No abstract

Background: Medical devices are becoming more complex, and doctors need to learn quickly how to use new medical tools. However, it is challenging to objectively assess the fundamental laparoscopic surgical skill level and determine skill readiness for advancement. There is a lack of objective models to compare performance between medical trainees and experienced doctors. Methods: This article discusses the use of similarity network models for individual tasks and a combination of tasks to show the level of similarity between residents and medical students while performing each task and their overall laparoscopic surgical skill level using a medical device (eg laparoscopic instruments). When a medical student is connected to most residents, that student is competent to the next training level. Performance of sixteen participants (5 residents and 11 students) while performing 3 tasks in 3 different training schedules is used in this study. Results: The promising result shows the general positive progression of students over 4 training sessions. Our results also indicate that students with different training schedules have different performance levels. Students’ progress in performing a task is quicker if the training sessions are held more closely compared to when the training sessions are far apart in time. Conclusions: This study provides a graph-based framework for evaluating new learners’ performance on medical devices and their readiness for advancement. This similarity network method could be used to classify students’ performance using similarity thresholds, facilitating decision-making related to training and progression through curricula.

The importance of sustainable and efficient food production has driven the need for applying increasingly advanced approaches in farming and agriculture. To keep up with this need, farmers and future farmers need to be trained in the ways of precision agriculture. With the widespread use of artificial intelligence across all industries, it is not surprising to find AI at the heart of precision agriculture. While AI has brought a lot of promise, it has also brought a lot of dread, due to the lack of understanding about what it is and what it can do. To help farmers buy into applying AI, a new educational program is needed. To this end, we have developed a simple active learning system to illustrate AI, particularly, machine learning. We present an overview of the system and discuss how it can contribute to future farmers' understanding of how AI works. CCS CONCEPTS • Computing methodologies → Object recognition; • Applied computing → Computer-assisted instruction.