Early detection of Parkinson’s disease through enriching the electronic health record using a biomedical knowledge graph
IntroductionEarly diagnosis of Parkinson’s disease (PD) is important to identify treatments to slow neurodegeneration. People who develop PD often have symptoms before the disease manifests and may be coded as diagnoses in the electronic health record (EHR).MethodsTo predict PD diagnosis, we embedde...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-05-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2023.1081087/full |
| _version_ | 1797829010229559296 |
|---|---|
| author | Karthik Soman Charlotte A. Nelson Gabriel Cerono Samuel M. Goldman Sergio E. Baranzini Ethan G. Brown |
| author_facet | Karthik Soman Charlotte A. Nelson Gabriel Cerono Samuel M. Goldman Sergio E. Baranzini Ethan G. Brown |
| author_sort | Karthik Soman |
| collection | DOAJ |
| description | IntroductionEarly diagnosis of Parkinson’s disease (PD) is important to identify treatments to slow neurodegeneration. People who develop PD often have symptoms before the disease manifests and may be coded as diagnoses in the electronic health record (EHR).MethodsTo predict PD diagnosis, we embedded EHR data of patients onto a biomedical knowledge graph called Scalable Precision medicine Open Knowledge Engine (SPOKE) and created patient embedding vectors. We trained and validated a classifier using these vectors from 3,004 PD patients, restricting records to 1, 3, and 5 years before diagnosis, and 457,197 non-PD group.ResultsThe classifier predicted PD diagnosis with moderate accuracy (AUC = 0.77 ± 0.06, 0.74 ± 0.05, 0.72 ± 0.05 at 1, 3, and 5 years) and performed better than other benchmark methods. Nodes in the SPOKE graph, among cases, revealed novel associations, while SPOKE patient vectors revealed the basis for individual risk classification.DiscussionThe proposed method was able to explain the clinical predictions using the knowledge graph, thereby making the predictions clinically interpretable. Through enriching EHR data with biomedical associations, SPOKE may be a cost-efficient and personalized way to predict PD diagnosis years before its occurrence. |
| first_indexed | 2024-04-09T13:13:32Z |
| format | Article |
| id | doaj.art-814bed3af30e4b41b23cf6ab26fbd7ec |
| institution | Directory Open Access Journal |
| issn | 2296-858X |
| language | English |
| last_indexed | 2024-04-09T13:13:32Z |
| publishDate | 2023-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj.art-814bed3af30e4b41b23cf6ab26fbd7ec2023-05-12T05:40:39ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2023-05-011010.3389/fmed.2023.10810871081087Early detection of Parkinson’s disease through enriching the electronic health record using a biomedical knowledge graphKarthik Soman0Charlotte A. Nelson1Gabriel Cerono2Samuel M. Goldman3Sergio E. Baranzini4Ethan G. Brown5Department of Neurology, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA, United StatesDepartment of Neurology, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA, United StatesDepartment of Neurology, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA, United StatesDivision of Occupational and Environmental Medicine, University of California, San Francisco, San Francisco, CA, United StatesDepartment of Neurology, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA, United StatesDepartment of Neurology, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA, United StatesIntroductionEarly diagnosis of Parkinson’s disease (PD) is important to identify treatments to slow neurodegeneration. People who develop PD often have symptoms before the disease manifests and may be coded as diagnoses in the electronic health record (EHR).MethodsTo predict PD diagnosis, we embedded EHR data of patients onto a biomedical knowledge graph called Scalable Precision medicine Open Knowledge Engine (SPOKE) and created patient embedding vectors. We trained and validated a classifier using these vectors from 3,004 PD patients, restricting records to 1, 3, and 5 years before diagnosis, and 457,197 non-PD group.ResultsThe classifier predicted PD diagnosis with moderate accuracy (AUC = 0.77 ± 0.06, 0.74 ± 0.05, 0.72 ± 0.05 at 1, 3, and 5 years) and performed better than other benchmark methods. Nodes in the SPOKE graph, among cases, revealed novel associations, while SPOKE patient vectors revealed the basis for individual risk classification.DiscussionThe proposed method was able to explain the clinical predictions using the knowledge graph, thereby making the predictions clinically interpretable. Through enriching EHR data with biomedical associations, SPOKE may be a cost-efficient and personalized way to predict PD diagnosis years before its occurrence.https://www.frontiersin.org/articles/10.3389/fmed.2023.1081087/fullParkinson diseaseneurodegenerative disorderelectronic health recordknowledge graphgraph algorithmmachine learning |
| spellingShingle | Karthik Soman Charlotte A. Nelson Gabriel Cerono Samuel M. Goldman Sergio E. Baranzini Ethan G. Brown Early detection of Parkinson’s disease through enriching the electronic health record using a biomedical knowledge graph Frontiers in Medicine Parkinson disease neurodegenerative disorder electronic health record knowledge graph graph algorithm machine learning |
| title | Early detection of Parkinson’s disease through enriching the electronic health record using a biomedical knowledge graph |
| title_full | Early detection of Parkinson’s disease through enriching the electronic health record using a biomedical knowledge graph |
| title_fullStr | Early detection of Parkinson’s disease through enriching the electronic health record using a biomedical knowledge graph |
| title_full_unstemmed | Early detection of Parkinson’s disease through enriching the electronic health record using a biomedical knowledge graph |
| title_short | Early detection of Parkinson’s disease through enriching the electronic health record using a biomedical knowledge graph |
| title_sort | early detection of parkinson s disease through enriching the electronic health record using a biomedical knowledge graph |
| topic | Parkinson disease neurodegenerative disorder electronic health record knowledge graph graph algorithm machine learning |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2023.1081087/full |
| work_keys_str_mv | AT karthiksoman earlydetectionofparkinsonsdiseasethroughenrichingtheelectronichealthrecordusingabiomedicalknowledgegraph AT charlotteanelson earlydetectionofparkinsonsdiseasethroughenrichingtheelectronichealthrecordusingabiomedicalknowledgegraph AT gabrielcerono earlydetectionofparkinsonsdiseasethroughenrichingtheelectronichealthrecordusingabiomedicalknowledgegraph AT samuelmgoldman earlydetectionofparkinsonsdiseasethroughenrichingtheelectronichealthrecordusingabiomedicalknowledgegraph AT sergioebaranzini earlydetectionofparkinsonsdiseasethroughenrichingtheelectronichealthrecordusingabiomedicalknowledgegraph AT ethangbrown earlydetectionofparkinsonsdiseasethroughenrichingtheelectronichealthrecordusingabiomedicalknowledgegraph |