Globally there is an increased digitalization going on with an increasing number of people having access to the internet, having smartphones and now also in many countries being expected to access health-related infor...Globally there is an increased digitalization going on with an increasing number of people having access to the internet, having smartphones and now also in many countries being expected to access health-related information and schedule appointments through websites, apps or web-based portals. Healthcare providers have also adopted this with an increasing number of public or private organizations providing web-based portals as well as app interfaces to some of the largest electronic healthcare systems. The benefit of this is easier access, more efficient provision of services, increased transparency and improved workflows. This may increase the population’s capability to manage their conditions and reduce the contacts to, thereby burdening healthcare professionals. But not all will be able to benefit from this digital (r)evolution. Those who will not be able to include people with dementia. For people with dementia to also be able to take advantage of digital health tools and services, it will require planning and involvement of caregivers. In 2017, we presented the Epital Care Model as a framework to organize an efficient people-centered cross-disciplinary and cross-sectoral way to organize activities, roles, responsibilities and describe geographical locations and used technologies in response to individuals’ specific diagnoses and everyday changes in their condition. In 2021, an EU-funded project was initiated to investigate how living labs and scaling up could be done building upon the ECM. One of the living labs was organized around an organization providing care to PWD in Netherlands. In the period 2021 to 2024, we have tried to identify ways for how the ECM could be used to digitally enable the services provided by the organization. In 2022, the care organization tanteLouise started a project originally named Daycare Centre2.0 (now called “Van Thuis Uit” meaning “From Home”), together with healthcare insurance company CZ, and developed a model for onboarding people with dementia and introducing展开更多
Objectives Medical knowledge extraction (MKE) plays a key role in natural language processing (NLP) research in electronic medical records (EMR),which are the important digital carriers for recording medical activitie...Objectives Medical knowledge extraction (MKE) plays a key role in natural language processing (NLP) research in electronic medical records (EMR),which are the important digital carriers for recording medical activities of patients.Named entity recognition (NER) and medical relation extraction (MRE) are two basic tasks of MKE.This study aims to improve the recognition accuracy of these two tasks by exploring deep learning methods.Methods This study discussed and built two application scenes of bidirectional long short-term memory combined conditional random field (BiLSTM-CRF) model for NER and MRE tasks.In the data preprocessing of both tasks,a GloVe word embedding model was used to vectorize words.In the NER task,a sequence labeling strategy was used to classify each word tag by the joint probability distribution through the CRF layer.In the MRE task,the medical entity relation category was predicted by transforming the classification problem of a single entity into a sequence classification problem and linking the feature combinations between entities also through the CRF layer.Results Through the validation on the I2B2 2010 public dataset,the BiLSTM-CRF models built in this study got much better results than the baseline methods in the two tasks,where the F1-measure was up to 0.88 in NER task and 0.78 in MRE task.Moreover,the model converged faster and avoided problems such as overfitting.Conclusion This study proved the good performance of deep learning on medical knowledge extraction.It also verified the feasibility of the BiLSTM-CRF model in different application scenarios,laying the foundation for the subsequent work in the EMR field.展开更多
针对军事领域的知识图谱的应用,设计实现了基于军事领域知识图谱的合成旅指挥员智能问答系统。首先,通过对军事领域应用的特点分析,设计实现了基于Jieba工具的中文分词模块、基于双向长短期记忆网络-条件随机场(Bidirectional Long Shor...针对军事领域的知识图谱的应用,设计实现了基于军事领域知识图谱的合成旅指挥员智能问答系统。首先,通过对军事领域应用的特点分析,设计实现了基于Jieba工具的中文分词模块、基于双向长短期记忆网络-条件随机场(Bidirectional Long Short Term Memory-Conditional Random Field,BiLSTM-CRF)的命名实体识别模块和基于Cypher语言的问题查询模块等关键模块;然后,构建了基于环球军事网以及新浪军事中爬取到的新闻数据构建数据集,进而基于此数据集进行命名实体识别算法实验对比分析;最后,对BiLSTM-CRF算法进行参数调优,使得模型的识别效果达到最优,进而对系统进行了展示。展开更多
文摘Globally there is an increased digitalization going on with an increasing number of people having access to the internet, having smartphones and now also in many countries being expected to access health-related information and schedule appointments through websites, apps or web-based portals. Healthcare providers have also adopted this with an increasing number of public or private organizations providing web-based portals as well as app interfaces to some of the largest electronic healthcare systems. The benefit of this is easier access, more efficient provision of services, increased transparency and improved workflows. This may increase the population’s capability to manage their conditions and reduce the contacts to, thereby burdening healthcare professionals. But not all will be able to benefit from this digital (r)evolution. Those who will not be able to include people with dementia. For people with dementia to also be able to take advantage of digital health tools and services, it will require planning and involvement of caregivers. In 2017, we presented the Epital Care Model as a framework to organize an efficient people-centered cross-disciplinary and cross-sectoral way to organize activities, roles, responsibilities and describe geographical locations and used technologies in response to individuals’ specific diagnoses and everyday changes in their condition. In 2021, an EU-funded project was initiated to investigate how living labs and scaling up could be done building upon the ECM. One of the living labs was organized around an organization providing care to PWD in Netherlands. In the period 2021 to 2024, we have tried to identify ways for how the ECM could be used to digitally enable the services provided by the organization. In 2022, the care organization tanteLouise started a project originally named Daycare Centre2.0 (now called “Van Thuis Uit” meaning “From Home”), together with healthcare insurance company CZ, and developed a model for onboarding people with dementia and introducing
基金Supported by the Zhejiang Provincial Natural Science Foundation(No.LQ16H180004)~~
文摘Objectives Medical knowledge extraction (MKE) plays a key role in natural language processing (NLP) research in electronic medical records (EMR),which are the important digital carriers for recording medical activities of patients.Named entity recognition (NER) and medical relation extraction (MRE) are two basic tasks of MKE.This study aims to improve the recognition accuracy of these two tasks by exploring deep learning methods.Methods This study discussed and built two application scenes of bidirectional long short-term memory combined conditional random field (BiLSTM-CRF) model for NER and MRE tasks.In the data preprocessing of both tasks,a GloVe word embedding model was used to vectorize words.In the NER task,a sequence labeling strategy was used to classify each word tag by the joint probability distribution through the CRF layer.In the MRE task,the medical entity relation category was predicted by transforming the classification problem of a single entity into a sequence classification problem and linking the feature combinations between entities also through the CRF layer.Results Through the validation on the I2B2 2010 public dataset,the BiLSTM-CRF models built in this study got much better results than the baseline methods in the two tasks,where the F1-measure was up to 0.88 in NER task and 0.78 in MRE task.Moreover,the model converged faster and avoided problems such as overfitting.Conclusion This study proved the good performance of deep learning on medical knowledge extraction.It also verified the feasibility of the BiLSTM-CRF model in different application scenarios,laying the foundation for the subsequent work in the EMR field.
文摘针对军事领域的知识图谱的应用,设计实现了基于军事领域知识图谱的合成旅指挥员智能问答系统。首先,通过对军事领域应用的特点分析,设计实现了基于Jieba工具的中文分词模块、基于双向长短期记忆网络-条件随机场(Bidirectional Long Short Term Memory-Conditional Random Field,BiLSTM-CRF)的命名实体识别模块和基于Cypher语言的问题查询模块等关键模块;然后,构建了基于环球军事网以及新浪军事中爬取到的新闻数据构建数据集,进而基于此数据集进行命名实体识别算法实验对比分析;最后,对BiLSTM-CRF算法进行参数调优,使得模型的识别效果达到最优,进而对系统进行了展示。
