Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945836701> ?p ?o ?g. }
- W2945836701 abstract "Machine learning has become ubiquitous and a key technology on mining electronic health records (EHRs) for facilitating clinical research and practice. Unsupervised machine learning, as opposed to supervised learning, has shown promise in identifying novel patterns and relations from EHRs without using human created labels. In this paper, we investigate the application of unsupervised machine learning models in discovering latent disease clusters and patient subgroups based on EHRs. We utilized Latent Dirichlet Allocation (LDA), a generative probabilistic model, and proposed a novel model named Poisson Dirichlet Model (PDM), which extends the LDA approach using a Poisson distribution to model patients' disease diagnoses and to alleviate age and sex factors by considering both observed and expected observations. In the empirical experiments, we evaluated LDA and PDM on three patient cohorts with EHR data retrieved from the Rochester Epidemiology Project (REP), for the discovery of latent disease clusters and patient subgroups. We compared the effectiveness of LDA and PDM in identifying latent disease clusters through the visualization of disease representations learned by two approaches. We also tested the performance of LDA and PDM in differentiating patient subgroups through survival analysis, as well as statistical analysis. The experimental results show that the proposed PDM could effectively identify distinguished disease clusters by alleviating the impact of age and sex, and that LDA could stratify patients into more differentiable subgroups than PDM in terms of p-values. However, the subgroups discovered by PDM might imply the underlying patterns of diseases of greater interest in epidemiology research due to the alleviation of age and sex. Both unsupervised machine learning approaches could be leveraged to discover patient subgroups using EHRs but with different foci." @default.
- W2945836701 created "2019-05-29" @default.
- W2945836701 creator A5009318195 @default.
- W2945836701 creator A5013873772 @default.
- W2945836701 creator A5014433885 @default.
- W2945836701 creator A5023303733 @default.
- W2945836701 creator A5027449919 @default.
- W2945836701 creator A5038589760 @default.
- W2945836701 creator A5053804590 @default.
- W2945836701 creator A5067918441 @default.
- W2945836701 creator A5080116611 @default.
- W2945836701 date "2019-05-17" @default.
- W2945836701 modified "2023-09-25" @default.
- W2945836701 title "Unsupervised Machine Learning for the Discovery of Latent Disease Clusters and Patient Subgroups Using Electronic Health Records" @default.
- W2945836701 cites W186945889 @default.
- W2945836701 cites W187156975 @default.
- W2945836701 cites W1902526473 @default.
- W2945836701 cites W1973597670 @default.
- W2945836701 cites W1977556410 @default.
- W2945836701 cites W1999802986 @default.
- W2945836701 cites W2001082470 @default.
- W2945836701 cites W2016381774 @default.
- W2945836701 cites W2024287605 @default.
- W2945836701 cites W2032980606 @default.
- W2945836701 cites W2057780602 @default.
- W2945836701 cites W2062533676 @default.
- W2945836701 cites W2062984732 @default.
- W2945836701 cites W2079530303 @default.
- W2945836701 cites W2089570507 @default.
- W2945836701 cites W2095897464 @default.
- W2945836701 cites W2109713080 @default.
- W2945836701 cites W2120441632 @default.
- W2945836701 cites W2137389079 @default.
- W2945836701 cites W2137393443 @default.
- W2945836701 cites W2174706414 @default.
- W2945836701 cites W2187089797 @default.
- W2945836701 cites W2354729568 @default.
- W2945836701 cites W2404901863 @default.
- W2945836701 cites W2517086456 @default.
- W2945836701 cites W2557074642 @default.
- W2945836701 cites W2768488789 @default.
- W2945836701 cites W2792962096 @default.
- W2945836701 cites W2805089815 @default.
- W2945836701 cites W2809721358 @default.
- W2945836701 cites W2985962305 @default.
- W2945836701 cites W767186437 @default.
- W2945836701 doi "https://doi.org/10.48550/arxiv.1905.10309" @default.
- W2945836701 hasPublicationYear "2019" @default.
- W2945836701 type Work @default.
- W2945836701 sameAs 2945836701 @default.
- W2945836701 citedByCount "0" @default.
- W2945836701 crossrefType "posted-content" @default.
- W2945836701 hasAuthorship W2945836701A5009318195 @default.
- W2945836701 hasAuthorship W2945836701A5013873772 @default.
- W2945836701 hasAuthorship W2945836701A5014433885 @default.
- W2945836701 hasAuthorship W2945836701A5023303733 @default.
- W2945836701 hasAuthorship W2945836701A5027449919 @default.
- W2945836701 hasAuthorship W2945836701A5038589760 @default.
- W2945836701 hasAuthorship W2945836701A5053804590 @default.
- W2945836701 hasAuthorship W2945836701A5067918441 @default.
- W2945836701 hasAuthorship W2945836701A5080116611 @default.
- W2945836701 hasBestOaLocation W29458367011 @default.
- W2945836701 hasConcept C100906024 @default.
- W2945836701 hasConcept C105795698 @default.
- W2945836701 hasConcept C119857082 @default.
- W2945836701 hasConcept C126322002 @default.
- W2945836701 hasConcept C154945302 @default.
- W2945836701 hasConcept C160735492 @default.
- W2945836701 hasConcept C162324750 @default.
- W2945836701 hasConcept C171686336 @default.
- W2945836701 hasConcept C2779134260 @default.
- W2945836701 hasConcept C3019952477 @default.
- W2945836701 hasConcept C33923547 @default.
- W2945836701 hasConcept C41008148 @default.
- W2945836701 hasConcept C500882744 @default.
- W2945836701 hasConcept C50522688 @default.
- W2945836701 hasConcept C71924100 @default.
- W2945836701 hasConcept C8038995 @default.
- W2945836701 hasConceptScore W2945836701C100906024 @default.
- W2945836701 hasConceptScore W2945836701C105795698 @default.
- W2945836701 hasConceptScore W2945836701C119857082 @default.
- W2945836701 hasConceptScore W2945836701C126322002 @default.
- W2945836701 hasConceptScore W2945836701C154945302 @default.
- W2945836701 hasConceptScore W2945836701C160735492 @default.
- W2945836701 hasConceptScore W2945836701C162324750 @default.
- W2945836701 hasConceptScore W2945836701C171686336 @default.
- W2945836701 hasConceptScore W2945836701C2779134260 @default.
- W2945836701 hasConceptScore W2945836701C3019952477 @default.
- W2945836701 hasConceptScore W2945836701C33923547 @default.
- W2945836701 hasConceptScore W2945836701C41008148 @default.
- W2945836701 hasConceptScore W2945836701C500882744 @default.
- W2945836701 hasConceptScore W2945836701C50522688 @default.
- W2945836701 hasConceptScore W2945836701C71924100 @default.
- W2945836701 hasConceptScore W2945836701C8038995 @default.
- W2945836701 hasLocation W29458367011 @default.
- W2945836701 hasLocation W29458367012 @default.
- W2945836701 hasOpenAccess W2945836701 @default.
- W2945836701 hasPrimaryLocation W29458367011 @default.
- W2945836701 hasRelatedWork W2136453262 @default.
- W2945836701 hasRelatedWork W2483960945 @default.