Log margin‐to‐thickness ratio improves disease‐specific survival prediction in oral cancer: A single cancer centre database

Huang, Chien-Yu; Lin, Yaoh‐Shiang; Kang, Bor‐Hwang; Chang, Kuo-Ting; Chi, Chao-Chuan; Lin, Ming-Yee; Su, Hsing‐Hao; Chang, Tun-Tschu; Lee, Huai-Pao; Lee, Ching‐Chih

doi:10.1111/coa.13237

Cited by 6 publications

(3 citation statements)

References 24 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, novel ways of analysing histopathology of OSCC may be useful for future prospective studies. For example, margin‐to‐thickness ratio has recently been explored as prognostic histopathological factors in OSCC 25 …”

Section: Discussionmentioning

confidence: 99%

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

Alkhadar

Macluskey

White

et al. 2020

J Oral Pathology Medicine

View full text Add to dashboard Cite

Background/Aim Machine learning analyses of cancer outcomes for oral cancer remain sparse compared to other types of cancer like breast or lung. The purpose of the present study was to compare the performance of machine learning algorithms in the prediction of global, recurrence‐free five‐year survival in oral cancer patients based on clinical and histopathological data. Methods Data were gathered retrospectively from 416 patients with oral squamous cell carcinoma. The data set was divided into training and test data set (75:25 split). Training performance of five machine learning algorithms (Logistic regression, K‐nearest neighbours, Naïve Bayes, Decision tree and Random forest classifiers) for prediction was assessed by k‐fold cross‐validation. Variables used in the machine learning models were age, sex, pain symptoms, grade of lesion, lymphovascular invasion, extracapsular extension, perineural invasion, bone invasion and type of treatment. Variable importance was assessed and model performance on the testing data was assessed using receiver operating characteristic curves, accuracy, sensitivity, specificity and F1 score. Results The best performing model was the Decision tree classifier, followed by the Logistic Regression model (accuracy 76% and 60%, respectively). The Naïve Bayes model did not display any predictive value with 0% specificity. Conclusions Machine learning presents a promising and accessible toolset for improving prediction of oral cancer outcomes. Our findings add to a growing body of evidence that Decision tree models are useful in models in predicting OSCC outcomes. We would advise that future similar studies explore a variety of machine learning models including Logistic regression to help evaluate model performance.

show abstract

Section: Discussionmentioning

confidence: 99%

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

Alkhadar

Macluskey

White

et al. 2020

J Oral Pathology Medicine

View full text Add to dashboard Cite

show abstract

“…Some authors have considered that millimetre distance – albeit with diverse interpretative ranges – is crucial for oncological outcomes 17-19 (among the most recent). Others, while confirming the importance of margins, also suggest that other factors affect prognosis 20 , 21 (among the most recent). There are also several authors who deny the prognostic significance of margins 22 , 23 (among the most recent), even in multivariate analyses 24 , 25 .…”

Section: Discussionmentioning

confidence: 78%

Multicentre study on resection margins in carcinoma of the oral cavity, oro-hypopharynx and larynx

Barzan

Montomoli

Carlo

et al. 2022

Acta Otorhinolaryngol Ital

View full text Add to dashboard Cite

SUMMARY Objective The prognostic significance of the resection margins is still subject of conflicting opinions. The purpose of this paper is to report the results of a study on the margins in carcinoma of the oral cavity, oro-hypopharynx and larynx. Methods A multicentre prospective study was carried out between 2015 and 2018 with the participation of 10 Italian reference hospitals. The primary objective was to evaluate local control in patients with well-defined clinical characteristics and comprehensive histopathological information. Results During the study period, 455 patients were enrolled; the minimum follow-up was 2 years. Previous treatment, grading and fresh specimen examination were identified as risk factors for local control in multivariate analysis. On the basis of these results, it seems possible to delineate “risk profiles” for different oncological outcomes. Discussion The prognostic significance of the margins is reduced, and other risk factors emerge, which require diversified treatment and follow-up. Conclusions Multidisciplinary treatment with adjuvant therapy, if indicated, reduces the prognostic importance of margins. Collaboration with a pathologist is an additional favourable prognostic factor and quality indicator. An appendix with literature review is present in the online version.

show abstract

“…These results suggest that a wider deep resection margin is required as tumor thickness increases. Another study further evaluated the value of this dynamic margin criteria and found that a log MTR of <33% was a predictor of less favorable outcome in the disease-specific survival of oral cancer [ 59 ]. Taken together, recent evidence suggests the need for dynamic resection margin criteria according to a tumor’s dimensions or the depth of invasion in oral cancer.…”

Section: Discussionmentioning

confidence: 99%

Surgical Extent for Oral Cancer: Emphasis on a Cut-Off Value for the Resection Margin Status: A Narrative Literature Review

Jang

Choi

Jeong

2022

Cancers

View full text Add to dashboard Cite

The optimal cut-off point of the resection margin was recently debated in oral cancer. To evaluate the current evidence of the dynamic criteria of the resection margin, a review of the available literature was performed. Studies were sourced from PubMed and EMBASE by searching for the keywords “mouth neoplasm”, “oral cancer”, “oral cavity cancer”, “oral squamous cell carcinoma”, “tongue cancer”, “margins of excision”, “surgical margin” and “resection margin”. We found approximately 998 articles on PubMed and 2227 articles on EMBASE. A total of 3225 articles was identified, and 2763 of those were left after removing the duplicates. By applying advanced filters about the relevance of the subjects, these were narrowed down to 111 articles. After the final exclusion, 42 full-text articles were reviewed. The universal cut-off criteria of 5 mm used for determining the resection margin status has been debated due to recent studies evaluating the impact of different margin criteria on patient prognosis. Of note, the degree of the microscopic extension from the gross tumor border correlates with tumor dimensions. Therefore, a relatively narrow safety margin can be justified in early-stage oral cancer without the additional risk of recurrence, while a wide safety margin might be required for advanced-stage oral cancer. This review suggests a surgical strategy to adjust the criteria for risk grouping and adjuvant treatments, according to individual tumor dimensions or characteristics. In the future, it might be possible to establish individual tumor-specific surgical margins and risk stratification during or after surgery. However, the results should be interpreted with caution because there is no strong evidence (e.g., prospective randomized controlled studies) yet to support the conclusions. Our study is meaningful in suggesting future research directions and discussions.

show abstract

Log margin‐to‐thickness ratio improves disease‐specific survival prediction in oral cancer: A single cancer centre database

Cited by 6 publications

References 24 publications

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

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

Multicentre study on resection margins in carcinoma of the oral cavity, oro-hypopharynx and larynx

Surgical Extent for Oral Cancer: Emphasis on a Cut-Off Value for the Resection Margin Status: A Narrative Literature Review

Contact Info

Product

Resources

About