Improving graph embeddings via entity linking: A case study on Italian clinical notes
The ever-increasing availability of Electronic Health Records (EHRs) is the key enabling factor of precision medicine, which aims to provide therapies and diagnoses based not only on medical literature, but also on clinical experience and individual information of patients (e.g. genomics, lifestyle,...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-02-01
|
| Series: | Intelligent Systems with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667305322000989 |
| _version_ | 1811170978669002752 |
|---|---|
| author | Daniela D'Auria Vincenzo Moscato Marco Postiglione Giuseppe Romito Giancarlo Sperlí |
| author_facet | Daniela D'Auria Vincenzo Moscato Marco Postiglione Giuseppe Romito Giancarlo Sperlí |
| author_sort | Daniela D'Auria |
| collection | DOAJ |
| description | The ever-increasing availability of Electronic Health Records (EHRs) is the key enabling factor of precision medicine, which aims to provide therapies and diagnoses based not only on medical literature, but also on clinical experience and individual information of patients (e.g. genomics, lifestyle, health history). The unstructured nature of EHRs has posed several challenges on their effective analysis, and heterogeneous graphs are the most suitable solution to handle the heterogeneity of information contained in EHRs. However, while EHRs are an extremely valuable data source, information from current medical literature has yet to be considered in clinical decision support systems. In this work, we build an heterogeneous graph from Italian EHRs provided by the Hospital of Naples Federico II, and we define a methodological workflow allowing us to predict the presence of a link between patients and diagnosed diseases. We empirically demonstrate that linking concepts to biomedical ontologies (e.g. UMLS, DBpedia) — which allow us to extract entities and relationships from medical literature — is significantly beneficial to our link-prediction workflow in terms of Area Under the ROC curve (AUC) and Mean Reciprocal Rank (MRR). |
| first_indexed | 2024-04-10T17:05:48Z |
| format | Article |
| id | doaj.art-01a708583b38493a8bd0e4a833301554 |
| institution | Directory Open Access Journal |
| issn | 2667-3053 |
| language | English |
| last_indexed | 2024-04-10T17:05:48Z |
| publishDate | 2023-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Intelligent Systems with Applications |
| spelling | doaj.art-01a708583b38493a8bd0e4a8333015542023-02-06T04:06:23ZengElsevierIntelligent Systems with Applications2667-30532023-02-0117200161Improving graph embeddings via entity linking: A case study on Italian clinical notesDaniela D'Auria0Vincenzo Moscato1Marco Postiglione2Giuseppe Romito3Giancarlo Sperlí4Faculty of Computer Science, Free University of Bozen-Bolzano, Bozen-Bolzano, 39100, ItalyUniversity of Naples “Federico II”, Dept. of Electrical Engineering and Information Technology (DIETI), Via Claudio 21, 80125, ItalyUniversity of Naples “Federico II”, Dept. of Electrical Engineering and Information Technology (DIETI), Via Claudio 21, 80125, ItalyUniversity of Naples “Federico II”, Dept. of Electrical Engineering and Information Technology (DIETI), Via Claudio 21, 80125, ItalyUniversity of Naples “Federico II”, Dept. of Electrical Engineering and Information Technology (DIETI), Via Claudio 21, 80125, Italy; Corresponding author.The ever-increasing availability of Electronic Health Records (EHRs) is the key enabling factor of precision medicine, which aims to provide therapies and diagnoses based not only on medical literature, but also on clinical experience and individual information of patients (e.g. genomics, lifestyle, health history). The unstructured nature of EHRs has posed several challenges on their effective analysis, and heterogeneous graphs are the most suitable solution to handle the heterogeneity of information contained in EHRs. However, while EHRs are an extremely valuable data source, information from current medical literature has yet to be considered in clinical decision support systems. In this work, we build an heterogeneous graph from Italian EHRs provided by the Hospital of Naples Federico II, and we define a methodological workflow allowing us to predict the presence of a link between patients and diagnosed diseases. We empirically demonstrate that linking concepts to biomedical ontologies (e.g. UMLS, DBpedia) — which allow us to extract entities and relationships from medical literature — is significantly beneficial to our link-prediction workflow in terms of Area Under the ROC curve (AUC) and Mean Reciprocal Rank (MRR).http://www.sciencedirect.com/science/article/pii/S2667305322000989Entity linkingGraph embeddingLink predictionHealth analyticsHealthcare |
| spellingShingle | Daniela D'Auria Vincenzo Moscato Marco Postiglione Giuseppe Romito Giancarlo Sperlí Improving graph embeddings via entity linking: A case study on Italian clinical notes Intelligent Systems with Applications Entity linking Graph embedding Link prediction Health analytics Healthcare |
| title | Improving graph embeddings via entity linking: A case study on Italian clinical notes |
| title_full | Improving graph embeddings via entity linking: A case study on Italian clinical notes |
| title_fullStr | Improving graph embeddings via entity linking: A case study on Italian clinical notes |
| title_full_unstemmed | Improving graph embeddings via entity linking: A case study on Italian clinical notes |
| title_short | Improving graph embeddings via entity linking: A case study on Italian clinical notes |
| title_sort | improving graph embeddings via entity linking a case study on italian clinical notes |
| topic | Entity linking Graph embedding Link prediction Health analytics Healthcare |
| url | http://www.sciencedirect.com/science/article/pii/S2667305322000989 |
| work_keys_str_mv | AT danieladauria improvinggraphembeddingsviaentitylinkingacasestudyonitalianclinicalnotes AT vincenzomoscato improvinggraphembeddingsviaentitylinkingacasestudyonitalianclinicalnotes AT marcopostiglione improvinggraphembeddingsviaentitylinkingacasestudyonitalianclinicalnotes AT giusepperomito improvinggraphembeddingsviaentitylinkingacasestudyonitalianclinicalnotes AT giancarlosperli improvinggraphembeddingsviaentitylinkingacasestudyonitalianclinicalnotes |