Actionable companion · Assessment and evidence of learning

From evidence to district action: Beyond Red Pen: Comparing the machine vs human grading of reflective assignments on clinical reasoning in Dermatology undergraduate students

AI-assisted editorial implementation guide. The district actions are proposed applications, not findings or recommendations attributed to the original authors. No additional peer review is asserted.

Evidence and context

Health-professions education context: test transfer to K–12 rather than assuming it.

Original authors’ abstract, reproduced under the linked source license:

ABSTRACT Background and Objective: The integration of Artificial Intelligence (AI) into medical education has been a significant advancement in recent years. AI-based tools like ChatGPT offer numerous advantages for teaching and student assessment. The objective of this study was to evaluate the effectiveness of ChatGPT in assessing reflective assignments compared to human grading. Methodology: This quasi-experimental study was conducted at Islamic International Medical College from December 2024 to March 2025. In this study a total of 120 3rd year MBBS students were assigned reflective essays after completing their Dermatology module. The e-assignment focused on reflecting on diagnosing scabies, applying clinical reasoning, and correlating clinical findings with patient history, following the Gibbs Reflective Cycle. Each submission was standardized to 500 words and graded using a structured rubric. First the selected faculty members manually assessed each assignment, and then ChatGPT applied the same rubric for grading of the assignments. The scores were then compared for alignment between human and ChatGPT grading. Results: It showed a strong correlation between ChatGPT and human scores, with minimal differences of 0.5-1.5 marks in a few cases. Clinical Reasoning scores showed a strong correlation (ρ = 0.678, p < 7×10-9) with a small effect size (d = -0.283), while Gibbs Cycle scores had an even stronger correlation (ρ = 0.734, p < 1×10-10) and negligible effect size (d = 0.037). Total scores showed very high correlation (ρ = 0.990, p < 1×10-10) but a large effect size (d = 3.422), suggesting consistent scoring with systematic differences in absolute values. Conclusion: ChatGPT serves as a valuable and reliable complement to human assessment, significantly improving grading efficiency, particularly in large-scale evaluations. KEYWORDS: AI in medical Education, Clinical Reasoning, Gibbs’ Reflective Cycle, Reflective Writing, Manual vs Automated Scoring

A 90-day district pilot

1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
2. Days 16–30 · Design. Redesign one low-stakes assessment: require a first attempt, an AI-assisted revision, a source-check log and a short oral explanation. Use the same rubric for the comparison task. Name an accountable owner and set the baseline, success threshold and budget before implementation.
3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
4. Days 61–90 · Decide. Blind-score reasoning, factual accuracy and unaided transfer on a fresh task. Record suspected misconduct separately from demonstrated evidence. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Lubna Rani Faysal; Shabana Ali; Mahwish Aftab Khan; Humaira Fayyaz Khan. Beyond Red Pen: Comparing the machine vs human grading of reflective assignments on clinical reasoning in Dermatology undergraduate students. Pakistan Journal of Medical Sciences (2026-05-01). https://doi.org/10.12669/pjms.42.5.12376

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 3.0 license. This guide has not undergone independent peer review.