A team at Sechenov University has built a system to guide personalized treatment for urolithiasis. The goal is to minimize mistakes, reduce complications, and lower the chance of recurrence. This progress was shared with socialbites.ca during coverage of the First Moscow State Medical University named after IM Sechenov.
If implemented, the project would underpin personalized care, lessen risks during and after procedures, cut the need for repeat interventions, shorten hospital stays, and boost patient satisfaction with the care received. A representative from the Institute of Regenerative Medicine described these potential benefits to socialbites.ca.
At present, physicians treat urolithiasis with lithotripsy, which breaks stones using ultrasound, lasers, and other technologies. The success of a given method depends on stone size, density, and other properties gathered through X-ray or CT imaging. Limited data can raise the likelihood of complications and recurrence.
The newly developed algorithm aims to identify the most effective treatment path for each patient with urolithiasis. The system learns from patterns and relationships among features found in previously collected stone samples and compares them with the patient’s data obtained from CT scans or radiographs.
The objective is to estimate missing parameters that describe the stones, including physicochemical, structural, and mechanical properties. The more complete the stone profile, the more accurately the optimal stone-breaking method can be chosen for any given situation.
Already, urine stone samples have been gathered, a dataset has been compiled, and research algorithms have been created. A classifier is being developed to detect dependencies and patterns within the dataset, forming the foundation of a trainable, intelligent system with growing predictive capabilities. (Attribution: Sechenov University press materials and related institutional studies)