- IRMS - Nicolae Testemitanu SUMPh
- 1. COLECȚIA INSTITUȚIONALĂ
- MedEspera: International Medical Congress for Students and Young Doctors
- MedEspera 2026
Please use this identifier to cite or link to this item:
http://hdl.handle.net/20.500.12710/34287
| Title: | MANAGEMENT OF URINARY STONES BY USING ARTIFICIAL INTELLIGENCE- BASED METHODS |
| Authors: | Leşan, Octavian Scutari, Adrian Borcoman, Marian Cazacu, Oleg |
| Keywords: | urinary stones;machine learning;artificial intelligence;segmentation;predictive models |
| Issue Date: | 2026 |
| Publisher: | Centrul Editorial-Poligrafic Medicina |
| Citation: | Leşan, Octavian; Scutari, Adrian; Borcoman, Marian; Cazacu, Oleg. MANAGEMENT OF URINARY STONES BY USING ARTIFICIAL INTELLIGENCE- BASED METHODS. In: MedEspera 2026, p. 471. ISBN 978-9975-82-486-6. |
| Abstract: | Introduction. Urinary stones is a common pathology characterized by different clinical variability and a high rate of recurrence. The introduction of artificial intelligence (AI) provides modern tools that optimize medical decision-making due to the integrated analysis of clinical and imaging data. Aim of study. To evaluate the role and impact of artificial intelligence-based methods in the diagnosis, selection of therapeutic strategies, and in the prevention of stone recurrence. Methods and materials. A review of recent literature on the application of machine learning algorithms and deep learning in the management of urinary stones was performed. The included studies were evaluating the use of AI in interpretation of CT images, the stone segmentation and quantification, correlation between stone composition and the density expressed in Houndsfield units and the development of predictive models for spontaneous elimination and the effectiveness of different treatment options. Results. AI-based algorithms demonstrated increased accuracy in the automatic detection and segmentation of urinary stones compared to conventional evaluation methods. Predictive models allowed the estimation of the probability of spontaneous elimination of ureteral stones, depending on size, location, and clinical parameters. More than that, the AI integration in the metabolic analysis contributed to the identification of individual risk factors involved in the recurrence of urinary stones. Conclusions. AI has the potential to improve the management of urinary stones by increasing diagnostic accuracy, optimizing treatment selection, and reducing the number of unnecessary therapeutic interventions. |
| metadata.dc.relation.ispartof: | MedEspera 2026. The 11th International Medical Congress for Students and Young Doctors, 6-8 May 2026 |
| URI: | https://medespera.md/documents/abstract-book-4.pdf https://repository.usmf.md/handle/20.500.12710/34287 |
| ISBN: | 978-9975-82-486-6 |
| Appears in Collections: | MedEspera 2026
|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
|