Mdpg : a novel multi-disease diagnosis prediction method based on patient knowledge graphs
© The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law..
Diagnosis prediction, a key factor in enhancing healthcare efficiency, remains a focal point in clinical decision support research. However, the time-series, sparse and multi-noise characteristics of electronic health record (EHR) data make it a great challenge. Existing methods commonly address these issues using RNNs and incorporating medical prior knowledge from medical knowledge bases, but they neglect the local spatial characteristics and spatial-temporal correlation of the data. Consequently, we propose MDPG, a diagnosis prediction model based on patient knowledge graphs. Initially, we represent the electronic visit records of patients as a patient-centered temporal knowledge graph, capturing the local spatial structure and temporal characteristics of the visit information. Subsequently, we design the spatial graph convolution block, temporal self-attention block, and spatial-temporal synchronous graph convolution block to capture the spatial, temporal, and spatial-temporal correlations embedded in them, respectively. Ultimately, we accomplish the prediction of patients' future states through multi-label classification. We conduct comprehensive experiments on two real-world datasets independently and evaluate the results using visit-level precisionk and code-level accuracy@k metrics. The experimental results demonstrate that MDPG outperforms all baseline models, yielding the best performance.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:12 |
|---|---|
| Enthalten in: |
Health information science and systems - 12(2024), 1 vom: 30. März, Seite 15 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Wang, Weiguang [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Diagnosis prediction |
|---|
| Anmerkungen: |
Date Revised 06.03.2024 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1007/s13755-024-00278-7 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM36929968X |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM36929968X | ||
| 003 | DE-627 | ||
| 005 | 20240306233303.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240305s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s13755-024-00278-7 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1318.xml |
| 035 | |a (DE-627)NLM36929968X | ||
| 035 | |a (NLM)38440103 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Wang, Weiguang |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Mdpg |b a novel multi-disease diagnosis prediction method based on patient knowledge graphs |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 06.03.2024 | ||
| 500 | |a published: Electronic-eCollection | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. | ||
| 520 | |a Diagnosis prediction, a key factor in enhancing healthcare efficiency, remains a focal point in clinical decision support research. However, the time-series, sparse and multi-noise characteristics of electronic health record (EHR) data make it a great challenge. Existing methods commonly address these issues using RNNs and incorporating medical prior knowledge from medical knowledge bases, but they neglect the local spatial characteristics and spatial-temporal correlation of the data. Consequently, we propose MDPG, a diagnosis prediction model based on patient knowledge graphs. Initially, we represent the electronic visit records of patients as a patient-centered temporal knowledge graph, capturing the local spatial structure and temporal characteristics of the visit information. Subsequently, we design the spatial graph convolution block, temporal self-attention block, and spatial-temporal synchronous graph convolution block to capture the spatial, temporal, and spatial-temporal correlations embedded in them, respectively. Ultimately, we accomplish the prediction of patients' future states through multi-label classification. We conduct comprehensive experiments on two real-world datasets independently and evaluate the results using visit-level precisionk and code-level accuracy@k metrics. The experimental results demonstrate that MDPG outperforms all baseline models, yielding the best performance | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Diagnosis prediction | |
| 650 | 4 | |a Healthcare representation learning | |
| 650 | 4 | |a Medical knowledge graphs | |
| 650 | 4 | |a Patient knowledge graphs | |
| 650 | 4 | |a Patient risk prediction | |
| 700 | 1 | |a Feng, Yingying |e verfasserin |4 aut | |
| 700 | 1 | |a Zhao, Haiyan |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Xin |e verfasserin |4 aut | |
| 700 | 1 | |a Cai, Ruikai |e verfasserin |4 aut | |
| 700 | 1 | |a Cai, Wei |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Xia |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Health information science and systems |d 2013 |g 12(2024), 1 vom: 30. März, Seite 15 |w (DE-627)NLM247587761 |x 2047-2501 |7 nnns |
| 773 | 1 | 8 | |g volume:12 |g year:2024 |g number:1 |g day:30 |g month:03 |g pages:15 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1007/s13755-024-00278-7 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 12 |j 2024 |e 1 |b 30 |c 03 |h 15 | ||