Skip to main content
Download PDF

Prediction of 5-year overall survival of tongue cancer based machine learning

BMC Oral Health volume 23, Article number: 567 (2023) Cite this article

Abstract

Objective

We aimed to develop a 5-year overall survival prediction model for patients with oral tongue squamous cell carcinoma based on machine learning methods.

Subjects and methods

The data were obtained from electronic medical records of 224 OTSCC patients at the PLA General Hospital. A five-year overall survival prediction model was constructed using logistic regression, Support Vector Machines, Decision Tree, Random Forest, Extreme Gradient Boosting, and Light Gradient Boosting Machine. Model performance was evaluated according to the area under the curve (AUC) of the receiver operating characteristic curve. The output of the optimal model was explained using the Python package (SHapley Additive exPlanations, SHAP).

Results

After passing through the grid search and secondary modeling, the Light Gradient Boosting Machine was the best prediction model (AUC = 0.860). As explained by SHapley Additive exPlanations, N-stage, age, systemic inflammation response index, positive lymph nodes, plasma fibrinogen, lymphocyte-to-monocyte ratio, neutrophil percentage, and T-stage could perform a 5-year overall survival prediction for OTSCC. The 5-year survival rate was 42%.

Conclusion

The Light Gradient Boosting Machine prediction model predicted 5-year overall survival in OTSCC patients, and this predictive tool has potential prognostic implications for patients with OTSCC.

Peer Review reports

Introduction

Oral tongue squamous cell carcinoma (OTSCC) is a common oral cancer. Because OTSCC is characterized by local invasion and early lymph node metastasis, it often leads to a high recurrence rate and mortality rate [1, 2]. According to statistics in the United States, 17,060 tongue cancer cases increased, and 3,020 tongue cancer patients died per day in 2019 [3]. Therefore, a clinically OTSCC survival prediction model is needed to assist clinicians in the treatment to make timely use of tertiary prevention strategies to reduce recurrence and complications [4].

Currently, the TNM staging system is an objective and accurate tool for predicting prognosis in OTSCC patients [5]. This prognostic tool only considers the characteristics of the tumor itself and does not contain multiple complex factors [6, 7]. Additionally, not everyone can afford it due to the expensive operation cost. Therefore, it is necessary to identify a simple, economic and accurate prognostic tool.

There have been relevant studies showing that machine learning of large medical data obtained from real-world electronic medical records is supporting doctors in the diagnosis and management of diabetic nephropathy [8]. Inspired by this, we hoped to use machine learning technology to build a predictive model to predict the 5-year survival rate of OTSCC patients based on electronic medical records. To the best of our knowledge, there is no predictive model of OTSCC patient survival using six machine learning methods based on electronic medical records.

Materials and methods

Data source

Data were obtained from the electronic medical records of 224 patients with OTSCC reported at the PLA General Hospital from August 2009 to December 2017, containing 51 clinical features as follows: age, sex, height, weight, body mass index (BMI), hypertension, diabetes, white blood cell count (WBC), neutrophil percentage (N), lymphocyte percentage (L), monocyte percentage (M), platelet count (PLT), lymphocyte-to-monocyte ratio (LMR), platelet-to-lymphocyte ratio (PLR), neutrophil-to-lymphocyte ratio (NLR), systemic inflammation response index (SIRI), hematocrit (Hct), mean cellular hemoglobin concentration (MCHC), average platelet volume (MPV), activated partial thrombin time (APTT), plasma fibrinogen (FIB), hemoglobin (Hb), albumin, glycosylated Hb, targeted therapy, tumor size, tumor location, T-stage, N-stage, positive lymph nodes, histologic grade, OTSCC classification, urinary specific gravity (SG), urinary red blood cell count (RBC), blood urea nitrogen (BUN), serum creatinine (SCR), serum uric acid (SUA), total bilirubin (T-BiL), direct bilirubin (D-BiL), homocysteine (HCY), γ-glutamine transferase (GGT), random blood glucose (RBG), total cholesterol (TC), triglyceride (TG), high-density lipoprotein (HDL), low density lipoprotein (LDL), calcium (Ca), phosphorus (P), serum potassium (K), serum sodium (Na), and bicarbonate.

Select the study subjects

Inclusion criteria were (1) patients with OTSCC presenting to the PLA General Hospital for the first time; (2) patients with a pathological diagnosis of OTSCC; (3) all patients had complete clinical records and follow-up data. Exclusion criteria comprised (1) patients who had a cold one week before surgery; (2) patients with other tumors; (3) patients receiving anti-tumor treatment before surgery. After applying strict inclusion and exclusion criteria, 224 patients finally met the requirements. The endpoint event of the present study was the overall survival rate (OS). The OS was defined as the interval between the date of surgery and death or the last follow-up. The last follow-up date was 1 April 2022. The flow chart of this study is shown in Fig. 1.

Fig. 1
figure 1

The flowchart for the machine learning process. Abbreviations: SHAP: SHapley Additive explanation

Full size image

Selection of clinical characteristics

With survival time and survival status as the outcome events, 18 characteristic variables with a significant correlation were selected by Cox proportional hazards model. Then, the top 8 important feature variables were selected from the 18 significantly correlated variables through LGBM, and secondary modeling was conducted through the grid search.

Model development

Predictive models were used to construct the 5-year overall survival of OTSCC patients using six machine learning methods, specifically, Logistic Regression, Support Vector machines (SVC), Decision Tree, Random Forest (RF), eXtreme Gradient Boosting (XGB), and Light Gradient Boosting Machine (LGBM).

Logic regression is an algorithm very similar to linear regression, but, in essence, the problem type treated by linear regression is not consistent with logical regression, and linear regression deals with numerical problems, while logical regression belongs to the classification algorithm [9]. Support vector machine is a 2-classification algorithm, which adopts the kernel skill based on mapping the input data to the high-dimensional feature space through the nonlinear transformation to achieve the linear separation of the high-dimensional space [10]. A Decision Tree is an example-based inductive learning algorithm that divides the disordered samples into different branches according to certain rules according to the characteristics of the samples to achieve the purpose of classification or regression [11]. Additionally, XGB, LGBM, and RF are also very commonly used algorithms in machine learning [12,13,14].

Using survival time and survival status as outcome events, the final output of the prediction model was defined as the 5-year OS of patients with OTSCC.

Statistical analysis

Taking survival time and survival status as the outcome events, six machine learning models were established after selecting significant features using Cox proportional hazards model. Through grid search and secondary modeling, the prediction performance of the six models was evaluated based on the size of the area AUC under the ROC curve, and the one corresponding to the largest AUC value was the best prediction model. The output of the optimal model was explained using the Python package (SHapley Additive exPlanations, SHAP). Two-sided P-values of < 0.05 were considered statistically significant. All statistical analyses were performed in SPSS24.0, Python3.9.7, and R 4.1.2.

Results

Patient baseline characteristics

In total, 224 OTSCC patients were included in the study. Among them, 150 patients were males (67.0%), and 74 patients (33.0%) were females. There were 136 cases (60.7%) of patients aged < 60 years, and 88 cases (39.3%) of patients aged > 60 years. Tumor size was ≤ 4 and > 4 in 193 (86.2%) and 31 (13.8%) cases, respectively. T-stage was T1, T2, and T3 in 69 (30.8%), 124 (55.4%), and 31 (13.8%) cases, respectively. N-stage was N0, N1, N2, and N3 in 129 (57.6%), 47 (21.0%), 44 (19.6%), and 4 (1.8%) cases, respectively. OTSCC classification was I, II, III, and IV in 48 (21.4%), 69 (30.8%), 12 (5.4%), and 95 (42.4%) cases, respectively. Histologic grade was I, II, and III in 103 (46.0%), 102 (45.5%), and 19 (8.5%) cases, respectively. Lymph nodes were positive in 95 (42.4%) cases and negative in 129 (57.6%) cases. The mean N was 0.58 ± 0.09, and the mean L was 0.32 ± 0.09. The mean SIRI was 1.27 ± 0.92, the mean LMR was 2.22 ± 1.54, the mean PLR was 5.16 ± 76.96, the mean SG was 1.02 ± 0.01, the mean WBC was 6.13 ± 1.86, mean FIB was 3.41 ± 0.91, mean HCY was 14.61 ± 6.50, mean albumin was 41.39 ± 3.75, and mean Na was 142.24 ± 2.67 (Table 1).

Table 1 Baseline characteristics of the 224 patients with OTSCC
Full size table

Cox proportional hazards model

Among the 51 clinical features, 18 variables were selected by Cox proportional hazards model, and p-value of each variable was less than 0.05. The 18 variables were age, tumor size, T-stage, N-stage, OTSCC classification, histologic grade, positive lymph nodes, N, L, SIRI, LMR, PLR, SG, WBC, FIB, HCY, albumin, and Na (Fig. 2).

Fig. 2
figure 2

Cox proportional hazards model. Abbreviations: SIRI: systemic inflammation response index; LMR: lymphocyte-to-monocyte; PLR: platelet-to-lymphocyte ratio; SG: urinary specific gravity; WBC: white blood cell count; FIB: plasma fibrinogen; HCY: homocysteine

Full size image

Model building

Six machine learning was performed on 18 variables to predict 5-year survival in OTSCC patients. The performance of 6 machine learning models is shown in Table 2. ROC curves under six machine learning are shown in Fig. 3. Random Forest (RF) had the maximum AUC value (AUC = 0.850), and eXtreme Gradient Boosting (XGB) and Light Gradient Boosting Machine (LGBM) had the minimum AUC value (AUC = 0.790).

Table 2 Predictive performance of the six machine learning models
Full size table
Fig. 3
figure 3

Six machine learning algorithms based on the AUC of the ROC curve. Abbreviations: AUC: Area Under the Curve; ROC: Receive Operating Characteristic

Full size image

Grid search and secondary modeling

After the grid search, the Light Gradient Boosting Machine (LGBM) model had the maximum AUC value (Fig. 4a, AUC = 0.851), exceeding the corresponding AUC value of Random Forest (RF) (AUC = 0.850). SHAP explains the results of the LGBM model by calculating the contribution of each variable to the prediction. The importance matrix plot of the LGBM model with 18 feature variables containing significant correlations is shown in Fig. 4b. The 18 feature variables were N-stage, SIRI, age, FIB, LMR, T-stage, N, positive lymph nodes, histologic grade, HCY, Na, WBC, albumin, L, tumor size, OTSCC classification, PLR, and SG.

Fig. 4
figure 4

a, b Grid Search and Secondary Modeling a LightGBM GridSearched ROC Curve of 18 Cox-features. b The importance matrix plot of the LGBM model with 18 feature variables containing significant correlations. c LightGBM GridSearched ROC Curve of Top 8 features. d The importance matrix plot of the LGBM model with top 8 feature variables containing significant correlations

Full size image

From these 18 significant correlation variables, the top 8 feature variables were selected for secondary modeling ROC curve (AUC = 0.860, Fig. 4c). The importance matrix map of the LGBM model is shown in Fig. 4d. The top 8 feature variables were N-stage, age, SIRI, positive lymph nodes, FIB, LMR, N, and T-stage.

Application of the predictive model

Figure 5a demonstrates the SHAP summary plot. Each point in each row represents the records of 224 patients with OTSCC under each feature. These features are ranked from the most important to less important order: N-stage, age, SIRI, positive lymph nodes, FIB, LMR, N, and T-stage. The N-stage is the most important feature. The higher the values of the features, the more positive the predictive effect on survival. The lower the value, the lower the contribution is.

Fig. 5
figure 5

a-c:SHAP summary plot and SHAP force plot. Abbreviations: SIRI: systemic inflammation response index; LMR: lymphocyte-to-monocyte; PLR: platelet-to-lymphocyte ratio

Full size image

Figure 5b shows the SHAP force plot. The predictive value is 0.42. The base value is the mean of the target feature variable across all records. Each band shows the effect of its characteristics in pushing the value of the target feature variable further or closer to the base value. Red stripes indicate their features pushing values to lower values. Blue stripes indicate their features pushing values to lower values. The wider the stripe, the higher the contribution (absolute value). The LMR and the FIB contributed positively to the predicted values. The N-stage is still the most important feature variable because its contribution is the largest (it has the widest strip).

Figure 5c illustrates the SHAP force plot for LGBM. The abscissa represents each patient, and the ordinate represents the SHAP value. The figure shows the SHAP values for the partial characteristics of some patients. Red indicates a positive correlation, and blue indicates a negative correlation.

Discussion

In this study, we developed a 5-year OS predictive model for OTSCC patients by building a database of 224 OTSCC patients based on 51 clinical features recorded in electronic medical records using six machine learning methods. The results showed that the 5-year overall survival of OTSCC patients was 42%. We selected the 18 features with a significant correlation (P < 0.05) from the 51 clinical features by using the Cox proportional hazards model. These 18 features were age, tumor size, T-stage, N-stage, OTSCC classification, histologic grade, positive lymph nodes, N, L, SIRI, LMR, PLR, SG, WBC, FIB, HCY, albumin, and Na. We also selected the top eight features (N-stage, age, SIRI, positive lymph nodes, FIB, LMR, N, and T-stage) from 18 features and determined the prediction model of LGBM with the maximum AUC value (AUC = 0.860) through grid search and secondary modeling. To the best of our knowledge, this was the first model to predict the 5-year overall survival of OTSCC patients using six machine learning models based on electronic medical records.

We interpreted the output of the optimal model (LGBM) using SHapley Additive exPlanations. We selected eight variables (N-stage, age, SIRI, positive lymph nodes, FIB, LMR, N, and T-stage, p < 0.05) to predict 5-year OS in patients with OTSCC. Several previous studies have identified these variables as risk factors for OTSCC patients. Muhammad Faisal et al. have shown that lymph node positivity, depth of invasion (DOI), and higher nodal ratio (LNR) were significant prognostic factors affecting OS in patients with OTSCC [15]. The study by Xiyin Guan et al. has shown significant associations of advanced age,advanced stage, N-stage, distant metastasis, and absence of surgery with all-cause and cancer-specific early mortality in patients with OTSCC [16]. Additionally, several studies have shown that serum inflammatory markers, such as LMR, NLR, and CRP, can be used as independent prognostic indicators to predict survival in OTSCC patients [17,18,19,20].

Nowadays, an increasing number of studies is using machine learning methods to build predictive models of diseases [21,22,23,24,25]. The study by Valentina L Kouznetsova et al. has shown the potential to distinguish oral cancer from periodontal disease by analyzing the metabolites of patients' saliva using machine learning methods [26]. Young Min Park et al. have demonstrated that predictive models that use clinical variables and MRI radiological features perform well in predicting disease recurrence and death in patients with oropharyngeal cancer [27]. Yi-Ju Tseng et al. have developed a machine learning-based algorithm that can provide survival risk stratification for oral cancer in advanced patients with comprehensive clinicopathological and genetic data [28]. Using a machine learning approach, Andres M Bur et al. have developed and validated a method to predict occult lymph node metastasis in clinical lymph node-negative metastatic oral squamous cell carcinoma [29].

This study had some limitations. Our study was a retrospective study involving a small sample size, which could lead to potential selection bias. Furthermore, the performance of machine learning algorithms may vary across large datasets; therefore, this study also requires validation with multicenter, large-sample datasets. Our prediction model was not verified by external datasets, and its accuracy is yet to be verified. Our study endpoint was OS, and further studies on disease-free survival should be conducted in the future.

Conclusion

We developed six machine learning models for 224 OTSCC patients, and the results showed that the 5-year overall survival of OTSCC patients was 42%. The LGBM prediction model had the maximum AUC value (AUC = 0.860). This predictive tool has potential prognostic implications for patients with OTSCC.

Availability of data and materials

Relevant data can be obtained by contacting the corresponding author.

References

  1. Lenze NR, Farquhar DR, Dorismond C, Sheth S, Zevallos JP, Blumberg J, Lumley C, Patel S, Hackman T, Weissler MC, et al. Age and risk of recurrence in oral tongue squamous cell carcinoma: Systematic review. Head Neck. 2020;42(12):3755–68.

    Article  PubMed  Google Scholar 

  2. Galli A, Bondi S, Canevari C, Tulli M, Giordano L, Di Santo D, Gianolli L, Bussi M. High-risk early-stage oral tongue squamous cell carcinoma, when free margins are not enough: Critical review. Head Neck. 2021;43(8):2510–22.

    Article  PubMed  Google Scholar 

  3. Siegel RL, Miller KD, Jemal A. Cancer statistics, 2019. CA Cancer J Clin. 2019;69(1):7–34.

    Article  PubMed  Google Scholar 

  4. Gormley M, Gray E, Richards C, Gormley A, Richmond RC, Vincent EE, Dudding T, Ness AR, Thomas SJ. An update on oral cavity cancer: epidemiological trends, prevention strategies and novel approaches in diagnosis and prognosis. Community Dent Health. 2022;39(3):197–205.

    PubMed  Google Scholar 

  5. Huang SH, O’Sullivan B. Overview of the 8th Edition TNM Classification for Head and Neck Cancer. Curr Treat Options Oncol. 2017;18(7):40.

    Article  PubMed  Google Scholar 

  6. Chen Y, Sun J, Hu D, Zhang J, Xu Y, Feng H, Chen Z, Luo Y, Lou Y, Wu H. Predictive Value of Pretreatment Lymphocyte-to-Monocyte Ratio and Platelet-to-Lymphocyte Ratio in the Survival of Nasopharyngeal Carcinoma Patients. Cancer Manag Res. 2021;13:8767–79.

    Article  PubMed  PubMed Central  Google Scholar 

  7. Chen L, Kong X, Wang Z, Wang X, Fang Y, Wang J. Pretreatment systemic inflammation response index in patients with breast cancer treated with neoadjuvant chemotherapy as a useful prognostic indicator. Cancer Manag Res. 2020;12:1543–67.

    Article  PubMed  PubMed Central  Google Scholar 

  8. Dong Z, Wang Q, Ke Y, Zhang W, Hong Q, Liu C, Liu X, Yang J, Xi Y, Shi J, et al. Prediction of 3-year risk of diabetic kidney disease using machine learning based on electronic medical records. J Transl Med. 2022;20(1):143.

    Article  PubMed  PubMed Central  Google Scholar 

  9. Baumgartner M, Falk C. Configurational Causal Modeling and Logic Regression. Multivariate Behav Res. 2023;58(2):292–310.

    Article  PubMed  Google Scholar 

  10. Heikamp K, Bajorath J. Support vector machines for drug discovery. Expert Opin Drug Discov. 2014;9(1):93–104.

    Article  PubMed  Google Scholar 

  11. Che D, Liu Q, Rasheed K, Tao X. Decision tree and ensemble learning algorithms with their applications in bioinformatics. Adv Exp Med Biol. 2011;696:191–9.

    Article  PubMed  Google Scholar 

  12. Shah AD, Bartlett JW, Carpenter J, Nicholas O, Hemingway H. Comparison of random forest and parametric imputation models for imputing missing data using MICE: a CALIBER study. Am J Epidemiol. 2014;179(6):764–74.

    Article  PubMed  PubMed Central  Google Scholar 

  13. Yan J, Xu Y, Cheng Q, Jiang S, Wang Q, Xiao Y, Ma C, Yan J, Wang X. LightGBM: accelerated genomically designed crop breeding through ensemble learning. Genome Biol. 2021;22(1):271.

    Article  PubMed  PubMed Central  Google Scholar 

  14. Karabayir I, Goldman SM, Pappu S, Akbilgic O. Gradient boosting for Parkinson’s disease diagnosis from voice recordings. BMC Med Inform Decis Mak. 2020;20(1):228.

    Article  PubMed  PubMed Central  Google Scholar 

  15. Faisal M, Dhanani R, Ullah S, Bakar MA, Irfan N, Malik KI, Loya A, Boban EM, Hussain R, Jamshed A. Prognostic outcomes of treatment naive oral tongue squamous cell carcinoma (OTSCC): a comprehensive analysis of 14 years. Eur Arch Otorhinolaryngol. 2021;278(8):3045–53.

    Article  PubMed  Google Scholar 

  16. Guan X, Li Y, Hu C. The incidence and risk factors for early death among patients with oral tongue squamous cell carcinomas. Int J Clin Pract. 2021;75(8):e14352.

    Article  PubMed  Google Scholar 

  17. Furukawa K, Kawasaki G, Naruse T, Umeda M. Prognostic significance of pretreatment lymphocyte-to-monocyte ratio in patients with tongue cancer. Anticancer Res. 2019;39(1):405–12.

    Article  PubMed  Google Scholar 

  18. Graupp M, Schaffer K, Wolf A, Vasicek S, Weiland T, Pondorfer P, Holzmeister C, Moser U, Thurnher D. C-reactive protein is an independent prognostic marker in patients with tongue carcinoma - a retrospective study. Clin Otolaryngol. 2018;43(4):1050–6.

    Article  PubMed  Google Scholar 

  19. Abbate V, Dell’Aversana Orabona G, Salzano G, Bonavolonta P, Maglitto F, Romano A, Tarabbia F, Turri-Zanoni M, Attanasi F, Di Lauro AE, et al. Pre-treatment Neutrophil-to-Lymphocyte Ratio as a predictor for occult cervical metastasis in early stage (T1–T2 cN0) squamous cell carcinoma of the oral tongue. Surg Oncol. 2018;27(3):503–7.

    Article  PubMed  Google Scholar 

  20. Wu CN, Chuang HC, Lin YT, Fang FM, Li SH, Chien CY. Prognosis of neutrophil-to-lymphocyte ratio in clinical early-stage tongue (cT1/T2N0) cancer. Onco Targets Ther. 2017;10:3917–24.

    Article  PubMed  PubMed Central  Google Scholar 

  21. Deo RC. Machine Learning in Medicine. Circulation. 2015;132(20):1920–30.

    Article  PubMed  PubMed Central  Google Scholar 

  22. Lo Vercio L, Amador K, Bannister JJ, Crites S, Gutierrez A, MacDonald ME, Moore J, Mouches P, Rajashekar D, Schimert S, Subbanna N, Tuladhar A, Wang N, Wilms M, Winder A, Forkert ND. Supervised machine learning tools: a tutorial for clinicians. J Neural Eng. 2020;17(6).

  23. Arfat Y, Mittone G, Esposito R, Cantalupo B. GM DEF, Aldinucci M: Machine learning for cardiology. Minerva Cardiol Angiol. 2022;70(1):75–91.

    Article  PubMed  Google Scholar 

  24. Handelman GS, Kok HK, Chandra RV, Razavi AH, Lee MJ, Asadi H. eDoctor: machine learning and the future of medicine. J Intern Med. 2018;284(6):603–19.

    Article  PubMed  Google Scholar 

  25. Eraslan G, Avsec Z, Gagneur J, Theis FJ. Deep learning: new computational modelling techniques for genomics. Nat Rev Genet. 2019;20(7):389–403.

    Article  PubMed  Google Scholar 

  26. Kouznetsova VL, Li J, Romm E, Tsigelny IF. Finding distinctions between oral cancer and periodontitis using saliva metabolites and machine learning. Oral Dis. 2021;27(3):484–93.

    Article  PubMed  Google Scholar 

  27. Min Park Y, Yol Lim J, Woo Koh Y, Kim SH, Chang Choi E. Prediction of treatment outcome using MRI radiomics and machine learning in oropharyngeal cancer patients after surgical treatment. Oral Oncol. 2021;122:105559.

    Article  PubMed  Google Scholar 

  28. Tseng YJ, Wang HY, Lin TW, Lu JJ, Hsieh CH, Liao CT. Development of a Machine Learning Model for Survival Risk Stratification of Patients With Advanced Oral Cancer. JAMA Netw Open. 2020;3(8):e2011768.

    Article  PubMed  PubMed Central  Google Scholar 

  29. Bur AM, Holcomb A, Goodwin S, Woodroof J, Karadaghy O, Shnayder Y, Kakarala K, Brant J, Shew M. Machine learning to predict occult nodal metastasis in early oral squamous cell carcinoma. Oral Oncol. 2019;92:20–5.

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

We are thankful to the staff and faculty of the Department of Stomatology, Chinese PLA General Hospital.

Funding

This work was supported by the National Key R&D Program of China (2020YFC2008900).

Author information

Author notes

  1. Liangbo Li and Cheng Pu contributed equally to this work.

Authors and Affiliations

  1. Medical School of Chinese PLA, Beijing, China

    Liangbo Li, Nenghao Jin & Liang Zhu

  2. Department of Stomatology, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China

    Liangbo Li, Nenghao Jin, Liang Zhu, Ye Tao & Haizhong Zhang

  3. Key Laboratory of Animal Disease and Human Health of Sichuan Province, Chengdu, China

    Cheng Pu & Yanchun Hu

  4. College of Veterinary Medicine, Sichuan Agricultural University, Sichuan, China

    Cheng Pu & Yanchun Hu

  5. Unicamillus International Meical University, Rome, Italy

    Piero Cascone

Authors
  1. Liangbo Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Cheng Pu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nenghao Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Liang Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yanchun Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Piero Cascone
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Ye Tao
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Haizhong Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Liangbo Li, contributions to design, data acquisition, analysis, and interpretation, drafted and critically revised the manuscript; Cheng Pu, contributions to design, data analysis and interpretation, critically revised the manuscript; Nenghao Jin, Liang Zhu, Yanchun Hu, contributions to conception, data acquisition, critically revised the manuscript; Piero Cascone, Ye Tao, Haizhong Zhang contributions to conception and design, data acquisition, analysis, and interpretation, critically revised the manuscript. All authors gave their final approval and agree to be accountable for all aspects of the work.

Corresponding authors

Correspondence to Ye Tao or Haizhong Zhang.

Ethics declarations

Ethics approval and consent to participate

Ethical approval was granted by the Research Ethics committee of the Chinese PLA General Hospital (S2019-016–02).All methods were carried out in accordance with relevant guidelines and regulations. All participants provided written informed consent to participate in the study.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, L., Pu, C., Jin, N. et al. Prediction of 5-year overall survival of tongue cancer based machine learning. BMC Oral Health 23, 567 (2023). https://doi.org/10.1186/s12903-023-03255-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1186/s12903-023-03255-w

Keywords

BMC Oral Health

ISSN: 1472-6831

Contact us