FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2783755046> ?p ?o ?g. }

• W2783755046 abstract "The application of medical knowledge strongly affects the performance of intelligent diagnosis, and method of learning the weights of medical knowledge plays a substantial role in probabilistic graphical models (PGMs). The purpose of this study is to investigate a discriminative weight-learning method based on a medical knowledge network (MKN).We propose a training model called the maximum margin medical knowledge network (M3KN), which is strictly derived for calculating the weight of medical knowledge. Using the definition of a reasonable margin, the weight learning can be transformed into a margin optimization problem. To solve the optimization problem, we adopt a sequential minimal optimization (SMO) algorithm and the clique property of a Markov network. Ultimately, M3KN not only incorporates the inference ability of PGMs but also deals with high-dimensional logic knowledge.The experimental results indicate that M3KN obtains a higher F-measure score than the maximum likelihood learning algorithm of MKN for both Chinese Electronic Medical Records (CEMRs) and Blood Examination Records (BERs). Furthermore, the proposed approach is obviously superior to some classical machine learning algorithms for medical diagnosis. To adequately manifest the importance of domain knowledge, we numerically verify that the diagnostic accuracy of M3KN is gradually improved as the number of learned CEMRs increase, which contain important medical knowledge.Our experimental results show that the proposed method performs reliably for learning the weights of medical knowledge. M3KN outperforms other existing methods by achieving an F-measure of 0.731 for CEMRs and 0.4538 for BERs. This further illustrates that M3KN can facilitate the investigations of intelligent healthcare." @default.
• W2783755046 created "2018-01-26" @default.
• W2783755046 creator A5007959430 @default.
• W2783755046 creator A5012962057 @default.
• W2783755046 creator A5048603612 @default.
• W2783755046 creator A5064238181 @default.
• W2783755046 creator A5065163787 @default.
• W2783755046 creator A5090300710 @default.
• W2783755046 date "2018-03-01" @default.
• W2783755046 modified "2023-10-16" @default.
• W2783755046 title "Max-margin weight learning for medical knowledge network" @default.
• W2783755046 cites W1169821766 @default.
• W2783755046 cites W1257817829 @default.
• W2783755046 cites W1511777166 @default.
• W2783755046 cites W1959840315 @default.
• W2783755046 cites W1972295703 @default.
• W2783755046 cites W1977970897 @default.
• W2783755046 cites W1983426246 @default.
• W2783755046 cites W1989494851 @default.
• W2783755046 cites W2017821710 @default.
• W2783755046 cites W2020176002 @default.
• W2783755046 cites W2020617621 @default.
• W2783755046 cites W2025100889 @default.
• W2783755046 cites W2031492656 @default.
• W2783755046 cites W2044513060 @default.
• W2783755046 cites W2052148895 @default.
• W2783755046 cites W2068674173 @default.
• W2783755046 cites W2074578935 @default.
• W2783755046 cites W2095010947 @default.
• W2783755046 cites W2105210342 @default.
• W2783755046 cites W2105644991 @default.
• W2783755046 cites W2110473494 @default.
• W2783755046 cites W2123556395 @default.
• W2783755046 cites W2135209143 @default.
• W2783755046 cites W2135341757 @default.
• W2783755046 cites W2136801552 @default.
• W2783755046 cites W2153635508 @default.
• W2783755046 cites W2157629899 @default.
• W2783755046 cites W2160987310 @default.
• W2783755046 cites W2169389444 @default.
• W2783755046 cites W2171042437 @default.
• W2783755046 cites W2263130483 @default.
• W2783755046 cites W2264272133 @default.
• W2783755046 cites W2292084368 @default.
• W2783755046 cites W2342735857 @default.
• W2783755046 cites W2401657145 @default.
• W2783755046 cites W2403004111 @default.
• W2783755046 cites W2429834429 @default.
• W2783755046 cites W2510045023 @default.
• W2783755046 cites W2590518618 @default.
• W2783755046 cites W2600356345 @default.
• W2783755046 cites W47392883 @default.
• W2783755046 doi "https://doi.org/10.1016/j.cmpb.2018.01.005" @default.
• W2783755046 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29428070" @default.
• W2783755046 hasPublicationYear "2018" @default.
• W2783755046 type Work @default.
• W2783755046 sameAs 2783755046 @default.
• W2783755046 citedByCount "5" @default.
• W2783755046 countsByYear W27837550462018 @default.
• W2783755046 countsByYear W27837550462019 @default.
• W2783755046 countsByYear W27837550462020 @default.
• W2783755046 crossrefType "journal-article" @default.
• W2783755046 hasAuthorship W2783755046A5007959430 @default.
• W2783755046 hasAuthorship W2783755046A5012962057 @default.
• W2783755046 hasAuthorship W2783755046A5048603612 @default.
• W2783755046 hasAuthorship W2783755046A5064238181 @default.
• W2783755046 hasAuthorship W2783755046A5065163787 @default.
• W2783755046 hasAuthorship W2783755046A5090300710 @default.
• W2783755046 hasConcept C119857082 @default.
• W2783755046 hasConcept C124101348 @default.
• W2783755046 hasConcept C134306372 @default.
• W2783755046 hasConcept C154945302 @default.
• W2783755046 hasConcept C207685749 @default.
• W2783755046 hasConcept C2776214188 @default.
• W2783755046 hasConcept C2780009758 @default.
• W2783755046 hasConcept C2985722590 @default.
• W2783755046 hasConcept C33923547 @default.
• W2783755046 hasConcept C36503486 @default.
• W2783755046 hasConcept C41008148 @default.
• W2783755046 hasConcept C49937458 @default.
• W2783755046 hasConcept C509550671 @default.
• W2783755046 hasConcept C71924100 @default.
• W2783755046 hasConcept C774472 @default.
• W2783755046 hasConcept C97931131 @default.
• W2783755046 hasConceptScore W2783755046C119857082 @default.
• W2783755046 hasConceptScore W2783755046C124101348 @default.
• W2783755046 hasConceptScore W2783755046C134306372 @default.
• W2783755046 hasConceptScore W2783755046C154945302 @default.
• W2783755046 hasConceptScore W2783755046C207685749 @default.
• W2783755046 hasConceptScore W2783755046C2776214188 @default.
• W2783755046 hasConceptScore W2783755046C2780009758 @default.
• W2783755046 hasConceptScore W2783755046C2985722590 @default.
• W2783755046 hasConceptScore W2783755046C33923547 @default.
• W2783755046 hasConceptScore W2783755046C36503486 @default.
• W2783755046 hasConceptScore W2783755046C41008148 @default.
• W2783755046 hasConceptScore W2783755046C49937458 @default.
• W2783755046 hasConceptScore W2783755046C509550671 @default.
• W2783755046 hasConceptScore W2783755046C71924100 @default.
• W2783755046 hasConceptScore W2783755046C774472 @default.
• W2783755046 hasConceptScore W2783755046C97931131 @default.

• next