Evaluating the Diagnostic Readiness of Radiologic Technology Students through AI-Assisted Case Simulations: A Data-Driven Outcomes-Based Framework
Ahmeda Ali, Alinair Carim and Mark Alipio
Received: 29 May 2026; Revised: 30 July 2026; Accepted: 15 August 2026; Published: 27 August 2026
DOI: https://doi.org/10.66074/3R9W2L4K
Abstract
Background: Radiologic technology education must prepare students to integrate anatomy, image quality, examination technique, patient safety, and professional judgment before full clinical immersion. Artificial intelligence can support controlled case simulation, but radiography-specific evidence remains limited, particularly for performance-based outcomes. Objective: To evaluate diagnostic readiness across first- to third-year Radiologic Technology students after an AI-assisted case simulation program organized around explicit outcomes and a common performance rubric. Methods: A single-school repeated-measures framework included 59 students from Iligan Medical Center College. Students completed a baseline assessment, eight weeks of structured AI-assisted cases, an immediate post-assessment, and a transfer assessment. Readiness was scored from 0 to 100 across case recognition, technique and protocol reasoning, image quality evaluation, patient safety, and AI verification. Results: The analysis showed an increase in mean readiness from 55.05 (SD = 7.97) at baseline to 69.73 (SD = 9.42) after the intervention, mean change = 14.68, 95% CI [12.53, 16.82], p < .001, d_z = 1.78. Transfer scores remained above baseline at 67.07 (SD = 10.06). The proportion meeting the 70-point readiness standard increased from 5.1% to 54.2% after the intervention. Conclusion: An outcomes-aligned AI-assisted simulation model can provide a rigorous structure for repeated assessment of radiologic technology students.
Keywords: assessment, competence, curriculum, preparedness, reasoning
Author Information: Iligan Medical Center College, Philippines; mark.alipio@imcc.edu.ph
Volume 1, Issue 1, September 2026