Primary light chain amyloidosis is a rare hematologic disease with multi-organ involvement.Nearly one-third of patients with amyloidosis experience five or more consultations before diagnosis,which may lead to a poor ...Primary light chain amyloidosis is a rare hematologic disease with multi-organ involvement.Nearly one-third of patients with amyloidosis experience five or more consultations before diagnosis,which may lead to a poor prognosis due to delayed diagnosis.Early risk prediction based on artificial intelligence is valuable for clinical diagnosis and treatment of amyloidosis.For this disease,we propose an Evolutionary Neural Architecture Searching(ENAS)based risk prediction model,which achieves high-precision early risk prediction using physical examination data as a reference factor.To further enhance the value of clinic application,we designed a natural language-based interpretable system around the NAS-assisted risk prediction model for amyloidosis,which utilizes a large language model and Retrieval-Augmented Generation(RAG)to achieve further interpretation of the predicted conclusions.We also propose a document-based global semantic slicing approach in RAG to achievemore accurate slicing and improve the professionalism of the generated interpretations.Tests and implementation show that the proposed risk prediction model can be effectively used for early screening of amyloidosis and that the interpretation method based on the large language model and RAG can effectively provide professional interpretation of predicted results,which provides an effective method and means for the clinical applications of AI.展开更多
电子病历数据经常存在缺失,严重影响分析结果.基于MIMIC数据库中的重症监护单元(intensive care unit,ICU)患者数据研究缺失值插补,数据集由23组临床常用生理变量以及不存在缺失的5260例样本构成.提出了一种基于深度嵌入聚类的K近邻插...电子病历数据经常存在缺失,严重影响分析结果.基于MIMIC数据库中的重症监护单元(intensive care unit,ICU)患者数据研究缺失值插补,数据集由23组临床常用生理变量以及不存在缺失的5260例样本构成.提出了一种基于深度嵌入聚类的K近邻插值方法.该方法以深度嵌入聚类为核心,通过多次聚类构造样本邻近度矩阵,再选择缺失样本的K个近邻样本,以这些近邻样本的平均值填补缺失.与均值插补、中值插补、后验分布估算插补和条件均值插补相比,该方法插补后的结果与原数据相似度更高,且更好地保留了样本间的差异性.展开更多
案件罪名预测任务是基于文本数据去预测案件所属罪名.针对现有方法在相似罪名和长尾数据集上表现不佳的问题,提出了一种基于图注意力网络的案件罪名预测方法CP-GAT(charge prediction based on graph attention network).该方法首先使...案件罪名预测任务是基于文本数据去预测案件所属罪名.针对现有方法在相似罪名和长尾数据集上表现不佳的问题,提出了一种基于图注意力网络的案件罪名预测方法CP-GAT(charge prediction based on graph attention network).该方法首先使用司法文书数据集中的案例事件描述文本和案例对应的法条信息建立异质图结构数据,构建后的异质图包含两种类型的节点(词节点、案例节点),两种类型的边(词节点与词节点相连的边,词节点与案例节点相连的边).在基于法律文本构建后的异质图上使用图注意力网络进行图特征提取,最后将得到的特征向量输入到罪名预测的分类器中,得到案例所属的罪名.在CAIL2018法律数据集上的实验结果表明,基于图注意力网络的罪名预测方法优于对比实验使用的方法,准确率和宏观F 1值分别达到了95.2%和66.1,验证了提出的方法有利于提升案件罪名预测任务的性能.展开更多
基金supported by Liaoning Province Key R&D Program Project(Grant Nos.2019JH2/10100027)in part by Grants from Shenyang Science and Technology Plan Project(Grant No.RC210469).
文摘Primary light chain amyloidosis is a rare hematologic disease with multi-organ involvement.Nearly one-third of patients with amyloidosis experience five or more consultations before diagnosis,which may lead to a poor prognosis due to delayed diagnosis.Early risk prediction based on artificial intelligence is valuable for clinical diagnosis and treatment of amyloidosis.For this disease,we propose an Evolutionary Neural Architecture Searching(ENAS)based risk prediction model,which achieves high-precision early risk prediction using physical examination data as a reference factor.To further enhance the value of clinic application,we designed a natural language-based interpretable system around the NAS-assisted risk prediction model for amyloidosis,which utilizes a large language model and Retrieval-Augmented Generation(RAG)to achieve further interpretation of the predicted conclusions.We also propose a document-based global semantic slicing approach in RAG to achievemore accurate slicing and improve the professionalism of the generated interpretations.Tests and implementation show that the proposed risk prediction model can be effectively used for early screening of amyloidosis and that the interpretation method based on the large language model and RAG can effectively provide professional interpretation of predicted results,which provides an effective method and means for the clinical applications of AI.
文摘电子病历数据经常存在缺失,严重影响分析结果.基于MIMIC数据库中的重症监护单元(intensive care unit,ICU)患者数据研究缺失值插补,数据集由23组临床常用生理变量以及不存在缺失的5260例样本构成.提出了一种基于深度嵌入聚类的K近邻插值方法.该方法以深度嵌入聚类为核心,通过多次聚类构造样本邻近度矩阵,再选择缺失样本的K个近邻样本,以这些近邻样本的平均值填补缺失.与均值插补、中值插补、后验分布估算插补和条件均值插补相比,该方法插补后的结果与原数据相似度更高,且更好地保留了样本间的差异性.
文摘案件罪名预测任务是基于文本数据去预测案件所属罪名.针对现有方法在相似罪名和长尾数据集上表现不佳的问题,提出了一种基于图注意力网络的案件罪名预测方法CP-GAT(charge prediction based on graph attention network).该方法首先使用司法文书数据集中的案例事件描述文本和案例对应的法条信息建立异质图结构数据,构建后的异质图包含两种类型的节点(词节点、案例节点),两种类型的边(词节点与词节点相连的边,词节点与案例节点相连的边).在基于法律文本构建后的异质图上使用图注意力网络进行图特征提取,最后将得到的特征向量输入到罪名预测的分类器中,得到案例所属的罪名.在CAIL2018法律数据集上的实验结果表明,基于图注意力网络的罪名预测方法优于对比实验使用的方法,准确率和宏观F 1值分别达到了95.2%和66.1,验证了提出的方法有利于提升案件罪名预测任务的性能.
