The use of intelligent analysis (IA) in determining the tactics of treating patients with nephrolithiasis

Abstract

Introduction:

The use of modern information technologies allows to increase confidence in the choice of a surgical treatment method of kidney stones, as well as to improve the quality of treatment due to an adequate combination of therapeutic techniques.

Materials and methods:

In our study we analyzed the treatment results of 625 patients with kidney stones. We created a register with the information on more than 50 parameters for each patient. Each example had an output parameter representing a predefined treatment strategy (extracorporeal shock-wave lithotripsy [ESWL]—1, percutaneous nephrolithotomy [PCNL]—2, pyelolithotomy or nephrolithotomy—3). The initial database served as the basis for training the neural network estimation technique. The aim of our study was to assess the possibility of using neural network algorithms in choosing a method for surgical treatment of urolithiasis.

Results:

A prospective study was conducted to assess the clinical effectiveness of implementing the recommendations of the system. The average number of sessions in the group using the neural network assessment technique was 1.4. Residual fragments remained at the time of discharge in seven (15.6%) patients: four in the kidney, three in the lower third of the ureter “stone path.” Inversion of therapeutic tactics—PCNL—was performed in four cases. The efficiency of the ESWL was 91.1%. The indicators of the ESWL in the comparison groups differed statistically significantly: in the second group, the efficiency was higher due to more stone fragmentation, with lower energy costs (the average number of sessions was 0.4 less).

Conclusion:

The presented technique can be of help for a practicing urologist to choose the optimal treatment method for each patient, thereby minimizing the risk of early postoperative complications.

Keywords

Neural network prediction urolithiasis diagnosis of urolithiasis surgical treatment of kidney stones

Get full access to this article

View all access options for this article.

References

Tafeit

Reibnegger

. Artificial neural networks in laboratory medicine and medical outcome prediction. Clin Chem Lab Med 1999; 37(9): 845–853.

Checcucci

Autorino

Cacciamani

, et al.; Uro-technology and SoMe Working Group of the Young Academic Urologists Working Party of the European Association of Urology. Artificial intelligence and neural networks in urology: current clinical applications. Minerva Urol E Nefrol 2020; 72(1): 49–57.

Tewari

. Artificial intelligence and neural networks: concept, applications and future in urology. Br J Urol 1997; 80(Suppl 3): 53–58.

Abbod

Catto

JWF

Linkens

, et al. Application of artificial intelligence to the management of urological cancer. Urol J 2007; 178(4): 1150–1156.

Yuri

Hariwibowo

Soeroharjo

, et al. Meta-analysis of optimal management of lower pole stone of 10 - 20 mm: flexible ureteroscopy (FURS) versus extracorporeal shock wave lithotripsy (ESWL) versus percutaneus nephrolithotomy (PCNL). Acta Med Indones 2018; 50(1): 18–25.

Anagnostou

Tolley

. Management of ureteric stones. Eur Urol 2004; 45(6): 714–721.

Hagan

Demuth

Beale

, et al. Neural Network Design. 2nd ed. Stillwater, OK: Martin Hagan, 2014.

Hamid

Dwivedi

Singh

, et al. Artificial neural networks in predicting optimum renal stone fragmentation by extracorporeal shock wave lithotripsy: a preliminary study. BJU Int 2003; 91: 821–824.

Seckiner

Sen

, et al. A neural network - based algorithm for predicting stone - free status after ESWL therapy. Int Braz J Urol Off J Braz Soc Urol 2017; 43(6): 1110–1114.

10.

Kubat

. Neural networks: a comprehensive foundation by Simon Haykin, Macmillan, 1994, ISBN 0-02-352781-7. Knowl Eng Rev 1999; 13(4): 409–412.

11.

Gomha

Sheir

Showky

, et al. Can we improve the prediction of stone-free status after extracorporeal shock wave lithotripsy for ureteral stones? A neural network or a statistical model? J Urol 2004; 172: 175–179.