Search

BACKGROUND: Based on the latest published data, 40,137 new cases of prostate cancer were reported in Russia in 2021, ranking second after lung cancer in men. Thus, prostate cancer is one of the most common malignant neoplasms in men. Accurate and timely detection of prostate cancer is important under the current conditions. AIM: This systematic review aimed to assess the quality of prediction models designed to detect prostate cancer during initial presentation. MATERIALS AND METHODS: A systematic search was performed in eLibrary.ru, PubMed, Google Scholar, Web of Science, and ResearchGate for relevant publications indexed from January 2019 to September 2023 in accordance with the PRISMA protocol. Two authors independently assessed the relevant studies for potential inclusion or exclusion. RESULTS: This systematic review meta-analysis included 21 studies. In total, data from 3,630 patients were analyzed, of which 47% had prostate cancer and 53% had benign prostate neoplasms. The mean age of the patients was 67.1 (36–90) years. In addition, 81% of the studies were based on T2-weighted imaging, 57% on diffusion-weighted imaging, and 76% on apparent diffusion coefficient. Moreover, 43% and 33% of the studies were dedicated to transition zone and prostate peripheral zone neoplasms, respectively, and 52% of the authors examined the whole prostate gland, without dividing it into zones. The most common machine-learning algorithms applied by the investigators were as follows: multiple logistic regression (76%), support vector machine (38%), and random forest (24%). Based on the meta-analysis performed for the receiver operating characteristic-area under the curve (ROC–AUC) assessment with random-effect approach in 73 prediction models described in the publications, the final ROC–AUC was 0.793 [95% CI 0.768–0.818], I2 = 86.71%, p 0.001. The most accurate prediction models were based on the T2-weighted imaging + apparent diffusion coefficients imaging protocol: 0.860 [95% CI 0.813–0.907], and models created according to the “white box” principle (0.834 [95% CI 0.806–0.861]) were more accurate than the “black box” ones (0.733 [95% CI 0.695–0.771]). The models using radiomics and clinical features were slightly more accurate than those using the radiomics parameters alone (0.869 [95% CI 0.844–0.895] vs. 0.779 [95% CI 0.751–0.807]). Model accuracy was nearly identical across transitional and/or peripheral zone studies. CONCLUSIONS: Artificial intelligence demonstrated promising results. However, the clinical applicability may require more intensive expert inspection in healthcare institutions and evaluation of efficacy in prospective studies.

Introduction. Currently, several virtual reality (VR) simulators have been described for the upper urinary tract stone surgery skill development, including retrograde or antegrade nephroscopy. However, their high cost and the lack of a detailed reconstruction of the intraluminal pelvicalyceal system (PCS) appearance limit their implementation into educational process and clinical practice.Objectives. To develop the approach for VR-reconstruction of the intraluminal appearance of the PCS via head mounted device (HMD), as well as estimate its usefulness for novices to improve spatial orientation during retrograde flexible nephroscopy.Materials & methods. Five residents without experience in self-performing retrograde flexible nephroscopy participated in a 7-day training course on the VR simulator developed, during which each novice studied six variants of the PCS. For the procedure simulation, a silicone kidney model was created with the stone placed in the calyx which was selected randomly in each case. Before and after VR-course, each resident assisted the experienced urologist during simulated retrograde nephroscopy to find the stone placed according to random selection. The nephroscopy time and the number of errors in stone-finding during retrograde flexible nephroscopy were analysed.Results. There was a statistically significant decrease in nephroscopy time (on avg by 17.6 minutes, p = 0.043) and errors to find targeted calyx, which was observed once after the training one resident only.Conclusion. The described VR simulator does not require significant time, technical and financial costs, and is available for wide implementation in the training of young specialists.