Robustly Extracting Medical Knowledge from EHRs: A Case Study of Learning a Health Knowledge Graph

Abstract In recent years, more and more attention has been paid to Human-Robot Collaborative Disassembly (HRCD) in the field of industrial remanufacturing. Compared with the traditional manufacturing, HRCD helps to improve the manufacturing flexibility with considering the manufacturing efficiency. In HRCD, knowledge could be obtained from the disassembly process and then provides useful information for the operator and robots to execute their disassembly tasks. Afterwards, a crucial point is to establish a knowledge-based system to facilitate the interaction between human operators and industrial robots. In this context, a knowledge recommendation system based on knowledge graph is proposed to effectively support Human-Robot Collaboration (HRC) in disassembly. A disassembly knowledge graph is constructed to organize and manage the knowledge in the process of HRCD. After that, based on this, a knowledge recommendation procedure is proposed to recommend disassembly knowledge for the operator. Finally, the case study demonstrates that the developed system can effectively acquire, manage and visualize the related knowledge of HRCD, and then assist the human operator to complete the disassembly task by knowledge recommendation, thus improving the efficiency of collaborative disassembly. This system could be used in the human-robot collaboration disassembly process for the operators to provide convenient knowledge recommendation service.

Download Full-text

Annotation Scheme and Specification for Named Entities and Relations on Chinese Medical Knowledge Graph

Lecture Notes in Computer Science - Chinese Lexical Semantics ◽

10.1007/978-3-030-38189-9_58 ◽

2020 ◽

pp. 563-574

Author(s):

Donghui Yue ◽

Kunli Zhang ◽

Lei Zhuang ◽

Xu Zhao ◽

Odmaa Byambasuren ◽

...

Keyword(s):

Medical Knowledge ◽

Knowledge Graph ◽

Annotation Scheme ◽

Named Entities

Download Full-text

Assessing the Social Impact of Mental Health Service Accessibility by a Nonprofit Social Enterprise: A Mixed--methods Case Study

Canadian journal of nonprofit and social economy research ◽

10.29173/cjnser.2021v12n1a378 ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

Aaron Turpin ◽

Micheal Shier ◽

Kate Scowen

Keyword(s):

Mental Health ◽

Mixed Methods ◽

Social Enterprise ◽

Social Impact ◽

Health Knowledge ◽

Assessment Model ◽

Mental Health Stigma ◽

Service Accessibility ◽

The Social

The following study sought to examine the social impact of a social enterprise mental health services model by assessing its impact on service accessibility and mental health stigma. A novel approach to case study – a mixed methods design was developed by collecting data from service users, counsellors, and community members of a social enterprise in Toronto, Ontario, using qualitative interviews and the Mental Health Knowledge Schedule (MAKS) survey. Findings show how the social enterprise increases service access and challenges mental health stigma by engaging in a variety of activities, including providing low--cost counselling, diversifying services, offering a positive and safe non--clinical environment, and engaging with the public directly by utilizing a storefront model. As a result of data triangulation analysis, common themes and discrepancies between respondent groups are identified and discussed. No significant relationships were found between mental health stigma and community member demographic characteristics. Insights on replication of this social impact assessment model are discussed.

Download Full-text

Knowledge, Attitude, and Practice of Physicians Regarding Vaccinations in Yerevan, Armenia: A Case Study of HPV

Vaccines ◽

10.3390/vaccines9101188 ◽

2021 ◽

Vol 9 (10) ◽

pp. 1188

Author(s):

Arman R. Badalyan ◽

Marine Hovhannisyan ◽

Gayane Ghavalyan ◽

Mary M. Ter-Stepanyan ◽

Rory Cave ◽

...

Keyword(s):

Cervical Cancer ◽

Vaccine Coverage ◽

Medical Knowledge ◽

Hpv Infection ◽

Healthcare Sector ◽

Vaccine Hesitancy ◽

Primary Data ◽

Cross Sectional ◽

New Vaccines

This paper highlights the low levels of vaccine coverage and high levels of reported vaccination hesitancy in Yerevan, Armenia, that present profound challenges to the control of disease through routine vaccination programmes. We draw on investigations of hesitancy towards the introduction of new vaccines, using the Human Papillomavirus (HPV) vaccine Gardasil as a case study, to interrogate underlying challenges to vaccine acceptance. We analyse primary data from the introduction of Gardasil, first used in Armenia in 2017, to investigate how levels of medical knowledge amongst physicians in 20 health facilities in Yerevan, Armenia, regarding vaccine science influence attitudes towards the introduction of a newly developed vaccine. A questionnaire-based cross-sectional study was completed by 348 physicians between December 2017 and September 2018. The responding physicians displayed a respectable level of knowledge and awareness regarding vaccination with respect to some characteristics (e.g., more than 81% knew that HPV infection was commonly asymptomatic, 73% knew that HPV infection was implicated in most cervical cancers, and 87% knew that cervical cancer is the most prevalent cancer amongst women) but low knowledge and poor understanding of other key issues such as the age at which women were most likely to develop cervical cancer (only 15% answered correctly), whether or not the vaccine should be administered to people who had already been infected (27% answered correctly) and whether sexually active young people should be treated for infection before vaccination (26% answered correctly). The study suggests that the drivers of vaccine hesitancy are complex and may not be consistent from vaccine to vaccine. The Armenian healthcare sector may need to provide additional training, awareness-raising and educational activities alongside the introduction of new vaccines to improve understanding of and trust in vaccination programmes.

Download Full-text

Does a Different Household Registration Affect Migrants’ Access to Basic Public Health Services in China?

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph16234615 ◽

2019 ◽

Vol 16 (23) ◽

pp. 4615 ◽

Cited By ~ 1

Author(s):

Meng

Keyword(s):

Public Health ◽

Health Services ◽

Low Income ◽

Health Knowledge ◽

Medical Knowledge ◽

Public Health Services ◽

Household Registration ◽

Career Training ◽

Permanent Settlement ◽

The Impact

On the basis of the China Migrants Dynamic Survey Data of 2015, the author provides an analysis of how a different household registration impacts migrants’ access to preventive care provided by public health services, such as health records and medical knowledge, in areas of immigration. This study shows that eliminating the distinction between agricultural and non-agricultural permanent residence registration could raise the rate of establishing health files, but it has no significant effect on migrants’ health knowledge. In fact, encouraging those with non-agricultural registration to move to different counties that belong to the same city or to different cities that belong to the same province can notably eliminate the impact of a different household registration status. Improving the income level of low-income migrants can have the same impact. Recommendations to enable migrants to obtain basic public health services include abolishing the separation of agricultural and non-agricultural household registration, increasing the permanent settlement rate of resident migrants, promoting basic medical security systems across the whole country, strengthening career training, and enhancing the education level of migrants.

Download Full-text

PW 2632 Health knowledge and helmet wearing behavior. A case study of namon hospital, amphur namon, kalasin province, 2016

10.1136/injuryprevention-2018-safety.674 ◽

2018 ◽

Author(s):

Attavit Neunchat

Keyword(s):

Health Knowledge

Download Full-text

BioKEEN: a library for learning and evaluating biological knowledge graph embeddings

Bioinformatics ◽

10.1093/bioinformatics/btz117 ◽

2019 ◽

Vol 35 (18) ◽

pp. 3538-3540 ◽

Cited By ~ 8

Author(s):

Mehdi Ali ◽

Charles Tapley Hoyt ◽

Daniel Domingo-Fernández ◽

Jens Lehmann ◽

Hajira Jabeen

Keyword(s):

Supplementary Information ◽

Knowledge Graph ◽

Biological Knowledge ◽

Command Line ◽

Graph Embeddings ◽

Command Line Interface ◽

Software Ecosystem ◽

Mapping Resource ◽

Significant Attention

Abstract Summary Knowledge graph embeddings (KGEs) have received significant attention in other domains due to their ability to predict links and create dense representations for graphs’ nodes and edges. However, the software ecosystem for their application to bioinformatics remains limited and inaccessible for users without expertise in programing and machine learning. Therefore, we developed BioKEEN (Biological KnowlEdge EmbeddiNgs) and PyKEEN (Python KnowlEdge EmbeddiNgs) to facilitate their easy use through an interactive command line interface. Finally, we present a case study in which we used a novel biological pathway mapping resource to predict links that represent pathway crosstalks and hierarchies. Availability and implementation BioKEEN and PyKEEN are open source Python packages publicly available under the MIT License at https://github.com/SmartDataAnalytics/BioKEEN and https://github.com/SmartDataAnalytics/PyKEEN Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33017346 ◽

2019 ◽

Vol 33 ◽

pp. 7346-7353

Author(s):

Lin Xu ◽

Qixian Zhou ◽

Ke Gong ◽

Xiaodan Liang ◽

Jianheng Tang ◽

...

Keyword(s):

Natural Language ◽

Medical Diagnosis ◽

Expert Knowledge ◽

Medical Knowledge ◽

Knowledge Graph ◽

Dialogue Systems ◽

Dialogue System ◽

Self Reports ◽

Medical Dialogue ◽

End To End

Beyond current conversational chatbots or task-oriented dialogue systems that have attracted increasing attention, we move forward to develop a dialogue system for automatic medical diagnosis that converses with patients to collect additional symptoms beyond their self-reports and automatically makes a diagnosis. Besides the challenges for conversational dialogue systems (e.g. topic transition coherency and question understanding), automatic medical diagnosis further poses more critical requirements for the dialogue rationality in the context of medical knowledge and symptom-disease relations. Existing dialogue systems (Madotto, Wu, and Fung 2018; Wei et al. 2018; Li et al. 2017) mostly rely on datadriven learning and cannot be able to encode extra expert knowledge graph. In this work, we propose an End-to-End Knowledge-routed Relational Dialogue System (KR-DS) that seamlessly incorporates rich medical knowledge graph into the topic transition in dialogue management, and makes it cooperative with natural language understanding and natural language generation. A novel Knowledge-routed Deep Q-network (KR-DQN) is introduced to manage topic transitions, which integrates a relational refinement branch for encoding relations among different symptoms and symptomdisease pairs, and a knowledge-routed graph branch for topic decision-making. Extensive experiments on a public medical dialogue dataset show our KR-DS significantly beats stateof-the-art methods (by more than 8% in diagnosis accuracy). We further show the superiority of our KR-DS on a newly collected medical dialogue system dataset, which is more challenging retaining original self-reports and conversational data between patients and doctors.

Download Full-text