Enhancing Error Detection on Medical Knowledge Graphs via Intrinsic Label
The construction of medical knowledge graphs (MKGs) is steadily progressing from manual to automatic methods, which inevitably introduce noise, which could impair the performance of downstream healthcare applications. Existing error detection approaches depend on the topological structure and extern...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/11/3/225 |
| _version_ | 1797241997040287744 |
|---|---|
| author | Guangya Yu Qi Ye Tong Ruan |
| author_facet | Guangya Yu Qi Ye Tong Ruan |
| author_sort | Guangya Yu |
| collection | DOAJ |
| description | The construction of medical knowledge graphs (MKGs) is steadily progressing from manual to automatic methods, which inevitably introduce noise, which could impair the performance of downstream healthcare applications. Existing error detection approaches depend on the topological structure and external labels of entities in MKGs to improve their quality. Nevertheless, due to the cost of manual annotation and imperfect automatic algorithms, precise entity labels in MKGs cannot be readily obtained. To address these issues, we propose an approach named Enhancing error detection on Medical knowledge graphs via intrinsic labEL (EMKGEL). Considering the absence of hyper-view KG, we establish a hyper-view KG and a triplet-level KG for implicit label information and neighborhood information, respectively. Inspired by the success of graph attention networks (GATs), we introduce the hyper-view GAT to incorporate label messages and neighborhood information into representation learning. We leverage a confidence score that combines local and global trustworthiness to estimate the triplets. To validate the effectiveness of our approach, we conducted experiments on three publicly available MKGs, namely PharmKG-8k, DiseaseKG, and DiaKG. Compared with the baseline models, the Precision@K value improved by 0.7%, 6.1%, and 3.6%, respectively, on these datasets. Furthermore, our method empirically showed that it significantly outperformed the baseline on a general knowledge graph, Nell-995. |
| first_indexed | 2024-04-24T18:32:12Z |
| format | Article |
| id | doaj.art-536a75f02a5b4ce784aef1f321d0572c |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-04-24T18:32:12Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-536a75f02a5b4ce784aef1f321d0572c2024-03-27T13:21:48ZengMDPI AGBioengineering2306-53542024-02-0111322510.3390/bioengineering11030225Enhancing Error Detection on Medical Knowledge Graphs via Intrinsic LabelGuangya Yu0Qi Ye1Tong Ruan2Zhejiang Laboratory, Hangzhou 311121, ChinaSchool of Information Science and Technology, East China University of Science and Technology, Shanghai 200237, ChinaSchool of Information Science and Technology, East China University of Science and Technology, Shanghai 200237, ChinaThe construction of medical knowledge graphs (MKGs) is steadily progressing from manual to automatic methods, which inevitably introduce noise, which could impair the performance of downstream healthcare applications. Existing error detection approaches depend on the topological structure and external labels of entities in MKGs to improve their quality. Nevertheless, due to the cost of manual annotation and imperfect automatic algorithms, precise entity labels in MKGs cannot be readily obtained. To address these issues, we propose an approach named Enhancing error detection on Medical knowledge graphs via intrinsic labEL (EMKGEL). Considering the absence of hyper-view KG, we establish a hyper-view KG and a triplet-level KG for implicit label information and neighborhood information, respectively. Inspired by the success of graph attention networks (GATs), we introduce the hyper-view GAT to incorporate label messages and neighborhood information into representation learning. We leverage a confidence score that combines local and global trustworthiness to estimate the triplets. To validate the effectiveness of our approach, we conducted experiments on three publicly available MKGs, namely PharmKG-8k, DiseaseKG, and DiaKG. Compared with the baseline models, the Precision@K value improved by 0.7%, 6.1%, and 3.6%, respectively, on these datasets. Furthermore, our method empirically showed that it significantly outperformed the baseline on a general knowledge graph, Nell-995.https://www.mdpi.com/2306-5354/11/3/225medical knowledge grapherror detectionconfidence scoregraph attention network |
| spellingShingle | Guangya Yu Qi Ye Tong Ruan Enhancing Error Detection on Medical Knowledge Graphs via Intrinsic Label Bioengineering medical knowledge graph error detection confidence score graph attention network |
| title | Enhancing Error Detection on Medical Knowledge Graphs via Intrinsic Label |
| title_full | Enhancing Error Detection on Medical Knowledge Graphs via Intrinsic Label |
| title_fullStr | Enhancing Error Detection on Medical Knowledge Graphs via Intrinsic Label |
| title_full_unstemmed | Enhancing Error Detection on Medical Knowledge Graphs via Intrinsic Label |
| title_short | Enhancing Error Detection on Medical Knowledge Graphs via Intrinsic Label |
| title_sort | enhancing error detection on medical knowledge graphs via intrinsic label |
| topic | medical knowledge graph error detection confidence score graph attention network |
| url | https://www.mdpi.com/2306-5354/11/3/225 |
| work_keys_str_mv | AT guangyayu enhancingerrordetectiononmedicalknowledgegraphsviaintrinsiclabel AT qiye enhancingerrordetectiononmedicalknowledgegraphsviaintrinsiclabel AT tongruan enhancingerrordetectiononmedicalknowledgegraphsviaintrinsiclabel |