Background and objectives: Although minimally invasive percutaneous nephrolithotomy (MPCNL) has demonstrated its efficacy, complete stone clearance was not always achieved, necessitating a second procedure. The purpose of this study was to evaluate factors associated with residual stone rate, operative duration, complications, and hospital stay, in order to develop algorithms for pre-operative prognosis and planning. Materials and Methods: This retrospective study involved 163 Bulgarian patients who underwent MPCNL with Holmium: YAG lithotripsy for the treatment of kidney stones. Patients were considered stone-free if no visible fragments (<3 mm) were found on nephroscopy at the end of the procedure, as well as on postoperative X-ray and abdominal ultrasound on the first postoperative day. Results: Immediate postoperative stone-free outcome was attained for 83.43% of the patients (136/163). Residuals were associated with staghorn stones (OR = 72.48, 95% CI: 5.76 to 91.81); stones in two locations (OR = 21.91, 95% CI: 4.15 to 137.56); larger stone size (OR = 1.12, 95% CI: 1.006 to 1.25); and higher density (OR = 1.03, 95% CI:1.005 to 1.06). The overall categorization accuracy for these factors was 93.80%, AUC = 0.971 (95% CI: 0.932 to 0.991), 89.71% sensitivity, and 96.30% specificity. Predictors of prolonged operative duration were staghorn stones and volume, R-square (adj.) = 39.00%, p < 0.001. Longer hospitalization was predicted for patients with hydronephrosis and staghorn stones, R-square (adj.) = 6.82%, p = 0.003. Post-operative complications were rare, predominantly of Clavien-Dindo Grade 1, and were more frequent in patients with hydronephrosis. We did not find a link between their occurrence and the outcome of MPCNL. Conclusions: Staghorn stones and stones in more than one location showed the strongest association with residual stone rate. Staghorn stones and larger volume were linked with a longer operative duration. Hydronephrosis increased the risk of complications and longer hospitalization.

The development of the Gleason grading system has proven to be an irreplaceable tool in prostate cancer diagnostics within urology. Despite the advancements and developments in diagnostics, there remains a discrepancy in the grading process among even the most experienced pathologists. AI algorithms have demonstrated potential in detecting cancer and assigning Gleason grades, offering a solution to the issue of significant variability among pathologists’ evaluations. Our paper explores the evolving role of AI in prostate cancer histopathology, with a key focus on outcomes and the reliability of various AI algorithms for Gleason pattern assessment. We conducted a non-systematic review of the published literature to examine the role of artificial intelligence in Gleason pattern diagnostics. The PubMed and Google Scholar databases were searched to gather pertinent information about recent advancements in artificial intelligence and their impact on Gleason patterns. We found that AI algorithms are increasingly being used to identify Gleason patterns in prostate cancer, with recent studies showing promising advancements that surpass traditional diagnostic methods. These findings highlight AI’s potential to be integrated into clinical practice, enhancing pathologists’ workflows and improving patient outcomes. The inter-observer variability in Gleason grading has seen an improvement in efficiency with the implementation of AI. Pathologists using AI have reported successful outcomes, demonstrating its effectiveness as a supplementary tool. While some refinements are still needed before AI can be fully implemented in clinical practice, its positive impact is anticipated soon.

Background: Advancements in artificial intelligence (AI) diagnostics for renal cell carcinoma (RCC) provide valuable information for classification and subtyping, which improve treatment options and patient care. RCC diagnoses are most commonly incidental due to a lack of specific characterizations of subtypes, often leading to overtreatment. Accurate diagnosis also allows for personalized patient management. Different diagnostic methods, such as histopathology, multi-omics, imaging, and perioperative diagnostics, show a lot of promise for AI. Objective: This literature review focuses on developments in RCC diagnostics and their outcomes, efficacy, and accuracy in classification. Method: We conducted a non-systematic review of the published literature to explore advancements in the diagnostics of RCC. The PubMed and Google Scholar databases were reviewed to extract relevant information. The literature shows that AI can help distinguish RCC from other kidney lesions and track tumor growth. The integration of radiomic features with clinical metadata further enhances the results. This enables clinicians to implement personalized treatment plans. The application of artificial intelligence in perioperative diagnostics enhances decision-making, improves patient safety, mitigates intraoperative complications, and accelerates recovery. Alongside the advancements in AI-assisted diagnostics, there are problems that need to be addressed, including selection bias, demand for larger and diverse datasets, and reliable validation. Conclusions: Despite the challenges, using AI to help with RCC diagnosis could lead to better patient outcomes, a new standard of care for RCC patients, and more personalized cancer management for each patient.

Background and Objectives: Because of its consistently high stone-free rates (SFRs), percutaneous nephrolithotomy (PCNL) continues to be the first-line treatment for renal stones larger than 20 mm. Standard 24 to 30 Fr access tracts, however, are linked to access-related morbidity, such as bleeding, pain, and extended hospital stays. These restrictions have led to progressive tract miniaturization and the development of mini-PCNL, ultra-mini PCNL, and micro-PCN techniques. Materials and Methods: We performed a narrative review of studies published through January 2026 using PubMed and Google Scholar. Search terms included percutaneous nephrolithotomy, mini-PCNL, ultra-mini PCNL, micro-PCNL, and vacuum-assisted PCNL. Original studies, systematic reviews, and meta-analyses reporting clinical outcomes, complications, and advancements were selected, whereas conference abstracts, non-English papers, and articles without accessible full text were excluded. Results: Across randomized trials, miniaturized PCNL generally preserves efficacy when patients are selected appropriately. Across randomized trials and meta-analyses, miniaturized PCNL achieved stone-free rates comparable to standard PCNL (typically ~80–90% for stones ≤20 mm and similar rates in selected stones >2 cm), while demonstrating lower hemoglobin decrease (mean difference approximately −0.6 to −1.0 g/dL), reduced transfusion rates, and shorter hospital stays, at the cost of longer operative time (mean difference ~8–12 min). On the other hand, operative time may increase, and smaller working channels can make visualization and fragment evacuation more demanding as stone burden rises. Raised intrarenal pressure is a recurring safety issue because it may increase infectious risk unless drainage is actively managed. Recent innovations aim to address these limitations, including vacuum-assisted access sheaths, pressure-controlled irrigation, improved laser and lithotripsy platforms, image-fusion guidance, navigation systems, and robotic assistance. Conclusions: PCNL now spans a spectrum of tract sizes rather than a single standard approach. When chosen appropriately and performed with attention to pressure control and fragment evacuation, miniaturized PCNL can reduce morbidity without sacrificing stone clearance. Future advancements in percutaneous stone surgery are more likely to rely on integrated technological solutions that improve accuracy, safety, and repeatability than on additional tract size reduction.