Machine Learning Algorithms for Predicting Treatment Outcomes of Oropharyngeal Cancer After Surgery
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Background and Objectives This study analyzed data from patients who were diagnosedwith human papilloma virus (HPV)-associated oropharyngeal (OPC) and treated surgically toconstruct a machine learning survival prediction model. Subjects and Method We retrospectively analyzed the clinico-pathological data of 203 pa-tients with HPV-associated oropharyngeal squamous cell carcinoma (OPSCC) from 2007 to 2015. Results In the Cox proportional hazard (CPH) model, the c-index values for the training setand the test set were 0.81 and 0.59, respectively. The univariate analysis showed that contralat-eral lymph nodes (LNs) metastasis, lymphovascular invasion, pN, stage, surgical margin sta-tus, histologic grade, pT, and the number of metastatic LNs had significant correlations withsurvival. Contrastively, the multivariate analysis showed pT and histologic grade to have sig-nificant correlation with survival. In the random survival forest model, the c-index values forthe training set and the test set were 0.83 and 0.87, respectively. In the DeepSurv model, the c-index values for the training set and the test set were 0.75 and 0.83. Among the three modelsmentioned above, Random Survival Forest and DeepSurv showed the best performance forpredicting the survival of HPV-associated OPSCC patients. Conclusion We confirmed that a survival prediction model using machine learning anddeep learning algorithms showed reasonable survival estimates for HPV-associated OPSCC patients.
Abstract
Background and Objectives This study analyzed data from patients who were diagnosedwith human papilloma virus (HPV)-associated oropharyngeal (OPC) and treated surgically toconstruct a machine learning survival prediction model. Subjects and Method We retrospectively analyzed the clinico-pathological data of 203 pa-tients with HPV-associated oropharyngeal squamous cell carcinoma (OPSCC) from 2007 to 2015. Results In the Cox proportional hazard (CPH) model, the c-index values for the training setand the test set were 0.81 and 0.59, respectively. The univariate analysis showed that contralat-eral lymph nodes (LNs) metastasis, lymphovascular invasion, pN, stage, surgical margin sta-tus, histologic grade, pT, and the number of metastatic LNs had significant correlations withsurvival. Contrastively, the multivariate analysis showed pT and histologic grade to have sig-nificant correlation with survival. In the random survival forest model, the c-index values forthe training set and the test set were 0.83 and 0.87, respectively. In the DeepSurv model, the c-index values for the training set and the test set were 0.75 and 0.83. Among the three modelsmentioned above, Random Survival Forest and DeepSurv showed the best performance forpredicting the survival of HPV-associated OPSCC patients. Conclusion We confirmed that a survival prediction model using machine learning anddeep learning algorithms showed reasonable survival estimates for HPV-associated OPSCC patients.
참고문헌 (25)
- Ang KK, "Human papillomavirus and survival of patients with oropharyngeal cancer", N Engl J Med, 363(1), pp.24~35 (2010)
- Fakhry C, "Validation of NRG oncology", RTOG-0129 risk groups for HPV-positive and HPV-negative oropharyngeal squamous cell cancer : Implications for risk-based therapeutic intensity trials, 2019, pp.125(12), 2027~2038
- Rosenthal DI, "Association of human papillomavirus and p16 status with outcomes in the IMCL-9815 phase III registration trial for patients with locoregionally advanced oropharyngeal squamous cell carcinoma of the head and neck treated with radiotherapy with or without cetuximab", J Clin Oncol, 34(12), pp.1300~1308 (2016)
- Gillison ML, "Radiotherapy plus cetuximab or cisplatin in human papillomavirus-positive oropharyngeal cancer (NRG Oncology RTOG 1016): A randomised, multicentre, non-inferiority trial", Lancet, 393(10166), pp.40~50 (2019)
- Marur S, "E1308 : Phase II trial of induction chemotherapy followed by reduced-dose radiation and weekly cetuximab in patients with HPVassociated resectable squamous cell carcinoma of the oropharynx—ECOG-ACRIN Cancer Research Group", J Clin Oncol, 35(5), pp.490~497 (2017)
- Chen AM, "Reduced-dose radiotherapy for human papillomavirus-associated squamous-cell carcinoma of the oropharynx: A single-arm, phase 2 study", Lancet Oncol, 18(6), pp.803~811 (2017)
- Chera BS, "Mature results of a prospective study of deintensified chemoradiotherapy for low-risk human papillomavirus-associated oropharyngeal squamous cell carcinoma", Cancer, 124(11), pp.2347~2354 (2018)
- Stock GT, "De-escalation treatment of human papillomavirus-positive oropharyngeal squamous cell carcinoma : An evidence-based review for the locally advanced disease", Curr Opin Oncol, 30(3), pp.146~151 (2018)
- O’Sullivan B, "Development and validation of a staging system for HPVrelated oropharyngeal cancer by the International Collaboration on Oropharyngeal cancer Network for Staging(ICON-S) : A multicentre cohort study", Lancet Oncol, 17(4), pp.440~451 (2016)
- Lydiatt WM, "Head and neck cancers-major changes in the American Joint Committee on cancer eighth edition cancer staging manual", CA Cancer J Clin, 67(2), pp.122~137 (2017)
- Hawkins PG, "Impact of American Joint Committee on Cancer eighth edition clinical stage and smoking history on oncologic outcomes in human papillomavirus-associated oropharyngeal squamous cell carcinoma", Head Neck, 41(4), pp.857~864 (2019)
- Chotchutipan T, "Volumetric 18F-FDG-PET parameters as predictors of locoregional failure in low-risk HPV-related oropharyngeal cancer after definitive chemoradiation therapy", Head Neck, 41(2), pp.366~373 (2019)
- Mazo C, "Transfer learning for classification of cardiovascular tissues in histological images", Comput Methods Programs Biomed, 165, pp.69~76 (2018)
- Karri SP, "Transfer learning based classification of optical coherence tomography images with diabetic macular edema and dry age-related macular degeneration", Biomed Opt Express, 8(2), pp.579~592 (2017)
- Gulshan V, "Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs", JAMA, 316(22), pp.2402~2410 (2016)
- Kermany DS, "Identifying medical diagnoses and treatable diseases by image-based deep learning", Cell, 172(5), pp.1122~1131 (2018)
- Hood DC, "Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs", Ophthalmology, 125(8), pp.1207~1208 (2018)
- Tschandl P, "Comparison of the accuracy of human readers versus machinelearning algorithms for pigmented skin lesion classification: An open, web-based, international, diagnostic study", Lancet Oncol, 20(7), pp.938~947 (2019)
- Harrell FE Jr, "Evaluating the yield of medical tests", JAMA, 247(18), pp.2543~2546 (1982)
- Katzman JL, "DeepSurv : personalized treatment recommender system using a Cox proportional hazards deep neural network", BMC Med Res Methodol, 18(1), pp.24~ (2018)
- Ishwaran H, "Random survival forests for competing risks", Biostatistics, 15(4), pp.757~773 (2014)
- Su X, "Interaction trees with censored survival data", Int J Biostat, 4(1), pp.Article 2.~ (2008)
- Fakhry C, "Development and validation of nomograms predictive of overall and progression-free survival in patients with oropharyngeal cancer", J Clin Oncol, 35(36), pp.4057~4065 (2017)
- Larsen CG, "Novel nomograms for survival and progression in HPV+and HPV- oropharyngeal cancer: A population-based study of 1,542 consecutive patients", Oncotarget, 7(44), pp.71761~71772 (2016)
- Rios Velazquez E, "Externally validated HPV-based prognostic nomogram for oropharyngeal carcinoma patients yields more accurate predictions than TNM staging", Radiother Oncol, 113(3), pp.324~330 (2014)