Skip to main content Skip to navigation

LiftUpp: Support to develop learner performance

Project Overview

The document examines LiftUpp, an innovative AI-driven platform aimed at improving learner performance in dental education through advanced data collection and analysis. It underscores a pivotal transition from conventional knowledge assessments to competency-based evaluations, which prioritize personalized feedback and the integration of curricula. Currently utilized in 70% of dental schools across the UK, LiftUpp is also extending its reach to other healthcare fields, highlighting its potential to enhance educational outcomes while addressing various challenges in workplace-based learning environments. The findings illustrate how generative AI can be effectively harnessed to tailor educational experiences, fostering a more adaptive and responsive approach to learner needs and competencies in the healthcare sector.

Key Applications

LiftUpp platform for workplace-based assessment

Context: Used in various medical education contexts, including dentistry, physiotherapy, and veterinary medicine, for assessing and developing student competence in clinical settings through real-time observational data collection during clinical sessions.

Implementation: Implemented via an iPad app that collects real-time observational data across different medical fields, facilitating workplace-based assessments tailored to each sub-domain's specific requirements.

Outcomes: ['Improved student performance assessment', 'Personalized feedback', 'Enhanced curriculum integration', 'Increased student satisfaction', 'Facilitated competency development']

Challenges: ['Complexities in data collection from multiple sources', 'Need for robust and defensible assessment methods', 'Data integration challenges with existing educational frameworks']

Implementation Barriers

Technical

Challenges in managing multi-source data from various assessments and clinical environments, including high administrative overhead and potential data loss with traditional data collection methods.

Proposed Solutions: Development of robust data collection methods and integration systems to streamline data fusion, and transition to digital platforms like LiftUpp that reduce paperwork and improve data accuracy.

Pedagogical

Need for sophisticated methods to assess and develop student competencies in real-world settings.

Proposed Solutions: Implementation of intelligent tutoring systems and data-driven models that focus on personalized learning.

Project Team

Frans A. Oliehoek

Researcher

Rahul Savani

Researcher

Elliot Adderton

Researcher

Xia Cui

Researcher

David Jackson

Researcher

Phil Jimmieson

Researcher

John Christopher Jones

Researcher

Keith Kennedy

Researcher

Ben Mason

Researcher

Adam Plumbley

Researcher

Luke Dawson

Researcher

Contact Information

For information about the paper, please contact the authors.

Authors: Frans A. Oliehoek, Rahul Savani, Elliot Adderton, Xia Cui, David Jackson, Phil Jimmieson, John Christopher Jones, Keith Kennedy, Ben Mason, Adam Plumbley, Luke Dawson

Source Publication: View Original PaperLink opens in a new window

Project Contact: Dr. Jianhua Yang

LLM Model Version: gpt-4o-mini-2024-07-18

Analysis Provider: Openai

Let us know you agree to cookies