Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385665301> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4385665301 abstract "We propose a drug recommendation model that integrates information from both structured data (patient demographic information) and unstructured texts (patient reviews). It is based on multitask learning to predict review ratings of several satisfaction-related measures for a given medicine, where related tasks can learn from each other for prediction. The learned models can then be applied to new patients for drug recommendation. This is fundamentally different from most recommender systems in e-commerce, which do not work well for new customers (referred to as the cold-start problem). To extract information from review texts, we employ both topic modeling and sentiment analysis. We further incorporate variable selection into the model via Bayesian LASSO, which aims to filter out irrelevant features. To our best knowledge, this is the first Bayesian multitask learning method for ordinal responses. We are also the first to apply multitask learning to medicine recommendation. The sample code and data are made available at GitHub: https://github.com/thrushcyc-github/BMull.We evaluate the proposed method on two sets of drug reviews involving 17 depression/high blood pressure-related drugs. Overall, our method performs better than existing benchmark methods in terms of accuracy and AUC (area under the receiver operating characteristic curve). It is effective even with a small sample size and only a few available features, and more robust to possible noninformative covariates. Due to our model explainability, insights generated from our model may work as a useful reference for doctors. In practice, however, a final decision should be carefully made by combining the information from the proposed recommender with doctors' domain knowledge and past experience.The sample code and data are publicly available at GitHub: https://github.com/thrushcyc-github/BMull." @default.
- W4385665301 created "2023-08-09" @default.
- W4385665301 creator A5008921281 @default.
- W4385665301 creator A5014139999 @default.
- W4385665301 creator A5038750761 @default.
- W4385665301 date "2023-08-01" @default.
- W4385665301 modified "2023-10-04" @default.
- W4385665301 title "Bayesian Multi-task Learning for Medicine Recommendation Based on Online Patient Reviews" @default.
- W4385665301 cites W1982652137 @default.
- W4385665301 cites W2020999234 @default.
- W4385665301 cites W2025605741 @default.
- W4385665301 cites W2052384471 @default.
- W4385665301 cites W2076167926 @default.
- W4385665301 cites W2104844823 @default.
- W4385665301 cites W2108306139 @default.
- W4385665301 cites W2114169935 @default.
- W4385665301 cites W2130141864 @default.
- W4385665301 cites W2159224109 @default.
- W4385665301 cites W2159514083 @default.
- W4385665301 cites W2168152978 @default.
- W4385665301 cites W2591060504 @default.
- W4385665301 cites W2897342798 @default.
- W4385665301 cites W3104393726 @default.
- W4385665301 cites W3141797743 @default.
- W4385665301 doi "https://doi.org/10.1093/bioinformatics/btad491" @default.
- W4385665301 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37551956" @default.
- W4385665301 hasPublicationYear "2023" @default.
- W4385665301 type Work @default.
- W4385665301 citedByCount "0" @default.
- W4385665301 crossrefType "journal-article" @default.
- W4385665301 hasAuthorship W4385665301A5008921281 @default.
- W4385665301 hasAuthorship W4385665301A5014139999 @default.
- W4385665301 hasAuthorship W4385665301A5038750761 @default.
- W4385665301 hasBestOaLocation W43856653011 @default.
- W4385665301 hasConcept C106131492 @default.
- W4385665301 hasConcept C107673813 @default.
- W4385665301 hasConcept C119857082 @default.
- W4385665301 hasConcept C124101348 @default.
- W4385665301 hasConcept C13280743 @default.
- W4385665301 hasConcept C136764020 @default.
- W4385665301 hasConcept C148483581 @default.
- W4385665301 hasConcept C154945302 @default.
- W4385665301 hasConcept C162324750 @default.
- W4385665301 hasConcept C185592680 @default.
- W4385665301 hasConcept C185798385 @default.
- W4385665301 hasConcept C187736073 @default.
- W4385665301 hasConcept C198531522 @default.
- W4385665301 hasConcept C205649164 @default.
- W4385665301 hasConcept C21569690 @default.
- W4385665301 hasConcept C2780451532 @default.
- W4385665301 hasConcept C28006648 @default.
- W4385665301 hasConcept C31972630 @default.
- W4385665301 hasConcept C37616216 @default.
- W4385665301 hasConcept C41008148 @default.
- W4385665301 hasConcept C43617362 @default.
- W4385665301 hasConcept C557471498 @default.
- W4385665301 hasConceptScore W4385665301C106131492 @default.
- W4385665301 hasConceptScore W4385665301C107673813 @default.
- W4385665301 hasConceptScore W4385665301C119857082 @default.
- W4385665301 hasConceptScore W4385665301C124101348 @default.
- W4385665301 hasConceptScore W4385665301C13280743 @default.
- W4385665301 hasConceptScore W4385665301C136764020 @default.
- W4385665301 hasConceptScore W4385665301C148483581 @default.
- W4385665301 hasConceptScore W4385665301C154945302 @default.
- W4385665301 hasConceptScore W4385665301C162324750 @default.
- W4385665301 hasConceptScore W4385665301C185592680 @default.
- W4385665301 hasConceptScore W4385665301C185798385 @default.
- W4385665301 hasConceptScore W4385665301C187736073 @default.
- W4385665301 hasConceptScore W4385665301C198531522 @default.
- W4385665301 hasConceptScore W4385665301C205649164 @default.
- W4385665301 hasConceptScore W4385665301C21569690 @default.
- W4385665301 hasConceptScore W4385665301C2780451532 @default.
- W4385665301 hasConceptScore W4385665301C28006648 @default.
- W4385665301 hasConceptScore W4385665301C31972630 @default.
- W4385665301 hasConceptScore W4385665301C37616216 @default.
- W4385665301 hasConceptScore W4385665301C41008148 @default.
- W4385665301 hasConceptScore W4385665301C43617362 @default.
- W4385665301 hasConceptScore W4385665301C557471498 @default.
- W4385665301 hasFunder F4320332161 @default.
- W4385665301 hasIssue "8" @default.
- W4385665301 hasLocation W43856653011 @default.
- W4385665301 hasLocation W43856653012 @default.
- W4385665301 hasOpenAccess W4385665301 @default.
- W4385665301 hasPrimaryLocation W43856653011 @default.
- W4385665301 hasRelatedWork W1773619406 @default.
- W4385665301 hasRelatedWork W2075040002 @default.
- W4385665301 hasRelatedWork W2126026531 @default.
- W4385665301 hasRelatedWork W2348159088 @default.
- W4385665301 hasRelatedWork W2377968345 @default.
- W4385665301 hasRelatedWork W2391634835 @default.
- W4385665301 hasRelatedWork W2402445420 @default.
- W4385665301 hasRelatedWork W2511071455 @default.
- W4385665301 hasRelatedWork W2977378428 @default.
- W4385665301 hasRelatedWork W2983785000 @default.
- W4385665301 hasVolume "39" @default.
- W4385665301 isParatext "false" @default.
- W4385665301 isRetracted "false" @default.
- W4385665301 workType "article" @default.