Locoregional recurrences and distant metastases are major problems for patients with squamous cell carcinoma of the head and neck (SCCHN). Because SCCHN is a heterogeneous group of tumours with varying characteristics, the present study concentrated on the subgroup of squamous cell carcinoma of the oral tongue (SCCOT) to investigate the use of machine learning approaches to predict the risk of recurrence from routine clinical data available at diagnosis. The approach also identified the most important parameters that identify and classify recurrence risk. A total of 66 patients with SCCOT were included. Clinical data available at diagnosis were analysed using statistical analysis and machine learning approaches. Tumour recurrence was associated with T stage (P=0.001), radiological neck metastasis (P=0.010) and diabetes (P=0.003). A machine learning model based on the random forest algorithm and with attendant explainability was used. Whilst patients with diabetes were overrepresented in the SCCOT cohort, diabetics had lower recurrence rates (P=0.015 after adjusting for age and other clinical features) and an improved 2-year survival (P=0.025) compared with non-diabetics. Clinical, radiological and histological data available at diagnosis were used to establish a prognostic model for patients with SCCOT. Using machine learning to predict recurrence produced a classification model with 71.2% accuracy. Notably, one of the findings of the feature importance rankings of the model was that diabetics exhibited less recurrence and improved survival compared with non-diabetics, even after accounting for the independent prognostic variables of tumour size and patient age at diagnosis. These data imply that the therapeutic manipulation of glucose levels used to treat diabetes may be useful for patients with SCCOT regardless of their diabetic status. Further studies are warranted to investigate the impact of diabetes in other SCCHN subtypes.

Department of Medical Biosciences Pathology Umeå University SE 901 85 Umeå Sweden

Department of Oral and Maxillo Facial Surgery Mater Dei Hospital 1 70125 Bari Italy

Research Centre for Applied Molecular Oncology Masaryk Memorial Cancer Institute Brno 656 53 Czech Republic

Zobrazit více v PubMed

Shah JP, Gil Z. Current concepts in management of oral cancer-surgery. Oral Oncol. 2009;45:394–401. doi: 10.1016/j.oraloncology.2008.05.017. PubMed DOI PMC

Marur S, Forastiere AA. Head and neck cancer: Changing epidemiology, diagnosis, and treatment. Mayo Clin Proc. 2008;83:489–501. doi: 10.4065/83.4.489. PubMed DOI

Lacy PD, Piccirillo JF, Merritt MG, Zequeira MR. Head and neck squamous cell carcinoma: Better to be young. Otolaryngol Head Neck Surg. 2000;122:253–258. doi: 10.1016/S0194-5998(00)70249-X. PubMed DOI

Bøje CR. Impact of comorbidity on treatment outcome in head and neck squamous cell carcinoma-a systematic review. Radiother Oncol. 2014;110:81–90. doi: 10.1016/j.radonc.2013.07.005. PubMed DOI

Bradford CR, Ferlito A, Devaney KO, Mäkitie AA, Rinaldo A. Prognostic factors in laryngeal squamous cell carcinoma. Laryngoscope Investig Otolaryngol. 2020;5:74–81. doi: 10.1002/lio2.353. PubMed DOI PMC

Huang Y, Xiao X, Sadeghi F, Feychting M, Hammar N, Fang F, Zhang Z, Liu Q. Blood metabolic biomarkers and the risk of head and neck cancer: An epidemiological study in the Swedish AMORIS Cohort. Cancer Lett. 2023;557:216091. doi: 10.1016/j.canlet.2023.216091. PubMed DOI

Gu X, Wang L, Coates PJ, Boldrup L, Fahraeus R, Wilms T, Norberg-Spaak L, Sgaramella N, Nylander K. Transfer-RNA-derived fragments are potential prognostic factors in patients with squamous cell carcinoma of the head and neck. Genes (Basel) 2020;11:1344. doi: 10.3390/genes11111344. PubMed DOI PMC

Gu X, Wang L, Boldrup L, Coates P, Fahraeus R, Sgaramella N, Wilms T, Nylander K. AP001056.1, A prognosis-related enhancer RNA in squamous cell carcinoma of the head and neck. Cancers (Basel) 2019;11:347. doi: 10.3390/cancers11030347. PubMed DOI PMC

Warner GC, Reis PP, Jurisica I, Sultan M, Arora S, Macmillan C, Makitie AA, Grénman R, Reid N, Sukhai M, et al. Molecular classification of oral cancer by cDNA microarrays identifies overexpressed genes correlated with nodal metastasis. Int J Cancer. 2004;110:857–868. doi: 10.1002/ijc.20197. PubMed DOI

Zhang F, Liu Y, Yang Y, Yang K. Development and validation of a fourteen-innate immunity-related gene pairs signature for predicting prognosis head and neck squamous cell carcinoma. BMC Cancer. 2020;20:1015. doi: 10.1186/s12885-020-07489-7. PubMed DOI PMC

Zhou RS, Zhang EX, Sun QF, Ye ZJ, Liu JW, Zhou DH, Tang Y. Integrated analysis of lncRNA-miRNA-mRNA ceRNA network in squamous cell carcinoma of tongue. BMC Cancer. 2019;19:779. doi: 10.1186/s12885-019-5983-8. PubMed DOI PMC

Sgaramella N, Gu X, Boldrup L, Coates PJ, Fåhraeus R, Califano L, Tartaro G, Colella G, Spaak LN, Strom A, et al. Searching for new targets and treatments in the battle against squamous cell carcinoma of the head and neck, with specific focus on tumours of the tongue. Curr Top Med Chem. 2018;18:214–218. doi: 10.2174/1568026618666180116121624. PubMed DOI

Brandwein-Gensler M, Teixeira MS, Lewis CM, Lee B, Rolnitzky L, Hille JJ, Genden E, Urken ML, Wang BY. Oral squamous cell carcinoma histologic risk assessment, but not margin status, is strongly predictive of local disease-free and overall survival. Am J Surg Pathol. 2005;29:167–178. doi: 10.1097/01.pas.0000149687.90710.21. PubMed DOI

Svetnik V, Liaw A, Tong C, Culberson JC, Sheridan RP, Feuston BP. Random forest: A classification and regression tool for compound classification and QSAR modeling. J Chem Inf Comput Sci. 2003;43:1947–1958. doi: 10.1021/ci034160g. PubMed DOI

Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, et al. Scikit-learn: Machine learning in python. J Mach Learn Res. 2011;12:2825–2830.

Alabi RO, Elmusrati M, Sawazaki-Calone I, Kowalski LP, Haglund C, Coletta RD, Mäkitie AA, Salo T, Almangush A, Leivo L. Comparison of supervised machine learning classification techniques in prediction of locoregional recurrences in early oral tongue cancer. Int J Med Inform. 2020;136:104068. doi: 10.1016/j.ijmedinf.2019.104068. PubMed DOI

Alabi RO, Elmusrati M, Leivo I, Almangush A, Mäkitie AA. Machine learning explainability in nasopharyngeal cancer survival using LIME and SHAP. Sci Rep. 2023;13:8984. doi: 10.1038/s41598-023-35795-0. PubMed DOI PMC

Alabi RO, Almangush A, Elmusrati M, Leivo I, Mäkitie A. Measuring the usability and quality of explanations of a machine learning web-based tool for oral tongue cancer prognostication. Int J Environ Res Public Health. 2022;19:8366. doi: 10.3390/ijerph19148366. PubMed DOI PMC

Alabi RO, Almangush A, Elmusrati M, Mäkitie AA. Deep machine learning for oral cancer: From precise diagnosis to precision medicine. Front Oral Health. 2022;2:794248. doi: 10.3389/froh.2021.794248. PubMed DOI PMC

Giovannucci E, Harlan DM, Archer MC, Bergenstal RM, Gapstur SM, Habel LA, Pollak M, Regensteiner JG, Yee D. Diabetes and cancer, a consensus report. Diabetes Care. 2010;33:1674–1685. doi: 10.2337/dc10-0666. PubMed DOI PMC

Wojciechowska J, Krajewski W, Bolanowski M, Kręcicki T, Zatoński T. Diabetes and cancer: A review of current knowledge. Exp Clin Endocrinol Diabetes. 2016;124:263–275. doi: 10.1055/s-0042-100910. PubMed DOI

Hadad SM, Coates P, Jordan LB, Dowling RJ, Chang MC, Done SJ, Purdie CA, Goodwin PJ, Stambolic V, Moulder-Thompson S, et al. Evidence for biological effects of metformin in operable breast cancer: Biomarker analysis in a pre-operative window of opportunity randomized trial. Breast Cancer Res Treat. 2015;150:149–155. doi: 10.1007/s10549-015-3307-5. PubMed DOI

Noto H, Goto A, Tsujimoto T, Noda M. Cancer risk in diabetic patients treated with metformin: A systematic review and meta-analysis. PLoS One. 2012;7:e33411. doi: 10.1371/journal.pone.0033411. PubMed DOI PMC

Dickerman BA, García-Albéniz X, Logan RW, Denaxas S, Hernán MA. Evaluating metformin strategies for cancer prevention: A target trial emulation using electronic health records. Epidemiology. 2023;34:690–699. doi: 10.1097/EDE.0000000000001626. PubMed DOI PMC

Hu X, Xiong H, Chen W, Huang L, Mao T, Yang L, Wang C, Huang D, Wang Z, Yu J, et al. Metformin reduces the increased risk of oral squamous cell carcinoma recurrence in patients with type 2 diabetes mellitus: A cohort study with propensity score analyses. Surg Oncol. 2020;35:453–459. doi: 10.1016/j.suronc.2020.09.023. PubMed DOI

Gutkind JS, Molinolo AA, Wu X, Wang Z, Nachmanson D, Harismendy O, Alexandrov LB, Wuertz BR, Ondrey FG, Laronde D, et al. Inhibition of mTOR signaling and clinical activity of metformin in oral premalignant lesions. JCI Insight. 2021;6:e147096. doi: 10.1172/jci.insight.147096. PubMed DOI PMC

Lee DJ, McMullen CP, Foreman A, Huang SH, Lu L, Xu W, de Almeida JR, Liu G, Bratman SV, Goldstein DP. Impact of metformin on disease control and survival in patients with head and neck cancer: A retrospective cohort study. J Otolaryngol Head Neck Surg. 2019;48:34. doi: 10.1186/s40463-019-0348-5. PubMed DOI PMC

Barrea L, Caprio M, Tuccinardi D, Moriconi E, Di Renzo L, Muscogiuri G, Colao A, Savastano S. Could ketogenic diet ‘starve’ cancer? Emerging evidence. Crit Rev Food Sci Nutr. 2022;62:1800–1821. doi: 10.1080/10408398.2020.1847030. PubMed DOI

Marcucci F, Rumio C. Glycolysis-induced drug resistance in tumors-A response to danger signals? Neoplasia. 2021;23:234–245. doi: 10.1016/j.neo.2020.12.009. PubMed DOI PMC

Spanier G, Ugele I, Nieberle F, Symeou L, Schmidhofer S, Brand A, Meier J, Spoerl S, Krupar R, Rümmele P, et al. The predictive power of CD3+ T cell infiltration of oral squamous cell tumors is limited to non-diabetic patients. Cancer Lett. 2021;499:209–219. doi: 10.1016/j.canlet.2020.11.029. PubMed DOI

Lundqvist L, Stenlund SH, Laurell G, Nylander K. The importance of stromal inflammation in squamous cell carcinoma of the tongue. J Oral Pathol Med. 2012;41:379–383. doi: 10.1111/j.1600-0714.2011.01107.x. PubMed DOI