Background: To examine the artificial intelligence (AI) tools currently being studied in modern medical education, and critically evaluate the level of validation and the quality of evidence presented in each individual study. Methods: This review (PROSPERO ID: CRD42023410752) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement. A database search was conducted using PubMed, Embase, and Cochrane Library. Articles written in the English language between 2000 and March 2023 were reviewed retrospectively using the MeSH Terms “AI” and “medical education” A total of 4642 potentially relevant studies were found. Results: After a thorough screening process, 36 studies were included in the final analysis. These studies consisted of 26 quantitative studies and 10 studies investigated the development and validation of AI tools. When examining the results of studies in which Support vector machines (SVMs) were employed, it has demonstrated high accuracy in assessing students’ experiences, diagnosing acute abdominal pain, classifying skilled and novice participants, and evaluating surgical training levels. Particularly in the comparison of surgical skill levels, it has achieved an accuracy rate of over 92%. Conclusion: AI tools demonstrated effectiveness in improving practical skills, diagnosing diseases, and evaluating student performance. However, further research with rigorous validation is required to identify the most effective AI tools for medical education.

Purpose: We present an augmented reality (AR) navigation system that conveys virtual organ models generated from transrectal ultrasonography (TRUS) onto a real laparoscopic video during radical prostatectomy. By providing this additional information about the actual anatomy, we can support surgeons in their working decisions. This work reports the system's first in-vivo application. Materials and Methods: The system uses custom-developed needles with colored heads that are inserted into the prostate as soon as the organ surface is uncovered. These navigation aids are once segmented in three-dimensional (3D) TRUS data that is acquired right after the placement of the needles and then continuously tracked in the laparoscopic video images by the surgical navigation system. The navigation system traces the navigation aids in real time and computes a registration between TRUS image and laparoscopic video based on the two-dimensional-three dimensional (2D-3D) point correspondences. With this registration, the system correctly superimposes TRUS-based 3D information on an additional AR monitor placed next to the normal laparoscopic screen. Surgical navigation guidance took place until the prostate was removed from the rectal wall. Finally, the navigation aids were removed together with the specimen inside the specimen bag. Results: The initial human in-vivo application of the surgical navigation system was successful. No complications occurred, the prostate was removed together with the navigation aids, and the system supported the surgeons as intended with an AR visualization in real time. In case of tissue deformations, changes in the spatial configuration of the navigation aids are detected, which preserves the system from erroneous navigation visualization. Conclusions: Feasibility of the navigation system was shown in the first in-vivo application. TRUS information could be superimposed via AR in real time. To show the benefit for the patient, results obtained from a larger number of trials are needed.

In this multicenter study we aimed to evaluate the efficacy and safety of percutaneous nephrolithotomy in children with respect to different features and using the Clavien classification system. Percutaneous nephrolithotomies performed in children at 3 urology departments between March 2006 and May 2010 were included in the study. Results are presented for complex/simple renal stones, tubeless/totally tubeless percutaneous nephrolithotomy, simultaneous bilateral percutaneous nephrolithotomy, instrument size and age groups. Patients were divided into 3 distinct groups, infants and toddlers (3 years or younger, group 1), preschool children (4 to 7 years, group 2) and school children (8 to 16 years, group 3). Perioperative complications are presented according to the modified Clavien classification system. A total of 140 percutaneous nephrolithotomies were performed in 130 patients (41.5% female, mean age 10.17 years). There were 23, 25 and 92 renal units in groups 1, 2 and 3, respectively. Pediatric instruments were used in 60 renal units and adult-sized instruments in 80. General assessment of complications showed Clavien grade I complications in 17 patients, II in 4, IIIa in 11 and IIIb in 7. There were no grade IV or V complications. Percutaneous nephrolithotomy can be applied safely in children of varying ages, even infants. Complications, as assessed with Clavien classification, are comparable to those seen in adults provided there is enough experience with the technique.