面向臨床決策支持系統(tǒng)的醫(yī)療文本分析模型
2023年電子技術(shù)應(yīng)用第5期
黃琦麟1,蔣理2,羅義蘭3,徐治強(qiáng)3,利節(jié)1
(1.重慶科技學(xué)院,重慶401331;2.重慶醫(yī)科大學(xué)附屬第一醫(yī)院,重慶 400042; 3.重慶重科加速創(chuàng)業(yè)孵化器有限公司,重慶 402760)
摘要: 醫(yī)療文本的特征提取及分析在建設(shè)臨床決策支持系統(tǒng)方面具有較大的實(shí)用價(jià)值。針對(duì)包含各種術(shù)語(yǔ)和縮寫(xiě)的原始醫(yī)療文本難以提取特征的情況,提出了一種基于BERT與Word2vec的醫(yī)療文本分析模型。該模型對(duì)醫(yī)療病歷中關(guān)鍵醫(yī)療實(shí)體進(jìn)行識(shí)別,基于知識(shí)建立權(quán)重評(píng)分機(jī)制,對(duì)醫(yī)學(xué)文本進(jìn)行語(yǔ)義分析。實(shí)驗(yàn)數(shù)據(jù)表明,模型在醫(yī)療文本特征提取方面具有一定優(yōu)勢(shì),對(duì)高血壓性腦出血病歷的分析診斷性能良好,能有效應(yīng)用于臨床決策支持系統(tǒng)。
中圖分類號(hào):TP183
文獻(xiàn)標(biāo)志碼:A
DOI: 10.16157/j.issn.0258-7998.223231
中文引用格式: 黃琦麟,蔣理,羅義蘭,等. 面向臨床決策支持系統(tǒng)的醫(yī)療文本分析模型[J]. 電子技術(shù)應(yīng)用,2023,49(5):57-61.
英文引用格式: Huang Qilin,Jiang Li,Luo Yilan,et al. A medical text analysis model for clinical decision support systems[J]. Application of Electronic Technique,2023,49(5):57-61.
文獻(xiàn)標(biāo)志碼:A
DOI: 10.16157/j.issn.0258-7998.223231
中文引用格式: 黃琦麟,蔣理,羅義蘭,等. 面向臨床決策支持系統(tǒng)的醫(yī)療文本分析模型[J]. 電子技術(shù)應(yīng)用,2023,49(5):57-61.
英文引用格式: Huang Qilin,Jiang Li,Luo Yilan,et al. A medical text analysis model for clinical decision support systems[J]. Application of Electronic Technique,2023,49(5):57-61.
A medical text analysis model for clinical decision support systems
Huang Qilin1,Jiang Li2,Luo Yilan3,Xu Zhiqiang3,Li Jie1
(1.Chongqing University of Science and Technology, Chongqing 401331, China; 2.The First Affiliated Hospital of Chongqing Medical University, Chongqing 400042, China; 3.Chongqing Zhongke Accelerated Business Incubator Co., Ltd., Chongqing 402760, China)
Abstract: Feature extraction and analysis of medical text is of great practical value in building clinical decision support systems. A medical text analysis model based on BERT and Word2vec is proposed for the situation that raw medical texts containing various terms and abbreviations are difficult to extract features. The model extracts key medical entities from medical records and establishes a weight scoring mechanism based on knowledge for semantic analysis of medical texts. The experimental data show that the model has certain advantages in medical text feature extraction, good performance in the analysis and diagnosis of hypertensive intracerebral hemorrhage medical records, and can be effectively used in clinical decision support systems.
Key words : clinical decision support system;named entity recognition;feature extraction;semantic analysis
0 引言
臨床決策支持系統(tǒng)用于增強(qiáng)臨床醫(yī)生的復(fù)雜決策過(guò)程,代表了當(dāng)今醫(yī)療保健的范式轉(zhuǎn)變。近年來(lái),臨床決策支持系統(tǒng)已經(jīng)廣泛應(yīng)用于各個(gè)醫(yī)療場(chǎng)景,包括心理治療、分診、預(yù)測(cè)病灶等。
電子健康病歷的收集為建立先進(jìn)的臨床決策支持系統(tǒng)提供了一個(gè)有效途徑,利用現(xiàn)有的醫(yī)療文本(如患病史、查體報(bào)告和輔助檢查報(bào)告)可以分析治療方案和醫(yī)療記錄文本之間的關(guān)系。在實(shí)際應(yīng)用中,臨床決策制定的首要任務(wù)是從原始非結(jié)構(gòu)化的醫(yī)療文本中提取有效語(yǔ)義特征并分析,以便制定完整的診斷性方案、手術(shù)治療方案、搶救性措施以及藥物治療方案等。
本文詳細(xì)內(nèi)容請(qǐng)下載:http://theprogrammingfactory.com/resource/share/2000005314
作者信息:
黃琦麟1,蔣理2,羅義蘭3,徐治強(qiáng)3,利節(jié)1
(1.重慶科技學(xué)院,重慶401331;2.重慶醫(yī)科大學(xué)附屬第一醫(yī)院,重慶 400042;3.重慶重科加速創(chuàng)業(yè)孵化器有限公司,重慶 402760)
此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。