Constructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling study
The needs of mitigating COVID-19 epidemic prompt policymakers to make public health-related decision under the guidelines of science. Tremendous unstructured COVID-19 publications make it challenging for policymakers to obtain relevant evidence. Knowledge graphs (KGs) can formalize unstructured know...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2021-09-01
|
| Series: | Journal of Safety Science and Resilience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266644962100030X |
| _version_ | 1818976518323306496 |
|---|---|
| author | Yunrong Yang Zhidong Cao Pengfei Zhao Dajun Daniel Zeng Qingpeng Zhang Yin Luo |
| author_facet | Yunrong Yang Zhidong Cao Pengfei Zhao Dajun Daniel Zeng Qingpeng Zhang Yin Luo |
| author_sort | Yunrong Yang |
| collection | DOAJ |
| description | The needs of mitigating COVID-19 epidemic prompt policymakers to make public health-related decision under the guidelines of science. Tremendous unstructured COVID-19 publications make it challenging for policymakers to obtain relevant evidence. Knowledge graphs (KGs) can formalize unstructured knowledge into structured form and have been used in supporting decision-making recently. Here, we introduce a novel framework that can extract the COVID-19 public health evidence knowledge graph (CPHE-KG) from papers relating to a modelling study. We screen out a corpus of 3096 COVID-19 modelling study papers by performing a literature assessment process. We define a novel annotation schema to construct the COVID-19 modelling study-related IE dataset (CPHIE). We also propose a novel multi-tasks document-level information extraction model SS-DYGIE++ based on the dataset. Leveraging the model on the new corpus, we construct CPHE-KG containing 60,967 entities and 51,140 relations. Finally, we seek to apply our KG to support evidence querying and evidence mapping visualization. Our SS-DYGIE++(SpanBERT) model has achieved a F1 score of 0.77 and 0.55 respectively in document-level entity recognition and coreference resolution tasks. It has also shown high performance in the relation identification task. With evidence querying, our KG can present the dynamic transmissions of COVID-19 pandemic in different countries and regions. The evidence mapping of our KG can show the impacts of variable non-pharmacological interventions to COVID-19 pandemic. Analysis demonstrates the quality of our KG and shows that it has the potential to support COVID-19 policy making in public health. |
| first_indexed | 2024-12-20T16:13:07Z |
| format | Article |
| id | doaj.art-781f8e88c2404c23a2134496af9346ac |
| institution | Directory Open Access Journal |
| issn | 2666-4496 |
| language | English |
| last_indexed | 2024-12-20T16:13:07Z |
| publishDate | 2021-09-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Journal of Safety Science and Resilience |
| spelling | doaj.art-781f8e88c2404c23a2134496af9346ac2022-12-21T19:33:55ZengKeAi Communications Co., Ltd.Journal of Safety Science and Resilience2666-44962021-09-0123146156Constructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling studyYunrong Yang0Zhidong Cao1Pengfei Zhao2Dajun Daniel Zeng3Qingpeng Zhang4Yin Luo5School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100190, China; The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaThe State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100190, China; Shenzhen Artificial Intelligence and Data Science Institute (Longhua), Shenzhen 518038, China; Corresponding author.The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100190, China; Shenzhen Artificial Intelligence and Data Science Institute (Longhua), Shenzhen 518038, ChinaThe State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100190, China; Shenzhen Artificial Intelligence and Data Science Institute (Longhua), Shenzhen 518038, ChinaSchool of Data Science, City University of Hong Kong - Hong Kong SAR, ChinaThe State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100190, China; Shenzhen Artificial Intelligence and Data Science Institute (Longhua), Shenzhen 518038, ChinaThe needs of mitigating COVID-19 epidemic prompt policymakers to make public health-related decision under the guidelines of science. Tremendous unstructured COVID-19 publications make it challenging for policymakers to obtain relevant evidence. Knowledge graphs (KGs) can formalize unstructured knowledge into structured form and have been used in supporting decision-making recently. Here, we introduce a novel framework that can extract the COVID-19 public health evidence knowledge graph (CPHE-KG) from papers relating to a modelling study. We screen out a corpus of 3096 COVID-19 modelling study papers by performing a literature assessment process. We define a novel annotation schema to construct the COVID-19 modelling study-related IE dataset (CPHIE). We also propose a novel multi-tasks document-level information extraction model SS-DYGIE++ based on the dataset. Leveraging the model on the new corpus, we construct CPHE-KG containing 60,967 entities and 51,140 relations. Finally, we seek to apply our KG to support evidence querying and evidence mapping visualization. Our SS-DYGIE++(SpanBERT) model has achieved a F1 score of 0.77 and 0.55 respectively in document-level entity recognition and coreference resolution tasks. It has also shown high performance in the relation identification task. With evidence querying, our KG can present the dynamic transmissions of COVID-19 pandemic in different countries and regions. The evidence mapping of our KG can show the impacts of variable non-pharmacological interventions to COVID-19 pandemic. Analysis demonstrates the quality of our KG and shows that it has the potential to support COVID-19 policy making in public health.http://www.sciencedirect.com/science/article/pii/S266644962100030XEvidence-based public healthKnowledge graphCOVID-19Decision-making support |
| spellingShingle | Yunrong Yang Zhidong Cao Pengfei Zhao Dajun Daniel Zeng Qingpeng Zhang Yin Luo Constructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling study Journal of Safety Science and Resilience Evidence-based public health Knowledge graph COVID-19 Decision-making support |
| title | Constructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling study |
| title_full | Constructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling study |
| title_fullStr | Constructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling study |
| title_full_unstemmed | Constructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling study |
| title_short | Constructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling study |
| title_sort | constructing public health evidence knowledge graph for decision making support from covid 19 literature of modelling study |
| topic | Evidence-based public health Knowledge graph COVID-19 Decision-making support |
| url | http://www.sciencedirect.com/science/article/pii/S266644962100030X |
| work_keys_str_mv | AT yunrongyang constructingpublichealthevidenceknowledgegraphfordecisionmakingsupportfromcovid19literatureofmodellingstudy AT zhidongcao constructingpublichealthevidenceknowledgegraphfordecisionmakingsupportfromcovid19literatureofmodellingstudy AT pengfeizhao constructingpublichealthevidenceknowledgegraphfordecisionmakingsupportfromcovid19literatureofmodellingstudy AT dajundanielzeng constructingpublichealthevidenceknowledgegraphfordecisionmakingsupportfromcovid19literatureofmodellingstudy AT qingpengzhang constructingpublichealthevidenceknowledgegraphfordecisionmakingsupportfromcovid19literatureofmodellingstudy AT yinluo constructingpublichealthevidenceknowledgegraphfordecisionmakingsupportfromcovid19literatureofmodellingstudy |