Extreme gradient boosting machine learning method for predicting medical treatment in patients with acute bronchiolitis

• Autorzy: Mateo J. , Rius-Peris J.M. , Maraña-Pérez A.I. , Valiente-Armero A. , Torres A.M.

Identyfikatory

DOI

10.1016/j.bbe.2021.04.015

• Języki publikacji: EN

Abstrakty

EN

Acute bronchiolitis is the most common lower respiratory tract infection of infancy. About 2% of infants under 12 months of age hospitalized with this condition each epidemic season. The choice of the correct treatment is important for the evolution of the disease. Therefore, a prediction model for medical treatment identification based on extreme gradient boosting (XGB) machine learning (ML) method is proposed in this paper. Four supervised machine learning algorithms including a k-nearest neighbours (KNN), decision tree (DT), Gaussian Naı¨ve Bayes (GNB) and support vector machine (SVM) were compared with the proposed XGB method. The performance of these methods was then tested implementing a standard 10-fold cross-validation process. The results indicate that the XGB has the best prediction accuracy (94%), high precision (>0.94) and high recall (>0.94). The KNN, SVM, and DT approaches also present moderate prediction accuracy (>87), moderate specificity (>0.87) and moderate sensitivity (>0.87). The GNB algorithm show relatively low classification performance. Based on these results for classification performance and prediction accuracy, the XGB is a solid candidate for a correct classification of patients to be treated. These findings suggest that XGB systems trained with clinical data may serve as a new tool to assist in the treatment of patients with acute bronchiolitis.

Słowa kluczowe

EN

bronchiolitis; medical treatment; machine learning; extreme gradient boosting

PL

oskrzeliki; leczenie medyczne; uczenie maszynowe

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2021
• Tom: Vol. 41, no. 2
• Strony: 792--801
• Opis fizyczny: Bibliogr. 52 poz., rys., tab., wykr.

Twórcy

autor

Mateo J.

• Neurobiological Research Group, Institute of Technology, Universidad de Castilla-La Mancha, Cuenca, Spain

autor

Rius-Peris J.M.

• Neurobiological Research Group, Institute of Technology, Universidad de Castilla-La Mancha, Cuenca, Spain; Clinical Pediatric Service, Virgen de la Luz Hospital, Cuenca, Spain

autor

Maraña-Pérez A.I.

• Neurobiological Research Group, Institute of Technology, Universidad de Castilla-La Mancha, Cuenca, Spain; Clinical Pediatric Service, Virgen de la Luz Hospital, Cuenca, Spain

autor

Valiente-Armero A.

• Neurobiological Research Group, Institute of Technology, Universidad de Castilla-La Mancha, Cuenca, Spain; Clinical Pediatric Service, Virgen de la Luz Hospital, Cuenca, Spain

autor

Torres A.M.

• Neurobiological Research Group, Institute of Technology, Universidad de Castilla-La Mancha, Cuenca, Spain

Bibliografia

• [1] Florin TA, Plint AC, Zorc JJ. Lancet 2017;389:211–24.
• [2] Hall CB et al. New Engl J Med 2009;360:588–98.
• [3] Friedman JN, Rieder MJ, Walton JM, Society CP, Committee AC, Therapy D, et al. Paediatr Child Health 2014;19:485–98.
• [4] Ralston SL et al. Pediatrics 2014;134:e1474–1502.
• [5] Meissner HC. New Engl J Med 2016;374:62–72.
• [6] Cebey-López M, et al. PLoS One 2016;11:e0146599.
• [7] Farley R, Spurling GK, Eriksson L, Del Mar CB. Cochrane Database Syst Rev 2014:10.
• [8] Akenroye AT, Baskin MN, Samnaliev M, Stack AM. Pediatrics 2014;133:e227–34.
• [9] Goossens H et al. Lancet 2005;365:579–87.
• [10] Chen I-L, Huang H-C, Chang Y-H, Huang H-Y, Yeh W-J, Wu TY, Suen J-L, Yang S-N, Hung C-H. Scientific Rep 2018;8:1–7.
• [11] Breakell R, Thorndyke B, Clennett J, Harkensee C. Eur J Pediatr 2018;177:47–51.
• [12] Oakley E, Brys T, Borland M, Neutze J, Phillips N, Krieser Dea. Emerg Med Australas 2018;30:389–97.
• [13] Macias CG, Mansbach JM, Fisher ES, Riederer M, Piedra PA, Sullivan AF, Espinola JA, Camargo Jr CA. Acad Pediatr 2015;15:69–76.
• [14] Mansbach JM, Clark S, Christopher NC, LoVecchio F, Kunz S, Acholonu U, Camargo CA. Pediatrics 2008;121:680–8.
• [15] Bennett TD, Callahan TJ, Feinstein JA, Ghosh D, Lakhani SA, Spaeder MC, Szefler SJ, Kahn MG. J Pediatr 2019;208:12–22.
• [16] Azevedo A. Data mining and knowledge discovery in databases. In Advanced Methodologies and Technologies in Network Architecture, Mobile Computing, and Data Analytics; 2019.
• [17] Ramirez-Bautista JA, Huerta-Ruelas JA, Kóczy LT, Hatwágner MF, Chaparro-Cárdenas SL, Hernández-Zavala A. Biocybern Biomed Eng 2020;40:404–14.
• [18] George ST, Subathra M, Sairamya N, Susmitha L, Premkumar MJ. Biocybern Biomed Eng 2020.
• [19] Kumar I, Bhadauria H, Virmani J, Thakur S. Biocybern Biomed Eng 2017;37:217–28.
• [20] Han J, Pei J, Kamber M. Data mining: concepts and techniques. Third Edition 2016.
• [21] Tuncer T, Dogan S, Acharya UR. Biocybern Biomed Eng 2020;40:211–20.
• [22] Aggarwal Y, Das J, Mazumder PM, Kumar R, Sinha RK. Biocybern Biomed Eng 2020.
• [23] Zhang S, Li X, Zong M, Zhu X, Wang R. IEEE Trans Neural Networks Learn Syst 2017;29:1774–85.
• [24] Geethanjali ASP. IEEE Access 2016;4:7716–27.
• [25] Wang Y, Xia S, Tang Q, Wu J, Zhu X. IEEE Trans Neural Networks Learn Syst 2018;29:3510–23.
• [26] Subudhi A, Dash M, Sabut S. Biocybern Biomed Eng 2020;40:277–89.
• [27] Zhang Z, Song Y, Cui H, Wu J, Schwartz F, Qi H. IEEE Trans Biomed Eng 2017;64:2288–99.
• [28] Xiao F, Wang Y, He L, Wang H, Li W, Liu Z. IEEE Access 2019;7:13121–34.
• [29] Chen T, Guestrin C. Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd acm SIGKDD international conference on knowledge discovery and data mining.
• [30] Chang W, Liu Y, Wu X, Xiao Y, Zhou S, Cao W. IEEE Access 2019;7:175248–58.
• [31] McConnochie KM. Am J Diseases Children 1983;137:11–3.
• [32] Chen W, Fu K, Zuo J, Zheng X, Huang T, Ren W. IET Radar Sonar Navigation 2017;11:1203–7.
• [33] He T. XGBoost eXtreme Gradient Boosting.
• [34] Yu S, Li X, Zhang X, Wang H. IEEE Access 2019;7:118931–42.
• [35] Zhou X, Obuchowski NA, McClish DK. Statistical methods in diagnostic medicine. 2nd ed. John Wiley and Sons; 2011.
• [36] Bailhache M, Bloudeau E, Richer O, Pillet P, Lagarde M. Acta Paediatr 2018;107:538–9.
• [37] Ferronato  E, Gilio AE, Ferraro AA, Paulis Md, Vieira SE. Clinics 2012;67:1001–6.
• [38] Patra S, Singh V, Pemde HK, Chandra J. Ital J Pediatr 2011;37:40.
• [39] Chong S-L, Liu N, Barbier S, Ong MEH. BMC Med Res Methodol 2015;15:22.
• [40] Patel SJ, Chamberlain DB, Chamberlain JM. Acad Emerg Med 2018;25:1463–70.
• [41] Goto T, Camargo CA, Faridi MK, Freishtat RJ, Hasegawa K. JAMA Network Open 2019;2:e186937–e186937.
• [42] Wellner B, Grand J, Canzone E, Coarr M, Brady PW, Simmons J, Kirkendall E, Dean N, Kleinman M, Sylvester P. JMIR Med Inf 2017;5 e45.
• [43] Ma B, Meng F, Yan G, Yan H, Chai B, Song F. Comput Biol Med 2020 103761.
• [44] Torlay L, Perrone Bertolotti M, Thomas E, Baciu M. Brain Inf 2017;4:159–69.
• [45] Ogunleye AA, Qing-Guo W. IEEE/ACM Trans Comput Biol Bioinf 2019.
• [46] Sodmann P, Vollmer M, Nath N, Kaderali L. Physiol Meas 2018;39 104005.
• [47] Shi H, Wang H, Huang Y, Zhao L, Qin C, Liu C. Comput Methods Programs Biomed 2019;171:1–10.
• [48] Ye C et al. J Med Internet Res 2018;20 e22.
• [49] Yu B, Qiu W, Chen C, Ma A, Jiang J, Zhou H, Ma Q. Bioinformatics 2020;36:1074–81.
• [50] Zhong J, Sun Y, Peng W, Xie M, Yang J, Tang X. IEEE Trans NanoBiosci 2018;17:243–50.
• [51] Kumar S, Mankame DP. Biocybern Biomed Eng 2020;40:1190–204.
• [52] Jain G, Mittal D, Thakur D, Mittal MK. Biocybern Biomed Eng 2020;40:1391–405.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).