Electronic Health Records (EHRs) often lack explicit links between medications and diagnoses, making clinical decision-making and research more difficult. Even when links exist, diagnosis lists may be incomplete, especially during early patient visits. Discharge summaries tend to provide more complete information, which can help infer accurate diagnoses, especially with the help of large language models (LLMs). This study investigates whether LLMs can predict implicitly mentioned diagnoses from clinical notes and link them to corresponding medications. We address two research questions: (1) Does majority voting across diverse LLM configurations outperform the best single configuration in diagnosis prediction? (2) How sensitive is majority voting accuracy to LLM hyperparameters such as temperature, top-p, and summary length? To evaluate, we created a new dataset of 240 expert-annotated medication-diagnosis pairs from 20 MIMIC-IV notes. Using GPT-3.5 Turbo, we ran 18 prompting configurations across short and long summary lengths, generating 8568 test cases. Results show that majority voting achieved 75 percent accuracy, outperforming the best single configuration at 66 percent. No single hyperparameter setting dominated, but combining deterministic, balanced, and exploratory strategies improved performance. Shorter summaries generally led to higher accuracy.In conclusion, ensemble-style majority voting with diverse LLM configurations improves diagnosis prediction in EHRs and offers a promising method to link medications and diagnoses in clinical texts.

翻译：电子健康记录（EHR）中常缺乏药物与诊断间的明确关联，这增加了临床决策与研究的难度。即使存在关联，诊断列表也可能不完整，尤其在患者早期就诊阶段。出院小结通常提供更完整的信息，有助于推断准确诊断，尤其是在大型语言模型（LLM）的辅助下。本研究探讨LLM能否从临床记录中预测隐含提及的诊断，并将其与相应药物关联。我们聚焦两个研究问题：（1）跨多样化LLM配置的多数投票法是否在诊断预测中优于最佳单一配置？（2）多数投票准确率对LLM超参数（如温度、top-p和摘要长度）的敏感度如何？为评估性能，我们基于20份MIMIC-IV记录创建了包含240组专家标注药物-诊断对的新数据集。使用GPT-3.5 Turbo模型，我们在长短两种摘要长度下运行18种提示配置，生成8568个测试案例。结果显示：多数投票法达到75%的准确率，优于最佳单一配置的66%。未发现单一超参数设置占绝对优势，但结合确定性、平衡性和探索性策略能提升性能。较短的摘要通常带来更高准确率。综上所述，采用多样化LLM配置的集成式多数投票法能改进EHR中的诊断预测，为临床文本中药物与诊断的关联提供了可行方法。