Tsitsiflis A. et al., 2022: The use of an artificial neural network in the evaluation of the extracorporeal shockwave lithotripsy as a treatment of choice for urinary lithiasis.
Tsitsiflis A, Kiouvrekis Y, Chasiotis G, Perifanos G, Gravas S, Stefanidis I, Tzortzis V, Karatzas A.
Department of Urology, Faculty of Medicine, School of Health Sciences, University of Thessaly, Larissa, Greece.
Department of Public and Integrated Health, University of Thessaly, Karditsa, Greece.
Business School, University of Nicosia, Nicosia, Cyprus.
Department of Internal Medicine, Faculty of Medicine, School of Health Sciences, University of Thessaly, Larissa, Greece.
Department of Nephrology, Faculty of Medicine, School of Health Sciences, University of Thessaly, Larissa, Greece.
Objective: Artificial neural networks (ANNs) are widely applied in medicine, since they substantially increase the sensitivity and specificity of the diagnosis, classification, and the prognosis of a medical condition. In this study, we constructed an ANN to evaluate several parameters of extracorporeal shockwave lithotripsy (ESWL), such as the outcome and safety of the procedure.
Methods: Patients with urinary lithiasis suitable for ESWL treatment were enrolled. An ANN was designed using MATLAB. Medical data were collected from all patients and 12 nodes were used as inputs. Conventional statistical analysis was also performed.
Results: Finally, 716 patients were included in our study. Univariate analysis revealed that diabetes and hydronephrosis were positively correlated with ESWL complications. Regarding efficacy, univariate analysis revealed that stone location, stone size, the number and density of shockwaves delivered, and the presence of a stent in the ureter were independent factors of the ESWL outcome. This was further confirmed when adjusted for sex and age in a multivariate analysis. The performance of the ANN at the end of the training state reached 98.72%. The four basic ratios (sensitivity, specificity, positive predictive value, and negative predictive value) were calculated for both training and evaluation data sets. The performance of the ANN at the end of the evaluation state was 81.43%.
Conclusion: Our ANN achieved high score in predicting the outcome and the side effects of the ESWL treatment for urinary stones.
Asian J Urol. 2022 Apr;9(2):132-138. doi: 10.1016/j.ajur.2021.09.005. Epub 2021 Sep 30. PMID: 35509481. FREE ARTICLE
The authors describe well how they constructed their ANN. However, the way the input parameters are chosen is difficult to understand: the stone size is differentiated in seven size groups, but the stone location just lists left or right kidney or ureter resp. and not the calyceal position or which part of the ureter. These parameters are known to influence the ESWL success rates. There is no hint why they were not used. There are no proper data on the treatment parameters and outcome evaluation. Success- and complication-rates are not detailed.
The statement ”Our study is the first attempt in the literature to construct a neural network predicting urinary lithiasis treatment”, is probably based on limited literature search (1)
1 Hameed BMZ, Shah M, Naik N, Rai BP, Karimi H, Rice P, Kronenberg P, Somani B. The Ascent of Artificial Intelligence in Endourology: a Systematic Review Over the Last 2 Decades. Curr Urol Rep. 2021 Oct 9;22(10):53. doi: 10.1007/s11934-021-01069-3. PMID: 34626246; PMCID: PMC85021
Free PMC article