The character changes applied. We list a few of them in

Aus KletterWiki
Version vom 19. Dezember 2017, 10:47 Uhr von Income8ping (Diskussion | Beiträge)

(Unterschied) ← Nächstältere Version | Aktuelle Version (Unterschied) | Nächstjüngere Version → (Unterschied)

Wechseln zu: Navigation, Suche

By reviewing the LDPMap approach, we conclude that this error is usually eliminated if we raise the threshold T1 to a value such that word similarity (LCS) is Haloxon employed to measure the two terms. BMC Health-related Genomics 2014, 7(Suppl 1):S11 http://www.biomedcentral.com/1755-8794/7/S1/SPage 10 ofFigure six Correctness comparison on LDPMap and UMLS Metathesaurus Browser for Group 2 working with Criterion two.Conclusions Inside the operate we proposed LDPMap, a layered dynamic programming approach to effectively mapping inaccurate healthcare terms to UMLS concepts. As a key benefit from the LDPMap algorithm, it runs substantially more rapidly than classical LCS method therefore tends to make it probable to efficiently deal with UMLS term queries. When similarity is counted on a word basis, LDPMap algorithm may perhaps yield a more desirable result than LCS. In other situations (like word merging), it is actually achievable that LCS query final results are much more preferable. Hence, inside the extensive query workflow of LDPMap, the LDPMap method is complemented by LCS and adjustable by parameter T 1 . Unique from utilizing LCS alone, the LDPMap query workflow only applies LCS (when necessary) to a very limited number of candidate terms therefore achieves an extremely fast query speed.In query effectiveness comparison, we observed that LDPMap has a extremely high accuracy in processing queries more than the UMLS Metathesaurus involving inaccurate terms.The character modifications applied. We list a few of them in Table 3. From this table, we can see that it contains concepts of unique lengths. The randomly generated character variations cover quite a few typical instances of text data inaccuracy, like, title= jir.2014.0227 misspellings, merging of two words, and particular character omissions. From Table 4 we can see that MetaMap cannot handle them effectively. As an alternative, it finds some conceptsFigure 3 Correctness comparison on LDPMap, UMLS Metathesaurus Browser, and MetaMap for Group 1 using Criterion 1.Ren et al. BMC Medical Genomics 2014, 7(Suppl 1):S11 http://www.biomedcentral.com/1755-8794/7/S1/SPage 9 ofFigure 4 Correctness comparison on LDPMap, UMLS Metathesaurus Browser, and MetaMap for Group two using Criterion 1.Figure five Correctness comparison on LDPMap and UMLS Metathesaurus Browser for Group 1 employing Criterion two.associated to person words within the query term. The UMLS Metathesaurus Browser will not do any improved on them. In contrast, LDPMap correctly answered all these queries except for "AlbunexIectable Product". While "Injectable Product" isn't appropriate, it truly is a minimum of closer to the original term than these returned by the UMLS Metathesaurus Browser and MetaMap. By reviewing the LDPMap approach, we conclude that this error can be eliminated if we raise the threshold T1 to a value such that word similarity (LCS) is employed to measure the two terms. To confirm this, we increase T 1 from 0.8 to0.85, and LDPMap effectively returns the original term. Even so, a high T1 implies that LDPMap provides additional preference to LCS-based similarity measurement than to concept similarity measurement defined above. Consequently, LDPMap might be less productive in handling real-world queries that include incomplete health-related terms (i.e., medical terms with missing words). It is quite evident that there will not exist 1 set of T 1 and T2 that fits all situations. Consequently, we will fine tune these parameters to leverage LDPMap in our future applications.Ren et al.