Reliability in performance assessment creates a potential application of artificial intelligence in veterinary education: evaluation of suturing skills at a single institution.

OBJECTIVES: To evaluate suturing skills of veterinary students using 3 common performance assessments (PAs) and to compare findings to data obtained by an electromyographic armband. SAMPLE: 16 second-year veterinary students. PROCEDURES: Students performed 4 suturing tasks on synthetic tissue models 1, 3, and 5 weeks after a surgical skills course. Digital videos were scored by 4 expert surgeons using 3 PAs (an Objective Structured Clinical Examination [OSCE]- style surgical binary checklist, an Objective Structured Assessment of Technical Skill [OSATS] checklist, and a surgical Global Rating Scale [GRS]). Surface electromyography (sEMG) data collected from the dominant forearm were input to machine learning algorithms. Performance assessment scores were compared between experts and correlated to task completion times and sEMG data. Inter-rater reliability was calculated using the intraclass correlation coefficient (ICC). Inter-rater agreement was calculated using percent agreement with varying levels of tolerance. RESULTS: Reliability was moderate for the OSCE and OSATS checklists and poor for the GRS. Agreement was achieved for the checklists when moderate tolerance was applied but remained poor for the GRS. sEMG signals did not correlate well with checklist scores or task times, but features extracted from signals permitted task differentiation by routine statistical comparison and correct task classification using machine learning algorithms. CLINICAL RELEVANCE: Reliability and agreement of an OSCE-style checklist, OSATS checklist, and surgical GRS assessment were insufficient to characterize suturing skills of veterinary students. To avoid subjectivity associated with PA by raters, further study of kinematics and EMG data is warranted in the surgical skills evaluation of veterinary students.

Low-Cost UVBot Using SLAM to Mitigate the Spread of Noroviruses in Occupational Spaces.

Noroviruses (NoVs) cause over 90% of non-bacterial gastroenteritis outbreaks in adults and children in developed countries. Therefore, there is a need for approaches to mitigate the transmission of noroviruses in workplaces to reduce their substantial health burden. We developed and validated a low-cost, autonomous robot called the UVBot to disinfect occupational spaces using ultraviolet (UV) lamps. The total cost of the UVBOT is less than USD 1000, which is much lower than existing commercial robots that cost as much as USD 35,000. The user-friendly desktop application allows users to control the robot remotely, check the disinfection map, and add virtual walls to the map. A 2D LiDAR and a simultaneous localization and mapping (SLAM) algorithm was used to generate a map of the space being disinfected. Tulane virus (TV), a human norovirus surrogate, was used to validate the UVBot's effectiveness. TV was deposited on a painted drywall and exposed to UV radiation at different doses. A 3-log (99.9%) reduction of TV infectivity was achieved at a UV dose of 45 mJ/cm2. We further calculated the sanitizing speed as 3.5 cm/s and the efficient sanitizing distance reached up to 40 cm from the UV bulb. The design, software, and environment test data are available to the public so that any organization with minimal engineering capabilities can reproduce the UVBot system.

Simulation-based robot-assisted surgical training: a health economic evaluation.

OBJECTIVE: To determine the overall cost effectiveness of surgical skills training on Robotic Surgical Simulator (RoSS). METHODS: This study evaluates the cost analysis of utilizing RoSS for robot-assisted surgical training, at Roswell Park Center for Robotic Surgery. Trainees were queried for time spent on the RoSS console over a period of 1 year, starting from June 2010 to June 2011. Time spent was converted to training time consumed on robotic console, resulting in loss of OR time and revenue. The mechanical durability of the RoSS was also determined. RESULTS: 105 trainees spent 361 h on the RoSS. This duration converted to 73 robot-assisted radical prostatectomy cases, and 72 animal lab sessions. RoSS prevented a potential loss of $600,000, while 72 animal labs would have cost more than $72,000 without including initial robot installation, annual maintenance and personnel expenses. The mechanical durability testing determined breakdown at 180 and 360 h for master control and pinch device, which were repaired under warranty. CONCLUSION: RoSS is a cost effective surgical simulator for implementation of a simulation-based robot-assisted surgical training program.

Development and validation of a composite scoring system for robot-assisted surgical training--the Robotic Skills Assessment Score.

BACKGROUND: A standardized scoring system does not exist in virtual reality-based assessment metrics to describe safe and crucial surgical skills in robot-assisted surgery. This study aims to develop an assessment score along with its construct validation. MATERIALS AND METHODS: All subjects performed key tasks on previously validated Fundamental Skills of Robotic Surgery curriculum, which were recorded, and metrics were stored. After an expert consensus for the purpose of content validation (Delphi), critical safety determining procedural steps were identified from the Fundamental Skills of Robotic Surgery curriculum and a hierarchical task decomposition of multiple parameters using a variety of metrics was used to develop Robotic Skills Assessment Score (RSA-Score). Robotic Skills Assessment mainly focuses on safety in operative field, critical error, economy, bimanual dexterity, and time. Following, the RSA-Score was further evaluated for construct validation and feasibility. Spearman correlation tests performed between tasks using the RSA-Scores indicate no cross correlation. Wilcoxon rank sum tests were performed between the two groups. RESULTS: The proposed RSA-Score was evaluated on non-robotic surgeons (n = 15) and on expert-robotic surgeons (n = 12). The expert group demonstrated significantly better performance on all four tasks in comparison to the novice group. Validation of the RSA-Score in this study was carried out on the Robotic Surgical Simulator. CONCLUSION: The RSA-Score is a valid scoring system that could be incorporated in any virtual reality-based surgical simulator to achieve standardized assessment of fundamental surgical tents during robot-assisted surgery.

Low cost augmented reality for training of MRI-guided needle biopsy of the spine.

In needle biopsy of the spine, an Augmented Reality (AR) image guidance system can be very effective in ensuring that while targeting the lesion with the biopsy needle, vital organs near the spine are not damaged and that the approach path is accurate. This procedure requires skill that is hard to master on patients. In this paper, we present a low cost AR based training set-up which consists of a software that uses one static single-camera tracking mechanism to locate the biopsy needle in the patient and which then augments the camera feed of the patient with virtual data providing real-time guidance to the surgeon for insertion of the biopsy needle. The setup is implemented using a phantom model consisting of a set of carefully modeled holes to simulate the needle insertion task. The lack of requirement of elaborate infrared tracking systems and high computing power makes this system very effective for educational and training purposes.