Artificial intelligence in endourology: emerging technology for individualized care

Artificial Intelligence in Endourology: Maximizing the Promise Through Consideration of the Principles of Diffusion of Innovation Theory

Introduction: Diffusion of Innovation Theory explains how ideas or products gain momentum and diffuse (or spread) through specific populations or social systems over time. The theory analyzes primary influencers of the spread of new ideas, including the innovation itself, communication channels, time, and social systems. Methods: The current study reviewed published medical literature to identify studies and applications of artificial intelligence (AI) in endourology and used E.M. Rogers' Diffusion of Innovation Theory to analyze the primary influencers of the adoption of AI in endourological care. The insights gained were triaged and prioritized into AI application-related action items or "tips" for facilitating the appropriate diffusion of the most valuable endourological innovations. Results: Published medical literature indicates that AI is still a research-based tool in endourology and is not widely used in clinical practice. The published studies have presented AI models and algorithms to assist with stone disease detection (n = 17), the prediction of management outcomes (n = 18), the optimization of operative procedures (n = 9), and the elucidation of stone disease chemistry and composition (n = 24). Five tips for facilitating appropriate adoption of endourological AI are: (1) Develop/prioritize training programs to establish the foundation for effective use; (2) create appropriate data infrastructure for implementation, including its maintenance and evolution over time; (3) deliver AI transparency to gain the trust of endourology stakeholders; (4) adopt innovations in the context of continuous quality improvement Plan-Do-Study-Act cycles as these approaches have proven track records for improving care quality; and (5) be realistic about what AI can/cannot currently do and document to establish the basis for shared understanding. Conclusion: Diffusion of Innovation Theory provides a framework for analyzing the influencers of the adoption of AI in endourological care. The five tips identified through this research may be used to facilitate appropriate diffusion of the most valuable endourological innovations.

Inflammation indexes and machine-learning algorithm in predicting urethroplasty success

PURPOSE

To assess the predictive capability of hematological inflammatory markers for urethral stricture recurrence after primary urethroplasty and to compare traditional statistical methods with a machine-learning-based artificial intelligence algorithm.

MATERIALS AND METHODS

Two hundred eighty-seven patients who underwent primary urethroplasty were scanned. Ages, smoking status, comorbidities, hematological inflammatory parameters (neutrophil-lymphocyte ratios, platelet-lymphocyte ratios [PLR], systemic immune-inflammation indexes [SII], and pan-immune-inflammation values [PIV]), stricture characteristics, history of previous direct-visual internal urethrotomy, urethroplasty techniques, and grafts/flaps placements were collected. Patients were followed up for one year for recurrence and grouped accordingly. Univariate and multivariate logistic regression analyses were conducted to create a predictive model. Additionally, a machine-learning-based logistic regression analysis was implemented to compare predictive performances. p<0.05 was considered statistically significant.

RESULTS

Comparative analysis between the groups revealed statistically significant differences in stricture length (p=0.003), localization (p=0.027), lymphocyte counts (p=0.008), PLR (p=0.003), SII (p=0.003), and PIV (p=0.001). In multivariate analysis, stricture length (odds ratio [OR] 1.230, 95% confidence interval [CI] 1.142-1.539, p<0.0001) and PIV (OR 1.002, 95% CI 1.000-1.003, p=0.039) were identified as significant predictors of recurrence. Classical logistic regression model exhibited a sensitivity of 0.76, specificity of 0.43 with an area under curve (AUC) of 0.65. However, the machine-learning algorithm outperformed traditional methods achieving a sensitivity of 0.80, specificity of 0.76 with a higher AUC of 0.82.

CONCLUSIONS

PIV and machine-learning algorithms shows promise on predicting urethroplasty outcomes, potentially leading to develop possible nomograms. Evolving machine-learning algorithms will contribute to more personalized and accurate approaches in managing urethral stricture.

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.

Design and Validation of a Deep Learning Model for Renal Stone Detection and Segmentation on Kidney-Ureter-Bladder Images

Kidney-ureter-bladder (KUB) imaging is used as a frontline investigation for patients with suspected renal stones. In this study, we designed a computer-aided diagnostic system for KUB imaging to assist clinicians in accurately diagnosing urinary tract stones. The image dataset used for training and testing the model comprised 485 images provided by Kaohsiung Chang Gung Memorial Hospital. The proposed system was divided into two subsystems, 1 and 2. Subsystem 1 used Inception-ResNetV2 to train a deep learning model on preprocessed KUB images to verify the improvement in diagnostic accuracy with image preprocessing. Subsystem 2 trained an image segmentation model using the ResNet hybrid, U-net, to accurately identify the contours of renal stones. The performance was evaluated using a confusion matrix for the classification model. We conclude that the model can assist clinicians in accurately diagnosing renal stones via KUB imaging. Therefore, the proposed system can assist doctors in diagnosis, reduce patients' waiting time for CT scans, and minimize the radiation dose absorbed by the body.

Ureteroscopy and lasertripsy with pop dusting using high power holmium laser for large urinary stones > 15 mm: 6.5-year prospective outcomes from a high-volume stone center

INTRODUCTION

Ureteroscopy and stone lasertripsy (URSL) is a recognized technique for treatment of urinary tract stones. Holmium:Yag laser has been successfully used for this purpose for the last two decades. More lately, pulse modulation with Moses technology and high power lasers have been introduced with the result of faster and more efficient stone lasertripsy. Pop dusting is a two-stage combined treatment using a long pulse Ho:YAG laser, initially in contact mode with the stone 'dusting' (0.2-0.5 J/40-50 Hz) followed by non-contact mode 'pop-dusting' (0.5-0.7 J/20-50 Hz). We wanted to look at the outcomes of lasertripsy for renal and ureteric stones using a high-power laser machine.

METHODS

Over a period of 6.5 years (January 2016-May 2022), we prospectively collected data for patients undergoing URSL for stones larger than 15 mm treated using high power Ho:YAG laser (60W Moses or 100W laser). Patient parameters, stone demographics and outcomes of URSL were analyzed.

RESULTS

A total of 201 patients, underwent URSL for large urinary stones. In 136 patients (61.6%) stones were multiple and the mean single and cumulative stone size was 18 mm and 22.4 mm respectively. A pre- and post-operative stent was placed in 92 (41.4%) and 169 (76%) respectively. The initial and final stone free rate (SFR) were 84.5% and 94% respectively and 10% patients underwent additional procedure to achieve stone free status. 7 (3.9%) complications were recorded, all related to UTI/sepsis, with 6 Clavien II and 1 Clavien IVa complication.

CONCLUSION

Dusting and pop-dusting has shown to be successful and safe with the ability to treat large, bilateral or multiple stones with low retreatment and complication rates.

Fifty years of basic and clinical renal stone research: have we achieved major breakthroughs? A debate

PURPOSE OF REVIEW

After 50 years of basic and clinical renal stone research, it is appropriate to evaluate whether breakthroughs have been achieved and if so, how they may be harnessed to combat stone disease therapeutically and prophylactically.

RECENT FINDINGS

Regarding stone therapeutics and prophylaxis, recent innovative studies are sparse. Researchers have resorted to publishing articles derived from data mining. Stone incidence and prevalence have increased during the past 50 years, suggesting the absence of any major breakthroughs. However, new sciences and technologies have created fresh opportunities. Information technology stores huge epidemiological databases leading to identification of new risk factors. Genetic coding has prompted identification of monogenic diseases associated with urolithiasis. Genome-wide association studies in combination with epigenomics, transcriptomics, proteomics, and metabolomics are providing new insights. High-throughput and culture-independent techniques promise to define the impact of microbiome on stone formation while artificial intelligent techniques contribute to diagnosis and prediction of treatment outcomes. These technologies, as well as those which are advancing surgical treatment of stones represent major breakthroughs in stone research.

SUMMARY

Although efforts to cure stones have not yielded major breakthroughs, technological advances have improved surgical management of this disease and represent significant headway in applied stone research.

Artificial Intelligence Can Guide Antibiotic Choice in Recurrent UTIs and Become an Important Aid to Improve Antimicrobial Stewardship

BACKGROUND

A correct approach to recurrent urinary tract infections (rUTIs) is an important pillar of antimicrobial stewardship. We aim to define an Artificial Neural Network (ANN) for predicting the clinical efficacy of the empiric antimicrobial treatment in women with rUTIs.

METHODS

We extracted clinical and microbiological data from 1043 women. We trained an ANN on 725 patients and validated it on 318.

RESULTS

The ANN showed a sensitivity of 87.8% and specificity of 97.3% in predicting the clinical efficacy of empirical therapy. The previous use of fluoroquinolones (HR = 4.23; p = 0.008) and cephalosporins (HR = 2.81; p = 0.003) as well as the presence of Escherichia coli with resistance against cotrimoxazole (HR = 3.54; p = 0.001) have been identified as the most important variables affecting the ANN output decision predicting the fluoroquinolones-based therapy failure. A previous isolation of Escherichia coli with resistance against fosfomycin (HR = 2.67; p = 0.001) and amoxicillin-clavulanic acid (HR = 1.94; p = 0.001) seems to be the most influential variable affecting the output decision predicting the cephalosporins- and cotrimoxazole-based therapy failure. The previously mentioned Escherichia coli with resistance against cotrimoxazole (HR = 2.35; p < 0.001) and amoxicillin-clavulanic acid (HR = 3.41; p = 0.007) seems to be the most influential variable affecting the output decision predicting the fosfomycin-based therapy failure.

CONCLUSIONS

ANNs seem to be an interesting tool to guide the antimicrobial choice in the management of rUTIs at the point of care.

Deep Learning Model for Computer-Aided Diagnosis of Urolithiasis Detection from Kidney-Ureter-Bladder Images

Kidney-ureter-bladder (KUB) imaging is a radiological examination with a low cost, low radiation, and convenience. Although emergency room clinicians can arrange KUB images easily as a first-line examination for patients with suspicious urolithiasis, interpreting the KUB images correctly is difficult for inexperienced clinicians. Obtaining a formal radiology report immediately after a KUB imaging examination can also be challenging. Recently, artificial-intelligence-based computer-aided diagnosis (CAD) systems have been developed to help clinicians who are not experts make correct diagnoses for further treatment more effectively. Therefore, in this study, we proposed a CAD system for KUB imaging based on a deep learning model designed to help first-line emergency room clinicians diagnose urolithiasis accurately. A total of 355 KUB images were retrospectively collected from 104 patients who were diagnosed with urolithiasis at Kaohsiung Chang Gung Memorial Hospital. Then, we trained a deep learning model with a ResNet architecture to classify KUB images in terms of the presence or absence of kidney stones with this dataset of pre-processed images. Finally, we tuned the parameters and tested the model experimentally. The results show that the accuracy, sensitivity, specificity, and F1-measure of the model were 0.977, 0.953, 1, and 0.976 on the validation set and 0.982, 0.964, 1, and 0.982 on the testing set, respectively. Moreover, the results demonstrate that the proposed model performed well compared to the existing CNN-based methods and was able to detect urolithiasis in KUB images successfully. We expect the proposed approach to help emergency room clinicians make accurate diagnoses and reduce unnecessary radiation exposure from computed tomography (CT) scans, along with the associated medical costs.