Artificial intelligence in laparoscopic simulation: a promising future for large-scale automated evaluations.

INTRODUCTION: A limitation to expanding laparoscopic simulation training programs is the scarcity of expert evaluators. In 2019, a new digital platform for remote and asynchronous laparoscopic simulation training was validated. Through this platform, 369 trainees have been trained in 14 institutions across Latin America, collecting 6729 videos of laparoscopic training exercises. The use of artificial intelligence (AI) has recently emerged in surgical simulation, showing usefulness in training assessment, virtual reality scenarios, and laparoscopic virtual reality simulation. An AI algorithm to assess basic laparoscopic simulation training exercises was developed. This study aimed to analyze the agreement between this AI algorithm and expert evaluators in assessing basic laparoscopic-simulated training exercises. METHODS: The AI algorithm was trained using 400-bean drop (BD) and 480-peg transfer (PT) videos and tested using 64-BD and 43-PT randomly selected videos, not previously used to train the algorithm. The agreement between AI and expert evaluators from the digital platform (EE) was then analyzed. The exercises being assessed involve using laparoscopic graspers to move objects across an acrylic board without dropping any objects in a determined time (BD < 24 s, PT < 55 s). The AI algorithm can detect object movement, identify if objects have fallen, track grasper clamps location, and measure exercise time. Cohen's Kappa test was used to evaluate the agreement between AI assessments and those performed by EE, using a pass/fail nomenclature based on the time to complete the exercise. RESULTS: After the algorithm was trained, 79.69% and 93.02% agreement were observed in BD and PT, respectively. The Kappa coefficients test observed for BD and PT were 0.59 (moderate agreement) and 0.86 (almost perfect agreement), respectively. CONCLUSION: This first approach of AI use in basic laparoscopic skills simulated training assessment shows promising results, providing a preliminary framework to expand the use of AI to other basic laparoscopic skills exercises.

Remote and asynchronous training network: from a SAGES grant to an eight-country remote laparoscopic simulation training program.

BACKGROUND: Limitations in surgical simulation training include lack of access to validated training programs with continuous year-round training and lack of experts' ongoing availability for feedback. A model of simulation training was developed to address these limitations. It incorporated basic and advanced laparoscopic skills curricula from a previously validated program and provided instruction through a digital platform. The platform allowed for remote and asynchronous feedback from a few trained instructors. The instructors were continuously available and provided personalized feedback using a variety of different media. We describe the upscaling of this model to teach trainees at fourteen centers in eight countries. METHODS: Institutions with surgical programs lacking robust simulation curricula and needing instructors for ongoing education were identified. The simulation centers ("skills labs") at these sites were equipped with necessary simulation training hardware. A remote training-the-administrators (TTA) program was developed where personnel were trained in how to manage the skills lab, schedule trainees, set up training stations, and use the platform. A train-the-trainers (TTT) program was created to establish a network of trained instructors, who provided objective feedback through the platform remotely and asynchronously. RESULTS: Between 2019 and 2022, seven institutions in Chile and one in each of the USA, Bolivia, Brazil, Ecuador, El Salvador, México, and Perú implemented a digital platform-based remote simulation curriculum. Most administrators were not physicians (19/33). Eight Instructors were trained with the TTT program and became active proctors. The platform has been used by 369 learners, of whom 57% were general surgeons and general surgery residents. A total of 6729 videos, 28,711 feedback inputs, and 233.7 and 510.2 training hours in the basic and advanced programs, respectively, were registered. CONCLUSION: A remote and asynchronous method of giving instruction and feedback through a digital platform has been effectively employed in the creation of a robust network of continuous year-round simulation-based training in laparoscopy. Training centers were successfully run only with trained administrators to assist in logistics and setup, and no on-site instructors were necessary.

Minimally invasive tele-mentoring opportunity-the mito project.

BACKGROUND: Simulation training is a validated method for acquiring laparoscopic skills. Training sessions may be sporadic or lack continuity in oversight by instructors since traditional programs mandate in-person teaching and evaluation. This study presents the development, implementation, and results of a novel smartphone application that enables remote teacher-student interaction. This interface is used to complete a validated program that provides learner-specific feedback. Outcomes of training via Lapp were compared to outcomes of traditional in-person training. METHODS: A web-based and mobile iOS and Android application (Lapp) was developed to enable a remote student-teacher interaction. Instructors use Lapp to assess video recorded training sessions of students at distant locations and guide them through the laparoscopic skill course with specific and personalized feedback. Surgical trainees at two remote training centers were taught using Lapp. A control group was assessed during traditional simulation training at the training facility, with in-person feedback. Pre- and post-training performances were video recorded for each trainee and blindly evaluated by two experts using a global rating scale (GRS) and a specific rating scale (SRS). RESULTS: A total of 30 trainees were trained via Lapp and compared with 25 locally taught. Performance in the Lapp group improved significantly after the course in both GRS and SRS scores, from 15 [6-17] to 23 [20-25], and from 12 [11-15] to 18 [15-20], respectively. The results between both groups were comparable. CONCLUSION: Laparoscopic simulation training using a mobile app is as effective as in-person instruction in teaching advanced laparoscopic surgical skills. Lapp provides an effective method of teaching through simulation remotely and may allow expansion of robust simulation training curriculums.

Smartphone application supplements laparoscopic training through simulation by reducing the need for feedback from expert tutors.

BACKGROUND: Simulation training is a validated, highly effective tool for learning laparoscopy. Feedback plays a crucial role in motor skills training. We present an app to guide students during advanced laparoscopy simulation training and evaluate its effect on training. METHODS: A smartphone(iOS)-app was developed. A group of trainees were randomized to use the app (YAPP) or not use the app (NAPP). We used blinded analysis with validated rating scales to assess their performance before and after the training. The number of requests for tutor feedback per session was recorded. Finally, the participants in the YAPP group completed a survey about their experience with the app. RESULTS: Fifteen YAPP and 10 NAPP completed the training program. There were no statistically significant differences between their skills performance scores (P = .338). The number of tutor feedback requests in the YAPP and NAPP was of 4 (3-6) and 13 (10-14) (P < .001), respectively. All participants in the YAPP group found the app was useful. CONCLUSION: The use of a smartphone app reduces the need for expert tutor feedback without decreasing the degree of skills acquisition.