STORZ MEDICAL – Literature Databases
STORZ MEDICAL – Literature Databases
Literature Databases
Literature Databases

Nakamae Y. et al., 2023: AI prediction of extracorporeal shock wave lithotripsy outcomes for ureteral stones by machine learning-based analysis with a variety of stone and patient characteristics.

Nakamae Y, Deguchi R, Nemoto M, Kimura Y, Yamashita S, Kohjimoto Y, Hara I.
Graduate School of Biology-Oriented Science and Technology, Kindai University, Kinokawa City, Japan.
Department of Urology, Wakayama Medical University, Wakayama City, Japan.
Graduate School of Biology-Oriented Science and Technology, Kindai University, Kinokawa City, Japan.
Faculty of Biology-Oriented Science and Technology, Kindai University, 930 Nishimitani, Kinokawa City, Wakayama, 649-6493, Japan.
Faculty of Informatics, Kindai University, Higashiosaka, Japan.

Abstract

We propose an artificial intelligence prediction method for extracorporeal shock wave lithotripsy treatment outcomes by analysis of a wide variety of variables. We retrospectively reviewed the records of 171 patients from between January 2009 and November 2019 that underwent shock wave lithotripsy at Wakayama Medical University, Japan, for ureteral stones shown on preoperative non-contrast computed tomography. This prediction method consisted of stone area extraction, stone analyzing factor extraction from non-contrast computed tomography images, and shock wave lithotripsy treatment result prediction by a non-linear support vector machine for analysis of 15 input and automatic measurement factors. Input factors included patient age, skin-to-stone distance, and maximum ureteral wall thickness, and the automatic measurement factors included 11 non-contrast computed tomography image texture factors in the stone area and stone volume. Permutation feature importance was also applied to the artificial intelligence prediction results to analyze the importance of each factor relating to estimate decision grounds. The prediction performance was evaluated by five-fold cross-validation, it obtained 0.742 of the mean area under the receiver operating characteristic curve. The proposed method is shown by these results to have robust data diversity and effective clinical application. As a result of permutation feature importance, some factors that showed high p-values in the significant difference tests were thought to have a high contribution to the proposed prediction method. Future issues include validation using a larger volume of high-resolution clinical non-contrast computed tomography image data and the application of deep learning.

Urolithiasis. 2023 Dec 2;52(1):9. doi: 10.1007/s00240-023-01506-7. PMID: 38041695

0
 

Comments 1

Hans-Göran Tiselius on Tuesday, 16 April 2024 11:00

In this report the authors describe how AI can be used to predict the outcome of SWL for ureteral stones.

Generally, it is my own experience that SWL of ureteral stones is so successful that any complicated analysis of multiple factors makes very little sense. From our own analysis [1] as many as 73%, 67% and 83% became stone-free after one single session of SWL carried out with the Storz Modulith SLX device. Important to state is, however, that different results might be expected with different lithotripters and different SWL techniques.

It is important to note that the current study was based on 171 patients treated for10 years; that is ~17 patients per year who obviously were treated by different operators Accordingly some doubts can be raised on the standardization of the SWL method. Moreover, it was stated that the energy was adapted to the tolerance of the patient which usually means suboptimal SWL energy results. The only pain treatment used was 50 mg of diclofenac sodium, which in my opinion is insufficient.

The first-time session resulted in 57% successfully (stone-free) patients. That is a number lower than expected given that the mean stone diameter (calculated from the volumes) was in average 8 mm.

The conclusion is that despite the thrilling novelty of AI, I am not certain that this method plays a role in prediction of the outcome of SWL treatment of ureteral stones.
Reference
1.Tiselius HG. How efficient is extracorporeal shockwave lithotripsy with modern lithotripters for removal of ureteral stones?
J Endourol. 2008 Feb;22(2):249-55. doi: 10.1089/end.2007.0225.

Hans-Göran Tiselius

In this report the authors describe how AI can be used to predict the outcome of SWL for ureteral stones. Generally, it is my own experience that SWL of ureteral stones is so successful that any complicated analysis of multiple factors makes very little sense. From our own analysis [1] as many as 73%, 67% and 83% became stone-free after one single session of SWL carried out with the Storz Modulith SLX device. Important to state is, however, that different results might be expected with different lithotripters and different SWL techniques. It is important to note that the current study was based on 171 patients treated for10 years; that is ~17 patients per year who obviously were treated by different operators Accordingly some doubts can be raised on the standardization of the SWL method. Moreover, it was stated that the energy was adapted to the tolerance of the patient which usually means suboptimal SWL energy results. The only pain treatment used was 50 mg of diclofenac sodium, which in my opinion is insufficient. The first-time session resulted in 57% successfully (stone-free) patients. That is a number lower than expected given that the mean stone diameter (calculated from the volumes) was in average 8 mm. The conclusion is that despite the thrilling novelty of AI, I am not certain that this method plays a role in prediction of the outcome of SWL treatment of ureteral stones. Reference 1.Tiselius HG. How efficient is extracorporeal shockwave lithotripsy with modern lithotripters for removal of ureteral stones? J Endourol. 2008 Feb;22(2):249-55. doi: 10.1089/end.2007.0225. Hans-Göran Tiselius
Monday, 20 May 2024