使用多模态深度学习从心电图信号预测实验室指标异常与异常预判
Abnormality Prediction and Forecasting of Laboratory Values from Electrocardiogram Signals Using Multimodal Deep Learning
AI总结：
本研究基于MIMIC-IV数据集训练融合ECG与临床元数据的多模态深度学习模型，实现多类实验室指标异常的预测与预判，为临床提供无创低成本的监测方案。
摘要：
本研究探究了结合心电图（ECG）数据与患者基础元数据来评估、监测即时实验室异常的可行性。我们采用MIMIC-IV数据集，基于ECG波形、人口统计学信息、生物特征数据与生命体征训练多模态深度学习模型。所用模型为面向元数据采用后期融合机制的结构化状态空间分类器，我们将任务设定为针对每项异常的独立二分类任务，并使用AUROC评估性能。模型取得了优异表现：在异常预测任务中，涵盖心脏、肾脏、血液、代谢、免疫、凝血类别的24项实验室指标AUROC均高于0.70；在异常预判任务中，同样有多达24项指标达到该水平。其中NTproBNP（>353 pg/mL）的预测效果最佳，AUROC超过0.90；血红蛋白（>17.5 g/dL）、白蛋白（>5.2 g/dL）、红细胞压积（>51%）等指标的AUROC也高于0.85。研究结果表明，ECG结合临床数据可实现实验室异常的即时预测与预判，为传统检测提供了无创、高性价比的替代方案，能够支持早期干预与强化患者监测，有望在改善诊疗效果的同时减少对侵入性、高成本检查的依赖。
英文摘要：
This study investigates the feasibility of using electrocardiogram (ECG) data combined with basic patient metadata to estimate and monitor prompt laboratory abnormalities. We use the MIMIC-IV dataset to train multimodal deep learning models on ECG waveforms, demographics, biometrics, and vital signs. Our model is a structured state space classifier with late fusion for metadata. We frame the task as individual binary classifications per abnormality and evaluate performance using AUROC. The models achieve strong performance, with AUROCs above 0.70 for 24 lab values in abnormality prediction and up to 24 in abnormality forecasting, across cardiac, renal, hematological, metabolic, immunological, and coagulation categories. NTproBNP (>353 pg/mL) is best predicted (AUROC > 0.90). Other values with AUROC > 0.85 include Hemoglobin (>17.5 g/dL), Albumin (>5.2 g/dL), and Hematocrit (>51%). Our findings show ECG combined with clinical data enables prompt abnormality prediction and forecasting of lab abnormalities, offering a non-invasive, cost-effective alternative to traditional testing. This can support early intervention and enhanced patient monitoring. ECG and clinical data can help estimate and monitor abnormal lab values, potentially improving care while reducing reliance on invasive and costly procedures.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
