Artificial Intelligence in Urology: Application of a Machine Learning Model to Predict the Risk of Urolithiasis in a General Population.

This research presents our application of artificial intelligence (AI) in predicting urolithiasis risk. Previous applications, including AI for stone disease, have focused on stone composition and aiding diagnostic imaging. AI applications centered around patient-specific characteristics, lifestyle considerations, and diet have been limited. Our study comprised a robust sample size of 976 Chilean participants, with meticulously analyzed demographic, lifestyle, and health data through a comprehensive questionnaire. We developed a predictive model using various classifiers, including logistic regression, decision trees, random forests, and extra trees, reaching high accuracy (88%) in identifying individuals at risk of kidney stone formation. Key protective factors highlighted by the algorithm include the pivotal role of hydration, physical activity, and dietary patterns that played a crucial role, emphasizing the protective nature of higher fruit and vegetable intake, balanced dairy consumption, and the nuanced impact of specific protein sources on kidney stone risk. In contrast, identified risk factors encompassed gender disparities with males found to be 2.31 times more likely to develop kidney stones than females. Thirst and self-perceived dark urine color emerged as strong predictors, with a significant increase in the likelihood of stone formation. The development of predictive tools with AI, in urolithiasis management signifies a paradigm shift toward more precise and personalized health care. The algorithm's ability to process extensive datasets, including dietary habits, heralds a new era of data-driven medical practice. This research underscores the transformative impact of AI in medical diagnostics and prevention, paving the way for a future where health care interventions are not only more effective but also tailored to individual patient needs. In this case, AI is an important tool that can help patients stay healthy, prevent diseases, and make informed decisions about their overall well-being.

Characteristics and Quality of Online Searches for Direct Anterior Versus Posterior Approach for Total Hip Arthroplasty.

BACKGROUND: Online resources are important for patient self-education and reflect public interest. We described commonly asked questions regarding the direct anterior versus posterior approach (DAA, PA) to total hip arthroplasty (THA) and the quality of associated websites. METHODS: We extracted the top 200 questions and websites in Google's "People Also Ask" section for 8 queries on January 8, 2023, and grouped websites and questions into DAA, PA, or comparison. Questions were categorized using Rothwell's classification (fact, policy, value) and THA-relevant subtopics. Websites were evaluated by information source, Journal of the American Medical Association Benchmark Criteria (credibility), DISCERN survey (information quality), and readability. RESULTS: We included 429 question/website combinations (questions: 52.2% DAA, 21.2% PA, 26.6% comparison; websites: 39.0% DAA, 11.0% PA, 9.6% comparison). Per Rothwell's classification, 56.2% of questions were fact, 31.7% value, 10.0% policy, and 2.1% unrelated. The THA-specific question subtopics differed between DAA and PA (P < .001), specifically for recovery timeline (DAA 20.5%, PA 37.4%), indications/management (DAA 13.4%, PA 1.1%), and technical details (DAA 13.8%, PA 5.5%). Information sources differed between DAA (61.7% medical practice/surgeon) and PA websites (44.7% government; P < .001). The median Journal of the American Medical Association Benchmark score was 1 (limited credibility, interquartile range 1 to 2), with the lowest scores for DAA websites (P < .001). The median DISCERN score was 55 ("good" quality, interquartile range 43 to 65), with the highest scores for comparison websites (P < .001). Median Flesch-Kincaid Grade Level scores were 12th grade level for both DAA and PA (P = .94). CONCLUSIONS: Patients' informational interests can guide counseling. Internet searches that explicitly compare THA approaches yielded websites that provide higher-quality information. Providers may also advise patients that physician websites and websites only describing the DAA may have less balanced perspectives, and limited information regarding surgical approaches is available from social media resources.

Transurethral Resection of Bladder Tumor Outcomes Are Predicted by a 5-Item Frailty Index.

OBJECTIVE: To evaluate the mFI-5 as a predictor of postoperative outcomes following transurethral resection of bladder tumor (TURBT). METHODS: The National Surgical Quality Improvement Program database was queried for TURBT cases from 2015-2019. mFI-5 scores were calculated by assigning a point to chronic obstructive pulmonary disease, congestive heart failure, dependent functional status, hypertension, and diabetes. Patients were stratified by mFI-5 scores. Demographics and 30-day outcomes including Clavien-Dindo (CD) complications, mortality, and increased healthcare resource utilization (HCRU) were compared. HCRU outcomes included prolonged length of stay, unplanned readmission, and discharge to continued care. Multivariate regression assessed the predictive value of mFI-5 scores on outcomes. RESULTS: 40,278 TURBT cases were identified (mFI-5 =0: 12,400, mFI-5 =1: 17,328, mFI-5 =2: 9225, mFI-5 ≥3: 1416). Patients with higher mFI-5 scores were more likely to be older, male, White, and have larger tumors, all P < .05. Increasing mFI-5 scores resulted in increased frequency of all adverse outcomes, all P < .001. On multivariate analysis, mFI-5 ≥ 3 classification was a predictor of CD I/II (OR=1.280), CD IV (OR=2.539), mortality (OR=2.202), HCRU (OR=2.094), prolonged length of stay (OR=2.136), discharge to continued care (OR=3.401), and unplanned readmission (OR=1.705), all P < .05. A mFI-5 ≥ 3 demonstrated a sensitivity ranging from 6.0%-13.5% and a specificity ranging from 96.6%-97.0% for all outcomes. CONCLUSION: The mFI-5 is an easily ascertainable preoperative risk assessment tool that is a predictor of adverse clinical and HCRU outcomes following TURBT.

Use of ChatGPT for Determining Clinical and Surgical Treatment of Lumbar Disc Herniation With Radiculopathy: A North American Spine Society Guideline Comparison.

OBJECTIVE: Large language models like chat generative pre-trained transformer (ChatGPT) have found success in various sectors, but their application in the medical field remains limited. This study aimed to assess the feasibility of using ChatGPT to provide accurate medical information to patients, specifically evaluating how well ChatGPT versions 3.5 and 4 aligned with the 2012 North American Spine Society (NASS) guidelines for lumbar disk herniation with radiculopathy. METHODS: ChatGPT's responses to questions based on the NASS guidelines were analyzed for accuracy. Three new categories-overconclusiveness, supplementary information, and incompleteness-were introduced to deepen the analysis. Overconclusiveness referred to recommendations not mentioned in the NASS guidelines, supplementary information denoted additional relevant details, and incompleteness indicated omitted crucial information from the NASS guidelines. RESULTS: Out of 29 clinical guidelines evaluated, ChatGPT-3.5 demonstrated accuracy in 15 responses (52%), while ChatGPT-4 achieved accuracy in 17 responses (59%). ChatGPT-3.5 was overconclusive in 14 responses (48%), while ChatGPT-4 exhibited overconclusiveness in 13 responses (45%). Additionally, ChatGPT-3.5 provided supplementary information in 24 responses (83%), and ChatGPT-4 provided supplemental information in 27 responses (93%). In terms of incompleteness, ChatGPT-3.5 displayed this in 11 responses (38%), while ChatGPT-4 showed incompleteness in 8 responses (23%). CONCLUSION: ChatGPT shows promise for clinical decision-making, but both patients and healthcare providers should exercise caution to ensure safety and quality of care. While these results are encouraging, further research is necessary to validate the use of large language models in clinical settings.

ChatGPT and its Role in the Decision-Making for the Diagnosis and Treatment of Lumbar Spinal Stenosis: A Comparative Analysis and Narrative Review.

STUDY DESIGN: Comparative Analysis and Narrative Review. OBJECTIVE: To assess and compare ChatGPT's responses to the clinical questions and recommendations proposed by The 2011 North American Spine Society (NASS) Clinical Guideline for the Diagnosis and Treatment of Degenerative Lumbar Spinal Stenosis (LSS). We explore the advantages and disadvantages of ChatGPT's responses through an updated literature review on spinal stenosis. METHODS: We prompted ChatGPT with questions from the NASS Evidence-based Clinical Guidelines for LSS and compared its generated responses with the recommendations provided by the guidelines. A review of the literature was performed via PubMed, OVID, and Cochrane on the diagnosis and treatment of lumbar spinal stenosis between January 2012 and April 2023. RESULTS: 14 questions proposed by the NASS guidelines for LSS were uploaded into ChatGPT and directly compared to the responses offered by NASS. Three questions were on the definition and history of LSS, one on diagnostic tests, seven on non-surgical interventions and three on surgical interventions. The review process found 40 articles that were selected for inclusion that helped corroborate or contradict the responses that were generated by ChatGPT. CONCLUSIONS: ChatGPT's responses were similar to findings in the current literature on LSS. These results demonstrate the potential for implementing ChatGPT into the spine surgeon's workplace as a means of supporting the decision-making process for LSS diagnosis and treatment. However, our narrative summary only provides a limited literature review and additional research is needed to standardize our findings as means of validating ChatGPT's use in the clinical space.

Open retropubic prostatectomy in a patient with bladder exstrophy for management of hematuria and urethral discharge - A case report.

Bladder exstrophy (BE) is a rare congenital disorder causing bladder and urethral malformation due to an abdominal wall embryological defect. Traditionally, BE had a poor life expectancy, but advances now offer a normal lifespan. A 57-year-old male with BE history and ureterosigmoidostomy repair presented with intractable hematuria, urethral discharge, and recurrent prostatic infections. He underwent retropubic subtotal prostatectomy without major complications, resolving urinary symptoms. Advances in BE management extend patient lifespans. This case demonstrates successful surgical management of hematuria and urethral discharge through radical prostatectomy in an adult with a history of BE.

Infections After Adoption of Antibiogram-directed Prophylaxis and Intracorporeal Urinary Diversion for Robot-assisted Radical Cystectomy.

BACKGROUND: Enhanced recovery after surgery (ERAS) has significantly decreased the morbidity associated with radical cystectomy. However, infectious complications including sepsis, urinary tract (UTIs), wound (WIs), and intra-abdominal (AIs) infections remain common. OBJECTIVE: To assess whether intracorporeal urinary diversion (ICUD) and antibiogram-directed antimicrobial prophylaxis would decrease infections after robotic-assisted radical cystectomy (RARC). DESIGN, SETTING, AND PARTICIPANTS: A retrospective analysis was performed of a prospectively maintained database of patients undergoing RARC between 2014 and 2022 at a tertiary care institution, identifying two groups based on adherence to a prospectively implemented modified ERAS protocol for RARC: modified-ERAS-ICUD and antibiogram-directed ampicillin-sulbactam, gentamicin, and fluconazole prophylaxis were utilized (from January 2019 to present time), and unmodified-ERAS-extracorporeal urinary diversion (UD) and guideline-recommended cephalosporin-based prophylaxis regimen were utilized (from November 2014 to June 2018). Patients receiving other prophylaxis regimens were excluded. INTERVENTION: ICUD and antibiogram-directed infectious prophylaxis. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The primary outcome was UTIs within 30 and 90 d postoperatively. The secondary outcomes were WIs, AIs, and sepsis within 30 and 90 d postoperatively, and Clostridioides difficile infection (CDI) within 90 d postoperatively. RESULTS AND LIMITATIONS: A total of 396 patients were studied (modified-ERAS: 258 [65.2%], unmodified-ERAS: 138 [34.8%]). UD via a neobladder was more common in the modified-ERAS cohort; all other intercohort demographic differences were not statistically different. Comparing cohorts, modified-ERAS had significantly reduced rates of 30-d (7.8% vs 15.9%, p = 0.027) and 90-d UTIs (11.2% vs 25.4%, p = 0.001), and 30-d WIs (1.2% vs. 8.7%, p < 0.001); neither group had a WI after 30 d. Rates of AIs, sepsis, and CDI did not differ between groups. On multivariate regression, the modified-ERAS protocol correlated with a reduced risk of UTIs and WIs (all p < 0.01). The primary limitation is the retrospective study design. CONCLUSIONS: Utilization of ICUD and antibiogram-based prophylaxis correlates with significantly decreased UTIs and WIs after RARC. PATIENT SUMMARY: In this study of infections after robotic radical cystectomy for bladder cancer, we found that intracorporeal (performed entirely inside the body) urinary diversion and an institution-specific antibiogram-directed antibiotic prophylaxis regimen led to fewer urinary tract infections and wound infections at our institution.