Machine learning applications to enhance patient specific care for urologic surgery

Area of Science:

• Urology
• Medical Informatics
• Artificial Intelligence

Background:

• Machine learning (ML) applications are increasingly prevalent in daily life and clinical settings.
• There is growing interest in leveraging ML for patient-specific urologic surgical care.

Purpose of the Study:

• To review the current literature on ML applications in patient-specific urologic surgical care.
• To identify how ML can assist in counseling and decision-making for urologic conditions.

Main Methods:

• A comprehensive literature search was conducted using PubMed-Medline and Google Scholar up to December 2020.
• Search terms included "urologic surgery" combined with "artificial intelligence," "machine learning," "neural network," and "automation."

Main Results:

• ML applications focus on disease-specific patient counseling, including predicting stone-free rates and renal mass pathology.
• For prostate and bladder cancers, ML aids in treatment counseling, outcome prediction, and staging via imaging.
• Automated segmentation and matching of preoperative and intraoperative imaging are also key ML applications.

Conclusions:

• Machine learning techniques can improve patient-centered surgical care and patient engagement in decision-making.
• The efficacy of ML tools is expected to increase with improved and expanded datasets, particularly with widespread EHR adoption.