+ OPSCC, the improvement is not uniform. We hypothesized that tobacco exposure remains a critical modifier of survival for HPV+ OPSCC patients. Methods We conducted a retrospective analysis of 611 OPSCC patients with concordant p16 and HPV testing treated at a single institute (2002-2013). Survival analysis was performed using Kaplan-Meier analysis and Cox regression. Recursive partitioning analysis (RPA) was used to define tobacco exposure associated with survival (p<0.05). Results Tobacco exposure impacted overall survival (OS) for HPV+ patients on univariate and multivariate analysis (p=0.002, p=0.003 respectively). RPA identified 30 pack-years (PY) as a threshold at which survival became significantly worse in HPV+ patients. OS and disease-free survival (DFS) for HPV+ >30 PY patients didn’t differ significantly from HPV- group (p= 0.72, p= 0.27, respectively). HPV+ >30 PY patients had substantially lower 5-year OS when compared to their ≤30 PYs counterparts: 78.4% vs 91.6%; p= 0.03, 76% vs 88.3%; p= 0.07, and 52.3% vs 74%; p= 0.05, for stages I, II, and III (AJCC 8th Edition Manual), respectively. Conclusions Tobacco exposure can eliminate the survival benefit associated with HPV+ status in OPSCC patients. Until this effect can be clearly quantified using prospective datasets, de-escalation of treatment for HPV+OPSCC smokers should be avoided.

Download Full-text