Discovering Medication Patterns for High-Complexity Drug-Using Diseases Through Electronic Medical Records
An Electronic Medical Record (EMR) is a professional document that contains all data generated during the treatment process. The EMR can utilize various data formats, such as numerical data, text, and images. Mining the information and knowledge hidden in the huge amount of EMR data is an essential...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8815770/ |
| _version_ | 1818323871387877376 |
|---|---|
| author | Huiqun Huang Xiaopu Shang Hongmei Zhao Nan Wu Weizi Li Yuan Xu Yang Zhou Lei Fu |
| author_facet | Huiqun Huang Xiaopu Shang Hongmei Zhao Nan Wu Weizi Li Yuan Xu Yang Zhou Lei Fu |
| author_sort | Huiqun Huang |
| collection | DOAJ |
| description | An Electronic Medical Record (EMR) is a professional document that contains all data generated during the treatment process. The EMR can utilize various data formats, such as numerical data, text, and images. Mining the information and knowledge hidden in the huge amount of EMR data is an essential requirement for clinical decision support, such as clinical pathway formulation and evidence-based medical research. In this paper, we propose a machine-learning-based framework to mine the hidden medication patterns in EMR text. The framework systematically integrates the Jaccard similarity evaluation, spectral clustering, the modified Latent Dirichlet Allocation and cross-matching among multiple features to find the residuals that describe additional knowledge and clusters hidden in multiple perspectives of highly complex medication patterns. These methods work together, step by step to reveal the underlying medication pattern. We evaluated the method by using real data from EMR text (patients with cirrhotic ascites) from a large hospital in China. The proposed framework outperforms other approaches for medication pattern discovery, especially for this disease with subtle medication treatment variances. The results also revealed little overlap among the discovered patterns; thus, the distinct features of each pattern are well studied through the proposed framework. |
| first_indexed | 2024-12-13T11:19:35Z |
| format | Article |
| id | doaj.art-3e4086aa14a0454cb8c34d373de82f73 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T11:19:35Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3e4086aa14a0454cb8c34d373de82f732022-12-21T23:48:32ZengIEEEIEEE Access2169-35362019-01-01712528012529910.1109/ACCESS.2019.29378928815770Discovering Medication Patterns for High-Complexity Drug-Using Diseases Through Electronic Medical RecordsHuiqun Huang0Xiaopu Shang1Hongmei Zhao2Nan Wu3Weizi Li4Yuan Xu5https://orcid.org/0000-0001-9589-6046Yang Zhou6Lei Fu7School of Software Engineering, Beijing Jiaotong University, Beijing, ChinaSchool of Economics and Management, Beijing Jiaotong University, Beijing, ChinaSchool of Economics and Management, Beijing Jiaotong University, Beijing, ChinaPeking University People’s Hospital, Beijing, ChinaInformatics Research Center, University of Reading, Berkshire, U.K.School of Economics and Management, Beijing Jiaotong University, Beijing, ChinaSchool of Economics and Management, Beijing Jiaotong University, Beijing, ChinaChinese PLA General Hospital, Beijing, ChinaAn Electronic Medical Record (EMR) is a professional document that contains all data generated during the treatment process. The EMR can utilize various data formats, such as numerical data, text, and images. Mining the information and knowledge hidden in the huge amount of EMR data is an essential requirement for clinical decision support, such as clinical pathway formulation and evidence-based medical research. In this paper, we propose a machine-learning-based framework to mine the hidden medication patterns in EMR text. The framework systematically integrates the Jaccard similarity evaluation, spectral clustering, the modified Latent Dirichlet Allocation and cross-matching among multiple features to find the residuals that describe additional knowledge and clusters hidden in multiple perspectives of highly complex medication patterns. These methods work together, step by step to reveal the underlying medication pattern. We evaluated the method by using real data from EMR text (patients with cirrhotic ascites) from a large hospital in China. The proposed framework outperforms other approaches for medication pattern discovery, especially for this disease with subtle medication treatment variances. The results also revealed little overlap among the discovered patterns; thus, the distinct features of each pattern are well studied through the proposed framework.https://ieeexplore.ieee.org/document/8815770/Electronic medical record (EMR)medication patterndiscoverymachine learninghigh-complexity drug-use pattern |
| spellingShingle | Huiqun Huang Xiaopu Shang Hongmei Zhao Nan Wu Weizi Li Yuan Xu Yang Zhou Lei Fu Discovering Medication Patterns for High-Complexity Drug-Using Diseases Through Electronic Medical Records IEEE Access Electronic medical record (EMR) medication pattern discovery machine learning high-complexity drug-use pattern |
| title | Discovering Medication Patterns for High-Complexity Drug-Using Diseases Through Electronic Medical Records |
| title_full | Discovering Medication Patterns for High-Complexity Drug-Using Diseases Through Electronic Medical Records |
| title_fullStr | Discovering Medication Patterns for High-Complexity Drug-Using Diseases Through Electronic Medical Records |
| title_full_unstemmed | Discovering Medication Patterns for High-Complexity Drug-Using Diseases Through Electronic Medical Records |
| title_short | Discovering Medication Patterns for High-Complexity Drug-Using Diseases Through Electronic Medical Records |
| title_sort | discovering medication patterns for high complexity drug using diseases through electronic medical records |
| topic | Electronic medical record (EMR) medication pattern discovery machine learning high-complexity drug-use pattern |
| url | https://ieeexplore.ieee.org/document/8815770/ |
| work_keys_str_mv | AT huiqunhuang discoveringmedicationpatternsforhighcomplexitydrugusingdiseasesthroughelectronicmedicalrecords AT xiaopushang discoveringmedicationpatternsforhighcomplexitydrugusingdiseasesthroughelectronicmedicalrecords AT hongmeizhao discoveringmedicationpatternsforhighcomplexitydrugusingdiseasesthroughelectronicmedicalrecords AT nanwu discoveringmedicationpatternsforhighcomplexitydrugusingdiseasesthroughelectronicmedicalrecords AT weizili discoveringmedicationpatternsforhighcomplexitydrugusingdiseasesthroughelectronicmedicalrecords AT yuanxu discoveringmedicationpatternsforhighcomplexitydrugusingdiseasesthroughelectronicmedicalrecords AT yangzhou discoveringmedicationpatternsforhighcomplexitydrugusingdiseasesthroughelectronicmedicalrecords AT leifu discoveringmedicationpatternsforhighcomplexitydrugusingdiseasesthroughelectronicmedicalrecords |