Machine learning-assisted decision-support models to better predict patients with calculous pyonephrosis

Early diagnostic model of pyonephrosis with calculi based on radiomic features combined with clinical variables

OBJECTIVE

This retrospective aims to develop a comprehensive predictive model based on CT radiomic features and clinical parameters, facilitating early preoperative diagnosis of pyonephrosis.

METHODS

Clinical and radiological data from 311 patients treated for upper urinary tract stones with obstructive pyelohydronephrosis, between January 2018 and May 2023, were retrospectively collected. Univariate and multivariate logistic regression analyses were conducted on clinical data to identify independent risk factors for pyonephrosis. A clinical model was developed using logistic regression. The 3D Slicer software was employed to manually delineate the region of interest (ROI) in the preoperative CT images, corresponding to the area of pyelohydronephrosis, for feature extraction. The optimal radiomic features were selected to construct radiomic models and calculate the radiomic score (Radscore). Subsequently, a combined clinical-radiomic model-the nomogram-was established by integrating the Radscore with independent risk factors.

RESULTS

Univariate and multivariate logistic regression analyses identified cystatin C, Hounsfield Unit (HU) of pyonephrosis, history of ipsilateral urological surgery, and positive urine culture as independent risk factors for pyonephrosis (P < 0.05). Fourteen optimal radiomic features were selected from CT images to construct four radiomic models, with the Naive Bayes model demonstrating the best predictive performance in both training and validation sets. In the training set, the AUCs for the clinical model, radiomic model, and nomogram were 0.902, 0.939, and 0.991, respectively; in the validation set, they were 0.843, 0.874, and 0.959. Both calibration and decision curves showed good agreement between the predicted probabilities of the nomogram and the actual occurrences.

CONCLUSION

The nomogram, constructed from CT radiomic features and clinical variables, provides an effective non-invasive predictive tool for pyonephrosis, surpassing both clinical and radiomic models.

Identification of Calculous Pyonephrosis by CT-Based Radiomics and Deep Learning

Urgent detection of calculous pyonephrosis is crucial for surgical planning and preventing severe outcomes. This study aims to evaluate the performance of computed tomography (CT)-based radiomics and a three-dimensional convolutional neural network (3D-CNN) model, integrated with independent clinical factors, to identify patients with calculous pyonephrosis. We recruited 182 patients receiving either percutaneous nephrostomy tube placement or percutaneous nephrolithotomy for calculous hydronephrosis or pyonephrosis. The regions of interest were manually delineated on plain CT images and the CT attenuation value (HU) was measured. Radiomics analysis was performed using least absolute shrinkage and selection operator (LASSO). A 3D-CNN model was also developed. The better-performing machine-learning model was combined with independent clinical factors to build a comprehensive clinical machine-learning model. The performance of these models was assessed using receiver operating characteristic analysis and decision curve analysis. Fever, blood neutrophils, and urine leukocytes were independent risk factors for pyonephrosis. The radiomics model showed higher area under the curve (AUC) than the 3D-CNN model and HU (0.876 vs. 0.599, 0.578; p = 0.003, 0.002) in the testing cohort. The clinical machine-learning model surpassed the clinical model in both the training (0.975 vs. 0.904, p = 0.019) and testing (0.967 vs. 0.889, p = 0.045) cohorts.

Machine learning constructs a diagnostic prediction model for calculous pyonephrosis

In order to provide decision-making support for the auxiliary diagnosis and individualized treatment of calculous pyonephrosis, the study aims to analyze the clinical features of the condition, investigate its risk factors, and develop a prediction model of the condition using machine learning techniques. A retrospective analysis was conducted on the clinical data of 268 patients with calculous renal pelvic effusion who underwent ultrasonography-guided percutaneous renal puncture and drainage in our hospital during January 2018 to December 2022. The patients were included into two groups, one for pyonephrosis and the other for hydronephrosis. At a random ratio of 7:3, the research cohort was split into training and testing data sets. Single factor analysis was utilized to examine the 43 characteristics of the hydronephrosis group and the pyonephrosis group using the T test, Spearman rank correlation test and chi-square test. Disparities in the characteristic distributions between the two groups in the training and test sets were noted. The features were filtered using the minimal absolute value shrinkage and selection operator on the training set of data. Auxiliary diagnostic prediction models were established using the following five machine learning (ML) algorithms: random forest (RF), xtreme gradient boosting (XGBoost), support vector machines (SVM), gradient boosting decision trees (GBDT) and logistic regression (LR). The area under the curve (AUC) was used to compare the performance, and the best model was chosen. The decision curve was used to evaluate the clinical practicability of the models. The models with the greatest AUC in the training dataset were RF (1.000), followed by XGBoost (0.999), GBDT (0.977), and SVM (0.971). The lowest AUC was obtained by LR (0.938). With the greatest AUC in the test dataset going to GBDT (0.967), followed by LR (0.957), XGBoost (0.950), SVM (0.939) and RF (0.924). LR, GBDT and RF models had the highest accuracy were 0.873, followed by SVM, and the lowest was XGBoost. Out of the five models, the LR model had the best sensitivity and specificity is 0.923 and 0.887. The GBDT model had the highest AUC among the five models of calculous pyonephrosis developed using the ML, followed by the LR model. The LR model was considered be the best prediction model when combined with clinical operability. As it comes to diagnosing pyonephrosis, the LR model was more credible and had better prediction accuracy than common analysis approaches. Its nomogram can be used as an additional non-invasive diagnostic technique.

A retrospective study using machine learning to develop predictive model to identify urinary infection stones in vivo

Preoperative diagnosis of urinary infection stones is difficult, and accurate detection of stone composition can only be performed ex vivo. To provide guidance for better perioperative management and postoperative prevention of infection stones, we developed a machine learning model for preoperative identification of infection stones in vivo. The clinical data of patients with urolithiasis who underwent surgery in our hospital from January 2011 to December 2015 and January 2017 to December 2021 were retrospectively analyzed. A total of 2565 patients were included in the study, and 1168 eligible patients with urinary calculi were randomly divided into training set (70%) and test set (30%). Five machine learning algorithms (Support Vector Machine (SVM), Multilayer Perceptron (MLP), Decision Tree (DT), Random Forest Classifier (RFC), and Adaptive Boost (AdaBoost)) and 14 preoperative variables were used to construct the prediction model. The performance measure was the area under the receiver operating characteristic curve (AUC) of the validation set. The importance of 14 features in each prediction model for predicting infection stones was analyzed. A total of 89 patients (5.34%) with infection stones were included in the validation set. All the five prediction models showed strong discrimination in the validation set (AUC: 0.689-0.772). AdaBoost model was selected as the final model (AUC: 0.772(95% confidence interval, 0.657-0.887); Sensitivity: 0.522; Specificity: 0.902), UC positivity, and urine pH value were two important predictors of infection stones. We developed a predictive model through machine learning that can quickly identify infection stones in vivo with good predictive performance. It can be used for risk assessment and decision support of infection stones, optimize the disease management of urinary calculi and improve the prognosis of patients.

Clinical Applications of Machine Learning for Urolithiasis and Benign Prostatic Hyperplasia: A Systematic Review

INTRODUCTION

Previous systematic reviews related to machine learning (ML) in urology often overlooked the literature related to endourology. Therefore, we aim to conduct a more focused systematic review examining the use of ML algorithms for benign prostatic hyperplasia (BPH) or urolithiasis. In addition, we are the first group to evaluate these articles using the STREAM-URO framework.

METHODS

Searches of MEDLINE, Embase, and the Cochrane CENTRAL databases were conducted from inception through July 12, 2021. Keywords included those related to ML, endourology, urolithiasis, and BPH. Two reviewers screened the citations that were eligible for title, abstract and full-text screening, with conflicts resolved by a third reviewer. Two reviewers extracted information from the studies, with discrepancies resolved by a third reviewer. The data collected was then qualitatively synthesized by consensus. Two reviewers evaluated each article according to the STREAM-URO checklist with discrepancies resolved by a third reviewer.

RESULTS

After identifying 459 unique citations, 63 articles were retained for data extraction. Most articles consisted of tabular (n=32) and computer vision (n=23) tasks. The two most common problem types were classification (n=40) and regression (n=12). In general, most studies utilized neural networks as their ML algorithm (n=36). Among the 63 studies retrieved, 58 were related to urolithiasis and five focused on BPH. The urolithiasis studies were designed for outcome prediction (n=20), stone classification (n=18), diagnostics (n=17), and therapeutics (n=3). The BPH studies were designed for outcome prediction (n=2), diagnostics (n=2), and therapeutics (n=1). On average, the urolithiasis and BPH articles met 13.8 (SD 2.6), and 13.4 (4.1) of the 26 STREAM-URO framework criteria, respectively.

CONCLUSIONS

The majority of the retrieved studies successfully helped with outcome prediction, diagnostics, and therapeutics for both urolithiasis and BPH. While ML shows great promise in improving patient care, it is important to adhere to the recently developed STREAM-URO framework to ensure the development of high-quality ML studies.