JMIR Publications

ABSTRACT

Background:

Shock wave lithotripsy (SWL), Ureteroscopy (URS) and percutaneous nephrolithotomy (PCNL) are established treatments for renal stones. Historically SWL has been a predominant and commonly used procedure for treating upper tract renal stones smaller than 20 mm in diameter due its noninvasive nature. However, the reported failure rate of SWL after one treatment session ranges from 30% to 60% (Yamashita et al. 2017). The failure rate can be reduced by identifying candidates likely to benefit from SWL and manage patients who are likely to fail SWL with other treatment modalities. This would enhance and optimize treatment results for SWL candidates.

Objective:

We proposed to develop a machine learning model that can predict SWL outcomes to assist practitioners in the decision-making process when considering patients for stone treatment.

Methods:

A dataset including 58,349 SWL procedures performed on 31,569 patient visits for SWL to a single hospital between 1990 and 2016 was used to construct and validate the predictive model. The AdaBoost algorithm was applied to a dataset with 17 predicting attributes related to patients’ information and stone characteristics, with success or failure as an outcome. The AdaBoost algorithm was applied to the dataset. The generated model’s performance was compared to that of 5 other machine learning algorithms, namely C4.5 decision tree, naïve Bayes, Bayesian network, K-nearest neighbors (KNN), and multilayer perceptron (MLP).

Results:

The developed model was validated with a testing dataset and had performed significantly better than the models generated by the other 5 predictive algorithms. The sensitivity of model was 0.875 and specificity 0.6528; while its positive predictive value was 0.7159 and negative predictive value 0.839. The C-statistics of the ROC analysis is 0.843 which reflects an excellent test.

Conclusions:

We have developed a rigorous machine learning model to assist physicians and decision makers to choose patients with renal stones who are most likely to have successful SWL treatment based on their demographics and stone characteristics. The proposed a machine learning model can assist physicians and decision makers in planning for SWL treatment and allow a more effective use of limited healthcare resources and improve patient prognoses.