Exploring clinical feasibility of zero-shot learning in a large language model for immunofixation electrophoresis image interpretation

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Gemini3 Pro achieved F1-scores of 89.80 (MK), 84.75 (AK), and 71.54 (GK) with detailed prompts

• Primary Outcome: F1-scores for IFE pattern classification across ten semantic classes

• Nnt Or Sensitivity: Sensitivity and specificity not reported; only F1-scores provided

• Confidence Interval: Not reported

Clinical Application

Promising proof-of-concept but requires significant validation before clinical implementation Relevant to Australian pathology laboratories; would require TGA evaluation as medical device software and integration with existing laboratory information systems Laboratory medicine specialists interpreting immunofixation electrophoresis for monoclonal protein detection

Abstract

INTRODUCTION: Immunofixation electrophoresis (IFE) is the gold standard method for detecting and typing monoclonal immunoglobulins, but its interpretation requires expert evaluation and remains susceptible to subjectivity and variability. Recent advances in multimodal large language models (LLMs) have enabled zero-shot visual reasoning without task-specific training. This study aimed to evaluate the feasibility and diagnostic performance of zero-shot multimodal LLMs for automated interpretation of IFE images. MATERIALS AND METHODS: A dataset of 487 immunofixation electrophoresis images representing ten semantic classes (AK, AL, GK, GL, K, L, LGL, MK, ML, and NONE) was retrospectively collected and annotated by expert laboratory specialists. Two multimodal LLMs, ChatGPT-5.2 and Gemini3 Pro, were evaluated using a zero-shot visual question answering (ZS-VQA) framework without additional training or fine-tuning. Each image was analyzed using two prompt configurations: a simple prompt and a detailed prompt with structured diagnostic guidance. Model performance was assessed using precision, recall, F1-score, and confusion matrix analysis. RESULTS: Gemini outperformed ChatGPT across most classes, particularly with detailed prompts, achieving high F1-scores in clinically relevant monoclonal categories such as MK (89.80), AK (84.75), and GK (71.54). Detailed prompting consistently improved recall and F1-scores, underscoring the importance of prompt design. In contrast, ChatGPT showed lower recall, F1-scores, and classification consistency. Both models performed less effectively in visually subtle patterns. CONCLUSIONS: Zero-shot multimodal LLMs, particularly Gemini, show promising potential for interpreting IFE images without task-specific training. However, performance variability and limitations in certain classes indicate that further optimization and validation are required before clinical implementation.

References

1. 1.Oztas, B., & Kosesoy, I. (2026). Exploring clinical feasibility of zero-shot learning in a large language model for immunofixation electrophoresis image interpretation. Clinica Chimica Acta, 120974. https://doi.org/10.1016/j.cca.2026.120974