Predictors of locoregional recurrence in early stage buccal cancer with pathologically clear surgical margins and negative neck

Zaman, Shakeel Uz; Aqil, Shakil; Sulaiman, Mohammad Ahsan

doi:10.1016/j.otoeng.2017.09.001

Cited by 4 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, demographic, clinicopathological, therapeutic and bio‐molecular data have all been used to populate clinical decision‐making tools, including statistical regression models and prognostic nomograms, in an attempt to predict poor clinical outcome post‐OSCC treatment. Unfortunately, such methods have gained limited acceptance in contemporary clinical practice due to data validity concerns and little demonstrable predictive accuracy 3‐12 …”

Section: Introductionmentioning

confidence: 99%

Machine learning and treatment outcome prediction for oral cancer

Chu

Lee

Adeoye

et al. 2020

J Oral Pathology Medicine

View full text Add to dashboard Cite

Background The natural history of oral squamous cell carcinoma (OSCC) is complicated by progressive disease including loco‐regional tumour recurrence and development of distant metastases. Accurate prediction of tumour behaviour is crucial in delivering individualized treatment plans and developing optimal patient follow‐up and surveillance strategies. Machine learning algorithms may be employed in oncology research to improve clinical outcome prediction. Methods Retrospective review of 467 OSCC patients treated over a 19‐year period facilitated construction of a detailed clinicopathological database. 34 prognostic features from the database were used to populate 4 machine learning algorithms, linear regression (LR), decision tree (DT), support vector machine (SVM) and k‐nearest neighbours (KNN) models, to attempt progressive disease outcome prediction. Principal component analysis (PCA) and bivariate analysis were used to reduce data dimensionality and highlight correlated variables. Models were validated for accuracy, sensitivity and specificity, with predictive ability assessed by receiver operating characteristic (ROC) and area under the curve (AUC) calculation. Results Out of 408 fully characterized OSCC patients, 151 (37%) had died and 131 (32%) exhibited progressive disease at the time of data retrieval. The DT model with 34 prognostic features was most successful in identifying “true positive” progressive disease, achieving 70.59% accuracy (AUC 0.67), 41.98% sensitivity and a high specificity of 84.12%. Conclusion Machine learning models assist clinicians in accessing digitized health information and appear promising in predicting progressive disease outcomes. The future will see increasing emphasis on the use of artificial intelligence to enhance understanding of aggressive tumour behaviour, recurrence and disease progression.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine learning and treatment outcome prediction for oral cancer

Chu

Lee

Adeoye

et al. 2020

J Oral Pathology Medicine

View full text Add to dashboard Cite

show abstract

“…Several studies have attempted to elucidate the discrepancy between negative margins and recurrence. Previous studies of OSCCs with negative margins have identified histological markers like lymphovascular invasion and non‐T4 muscular invasion as predictors of recurrence 8,9 . In 2005 Brandwein‐Gensler and colleagues proposed a histologic risk scoring scheme based on perineural invasion, lymphocytic infiltration at the interface and the worst pattern of invasion in effort to identify tumors with negative margins that might still benefit from adjuvant therapy due to higher risk of recurrence 10 .…”

Section: Discussionmentioning

confidence: 99%

Cumulative suppressive index as a predictor of relapse free survival and overall survival in Human Papilloma Virus‐negative oral squamous cell carcinomas with negative resection margins

et al. 2020

View full text Add to dashboard Cite

Background: This study aimed to analyze margin status and the impact of the immune elements on recurrence in patients with oral squamous cell carcinoma (OSCC), employing a prognostic biomarker, cumulative suppressive index (CSI), which reflects FoxP3+, PD-L1+, and CD8+ cell spatial relationships in the tumor microenvironment. Methods: Cox proportional hazards regression was used to evaluate the interactive effect of the margin by CSI discrepancy (high, 3-4 vs low, 0-2) on recurrence free survival (RFS) and overall survival (OS) in 119 patients with stage I to IVA OSCC. Results: In cases with negative margins, multivariable analysis showed high CSI was significantly associated with worse RFS (HR = 2.59, 95% CI [1.03, 6.49], P = .04) and OS (HR = 5.49, 95% CI [1.48, 20.35], P = .01) compared to low CSI. However, high CSI was not significantly associated with recurrence in cases with positive margins.

show abstract

“…Among the three main treatments applied in BSCC, surgery was found to be the only signi cantly effective treatment, and so the radiotherapy and chemotherapy statuses were not included in the nal nomogram. Surgical treatment should be the rst choice of treatment for BSCC [18,20,21], while avoiding unnecessary radiotherapy and chemotherapy can reduce the burden on medical resources, alleviate the additional injury and pain experienced by patients, and reduce costs. This information can further help clinicians to make rational clinical decisions.…”

Section: Discussionmentioning

confidence: 99%

Nomogram for predicting cancer-specific survival of patients with buccal squamous cell carcinoma: a population-based study

Wang

chu²,

Yang

et al. 2020

Preprint

View full text Add to dashboard Cite

Background The use of the traditional American Joint Committee on Cancer (AJCC) staging system alone has limitations in predicting the survival of buccal squamous cell carcinoma (BSCC) patients. We aimed to establish a comprehensive prognostic nomogram whose prognostic value compared with AJCC system. Methods Patients were obtained from the SEER (Surveillance, Epidemiology, and End Result) database. The Cox regression model was used to select variables using a backward stepwise selection method. Based on the predictive model for determining prognostic factors, a nomogram was developed to predict the cancer-specific survival rates of BSCC patients at 3, 5 and 8 years. We used several standard model validation methods to evaluate the performance of the survival model: concordance index (C-index), area under the time-dependent receiver operating characteristic curve (AUC), net reclassification improvement (NRI), calibration plots, decision curve analyses (DCAs), and integrated discrimination improvement (IDI). Results Multivariate analysis showed that age, AJCC stage, N stage, M stage, pathological grade, and surgical status were risk factors for survival. The c-index chart, the AUC chart, and the calibration chart show that the performance of the nomogram is better, and the NRI and IDI values show that the performance of the nomogram is better than that of the AJCC staging system. The 3-year, 5-year and 8-year DCA curves of nomogram show that it has more net benefit than traditional AJCC staging system, both in terms of training and validation queues. Conclusion We developed and validated the first BSCC prognosis nomogram, which has a better prognostic value than the separate AJCC staging system. Our BSCC prognosis nomogram is a valuable tool for explaining the risks of the next 3, 5 and 8 years in clinical practice.

show abstract

Predictors of locoregional recurrence in early stage buccal cancer with pathologically clear surgical margins and negative neck

Cited by 4 publications

References 18 publications

Machine learning and treatment outcome prediction for oral cancer

Machine learning and treatment outcome prediction for oral cancer

Cumulative suppressive index as a predictor of relapse free survival and overall survival in Human Papilloma Virus‐negative oral squamous cell carcinomas with negative resection margins

Nomogram for predicting cancer-specific survival of patients with buccal squamous cell carcinoma: a population-based study

Contact Info

Product

Resources

About