An artificial intelligence-based clinical decision support system for large kidney stone treatment

Current advances in the use of artificial intelligence in predicting and managing urological complications

BACKGROUND

Artificial intelligence (AI) has emerged as a promising avenue for improving patient care and surgical outcomes in urological surgery. However, the extent of AI's impact in predicting and managing complications is not fully elucidated.

OBJECTIVES

We review the application of AI to foresee and manage complications in urological surgery, assess its efficacy, and discuss challenges to its use.

METHODS AND MATERIALS

A targeted non-systematic literature search was conducted using the PubMed and Google Scholar databases to identify studies on AI in urological surgery and its complications. Evidence from the studies was synthesised.

RESULTS

Incorporating AI into various facets of urological surgery has shown promising advancements. From preoperative planning to intraoperative guidance, AI is revolutionising the field, demonstrating remarkable proficiency in tasks such as image analysis, decision-making support, and complication prediction. Studies show that AI programmes are highly accurate, increase surgical precision and efficiency, and reduce complications. However, implementation challenges exist in AI errors, human errors, and ethical issues.

CONCLUSION

AI has great potential in predicting and managing surgical complications of urological surgery. Advancements have been made, but challenges and ethical considerations must be addressed before widespread AI implementation.

Artificial intelligence in urolithiasis: a systematic review of utilization and effectiveness

PURPOSE

Mirroring global trends, artificial intelligence advances in medicine, notably urolithiasis. It promises accurate diagnoses, effective treatments, and forecasting epidemiological risks and stone passage. This systematic review aims to identify the types of AI models utilised in urolithiasis studies and evaluate their effectiveness.

METHODS

The study was registered with PROSPERO. Pubmed, EMBASE, Google Scholar, and Cochrane Library databases were searched for relevant literature, using keywords such as 'urology,' 'artificial intelligence,' and 'machine learning.' Only original AI studies on urolithiasis were included, excluding reviews, unrelated studies, and non-English articles. PRISMA guidelines followed.

RESULTS

Out of 4851 studies initially identified, 71 were included for comprehensive analysis in the application of AI in urolithiasis. AI showed notable proficiency in stone composition analysis in 12 studies, achieving an average precision of 88.2% (Range 0.65-1). In the domain of stone detection, the average precision remarkably reached 96.9%. AI's accuracy rate in predicting spontaneous ureteral stone passage averaged 87%, while its performance in treatment modalities such as PCNL and SWL achieved average accuracy rates of 82% and 83%, respectively. These AI models were generally superior to traditional diagnostic and treatment methods.

CONCLUSION

The consolidated data underscores AI's increasing significance in urolithiasis management. Across various dimensions-diagnosis, monitoring, and treatment-AI outperformed conventional methodologies. High precision and accuracy rates indicate that AI is not only effective but also poised for integration into routine clinical practice. Further research is warranted to establish AI's long-term utility and to validate its role as a standard tool in urological care.

Artificial Neural Network-based Model for Predicting Cardiologists' Over-apron Dose in CATHLABs

Aim

The radiation dose that cardiologists receive in the catheterization laboratory is influenced by various factors. Handling high-stress tasks in interventional cardiology departments may cause physicians to overlook the use of dosimeters. Therefore, it is essential to develop a model for predicting cardiologists' radiation exposure.

Materials and Methods

This study developed an artificial neural network (ANN) model to predict the over-apron radiation dose received by cardiologists during catheterization procedures, using dose area product (DAP) values. Leveraging a validated Monte Carlo simulation program, we generated data from simulations with varying spectra (70, 81, and 90 kVp) and tube orientations, resulting in 125 unique scenarios. We then used these data to train a multilayer perceptron neural network with four input features: DAP, energy spectrum, tube angulation, and the resulting cardiologist's dose.

Results

The model demonstrated high predictive accuracy with a correlation coefficient (R-value) of 0.95 and a root mean square error (RMSE) of 3.68 µSv, outperforming a traditional linear regression model, which had an R-value of 0.48 and an RMSE of 18.15 µSv. This significant improvement highlights the effectiveness of advanced techniques such as ANNs in accurately predicting occupational radiation doses.

Conclusion

This study underscores the potential of ANN models for accurate radiation dose prediction, enhancing safety protocols, and providing a reliable tool for real-time exposure assessment in clinical settings. Future research should focus on broader validation and integration into real-time monitoring systems.

Use of Temporally Validated Machine Learning Models To Predict Outcomes of Percutaneous Nephrolithotomy Using Data from the British Association of Urological Surgeons Percutaneous Nephrolithotomy Audit

BACKGROUND AND OBJECTIVE

Machine learning (ML) is a subset of artificial intelligence that uses data to build algorithms to predict specific outcomes. Few ML studies have examined percutaneous nephrolithotomy (PCNL) outcomes. Our objective was to build, streamline, temporally validate, and use ML models for prediction of PCNL outcomes (intensive care admission, postoperative infection, transfusion, adjuvant treatment, postoperative complications, visceral injury, and stone-free status at follow-up) using a comprehensive national database (British Association of Urological Surgeons PCNL).

METHODS

This was an ML study using data from a prospective national database. Extreme gradient boosting (XGB), deep neural network (DNN), and logistic regression (LR) models were built for each outcome of interest using complete cases only, imputed, and oversampled and imputed/oversampled data sets. All validation was performed with complete cases only. Temporal validation was performed with 2019 data only. A second round used a composite of the most important 11 variables in each model to build the final model for inclusion in the shiny application. We report statistics for prognostic accuracy.

KEY FINDINGS AND LIMITATIONS

The database contains 12 810 patients. The final variables included were age, Charlson comorbidity index, preoperative haemoglobin, Guy's stone score, stone location, size of outer sheath, preoperative midstream urine result, primary puncture site, preoperative dimercapto-succinic acid scan, stone size, and image guidance (https://endourology.shinyapps.io/PCNL_Demographics/). The areas under the receiver operating characteristic curve was >0.6 in all cases.

CONCLUSIONS AND CLINICAL IMPLICATIONS

This is the largest ML study on PCNL outcomes to date. The models are temporally valid and therefore can be implemented in clinical practice for patient-specific risk profiling. Further work will be conducted to externally validate the models.

PATIENT SUMMARY

We applied artificial intelligence to data for patients who underwent a keyhole surgery to remove kidney stones and developed a model to predict outcomes for this procedure. Doctors could use this tool to advise patients about their risk of complications and the outcomes they can expect after this surgery.

Acoustic emission of kidney stones: a medical adaptation of statistical breakdown mechanisms

Kidney stones have a prevalence rate of > 10% in some countries. There has been a significant increase in surgery to treat kidney stones over the last 10 years, and it is crucial that such techniques are as effective as possible, while limiting complications. A selection of kidney stones with different chemical and structural properties were subjected to compression. Under compression, they emit acoustic signals called crackling noise. The variability of the crackling noise was surprisingly great comparing weddellite, cystine and uric acid stones. Two types of signals were found in all stones. At high energies of the emitted sound waves, we found avalanche behaviour, while all stones also showed signals of local, uncorrelated collapse. These two types of events are called 'wild' for avalanches and 'mild' for uncorrelated events. The key observation is that the crossover from mild to wild collapse events differs greatly between different stones. Weddellite showed brittle collapse, extremely low crossover energies (< 5 aJ) and wild avalanches over 6 orders of magnitude. In cystine and uric acid stones, the collapse was more complicated with a dominance of local "mild" breakings, although they all contained some stress-induced collective avalanches. Cystine stones had high crossover energies, typically [Formula: see text] 750 aJ, and a narrow window over which they showed wild avalanches. Uric acid stones gave moderate values of crossover energies, [Formula: see text] 200 aJ, and wild avalanche behaviour for [Formula: see text] 3 orders of magnitude. Further research extended to all stone types, and measurement of stone responses to different lithotripsy strategies, will assist in optimisation of settings of the laser and other lithotripsy devices to insight fragmentation by targeting the 'wild' avalanche regime.

A novel post-percutaneous nephrolithotomy sepsis prediction model using machine learning

OBJECTIVES

To establish a predictive model for sepsis after percutaneous nephrolithotomy (PCNL) using machine learning to identify high-risk patients and enable early diagnosis and intervention by urologists.

METHODS

A retrospective study including 694 patients who underwent PCNL was performed. A predictive model for sepsis using machine learning was constructed based on 22 preoperative and intraoperative parameters.

RESULTS

Sepsis occurred in 45 of 694 patients, including 16 males (35.6%) and 29 females (64.4%). Data were randomly segregated into an 80% training set and a 20% validation set via 100-fold Monte Carlo cross-validation. The variables included in this study were highly independent. The model achieved good predictive power for postoperative sepsis (AUC = 0.89, 87.8% sensitivity, 86.9% specificity, and 87.4% accuracy). The top 10 variables that contributed to the model prediction were preoperative midstream urine bacterial culture, sex, days of preoperative antibiotic use, urinary nitrite, preoperative blood white blood cell (WBC), renal pyogenesis, staghorn stones, history of ipsilateral urologic surgery, cumulative stone diameters, and renal anatomic malformation.

CONCLUSION

Our predictive model is suitable for sepsis estimation after PCNL and could effectively reduce the incidence of sepsis through early intervention.

Surgical Artificial Intelligence: Endourology

Endourology is ripe with information that includes patient factors, laboratory tests, outcomes, and visual data, which is becoming increasingly complex to assess. Artificial intelligence (AI) has the potential to explore and define these relationships; however, humans might not be involved in the input, analysis, or even determining the methods of analysis. Herein, the authors present the current state of AI in endourology and highlight the need for urologists to share their proposed AI solutions for reproducibility outside of their institutions and prepare themselves to properly critique this new technology.

[Imaging for urolithiasis]

The substantial reduction of radiation exposure using (ultra-)low dose programs in native computed tomographic imaging has led to considerable changes in imaging diagnostics and treatment planning in urolithiasis in recent years. In addition, especially in Germany, ultrasound diagnostics is highly available in terms of equipment and with increasing expertise. This can largely replace the previous radiation-associated procedures in emergency and follow-up diagnostics, but also in intraoperative imaging, e.g., in percutaneous stone therapy (intraoperative fluoroscopy). This is reflected in the international guidelines, which recommend these two modalities as first-line diagnostics in all areas mentioned. Continuous technical development enables ever higher resolution imaging and thus improved diagnostics with high sensitivity and specificity. This also enables reliable imaging of particularly vulnerable patient groups, such as children or pregnant women. In addition, methods from the field of artificial intelligence (AI; machine learning, deep learning) are increasingly being used for automated stone detection and stone characterization including its composition. Furthermore, AI models can provide prognosis models as well as individually tailored treatment, follow-up, and prophyaxis. This will enable further personalization of diagnostics and therapy in the field of urolithiasis.

A multicenter study on the application of artificial intelligence radiological characteristics to predict prognosis after percutaneous nephrolithotomy

Background

A model to predict preoperative outcomes after percutaneous nephrolithotomy (PCNL) with renal staghorn stones is developed to be an essential preoperative consultation tool.

Objective

In this study, we constructed a predictive model for one-time stone clearance after PCNL for renal staghorn calculi, so as to predict the stone clearance rate of patients in one operation, and provide a reference direction for patients and clinicians.

Methods

According to the 175 patients with renal staghorn stones undergoing PCNL at two centers, preoperative/postoperative variables were collected. After identifying characteristic variables using PCA analysis to avoid overfitting. A predictive model was developed for preoperative outcomes after PCNL in patients with renal staghorn stones. In addition, we repeatedly cross-validated their model's predictive efficacy and clinical application using data from two different centers.

Results

The study included 175 patients from two centers treated with PCNL. We used a training set and an external validation set. Radionics characteristics, deep migration learning, clinical characteristics, and DTL+Rad-signature were successfully constructed using machine learning based on patients' pre/postoperative imaging characteristics and clinical variables using minimum absolute shrinkage and selection operator algorithms. In this study, DTL-Rad signal was found to be the outstanding predictor of stone clearance in patients with renal deer antler-like stones treated by PCNL. The DTL+Rad signature showed good discriminatory ability in both the training and external validation groups with AUC values of 0.871 (95% CI, 0.800-0.942) and 0.744 (95% CI, 0.617-0.871). The decision curve demonstrated the radiographic model's clinical utility and illustrated specificities of 0.935 and 0.806, respectively.

Conclusion

We found a prediction model combining imaging characteristics, neural networks, and clinical characteristics can be used as an effective preoperative prediction method.

Predicting the Stone-Free Status of Percutaneous Nephrolithotomy with the Machine Learning System

Purpose

The study aimed to create a machine learning model (MLM) to predict the stone-free status (SFS) of patients undergoing percutaneous nephrolithotomy (PCNL) and compare its performance to the S.T.O.N.E. and Guy's stone scores.

Patients and Methods

This is a retrospective study that included 320 PCNL patients. Pre-operative and post-operative variables were extracted and entered into three MLMs: RFC, SVM, and XGBoost. The methods used to assess the performance of each were mean bootstrap estimate, 10-fold cross-validation, classification report, and AUC. Each model was externally validated and evaluated by mean bootstrap estimate with CI, classification report, and AUC.

Results

Out of the 320 patients who underwent PCNL, the SFS was found to be 69.4%. The RFC mean bootstrap estimate was 0.75 and 95% CI: [0.65-0.85], 10-fold cross-validation of 0.744, an accuracy of 0.74, and AUC of 0.761. The XGBoost results were 0.74 [0.63-0.85], 0.759, 0.72, and 0.769, respectively. The SVM results were 0.70 [0.60-0.79], 0.725, 0.74, and 0.751, respectively. The AUC of Guy's stone score and the S.T.O.N.E. score were 0.666 and 0.71, respectively. The RFC external validation set had a mean bootstrap estimate of 0.87 and 95% CI: [0.81-0.92], an accuracy of 0.70, and an AUC of 0.795, While the XGBoost results were 0.84 [0.78-0.91], 0.74, and 0.84, respectively. The SVM results were 0.86 [0.80-0.91], 0.79, and 0.858, respectively.

Conclusion

MLMs can be used with high accuracy in predicting SFS for patients undergoing PCNL. MLMs we utilized predicted the SFS with AUCs superior to those of GSS and S.T.O.N.E scores.

Transforming urinary stone disease management by artificial intelligence-based methods: A comprehensive review

Objective

To provide a comprehensive review on the existing research and evidence regarding artificial intelligence (AI) applications in the assessment and management of urinary stone disease.

Methods

A comprehensive literature review was performed using PubMed, Scopus, and Google Scholar databases to identify publications about innovative concepts or supporting applications of AI in the improvement of every medical procedure relating to stone disease. The terms ''endourology'', ''artificial intelligence'', ''machine learning'', and ''urolithiasis'' were used for searching eligible reports, while review articles, articles referring to automated procedures without AI application, and editorial comments were excluded from the final set of publications. The search was conducted from January 2000 to September 2023 and included manuscripts in the English language.

Results

A total of 69 studies were identified. The main subjects were related to the detection of urinary stones, the prediction of the outcome of conservative or operative management, the optimization of operative procedures, and the elucidation of the relation of urinary stone chemistry with various factors.

Conclusion

AI represents a useful tool that provides urologists with numerous amenities, which explains the fact that it has gained ground in the pursuit of stone disease management perfection. The effectiveness of diagnosis and therapy can be increased by using it as an alternative or adjunct to the already existing data. However, little is known concerning the potential of this vast field. Electronic patient records, containing big data, offer AI the opportunity to develop and analyze more precise and efficient diagnostic and treatment algorithms. Nevertheless, the existing applications are not generalizable in real-life practice, and high-quality studies are needed to establish the integration of AI in the management of urinary stone disease.

The role of 'artificial intelligence, machine learning, virtual reality, and radiomics' in PCNL: a review of publication trends over the last 30 years

Introduction

We wanted to analyze the trend of publications in a period of 30 years from 1994 to 2023, on the application of 'artificial intelligence (AI), machine learning (ML), virtual reality (VR), and radiomics in percutaneous nephrolithotomy (PCNL)'. We conducted this study by looking at published papers associated with AI and PCNL procedures, including simulation training, with preoperative and intraoperative applications.

Materials and Methods

Although MeSH terms research on the PubMed database, we performed a comprehensive review of the literature from 1994 to 2023 for all published papers on 'AI, ML, VR, and radiomics' in 'PCNL', with papers in all languages included. Papers were divided into three 10-year periods: Period 1 (1994-2003), Period 2 (2004-2013), and Period 3 (2014-2023).

Results

Over a 30-year timeframe, 143 papers have been published on the subject with 116 (81%) published in the last decade, with a relative increase from Period 2 to Period 3 of +427% (p = 0.0027). There was a gradual increase in areas such as automated diagnosis of larger stones, automated intraoperative needle targeting, and VR simulators in surgical planning and training. This increase was most marked in Period 3 with automated targeting with 52 papers (45%), followed by the application of AI, ML, and radiomics in predicting operative outcomes (22%, n = 26) and VR for simulation (18%, n = 21). Papers on technological innovations in PCNL (n = 9), intelligent construction of personalized protocols (n = 6), and automated diagnosis (n = 2) accounted for 15% of publications. A rise in automated targeting for PCNL and PCNL training between Period 2 and Period 3 was +247% (p = 0.0055) and +200% (p = 0.0161), respectively.

Conclusion

An interest in the application of AI in PCNL procedures has increased in the last 30 years, and a steep rise has been witnessed in the last 10 years. As new technologies are developed, their application in devices for training and automated systems for precise renal puncture and outcome prediction seems to play a leading role in modern-day AI-based publication trends on PCNL.

Theranostic roles of machine learning in clinical management of kidney stone disease

Kidney stone disease (KSD) is a common illness caused by deposition of solid minerals formed inside the kidney. The disease prevalence varies, based on sociodemographic, lifestyle, dietary, genetic, gender, age, environmental and climatic factors, but has been continuously increasing worldwide. KSD is a highly recurrent disease, and the recurrence rate is about 11% within two years after the stone removal. Recently, machine learning has been widely used for KSD detection, stone type prediction, determination of appropriate treatment modality and prediction of therapeutic outcome. This review provides a brief overview of KSD and discusses how machine learning can be applied to diagnostics, therapeutics and prognostics in clinical management of KSD for better therapeutic outcome.

Deep learning model-assisted detection of kidney stones on computed tomography

Introduction:

The aim of this study was to investigate the success of a deep learning model in detecting kidney stones in different planes according to stone size on unenhanced computed tomography (CT) images.

Materials and Methods:

This retrospective study included 455 patients who underwent CT scanning for kidney stones between January 2016 and January 2020; of them, 405 were diagnosed with kidney stones and 50 were not. Patients with renal stones of 0–1 cm, 1–2 cm, and >2 cm in size were classified into groups 1, 2, and 3, respectively. Two radiologists reviewed 2,959 CT images of 455 patients in three planes. Subsequently, these CT images were evaluated using a deep learning model. The accuracy rate, sensitivity, specificity, and positive and negative predictive values of the deep learning model were determined.

Results:

The training group accuracy rates of the deep learning model were 98.2%, 99.1%, and 97.3% in the axial plane; 99.1%, 98.2%, and 97.3% in the coronal plane; and 98.2%, 98.2%, and 98.2% in the sagittal plane, respectively. The testing group accuracy rates of the deep learning model were 78%, 68% and 70% in the axial plane; 63%, 72%, and 64% in the coronal plane; and 85%, 89%, and 93% in the sagittal plane, respectively.

Conclusions:

The use of deep learning algorithms for the detection of kidney stones is reliable and effective. Additionally, these algorithms can reduce the reporting time and cost of CT-dependent urolithiasis detection, leading to early diagnosis and management.

Machine Learning for Renal Pathologies: An Updated Survey

Within the literature concerning modern machine learning techniques applied to the medical field, there is a growing interest in the application of these technologies to the nephrological area, especially regarding the study of renal pathologies, because they are very common and widespread in our society, afflicting a high percentage of the population and leading to various complications, up to death in some cases. For these reasons, the authors have considered it appropriate to collect, using one of the major bibliographic databases available, and analyze the studies carried out until February 2022 on the use of machine learning techniques in the nephrological field, grouping them according to the addressed pathologies: renal masses, acute kidney injury, chronic kidney disease, kidney stone, glomerular disease, kidney transplant, and others less widespread. Of a total of 224 studies, 59 were analyzed according to inclusion and exclusion criteria in this review, considering the method used and the type of data available. Based on the study conducted, it is possible to see a growing trend and interest in the use of machine learning applications in nephrology, becoming an additional tool for physicians, which can enable them to make more accurate and faster diagnoses, although there remains a major limitation given the difficulty in creating public databases that can be used by the scientific community to corroborate and eventually make a positive contribution in this area.

A warning system for urolithiasis via retrograde intrarenal surgery using machine learning: an experimental study

Background

To develop a warning system that can prevent or minimize laser exposure resulting in kidney and ureter damage during retrograde intrarenal surgery (RIRS) for urolithiasis. Our study builds on the hypothesis that shock waves of different degrees are delivered to the hand of the surgeon depending on whether the laser hits the stone or tissue.

Methods

A surgical environment was simulated for RIRS by filling the body of a raw whole chicken with water and stones from the human body. We developed an acceleration measurement system that recorded the power signal data for a number of hours, yielding distinguishable characteristics among three different states (idle state, stones, and tissue–laser interface) by conducting fast Fourier transform (FFT) analysis. A discrete wavelet transform (DWT) was used for feature extraction, and a random forest classification algorithm was applied to classify the current state of the laser-tissue interface.

Results

The result of the FFT showed that the magnitude spectrum is different within the frequency range of < 2500 Hz, indicating that the different states are distinguishable. Each recorded signal was cut in only 0.5-s increments and transformed using the DWT. The transformed data were entered into a random forest classifier to train the model. The test result was only measured with the dataset that was isolated from the training dataset. The maximum average test accuracy was > 95%. The procedure was repeated with random signal dummy data, resulting in an average accuracy of 33.33% and proving that the proposed method caused no bias.

Conclusions

Our monitoring system receives the shockwave signals generated from the RIRS urolithiasis treatment procedure and generates the laser irradiance status by rapidly recognizing (in 0.5 s) the current laser exposure state with high accuracy (95%). We postulate that this can significantly minimize surgeon error during RIRS.

Predicting the Stone-Free Status of Percutaneous Nephrolithotomy With the Machine Learning System: Comparative Analysis With Guy’s Stone Score and the S.T.O.N.E Score System

Purpose: The aim of the study was to use machine learning methods (MLMs) to predict the stone-free status after percutaneous nephrolithotomy (PCNL). We compared the performance of this system with Guy’s stone score and the S.T.O.N.E score system.

Materials and Methods: Data from 222 patients (90 females, 41%) who underwent PCNL at our center were used. Twenty-six parameters, including individual variables, renal and stone factors, and surgical factors were used as input data for MLMs. We evaluated the efficacy of four different techniques: Lasso-logistic (LL), random forest (RF), support vector machine (SVM), and Naive Bayes. The model performance was evaluated using the area under the curve (AUC) and compared with that of Guy’s stone score and the S.T.O.N.E score system.

Results: The overall stone-free rate was 50% (111/222). To predict the stone-free status, all receiver operating characteristic curves of the four MLMs were above the curve for Guy’s stone score. The AUCs of LL, RF, SVM, and Naive Bayes were 0.879, 0.803, 0.818, and 0.803, respectively. These values were higher than the AUC of Guy’s score system, 0.800. The accuracies of the MLMs (0.803% to 0.818%) were also superior to the S.T.O.N.E score system (0.788%). Among the MLMs, Lasso-logistic showed the most favorable AUC.

Conclusion: Machine learning methods can predict the stone-free rate with AUCs not inferior to those of Guy’s stone score and the S.T.O.N.E score system.

Artificial intelligence in endourology: emerging technology for individualized care

PURPOSE OF REVIEW

Artificial intelligence in medicine has allowed for efficient processing of large datasets to perform cognitive tasks that facilitate clinical decision-making, and it is an emerging area of research. This review aims to highlight the most pertinent and recent research in artificial intelligence in endourology, where it has been used to optimize stone diagnosis, support decision-making regarding management, predict stone recurrence, and provide new tools for bioinformatics research within endourology.

RECENT FINDINGS

Artificial neural networks (ANN) and machine learning approaches have demonstrated high accuracy in predicting stone diagnoses, stone composition, and outcomes of spontaneous stone passage, shockwave lithotripsy (SWL), or percutaneous nephrolithotomy (PCNL); some of these models outperform more traditional predictive models and existing nomograms. In addition, these approaches have been used to predict stone recurrence, quality of life scores, and provide novel methods of mining the electronic medical record for research.

SUMMARY

Artificial intelligence can be used to enhance existing approaches to stone diagnosis, management, and prevention to provide a more individualized approach to endourologic care. Moreover, it may support an emerging area of bioinformatics research within endourology. However, despite high accuracy, many of the published algorithms lack external validity and require further study before they are more widely adopted.

Development of prediction models of spontaneous ureteral stone passage through machine learning: Comparison with conventional statistical analysis

Objectives

To develop a prediction model of spontaneous ureteral stone passage (SSP) using machine learning and logistic regression and compare the performance of the two models. Indications for management of ureteral stones are unclear, and the clinician determines whether to wait for SSP or perform active treatment, especially in well-controlled patients, to avoid unwanted complications. Therefore, suggesting the possibility of SSP would help make a clinical decision regarding ureteral stones.

Methods

Patients diagnosed with unilateral ureteral stones at our emergency department between August 2014 and September 2018 were included and underwent non-contrast-enhanced computed tomography 4 weeks from the first stone episode. Predictors of SSP were applied to build and validate the prediction model using multilayer perceptron (MLP) with the Keras framework.

Results

Of 833 patients, SSP was observed in 606 (72.7%). SSP rates were 68.2% and 75.6% for stone sizes 5–10 mm and <5 mm, respectively. Stone opacity, location, and whether it was the first ureteral stone episode were significant predictors of SSP. Areas under the curve (AUCs) for receiver operating characteristic (ROC) curves for MLP, and logistic regression were 0.859 and 0.847, respectively, for stones <5 mm, and 0.881 and 0.817, respectively, for 5–10 mm stones.

Conclusion

SSP prediction models were developed in patients with well-controlled unilateral ureteral stones; the performance of the models was good, especially in identifying SSP for 5–10-mm ureteral stones without definite treatment guidelines. To further improve the performance of these models, future studies should focus on using machine learning techniques in image analysis.

The Ascent of Artificial Intelligence in Endourology: a Systematic Review Over the Last 2 Decades

Purpose of Review

To highlight and review the application of artificial intelligence (AI) in kidney stone disease (KSD) for diagnostics, predicting procedural outcomes, stone passage, and recurrence rates. The systematic review was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) checklist.

Recent Findings

This review discusses the newer advancements in AI-driven management strategies, which holds great promise to provide an essential step for personalized patient care and improved decision making. AI has been used in all areas of KSD including diagnosis, for predicting treatment suitability and success, basic science, quality of life (QOL), and recurrence of stone disease. However, it is still a research-based tool and is not used universally in clinical practice. This could be due to a lack of data infrastructure needed to train the algorithms, wider applicability in all groups of patients, complexity of its use and cost involved with it.

Summary

The constantly evolving literature and future research should focus more on QOL and the cost of KSD treatment and develop evidence-based AI algorithms that can be used universally, to guide urologists in the management of stone disease.

Lean: Introduction of a Quality Improvement Concept into Percutaneous Nephrolithotomy to Improve Efficiency while Maintaining Safety

Introduction and objective Standardization of surgical interventions reduces complications and costs and positively impacts intra and postoperative outcomes. Implementation of the lean concept, initially proposed in the auto industry, now becomes an interesting approach in the surgical setting. We want to present the results of how percutaneous nephrolithotripsy (PCNL) in a high-level center can be positively impacted by implementing the lean concept.

Methods We evaluated a total of 140 PCNL procedures. Group 1 included all cases operated prior to implementing the lean concept and group 2 was composed of those operated after implementing the lean concept. We looked for all seven sources of waste to identify and modify our practice to improve efficiency and safety. We then collected intraoperative times and compared the ones prior to those after the implementation.

Results After implementing the lean concept, with an average of six PCNL cases per day, a comparison was made to an equivalent number of cases prior to the lean implementation (group 1). The average total operative time for PCNL preintervention was 138 (confidence interval [CI]: 79 to 170) minutes and postlean intervention was 71.1 (CI: 43 to 157) minutes. Surgical time (cystoscopy to skin closure) was 36.1 (CI: 25 to 50) minutes prelean and 50 minutes postlean (CI: 23 to 154). For this last one, bilateral procedures were performed. Operative room turnover time was 27.8 (CI: 21 to 38) minutes prelean and 5.67 (CI: 3.5 to 12) minutes postlean. Induction time was 16.5 (CI: 5 to 55) minutes prelean and 5.4 (CI: 3.5 to 7.5) minutes postlean.

Conclusion Implementation of the lean concept enables optimization of the surgical procedure, allowing hospitals to reduce costs and standardization.

Artificial intelligence in stone disease

PURPOSE OF REVIEW

Artificial intelligence (AI) is the ability of a machine, or computer, to simulate intelligent behavior. In medicine, the use of large datasets enables a computer to learn how to perform cognitive tasks, thereby facilitating medical decision-making. This review aims to describe advancements in AI in stone disease to improve diagnostic accuracy in determining stone composition, to predict outcomes of surgical procedures or watchful waiting and ultimately to optimize treatment choices for patients.

RECENT FINDINGS

AI algorithms show high accuracy in different realms including stone detection and in the prediction of surgical outcomes. There are machine learning algorithms for outcomes after percutaneous nephrolithotomy, extracorporeal shockwave lithotripsy, and for ureteral stone passage. Some of these algorithms show better predictive capabilities compared to existing scoring systems and nomograms.

SUMMARY

The use of AI can facilitate the development of diagnostic and treatment algorithms in patients with stone disease. Although the generalizability and external validity of these algorithms remain uncertain, the development of highly accurate AI-based tools may enable the urologist to provide more customized patient care and superior outcomes.

Application of Artificial Intelligence-Based Classifiers to Predict the Outcome Measures and Stone-Free Status Following Percutaneous Nephrolithotomy for Staghorn Calculi: Cross-Validation of Data and Estimation of Accuracy

Objective: To develop a decision support system (DSS) for the prediction of the postoperative outcome of a kidney stone treatment procedure, particularly percutaneous nephrolithotomy (PCNL) to serve as a promising tool to provide counseling before an operation. Materials and Methods: The overall procedure includes data collection and prediction model development. Pre-/postoperative variables of 100 patients with staghorn calculus, who underwent PCNL, were collected. For feature vector, variables and categories including patient history variables, kidney stone parameters, and laboratory data were considered. The prediction model was developed using machine learning techniques, which include dimensionality reduction and supervised classification. Multiple classifier scheme was used for prediction. The derived DSS was evaluated by running the leave-one-patient-out cross-validation approach on the data set. Results: The system provided favorable accuracy (81%) in predicting the outcome of a treatment procedure. Performance in predicting the stone-free rate with the Minimum Redundancy Maximum Relevance feature (MRMR) treatment extracting top 3 features using Random Forest (RF) was 67%, with MRMR treatment extracting top 5 features using RF was 63%, and with MRMR treatment extracting top 10 features using Decision Tree was 62%. The statistical significance using standard error between the best area under the curves (AUCs) obtained from the Linear Discriminant Analysis (LDA) and MRMR. The results obtained from the LDA approach (0.81 AUC) was statistically significant (p = 0.027, z = 2.21) from the MRMR (0.64 AUC) (p = 0.05). Conclusion: The promising results of the developed DSS could be used in assisting urologists to provide counseling, predict a surgical outcome, and ultimately choose an appropriate surgical treatment for removing kidney stones.

A step edge detector based on bilinear transformation

Nowadays, Canny edge detector is considered to be one of the best edge detection approaches for the images with step form. Various overgeneralized versions of these edge detectors have been offered up to now, e.g. Saryazdi edge detector. This paper proposes a new discrete version of edge detection which is obtained from Shen-Castan and Saryazdi filters by using bilinear transformation. Different experimentations are conducted to decide the suitable parameters of the proposed edge detector and to examine its validity. To evaluate the strength of the proposed model, the results are compared to Canny, Sobel, Prewitt, LOG and Saryazdi methods. Finally, by calculation of mean square error (MSE) and peak signal-to-noise ratio (PSNR), the value of PSNR is always equal to or greater than the PSNR value of suggested methods. Moreover, by calculation of Baddeley’s error metric (BEM) on ten test images from the Berkeley Segmentation DataSet (BSDS), we show that the proposed method outperforms the other methods. Therefore, visual and quantitative comparison shows the efficiency and strength of proposed method.

A classification model based on svm and fuzzy rough set for network intrusion detection

Intrusion Detection Systems (IDS) are designed to provide security into computer networks. Different classification models such as Support Vector Machine (SVM) has been successfully applied on the network data. Meanwhile, the extension or improvement of the current models using prototype selection simultaneous with their training phase is crucial due to the serious inefficacies during training (i.e. learning overhead). This paper introduces an improved model for prototype selection. Applying proposed prototype selection along with SVM classification model increases attack discovery rate. In this article, we use fuzzy rough sets theory (FRST) for prototype selection to enhance SVM in intrusion detection. Testing and evaluation of the proposed IDS have been mainly performed on NSL-KDD dataset as a refined version of KDD-CUP99. Experimentations indicate that the proposed IDS outperforms the basic and simple IDSs and modern IDSs in terms of precision, recall, and accuracy rate.

Artificial intelligence (AI) in urology-Current use and future directions: An iTRUE study

OBJECTIVE

Artificial intelligence (AI) is used in various urological conditions such as urolithiasis, pediatric urology, urogynecology, benign prostate hyperplasia (BPH), renal transplant, and uro-oncology. The various models of AI and its application in urology subspecialties are reviewed and discussed.

MATERIAL AND METHODS

Search strategy was adapted to identify and review the literature pertaining to the application of AI in urology using the keywords "urology," "artificial intelligence," "machine learning," "deep learning," "artificial neural networks," "computer vision," and "natural language processing" were included and categorized. Review articles, editorial comments, and non-urologic studies were excluded.

RESULTS

The article reviewed 47 articles that reported characteristics and implementation of AI in urological cancer. In all cases with benign conditions, artificial intelligence was used to predict outcomes of the surgical procedure. In urolithiasis, it was used to predict stone composition, whereas in pediatric urology and BPH, it was applied to predict the severity of condition. In cases with malignant conditions, it was applied to predict the treatment response, survival, prognosis, and recurrence on the basis of the genomic and biomarker studies. These results were also found to be statistically better than routine approaches. Application of radiomics in classification and nuclear grading of renal masses, cystoscopic diagnosis of bladder cancers, predicting Gleason score, and magnetic resonance imaging with computer-assisted diagnosis for prostate cancers are few applications of AI that have been studied extensively.

CONCLUSIONS

In the near future, we will see a shift in the clinical paradigm as AI applications will find their place in the guidelines and revolutionize the decision-making process.

A Novel Clinical-Radiomics Model Pre-operatively Predicted the Stone-Free Rate of Flexible Ureteroscopy Strategy in Kidney Stone Patients

Purpose: The purpose of the study is to develop and validate a novel clinical-radiomics nomogram model for pre-operatively predicting the stone-free rate of flexible ureteroscopy (fURS) in kidney stone patients. Patients and Methods: Altogether, 2,129 fURS cases with kidney stones were retrospectively analyzed, and 264 patients with a solitary kidney stone were included in a further study. For lower calyx calculi, a radiomics model was generated in a primary cohort of 99 patients who underwent non-contrast-enhanced computed tomography (NCCT). Radiomics feature selection and signature building were conducted by using the least absolute shrinkage and selection operator (LASSO) method. Multivariate logistic regression analysis was employed to build a model incorporating radiomics and potential clinical factors. Model performance was evaluated by its discrimination, calibration, and clinical utility. The model was internally validated in 43 patients. Results: The overall success rate of fURS was 72%, while the stone-free rate (SFR) for lower calyx calculi and non-lower calyx calculi was 56.3 and 90.16%, respectively. On multivariate logistic regression analysis of the primary cohort, independent predictors for SFR were radiomics signature, stone volume, operator experience, and hydronephrosis level, which were all selected into the nomogram. The area under the curve (AUC) of clinical-radiomics model was 0.949 and 0.947 in the primary and validation cohorts, respectively. Moreover, the calibration curve showed a satisfactory predictive accuracy, and the decision curve analysis indicated that the nomogram has superior clinical application value. Conclusion: In this novel clinical-radiomics model, the radiomics scores, stone volume, hydronephrosis level, and operator experience were crucial for the flexible ureteroscopy strategy.

Numerical function optimization by conditionalized PSO algorithm

A lot of research has been directed to the new optimizers that can find a suboptimal solution for any optimization problem named as heuristic black-box optimizers. They can find the suboptimal solutions of an optimization problem much faster than the mathematical programming methods (if they find them at all). Particle swarm optimization (PSO) is an example of this type. In this paper, a new modified PSO has been proposed. The proposed PSO incorporates conditional learning behavior among birds into the PSO algorithm. Indeed, the particles, little by little, learn how they should behave in some similar conditions. The proposed method is named Conditionalized Particle Swarm Optimization (CoPSO). The problem space is first divided into a set of subspaces in CoPSO. In CoPSO, any particle inside a subspace will be inclined towards its best experienced location if the particles in its subspace have low diversity; otherwise, it will be inclined towards the global best location. The particles also learn to speed-up in the non-valuable subspaces and to speed-down in the valuable subspaces. The performance of CoPSO has been compared with the state-of-the-art methods on a set of standard benchmark functions.

Cluster ensemble selection using balanced normalized mutual information

A bad partition in an ensemble will be removed by a cluster ensemble selection framework from the final ensemble. It is the main idea in cluster ensemble selection to remove these partitions (bad partitions) from the selected ensemble. But still, it is likely that one of them contains some reliable clusters. Therefore, it may be reasonable to apply the selection phase on cluster level. To do this, a cluster evaluation metric is needed. Some of these metrics have been recently introduced; each of them has its limitations. The weak points of each method have been addressed in the paper. Subsequently, a new metric for cluster assessment has been introduced. The new measure is named Balanced Normalized Mutual Information (BNMI) criterion. It balances the deficiency of the traditional NMI-based criteria. Additionally, an innovative cluster ensemble approach has been proposed. To create the consensus partition considering the elected clusters, a set of different aggregation-functions (called also consensus-functions) have been utilized: the ones which are based upon the co-association matrix (CAM), the ones which are based on hyper graph partitioning algorithms, and the ones which are based upon intermediate space. The experimental study indicates that the state-of-the-art cluster ensemble methods are outperformed by the proposed cluster ensemble approach.

Artificial intelligence in the diagnosis, treatment and prevention of urinary stones

PURPOSE OF REVIEW

There has a been rapid progress in the use of artificial intelligence in all aspects of healthcare, and in urology, this is particularly astute in the overall management of urolithiasis. This article reviews advances in the use of artificial intelligence for the diagnosis, treatment and prevention of urinary stone disease over the last 2 years. Pertinent studies were identified via a nonsystematic review of the literature performed using MEDLINE and the Cochrane database.

RECENT FINDINGS

Twelve articles have been published, which met the inclusion criteria. This included three articles in the detection and diagnosis of stones, six in the prediction of postprocedural outcomes including percutaneous nephrolithotomy and shock wave lithotripsy, and three in the use of artificial intelligence in prevention of stone disease by predicting patients at risk of stones, detecting the stone type via digital photographs and detecting risk factors in patients most at risk of not attending outpatient appointments.

SUMMARY

Our knowledge of artificial intelligence in urology has greatly advanced in the last 2 years. Its role currently is to aid the endourologist as opposed to replacing them. However, the ability of artificial intelligence to efficiently process vast quantities of data, in combination with the shift towards electronic patient records provides increasingly more 'big data' sets. This will allow artificial intelligence to analyse and detect novel diagnostic and treatment patterns in the future.

AN ARTIFICIAL NEURAL NETWORK-BASED MODEL FOR PREDICTING ANNUAL DOSE IN HEALTHCARE WORKERS OCCUPATIONALLY EXPOSED TO DIFFERENT LEVELS OF IONIZING RADIATION

We presented an artificial intelligence-based model to predict annual effective dose (AED) value of health workers. Potential factors affecting AED and the results of annual blood tests were collected from 91 radiation workers. Filter-based feature selection strategy revealed that the eight factors plate, red cell distribution width (RDW), educational degree, nonacademic course in radiation protection (hour), working hours per month, department and the number of procedures done per year and work in radiology department or not (0,1) were the most important predictors for AED. The prediction model was developed using a multilayer perceptron neural network and these prediction parameters as inputs. The model provided favorable accuracy in predicting AED value while a regression model did not. There was a strong linear relationship between the predicted AED values and the measured doses (R-value =0.89 for training samples and 0.86 for testing samples). These results are promising and show that artificial neural networks can be used to improve/facilitate dose estimation process.

Predicting the Postoperative Outcome of Percutaneous Nephrolithotomy with Machine Learning System: Software Validation and Comparative Analysis with Guy's Stone Score and the CROES Nomogram

Purpose: To validate the output of a machine learning-based software as an intelligible interface for predicting multiple outcomes after percutaneous nephrolithotomy (PCNL). We compared the performance of this system with Guy's stone score (GSS) and the Clinical Research Office of Endourological Society (CROES) nomogram. Patients and Methods: Data from 146 adult patients (87 males, 59%) who underwent PCNL at our institute were used. To validate the system, accuracy of the software for predicting each postoperative outcome was compared with the actual outcome. Similarly, preoperative data were analyzed with GSS and CROES nomograms to determine stone-free status as predicted by these nomograms. A receiver operating characteristic (ROC) curve was generated for each scoring system, and the area under the ROC curve (AUC) was calculated and used to assess the predictive performance of all three models. Results: Overall stone-free rate was 72.6% (106/146). Forty of 146 patients (27.4%) were scheduled for 42 ancillary procedures (extracorporeal shockwave lithotripsy [SWL] [n = 31] or repeat PCNL [n = 11]) to manage residual renal stones. Overall, the machine learning system predicted the PCNL outcomes with an accuracy ranging between 80% and 95.1%. For predicting the stone-free status, the AUC for the software (0.915) was significantly larger than the AUC for GSS (0.615) or CROES nomograms (0.621) (p < 0.001). Conclusion: At the internal institutional level, the machine learning-based software was a promising tool for recording, processing, and predicting outcomes after PCNL. Validation of this system against an external dataset is highly recommended before its widespread application.