Medical information extraction system and method based on depth learning and distributed semantic features

Abstract

he invention discloses a medical information extraction system and method based on depth learning and distributed semantic features. The system is composed of a pretreatment module, a linguistic-model-based word vector training module, a massive medical knowledge base reinforced learning module, and a depth-artificial-neural-network-based medical term entity identification module. With a depth learning method, generation of the probability of a linguistic model is used as an optimization objective; and a primary word vector is trained by using medical text big data; on the basis of the massive medical knowledge base, a second depth artificial neural network is trained, and the massive knowledge base is combined to the feature leaning process of depth learning based on depth reinforced learning, so that distributed semantic features for the medical field are obtained; and then Chinese medical term entity identification is carried out by using the depth learning method based on the optimized statement-level maximum likelihood probability. Therefore, the word vector is generated by using lots of unmarked linguistic data, so that the tedious feature selection and optimization adjustment process during medical natural language process can be avoided.

Description

technical field

[0001] The invention relates to a medical information extraction system based on deep learning and distributed semantic features and an implementation method thereof. Background technique

[0002] Widespread use of health information technology has led to an unprecedented expansion of electronic health record (EHR) data. Electronic medical record data has not only been used to support clinical operation tasks (eg, clinical decision support system), but also can support a variety of clinical research tasks. Much important patient information is scattered in narrative medical texts, but most computer applications can only understand structured data. Therefore, the technology of clinical natural language processing (Clinical NLP), which can extract important patient information in medical texts, has been introduced into the medical field and has shown great utility in many applications.

[0003] According to the 6th Conference on Information Understanding (MUC...

Examples

Embodiment Construction

[0061] The present invention takes the probability of generating a language model as an optimization goal through a deep learning method, and uses medical text big data to train primary word vectors; based on a massive medical knowledge base, trains a second deep artificial neural network, and through deep reinforcement learning, massive knowledge The library is integrated into the feature learning process of deep learning to obtain the distributed semantic features of the true medical field; finally, the deep learning method based on the optimized sentence-level maximum likelihood probability is used for the entity recognition of Chinese medical names.

[0062] Such as figure 1 As shown, the medical information extraction system based on deep learning and distributed semantic features includes a preprocessing module 1, a language model-based word vector training module 2, a massive medical knowledge base reinforcement learning module 3, and a medical name entity based on a dee...

technical field

[0001] The invention relates to a medical information extraction system based on deep learning and distributed semantic features and an implementation method thereof. Background technique

[0002] Widespread use of health information technology has led to an unprecedented expansion of electronic health record (EHR) data. Electronic medical record data has not only been used to support clinical operation tasks (eg, clinical decision support system), but also can support a variety of clinical research tasks. Much important patient information is scattered in narrative medical texts, but most computer applications can only understand structured data. Therefore, the technology of clinical natural language processing (Clinical NLP), which can extract important patient information in medical texts, has been introduced into the medical field and has shown great utility in many applications.

[0003] According to the 6th Conference on Information Understanding (MUC...

Examples

Embodiment Construction

[0061] The present invention takes the probability of generating a language model as an optimization goal through a deep learning method, and uses medical text big data to train primary word vectors; based on a massive medical knowledge base, trains a second deep artificial neural network, and through deep reinforcement learning, massive knowledge The library is integrated into the feature learning process of deep learning to obtain the distributed semantic features of the true medical field; finally, the deep learning method based on the optimized sentence-level maximum likelihood probability is used for the entity recognition of Chinese medical names.

[0062] Such as figure 1 As shown, the medical information extraction system based on deep learning and distributed semantic features includes a preprocessing module 1, a language model-based word vector training module 2, a massive medical knowledge base reinforcement learning module 3, and a medical name entity based on a dee...

Images