Decision making on the treatment of vestibular schwannoma (VS) is mainly based on the symptoms, tumor size, patient's preference, and experience of the medical team. Here we provide objective tools to support the decision process by answering two questions: can a single checkup predict the need of active treatment?, and which attributes of VS development are important in decision making on active treatment? Using a machine-learning analysis of medical records of 93 patients, the objectives were addressed using two classification tasks: a time-independent case-based reasoning (CBR), where each medical record was treated as independent, and a personalized dynamic analysis (PDA), during which we analyzed the individual development of each patient's state in time. Using the CBR method we found that Koos classification of tumor size, speech reception threshold, and pure tone audiometry, collectively predict the need for active treatment with approximately 90% accuracy; in the PDA task, only the increase of Koos classification and VS size were sufficient. Our results indicate that VS treatment may be reliably predicted using only a small set of basic parameters, even without the knowledge of individual development, which may help to simplify VS treatment strategies, reduce the number of examinations, and increase cause effectiveness.

Department of Auditory Neuroscience Institute of Experimental Medicine Czech Academy of Sciences Prague Czech Republic

Department of Cognitive Systems and Neurosciences Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Jugoslávských partyzánů 1580 3 160 00 Prague 6 Czech Republic

Department of Otorhinolaryngology 3rd Faculty of Medicine University Hospital Královské Vinohrady Charles University Prague Prague Czech Republic

Department of Otorhinolaryngology and Head and Neck Surgery 1st Faculty of Medicine University Hospital Motol Charles University Prague Prague Czech Republic

Faculty of Management Prague University of Economics and Business Jindrichuv Hradec Czech Republic

Zobrazit více v PubMed

Springborg JB, Poulsgaard L, Thomsen J. Nonvestibular schwannoma tumors in the cerebellopontine angle: A structured approach and management guidelines. Skull Base. 2008;18:217–227. doi: 10.1055/s-2007-1016959. PubMed DOI PMC

Halliday J, Rutherford SA, McCabe MG, Evans DG. An update on the diagnosis and treatment of vestibular schwannoma. Expert Rev. Neurother. 2018;18:29–39. doi: 10.1080/14737175.2018.1399795. PubMed DOI

Lee JD, Lee BD, Hwang SC. Vestibular schwannoma in patients with sudden sensorineural hearing loss. Skull Base. 2011;21:75–78. doi: 10.1055/s-0030-1261257. PubMed DOI PMC

Chovanec M, et al. Does attempt at hearing preservation microsurgery of vestibular schwannoma affect postoperative tinnitus? BioMed Res. Int. 2015;2015:783169. doi: 10.1155/2015/783169. PubMed DOI PMC

Čada Z, et al. Vertigo perception and quality of life in patients after surgical treatment of vestibular schwannoma with pretreatment prehabituation by chemical vestibular ablation. BioMed Res. Int. 2016;2016:11. doi: 10.1155/2016/6767216. PubMed DOI PMC

Betka J, et al. Complications of microsurgery of vestibular schwannoma. BioMed Res. Int. 2014;2014:315952. doi: 10.1155/2014/315952. PubMed DOI PMC

Darrouzet V, Martel J, Enée V, Bébéar J-P, Guérin J. Vestibular schwannoma surgery outcomes: Our multidisciplinary experience in 400 cases over 17 years. Laryngoscope. 2004;114:681–688. doi: 10.1097/00005537-200404000-00016. PubMed DOI

Starnoni D, et al. Surgical management for large vestibular schwannomas: A systematic review, meta-analysis, and consensus statement on behalf of the EANS skull base section. Acta Neurochir. (Wien) 2020;162:2595–2617. doi: 10.1007/s00701-020-04491-7. PubMed DOI PMC

Prasad SC, et al. Decision making in the wait-and-scan approach for vestibular schwannomas: Is there a price to pay in terms of hearing, facial nerve, and overall outcomes? Neurosurgery. 2018;83:858–870. doi: 10.1093/neuros/nyx568. PubMed DOI

Cha D, Shin SH, Kim SH, Choi JY, Moon IS. Machine learning approach for prediction of hearing preservation in vestibular schwannoma surgery. Sci. Rep. 2020;10:7136. doi: 10.1038/s41598-020-64175-1. PubMed DOI PMC

Fayyad U, Piatetsky-Shapiro G, Smyth P. From data mining to knowledge discovery in databases. AI Mag. 1996;17:37–37.

Chen M-S, Han J, Yu PS. Data mining: An overview from a database perspective. IEEE Trans. Knowl. Data Eng. 1996;8:866–883. doi: 10.1109/69.553155. DOI

Patel H, Prajapati P. Study and analysis of decision tree based classification algorithms. Int. J. Comput. Sci. Eng. 2018;6:74–78.

Quinlan JR. Induction of decision trees. Mach. Learn. 1986;1:81–106.

Sharma H, Kumar S. A survey on decision tree algorithms of classification in data mining. Int. J. Sci. Res. IJSR. 2016;5:2094.

Jin, X., Xu, A., Bie, R. & Guo, P. Machine learning techniques and chi-square feature selection for cancer classification using SAGE gene expression profiles. in Data Mining for Biomedical Applications (eds. Li, J., Yang, Q. & Tan, A.-H.) 106–115. 10.1007/11691730_11 (Springer, 2006).

Ren Q, Cheng H, Han H. Research on machine learning framework based on random forest algorithm. AIP Conf. Proc. 2017;1820:080020. doi: 10.1063/1.4977376. DOI

Tin Kam Ho. Random decision forests. in Proceedings of 3rd International Conference on Document Analysis and Recognition. Vol. 1. 278–282 (1995).

Laber E, Murtinho L. Minimization of Gini impurity: NP-completeness and approximation algorithm via connections with the k-means problem. Electron. Notes Theor. Comput. Sci. 2019;346:567–576. doi: 10.1016/j.entcs.2019.08.050. DOI

Raileanu L, Stoffel K. Theoretical comparison between the Gini index and information gain criteria. Ann. Math. Artif. Intell. 2004;41:77–93. doi: 10.1023/B:AMAI.0000018580.96245.c6. DOI

Natekin A, Knoll A. Gradient boosting machines, a tutorial. Front. Neurorobot. 2013;7:11. doi: 10.3389/fnbot.2013.00021. PubMed DOI PMC

Zhang Z, Zhao Y, Canes A, Steinberg D, Lyashevska O. Predictive analytics with gradient boosting in clinical medicine. Ann. Transl. Med. 2019;7:7. doi: 10.21037/atm.2018.12.26. PubMed DOI PMC

Levy JJ, O’Malley AJ. Don’t dismiss logistic regression: The case for sensible extraction of interactions in the era of machine learning. BMC Med. Res. Methodol. 2020;20:1–15. doi: 10.1186/s12874-020-01046-3. PubMed DOI PMC

Menard, S. W. Logistic Regression: From Introductory to Advanced Concepts and Applications. (SAGE, 2010).

Peng J, Lee K, Ingersoll G. An introduction to logistic regression analysis and reporting. J. Educ. Res. 2002;96:3–14. doi: 10.1080/00220670209598786. DOI

Draper, N. R. & Smith, H. Applied Regression Analysis. (Wiley-Interscience, 1998).

Chordia T, Goyal A, Tong Q. Pairwise correlations. SSRN Electron. J. 2011 doi: 10.2139/ssrn.1785390. DOI

Meng J, et al. Prognostic value of an immunohistochemical signature in patients with esophageal squamous cell carcinoma undergoing radical esophagectomy. Mol. Oncol. 2017;12:196. doi: 10.1002/1878-0261.12158. PubMed DOI PMC

Muthukrishnan, R. & Rohini, R. LASSO: A feature selection technique in predictive modeling for machine learning. in 2016 IEEE International Conference on Advances in Computer Applications (ICACA). 18–20. 10.1109/ICACA.2016.7887916 (2016).

Battineni G, Chintalapudi N, Amenta F. Machine learning in medicine: Performance calculation of dementia prediction by support vector machines (SVM) Inform. Med. Unlocked. 2019;16:100200. doi: 10.1016/j.imu.2019.100200. DOI

Cervantes J, Garcia-Lamont F, Rodríguez-Mazahua L, Lopez A. A comprehensive survey on support vector machine classification: Applications, challenges and trends. Neurocomputing. 2020;408:189–215. doi: 10.1016/j.neucom.2019.10.118. DOI

Cortes C, Vapnik V. Support-vector networks. Mach. Learn. 1995;20:273–297.

Amato F, et al. Artificial neural networks in medical diagnosis. J. Appl. Biomed. 2013;11:47–58. doi: 10.2478/v10136-012-0031-x. DOI

Shahid N, Rappon T, Berta W. Applications of artificial neural networks in health care organizational decision-making: A scoping review. PLoS ONE. 2019;14:e212356. PubMed PMC

Hajian-Tilaki K. Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation. Casp. J. Intern. Med. 2013;4:627–635. PubMed PMC

ZouKelly H, James OA, Laura M. Receiver-operating characteristic analysis for evaluating diagnostic tests and predictive models. Circulation. 2007;115:654–657. doi: 10.1161/CIRCULATIONAHA.105.594929. PubMed DOI

Ebenuwa SH, Sharif MS, Alazab M, Al-Nemrat A. Variance ranking attributes selection techniques for binary classification problem in imbalance data. IEEE Access. 2019;7:24649–24666. doi: 10.1109/ACCESS.2019.2899578. DOI

Beenstock M. Predicting the stability and growth of acoustic neuromas. Otol. Neurotol. 2002;23:542–549. doi: 10.1097/00129492-200207000-00025. PubMed DOI

Artz JCJM, Timmer FCA, Mulder JJS, Cremers CWRJ, Graamans K. Predictors of future growth of sporadic vestibular schwannomas obtained by history and radiologic assessment of the tumor. Eur. Arch. Otorhinolaryngol. 2009;266:641–646. doi: 10.1007/s00405-008-0791-9. PubMed DOI

Malhotra PS, et al. Clinical, radiographic, and audiometric predictors in conservative management of vestibular schwannoma. Otol. Neurotol. 2009;30:507–514. doi: 10.1097/MAO.0b013e31819d3465. PubMed DOI

Agrawal Y, Clark JH, Limb CJ, Niparko JK, Francis HW. Predictors of vestibular schwannoma growth and clinical implications. Otol. Neurotol. 2010;31:807–812. doi: 10.1097/MAO.0b013e3181de46ae. PubMed DOI

Timmer FCA, et al. Prediction of vestibular schwannoma growth: A novel rule based on clinical symptomatology. Ann. Otol. Rhinol. Laryngol. 2011;120:807–813. doi: 10.1177/000348941112001206. PubMed DOI

Jethanamest D, et al. Conservative management of vestibular schwannoma: Predictors of growth and hearing. Laryngoscope. 2015;125:2163–2168. doi: 10.1002/lary.25159. PubMed DOI

Hunter JB, et al. Single institutional experience with observing 564 vestibular schwannomas: Factors associated with tumor growth. Otol. Neurotol. 2016;37:1630–1636. doi: 10.1097/MAO.0000000000001219. PubMed DOI PMC

D’Haese S, et al. Vestibular schwannoma: Natural growth and possible predictive factors. Acta Otolaryngol. (Stockh.) 2019;139:753–758. doi: 10.1080/00016489.2019.1635268. PubMed DOI

Fieux M, et al. MRI monitoring of small and medium-sized vestibular schwannomas: Predictors of growth. Acta Otolaryngol. (Stockh.) 2020;140:361–365. doi: 10.1080/00016489.2020.1717608. PubMed DOI

Kleijwegt M, Bettink F, Malessy M, Putter H, Vandermey A. Clinical predictors leading to change of initial conservative treatment of 836 vestibular schwannomas. J. Neurol. Surg. Part B Skull Base. 2020;81:15–21. doi: 10.1055/s-0039-1678708. PubMed DOI PMC

Hentschel MA, et al. Development of a model to predict vestibular schwannoma growth: An opportunity to introduce new wait and scan strategies. Clin. Otolaryngol. 2021;46:273–283. doi: 10.1111/coa.13661. PubMed DOI PMC

Herwadker A, Vokurka EA, Evans DGR, Ramsden RT, Jackson A. Size and growth rate of sporadic vestibular schwannoma: Predictive value of information available at presentation. Otol. Neurotol. 2005;26:86–92. doi: 10.1097/00129492-200501000-00015. PubMed DOI

Wolbers JG, et al. Identifying at diagnosis the vestibular schwannomas at low risk of growth in a long-term retrospective cohort. Clin. Otolaryngol. 2016;41:788–792. doi: 10.1111/coa.12661. PubMed DOI

Bellman, R. E. Dynamic Programming. (Princeton University Press, 1957).

Keogh, E. & Mueen, A. Curse of dimensionality. in Encyclopedia of Machine Learning and Data Mining (eds. Sammut, C. & Webb, G. I.) 314–315. 10.1007/978-1-4899-7687-1_192 (Springer, 2017).

Venkat, N. The Curse of Dimensionality: Inside Out. 10.13140/RG.2.2.29631.36006 (2018).

Verleysen, M. & François, D. The curse of dimensionality in data mining and time series prediction. in Computational Intelligence and Bioinspired Systems (eds. Cabestany, J., Prieto, A. & Sandoval, F.) Vol. 3512. 758–770 (Springer, 2005).

LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436–444. doi: 10.1038/nature14539. PubMed DOI