Download PDF
Eur J Pediatr Surg 2021; 31(05): 414-419
DOI: 10.1055/s-0040-1715655
Original Article

Application of Machine Learning Techniques for Enuresis Prediction in Children

Baran Tokar 
1   Department of Pediatric Surgery, School of Medicine, Eskisehir Osmangazi University, Eskisehir, Turkey
,
Mukaddes Baskaya
2   Department of Pediatric Nursing, Eskisehir Osmangazi University, Eskisehir, Turkey
,
Ozer Celik
3   Department of Mathematics–Computer, Eskisehir Osmangazi University, Eskisehir, Turkey
,
Fatih Cemrek
4   Department of Statistics, Eskisehir Osmangazi University, Eskisehir, Turkey
,
Ayfer Acikgoz
2   Department of Pediatric Nursing, Eskisehir Osmangazi University, Eskisehir, Turkey
› Author Affiliations
› Further Information
Also available at
    Permissions and Reprints

Abstract

Introduction As a subset of artificial intelligence, machine learning techniques (MLTs) may evaluate very large and raw datasets. In this study, the aim is to establish a model by MLT for the prediction of enuresis in children.

Materials and Methods The study included 8,071 elementary school students. A total of 704 children had enuresis. For analysis of data with MLT, another group including 704 nonenuretic children was structured with stratified sampling. Out of 34 independent variables, 14 with high feature values significantly affecting enuresis were selected. A model of estimation was created by training the data.

Results Fourteen independent variables in order of feature importance value were starting age of toilet training, having urinary urgency, holding maneuvers to prevent voiding, frequency of defecation, history of enuresis in mother and father, having child's own room, parent's education level, history of enuresis in siblings, consanguineous marriage, incomplete bladder emptying, frequent voiding, gender, history of urinary tract infection, and surgery in the past. The best MLT algorithm for the prediction of enuresis was determined as logistic regression algorithm. The total accuracy rate of the model in prediction was 81.3%.

Conclusion MLT might provide a faster and easier evaluation process for studies on enuresis with a large dataset. The model in this study may suggest that selected variables with high feature values could be preferred with priority in any screening studies for enuresis. MLT may prevent clinical errors due to human cognitive biases and may help the physicians to be proactive in diagnosis and treatment of enuresis.

Keywords

enuresis - artificial intelligence - machine learning techniques - children - urinary incontinence


Publication History

Received: 18 February 2020

Accepted: 01 July 2020

Article published online:
20 August 2020

© 2020. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 

  • References

  • 1 Nørgaard JP, Djurhuus JC, Watanabe H, Stenberg A, Lettgen B. Experience and current status of research into the pathophysiology of nocturnal enuresis. Br J Urol 1997; 79 (06) 825-835
    CrossrefPubMedSearch in Google Scholar
  • 2 Caldwell PH, Edgar D, Hodson E, Craig JC. 4. Bedwetting and toileting problems in children. Med J Aust 2005; 182 (04) 190-195
    CrossrefPubMedSearch in Google Scholar
  • 3 Bozlu M, Cayan S, Doruk E, Canpolat B, Akbay E. The epidemiology of nocturnal and diurnal enuresis in childhood and adolescence. Turk J Urol 2002; 28: 70-75
    PubMedSearch in Google Scholar
  • 4 Kaisler SH, Armour F, Espinosa JA, Money W. . Big data: issues and challenges moving forward in: Proceedings of the 46th IEEE Annual Hawaii International Conference on System Sciences (HICC 2013), 2013: 995-1004 . Available at: https://doi.org/10.1109/HICSS.2013.645
    CrossrefPubMed
  • 5 Czarnowski I, Jędrzejowicz P. An approach to data reduction for learning from big datasets: integrating stacking, rotation, and agent population learning techniques. Complexity 2018; (01) 1-13 . Available at: https://doi.org/10.1155/2018/7404627
    CrossrefPubMedSearch in Google Scholar
  • 6 Perwej Y. An experiential study of the big data. Int Trans Electr Comp Engineer Syst 2017; 4: 14-25
    PubMedSearch in Google Scholar
  • 7 Akbal C, Genc Y, Burgu B, Ozden E, Tekgul S. Dysfunctional voiding and incontinence scoring system: quantitative evaluation of incontinence symptoms in pediatric population. J Urol 2005; 173 (03) 969-973
    CrossrefPubMedSearch in Google Scholar
  • 8 Sidey-Gibbons JAM, Sidey-Gibbons CJ. Machine learning in medicine: a practical introduction. BMC Med Res Methodol 2019; 19 (01) 64
    CrossrefPubMedSearch in Google Scholar
  • 9 De S, Teixeira-Pinto A, Sewell JR, Caldwell PH. Prevalence, patient and consultation characteristics of enuresis in Australian paediatric practice. J Paediatr Child Health 2018; 54 (06) 620-624
    CrossrefPubMedSearch in Google Scholar
  • 10 Gür E, Turhan P, Can G. et al. Enuresis: prevalence, risk factors and urinary pathology among school children in Istanbul, Turkey. Pediatr Int 2004; 46 (01) 58-63
    CrossrefPubMedSearch in Google Scholar
  • 11 Erdogan A, Akkurt H, Boettjer NK, Yurtseven E, Can G, Kiran S. Prevalence and behavioural correlates of enuresis in young children. J Paediatr Child Health 2008; 44 (05) 297-301
    CrossrefPubMedSearch in Google Scholar
  • 12 Butler RJ, Heron J. The prevalence of infrequent bedwetting and nocturnal enuresis in childhood. A large British cohort. Scand J Urol Nephrol 2008; 42 (03) 257-264
    CrossrefPubMedSearch in Google Scholar
  • 13 Sahin AH, Sahin H, Budak YU, Sancar S, Tatar H. Prevalence of nocturnal enuresis among primary school children in Bursa, Turkey. Turk Silahli Kuvvetleri Koruyucu Hekim Bul 2012; 11: 139-144
    PubMedSearch in Google Scholar
  • 14 Weissbach A, Leiberman A, Tarasiuk A, Goldbart A, Tal A. Adenotonsilectomy improves enuresis in children with obstructive sleep apnea syndrome. Int J Pediatr Otorhinolaryngol 2006; 70 (08) 1351-1356
    CrossrefPubMedSearch in Google Scholar
  • 15 Acar IC, Zümrütbas AE, Eskicorapci S, Tegin C, Sinik Z, Kara CO. The effects of adenoidectomy and tonsillectomy on monosymptomatic enuresis nocturna. Pamukkale Med J 2011; 4: 9-13
    PubMedSearch in Google Scholar
  • 16 Khazaie H, Eghbali F, Amirian H, Moradi MR, Ghadami MR. Risk factors of nocturnal enuresis in children with attention deficit hyperactivity disorder. Shanghai Jingshen Yixue 2018; 30 (01) 20-26
    PubMedSearch in Google Scholar
  • 17 Gunes A, Gunes G, Acik Y, Akilli A. The epidemiology and factors associated with nocturnal enuresis among boarding and daytime school children in southeast of Turkey: a cross sectional study. BMC Public Health 2009; 9: 357
    CrossrefPubMedSearch in Google Scholar
  • 18 Somoza Argibay I, Méndez Gallart R, Casal Beloy I, García González M. Urinary incontinence and lower urinary tract dysfunction prevalence in schoolchildren: risk factors [in Spanish]. Cir Pediatr 2019; 32 (03) 145-149
    PubMedSearch in Google Scholar
  • 19 Fuyama M, Ikeda H, Oyake C, Onuki Y, Watanabe T, Isoyama K. Clinical features of, and association of bladder ultrasound and uroflowmetry with, overactive bladder recovery period in children. Pediatr Int (Roma) 2018; 60 (06) 569-575
    CrossrefPubMedSearch in Google Scholar
  • 20 Barone JG, Jasutkar N, Schneider D. Later toilet training is associated with urge incontinence in children. J Pediatr Urol 2009; 5 (06) 458-461
    CrossrefPubMedSearch in Google Scholar
  • 21 Söderstrom U, Hoelcke M, Alenius L, Söderling AC, Hjern A. Urinary and faecal incontinence: a population-based study. Acta Paediatr 2004; 93 (03) 386-389
    CrossrefPubMedSearch in Google Scholar
  • 22 Penbegül N, Çelik H, Palancı Y. et al. Prevalence of enuresis nocturna among a group of primary school children living in Diyarbakır. Turk J Urol 2013; 39 (02) 101-105
    CrossrefPubMedSearch in Google Scholar
  • 23 Gümüş B, Vurgun N, Lekili M, Işcan A, Müezzinoğlu T, Büyuksu C. Prevalence of nocturnal enuresis and accompanying factors in children aged 7-11 years in Turkey. Acta Paediatr 1999; 88 (12) 1369-1372
    CrossrefPubMedSearch in Google Scholar
  • 24 Ozden C, Ozdal OL, Altinova S, Oguzulgen I, Urgancioglu G, Memis A. Prevalence and associated factors of enuresis in Turkish children. Int Braz J Urol 2007; 33 (02) 216-222
    CrossrefPubMedSearch in Google Scholar
  • 25 Miller DD, Brown EW. Artificial intelligence in medical practice: the question to the answer?. Am J Med 2018; 131 (02) 129-133
    CrossrefPubMedSearch in Google Scholar
  • 26 Goodfellow I, Bengio Y, Courville A. Deep Learning. Cambridge, MA, London, UK: The MIT Press; 2016: 96-161
    Search in Google Scholar
  • 27 Rahman SN, Monaghan TF, Weiss JP. Development and validation of a machine learning algorithm for predicting response to anticholinergic medications for overactive bladder syndrome. Obstet Gynecol 2020; 135 (02) 483
    CrossrefPubMedSearch in Google Scholar