AI Simplification of Dermatopathology Reports for Patients: Basic vs. Prompt-Engineered Approaches

Background: Patients struggle to comprehend dermatopathology reports, causing anxiety. As artificial intelligence (AI) tools become accessible for medical interpretation, patients may use them to understand pathology reports, but optimal approaches remain unexplored.

Objective: To evaluate whether prompt-engineered AI simplification of dermatopathology reports improves factualness, completeness, and reduces potential harm compared to basic AI usage.

Methods: Survey-based evaluation study (January-April 2025) of 52 US dermatology professionals (70.3% response rate). Six fictitious dermatopathology reports were simplified using: (1) Basic ChatGPT-4.0 with simple prompt and (2) Custom "DermDecoder" GPT with structured 489-word prompt. Participants rated reports on 3-point Likert scales for factualness, completeness, and potential harm, with free-text responses analyzed thematically.

Results: Mean ratings ranged from 1.27-1.63 (factualness/completeness) and 1.31-1.83 (harmfulness), indicating "Agree" to "Mostly Agree" or "Completely Harmless" to "Mostly Harmless." DermDecoder performed significantly worse for completeness in psoriasis (t=-2.79, p=0.007) and harmfulness in molluscum contagiosum (p=0.049) and melanoma in-situ (p=0.048). Free-text analysis revealed Basic Prompt preserved details but lacked clinical context, while DermDecoder provided generic education disconnected from pathological findings.

Limitations: Fictitious reports, limited sample size, rapidly evolving AI capabilities, and absence of patient perspectives.

Conclusion: Neither AI approach successfully balanced professional accuracy with patient accessibility, necessitating human-in-the-loop oversight for AI-generated medical explanations.