Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Advancing Problem-Based Learning with Clinical Reasoning for Improved Differential Diagnosis in Medical Education

Yuansong Xu, Yuheng Shao, Jiahe Dong, Shaohan Shi, Chang Jiang, Quan Li

TL;DR

The paper addresses the need to enhance clinical reasoning and differential diagnosis within medical education by integrating a learner-centered PBL tool, e-MedLearn, into the learning process. It follows a three-phase design: Phase One interviews to identify current PBL practices and barriers, Phase Two design iterations to derive a technology-mediated solution, and Phase Three evaluations via a controlled study and testing interviews. Results show that e-MedLearn improves targeted data construction, information analysis, and record-and-review workflows, reduces perceived workload, and enhances evidence-based reasoning, prognosis consideration, and reflective practice compared with a baseline. These findings suggest that a structured, AI-assisted PBL platform can bridge the gap between knowledge and clinical practice, support sustainable medical learning ecosystems, and foster human-centered, patient-focused diagnostic training in medical education.

Abstract

Medical education increasingly emphasizes students' ability to apply knowledge in real-world clinical settings, focusing on evidence-based clinical reasoning and differential diagnoses. Problem-based learning (PBL) addresses traditional teaching limitations by embedding learning into meaningful contexts and promoting active participation. However, current PBL practices are often confined to medical instructional settings, limiting students' ability to self-direct and refine their approaches based on targeted improvements. Additionally, the unstructured nature of information organization during analysis poses challenges for record-keeping and subsequent review. Existing research enhances PBL realism and immersion but overlooks the construction of logic chains and evidence-based reasoning. To address these gaps, we designed e-MedLearn, a learner-centered PBL system that supports more efficient application and practice of evidence-based clinical reasoning. Through controlled study (N=19) and testing interviews (N=13), we gathered data to assess the system's impact. The findings demonstrate that e-MedLearn improves PBL experiences and provides valuable insights for advancing clinical reasoning-based learning.

Advancing Problem-Based Learning with Clinical Reasoning for Improved Differential Diagnosis in Medical Education

TL;DR

The paper addresses the need to enhance clinical reasoning and differential diagnosis within medical education by integrating a learner-centered PBL tool, e-MedLearn, into the learning process. It follows a three-phase design: Phase One interviews to identify current PBL practices and barriers, Phase Two design iterations to derive a technology-mediated solution, and Phase Three evaluations via a controlled study and testing interviews. Results show that e-MedLearn improves targeted data construction, information analysis, and record-and-review workflows, reduces perceived workload, and enhances evidence-based reasoning, prognosis consideration, and reflective practice compared with a baseline. These findings suggest that a structured, AI-assisted PBL platform can bridge the gap between knowledge and clinical practice, support sustainable medical learning ecosystems, and foster human-centered, patient-focused diagnostic training in medical education.

Abstract

Medical education increasingly emphasizes students' ability to apply knowledge in real-world clinical settings, focusing on evidence-based clinical reasoning and differential diagnoses. Problem-based learning (PBL) addresses traditional teaching limitations by embedding learning into meaningful contexts and promoting active participation. However, current PBL practices are often confined to medical instructional settings, limiting students' ability to self-direct and refine their approaches based on targeted improvements. Additionally, the unstructured nature of information organization during analysis poses challenges for record-keeping and subsequent review. Existing research enhances PBL realism and immersion but overlooks the construction of logic chains and evidence-based reasoning. To address these gaps, we designed e-MedLearn, a learner-centered PBL system that supports more efficient application and practice of evidence-based clinical reasoning. Through controlled study (N=19) and testing interviews (N=13), we gathered data to assess the system's impact. The findings demonstrate that e-MedLearn improves PBL experiences and provides valuable insights for advancing clinical reasoning-based learning.

Paper Structure

This paper contains 57 sections, 19 figures, 12 tables.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Problem-Based Learning in Clinical Education Practice
  4. Design Medical Diagnostic Tools with Physicians
  5. Human-Centered Medical AI
  6. Overview of Clinical Reasoning-based Differential Diagnosis
  7. Method
  8. Phase One: Identify Current Practices and Challenges in PBL
  9. Procedures and Data Analysis
  10. Perception of PBL Organization and Implementation
  11. Teachers' case selection reflects their expectations for students to grasp the relevant knowledge
  12. The teacher's role as a guide facilitates student discussion and encourages active exploration
  13. Students acknowledge that PBL increases their engagement and motivation, and they express a desire for more integrated information organization
  14. The Acquisition of Learning and Improvement
  15. Teachers strive to impart a wide range of skills and improvements to their students, but they are often constrained by limited classroom time and the need to address the broader requirements of the majority
  16. ...and 42 more sections

Figures (19)

  • Figure 1: Overview of Differential Diagnosis workflow. The process consists of acquiring data, identifying key features from data, formulating problem representation from these features, developing diagnosis in a structured framework with the following plans for test and treatment, and iteratively updating diagnosis and plans with supplement evidence from test results.
  • Figure 2: The stages and steps of the e-MedLearn prototype system pipeline.
  • Figure 3: In Step 1: Status Identification, the e-MedLearn platform provides a top-down, multi-level selection process to help users determine the content of their learning.
  • Figure 4: In Step 2: Case Selection, relevant cases are presented as cards, with each card displaying difficulty scores for reference. Users can also search cases by content.
  • Figure 5: Step 3: The Problem Formulation interface includes: (A) Case information card. (B) The prompting QA section. (C) The template mind map to organize and record analyzed information.
  • ...and 14 more figures