Discovering disease–disease associations using electronic health records in The Guideline Advantage (TGA) dataset
Abstract Certain diseases have strong comorbidity and co-occurrence with others. Understanding disease–disease associations can potentially increase awareness among healthcare providers of co-occurring conditions and facilitate earlier diagnosis, prevention and treatment of patients. In this study,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-021-00345-z |
| _version_ | 1818688897395195904 |
|---|---|
| author | Aixia Guo Yosef M. Khan James R. Langabeer Randi E. Foraker |
| author_facet | Aixia Guo Yosef M. Khan James R. Langabeer Randi E. Foraker |
| author_sort | Aixia Guo |
| collection | DOAJ |
| description | Abstract Certain diseases have strong comorbidity and co-occurrence with others. Understanding disease–disease associations can potentially increase awareness among healthcare providers of co-occurring conditions and facilitate earlier diagnosis, prevention and treatment of patients. In this study, we utilized the valuable and large The Guideline Advantage (TGA) longitudinal electronic health record dataset from 70 outpatient clinics across the United States to investigate potential disease–disease associations. Specifically, the most prevalent 50 disease diagnoses were manually identified from 165,732 unique patients. To investigate the co-occurrence or dependency associations among the 50 diseases, the categorical disease terms were first mapped into numerical vectors based on disease co-occurrence frequency in individual patients using the Word2Vec approach. Then the novel and interesting disease association clusters were identified using correlation and clustering analyses in the numerical space. Moreover, the distribution of time delay (Δt) between pair-wise strongly associated diseases (correlation coefficients ≥ 0.5) were calculated to show the dependency among the diseases. The results can indicate the risk of disease comorbidity and complications, and facilitate disease prevention and optimal treatment decision-making. |
| first_indexed | 2024-12-17T12:01:30Z |
| format | Article |
| id | doaj.art-01d193938ce24f79bf4641b741d2fe72 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-17T12:01:30Z |
| publishDate | 2021-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-01d193938ce24f79bf4641b741d2fe722022-12-21T21:49:49ZengNature PortfolioScientific Reports2045-23222021-10-0111111010.1038/s41598-021-00345-zDiscovering disease–disease associations using electronic health records in The Guideline Advantage (TGA) datasetAixia Guo0Yosef M. Khan1James R. Langabeer2Randi E. Foraker3Institute for Informatics (I2), Washington University School of MedicineHealth Informatics and Analytics, Centers for Health Metrics and Evaluation, American Heart AssociationSchool of Biomedical Informatics, Health Science Center at Houston, The University of TexasInstitute for Informatics (I2), Washington University School of MedicineAbstract Certain diseases have strong comorbidity and co-occurrence with others. Understanding disease–disease associations can potentially increase awareness among healthcare providers of co-occurring conditions and facilitate earlier diagnosis, prevention and treatment of patients. In this study, we utilized the valuable and large The Guideline Advantage (TGA) longitudinal electronic health record dataset from 70 outpatient clinics across the United States to investigate potential disease–disease associations. Specifically, the most prevalent 50 disease diagnoses were manually identified from 165,732 unique patients. To investigate the co-occurrence or dependency associations among the 50 diseases, the categorical disease terms were first mapped into numerical vectors based on disease co-occurrence frequency in individual patients using the Word2Vec approach. Then the novel and interesting disease association clusters were identified using correlation and clustering analyses in the numerical space. Moreover, the distribution of time delay (Δt) between pair-wise strongly associated diseases (correlation coefficients ≥ 0.5) were calculated to show the dependency among the diseases. The results can indicate the risk of disease comorbidity and complications, and facilitate disease prevention and optimal treatment decision-making.https://doi.org/10.1038/s41598-021-00345-z |
| spellingShingle | Aixia Guo Yosef M. Khan James R. Langabeer Randi E. Foraker Discovering disease–disease associations using electronic health records in The Guideline Advantage (TGA) dataset Scientific Reports |
| title | Discovering disease–disease associations using electronic health records in The Guideline Advantage (TGA) dataset |
| title_full | Discovering disease–disease associations using electronic health records in The Guideline Advantage (TGA) dataset |
| title_fullStr | Discovering disease–disease associations using electronic health records in The Guideline Advantage (TGA) dataset |
| title_full_unstemmed | Discovering disease–disease associations using electronic health records in The Guideline Advantage (TGA) dataset |
| title_short | Discovering disease–disease associations using electronic health records in The Guideline Advantage (TGA) dataset |
| title_sort | discovering disease disease associations using electronic health records in the guideline advantage tga dataset |
| url | https://doi.org/10.1038/s41598-021-00345-z |
| work_keys_str_mv | AT aixiaguo discoveringdiseasediseaseassociationsusingelectronichealthrecordsintheguidelineadvantagetgadataset AT yosefmkhan discoveringdiseasediseaseassociationsusingelectronichealthrecordsintheguidelineadvantagetgadataset AT jamesrlangabeer discoveringdiseasediseaseassociationsusingelectronichealthrecordsintheguidelineadvantagetgadataset AT randieforaker discoveringdiseasediseaseassociationsusingelectronichealthrecordsintheguidelineadvantagetgadataset |