Shashikumar Supreeth P, Mohammadi Sina, Krishnamoorthy Rishivardhan, Patel Avi, Wardi Gabriel, Ahn Joseph C, Singh Karandeep, Aronoff-Spencer Eliah, Nemati Shamim
Division of Biomedical Informatics, UC San Diego, San Diego, CA, USA.
Department of Emergency Medicine, UC San Diego, San Diego, CA, USA.
NPJ Digit Med. 2025 May 17;8(1):290. doi: 10.1038/s41746-025-01689-w.
Sepsis is a dysregulated host response to infection with high mortality and morbidity. Early detection and intervention have been shown to improve patient outcomes, but existing computational models relying on structured electronic health record data often miss contextual information from unstructured clinical notes. This study introduces COMPOSER-LLM, an open-source large language model (LLM) integrated with the COMPOSER model to enhance early sepsis prediction. For high-uncertainty predictions, the LLM extracts additional context to assess sepsis-mimics, improving accuracy. Evaluated on 2500 patient encounters, COMPOSER-LLM achieved a sensitivity of 72.1%, positive predictive value of 52.9%, F-1 score of 61.0%, and 0.0087 false alarms per patient hour, outperforming the standalone COMPOSER model. Prospective validation yielded similar results. Manual chart review found 62% of false positives had bacterial infections, demonstrating potential clinical utility. Our findings suggest that integrating LLMs with traditional models can enhance predictive performance by leveraging unstructured data, representing a significant advance in healthcare analytics.
脓毒症是宿主对感染的失调反应，具有高死亡率和发病率。早期检测和干预已被证明可改善患者预后，但现有的依赖结构化电子健康记录数据的计算模型常常遗漏非结构化临床笔记中的背景信息。本研究引入了COMPOSER-LLM，这是一种与COMPOSER模型集成的开源大语言模型（LLM），以增强脓毒症早期预测。对于高不确定性预测，该大语言模型提取额外的背景信息以评估脓毒症模拟情况，从而提高准确性。在2500次患者会诊中进行评估时，COMPOSER-LLM的灵敏度达到72.1%，阳性预测值为52.9%，F1分数为61.0%，每患者小时假警报为0.0087次，优于独立的COMPOSER模型。前瞻性验证产生了类似结果。人工病历审查发现62%的假阳性有细菌感染，证明了其潜在的临床实用性。我们的研究结果表明，将大语言模型与传统模型相结合可以通过利用非结构化数据来提高预测性能，这代表了医疗保健分析领域的一项重大进展。
