Document (#40958)

Author

Soldaini, L.
Yates, A.
Goharian, N.

Title

Learning to reformulate long queries for clinical decision support

Source

Journal of the Association for Information Science and Technology. 68(2017) no.11, S.2602-2619

Year

2017

Abstract

The large volume of biomedical literature poses a serious problem for medical professionals, who are often struggling to keep current with it. At the same time, many health providers consider knowledge of the latest literature in their field a key component for successful clinical practice. In this work, we introduce two systems designed to help retrieving medical literature. Both receive a long, discursive clinical note as input query, and return highly relevant literature that could be used in support of clinical practice. The first system is an improved version of a method previously proposed by the authors; it combines pseudo relevance feedback and a domain-specific term filter to reformulate the query. The second is an approach that uses a deep neural network to reformulate a clinical note. Both approaches were evaluated on the 2014 and 2015 TREC CDS datasets; in our tests, they outperform the previously proposed method by up to 28% in inferred NDCG; furthermore, they are competitive with the state of the art, achieving up to 8% improvement in inferred NDCG.

Content

Vgl.: http://onlinelibrary.wiley.com/doi/10.1002/asi.23924/full.

Footnote

Beitrag in einem Special issue on biomedical information retrieval.

Field

Medizin

Similar documents (author)

1. Cohan, A.; Young, S.; Yates, A.; Goharian, N.: Triaging content severity in online mental health forums (2017) 4.06

   4.0613146 = sum of:
     4.0613146 = sum of:
       1.745625 = weight(author_txt:yates in 4930) [ClassicSimilarity], result of:
         1.745625 = score(doc=4930,freq=1.0), product of:
           0.63788766 = queryWeight, product of:
             8.757029 = idf(docFreq=18, maxDocs=44421)
             0.07284293 = queryNorm
           2.7365713 = fieldWeight in 4930, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             8.757029 = idf(docFreq=18, maxDocs=44421)
             0.3125 = fieldNorm(doc=4930)
       2.3156893 = weight(author_txt:goharian in 4930) [ClassicSimilarity], result of:
         2.3156893 = score(doc=4930,freq=1.0), product of:
           0.7701295 = queryWeight, product of:
             1.0987775 = boost
             9.622026 = idf(docFreq=7, maxDocs=44421)
             0.07284293 = queryNorm
           3.0068831 = fieldWeight in 4930, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             9.622026 = idf(docFreq=7, maxDocs=44421)
             0.3125 = fieldNorm(doc=4930)
   

2. Mengle, S.; Goharian, N.: Passage detection using text classification (2009) 1.85

   1.8525516 = sum of:
     1.8525516 = product of:
       3.7051032 = sum of:
         3.7051032 = weight(author_txt:goharian in 3765) [ClassicSimilarity], result of:
           3.7051032 = score(doc=3765,freq=1.0), product of:
             0.7701295 = queryWeight, product of:
               1.0987775 = boost
               9.622026 = idf(docFreq=7, maxDocs=44421)
               0.07284293 = queryNorm
             4.811013 = fieldWeight in 3765, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.622026 = idf(docFreq=7, maxDocs=44421)
               0.5 = fieldNorm(doc=3765)
       0.5 = coord(1/2)
   

3. Mengle, S.S.R.; Goharian, N.: Ambiguity measure feature-selection algorithm (2009) 1.85

   1.8525516 = sum of:
     1.8525516 = product of:
       3.7051032 = sum of:
         3.7051032 = weight(author_txt:goharian in 3804) [ClassicSimilarity], result of:
           3.7051032 = score(doc=3804,freq=1.0), product of:
             0.7701295 = queryWeight, product of:
               1.0987775 = boost
               9.622026 = idf(docFreq=7, maxDocs=44421)
               0.07284293 = queryNorm
             4.811013 = fieldWeight in 3804, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.622026 = idf(docFreq=7, maxDocs=44421)
               0.5 = fieldNorm(doc=3804)
       0.5 = coord(1/2)
   

4. Mengle, S.S.R.; Goharian, N.: Detecting relationships among categories using text classification (2010) 1.85

   1.8525516 = sum of:
     1.8525516 = product of:
       3.7051032 = sum of:
         3.7051032 = weight(author_txt:goharian in 449) [ClassicSimilarity], result of:
           3.7051032 = score(doc=449,freq=1.0), product of:
             0.7701295 = queryWeight, product of:
               1.0987775 = boost
               9.622026 = idf(docFreq=7, maxDocs=44421)
               0.07284293 = queryNorm
             4.811013 = fieldWeight in 449, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.622026 = idf(docFreq=7, maxDocs=44421)
               0.5 = fieldNorm(doc=449)
       0.5 = coord(1/2)
   

5. Baeza-Yates, R.A.: Introduction to data structures and algorithms related to information retrieval (1992) 1.40

   1.3965001 = sum of:
     1.3965001 = product of:
       2.7930002 = sum of:
         2.7930002 = weight(author_txt:yates in 4082) [ClassicSimilarity], result of:
           2.7930002 = score(doc=4082,freq=1.0), product of:
             0.63788766 = queryWeight, product of:
               8.757029 = idf(docFreq=18, maxDocs=44421)
               0.07284293 = queryNorm
             4.3785143 = fieldWeight in 4082, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.757029 = idf(docFreq=18, maxDocs=44421)
               0.5 = fieldNorm(doc=4082)
       0.5 = coord(1/2)
   

Similar documents (content)

1. Pluye, P.; Grad, R.; Repchinsky, C.; Jovaisas, B.; Johnson-Lafleur, J.; Carrier, M.-E.; Granikov, V.; Farrell, B.; Rodriguez, C.; Bartlett, G.; Loiselle, C.; Légaré, F.: Four levels of outcomes of information-seeking : a mixed methods study in primary health care (2013) 0.13

   0.13087037 = sum of:
     0.13087037 = product of:
       0.65435183 = sum of:
         0.018465912 = weight(abstract_txt:they in 1534) [ClassicSimilarity], result of:
           0.018465912 = score(doc=1534,freq=2.0), product of:
             0.055744193 = queryWeight, product of:
               1.0517541 = boost
               3.7477977 = idf(docFreq=2845, maxDocs=44421)
               0.014141949 = queryNorm
             0.33126163 = fieldWeight in 1534, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.7477977 = idf(docFreq=2845, maxDocs=44421)
               0.0625 = fieldNorm(doc=1534)
         0.022584958 = weight(abstract_txt:method in 1534) [ClassicSimilarity], result of:
           0.022584958 = score(doc=1534,freq=1.0), product of:
             0.080323376 = queryWeight, product of:
               1.2625116 = boost
               4.4988065 = idf(docFreq=1342, maxDocs=44421)
               0.014141949 = queryNorm
             0.2811754 = fieldWeight in 1534, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.4988065 = idf(docFreq=1342, maxDocs=44421)
               0.0625 = fieldNorm(doc=1534)
         0.03432398 = weight(abstract_txt:proposed in 1534) [ClassicSimilarity], result of:
           0.03432398 = score(doc=1534,freq=2.0), product of:
             0.08427217 = queryWeight, product of:
               1.2931726 = boost
               4.608063 = idf(docFreq=1203, maxDocs=44421)
               0.014141949 = queryNorm
             0.4072991 = fieldWeight in 1534, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.608063 = idf(docFreq=1203, maxDocs=44421)
               0.0625 = fieldNorm(doc=1534)
         0.048642535 = weight(abstract_txt:medical in 1534) [ClassicSimilarity], result of:
           0.048642535 = score(doc=1534,freq=1.0), product of:
             0.13395941 = queryWeight, product of:
               1.6304257 = boost
               5.8098235 = idf(docFreq=361, maxDocs=44421)
               0.014141949 = queryNorm
             0.36311397 = fieldWeight in 1534, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.8098235 = idf(docFreq=361, maxDocs=44421)
               0.0625 = fieldNorm(doc=1534)
         0.5303344 = weight(abstract_txt:clinical in 1534) [ClassicSimilarity], result of:
           0.5303344 = score(doc=1534,freq=5.0), product of:
             0.52278 = queryWeight, product of:
               5.092651 = boost
               7.2588162 = idf(docFreq=84, maxDocs=44421)
               0.014141949 = queryNorm
             1.0144504 = fieldWeight in 1534, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               7.2588162 = idf(docFreq=84, maxDocs=44421)
               0.0625 = fieldNorm(doc=1534)
       0.2 = coord(5/25)
   

2. Grad, R.; Pluye, P.; Granikov, V.; Johnson-Lafleur, J.; Shulha, M.; Sridhar, S.B.; Moscovici, J.L.; Bartlett, G.; Vandal, A.C.; Marlow, B.; Kloda, L.: Physicians' assessment of the value of clinical information : Operationalization of a theoretical model (2011) 0.12

   0.122339636 = sum of:
     0.122339636 = product of:
       0.76462275 = sum of:
         0.020743154 = weight(abstract_txt:support in 763) [ClassicSimilarity], result of:
           0.020743154 = score(doc=763,freq=1.0), product of:
             0.07589485 = queryWeight, product of:
               1.2272147 = boost
               4.37303 = idf(docFreq=1522, maxDocs=44421)
               0.014141949 = queryNorm
             0.2733144 = fieldWeight in 763, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.37303 = idf(docFreq=1522, maxDocs=44421)
               0.0625 = fieldNorm(doc=763)
         0.045169916 = weight(abstract_txt:method in 763) [ClassicSimilarity], result of:
           0.045169916 = score(doc=763,freq=4.0), product of:
             0.080323376 = queryWeight, product of:
               1.2625116 = boost
               4.4988065 = idf(docFreq=1342, maxDocs=44421)
               0.014141949 = queryNorm
             0.5623508 = fieldWeight in 763, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               4.4988065 = idf(docFreq=1342, maxDocs=44421)
               0.0625 = fieldNorm(doc=763)
         0.027883856 = weight(abstract_txt:practice in 763) [ClassicSimilarity], result of:
           0.027883856 = score(doc=763,freq=1.0), product of:
             0.09244093 = queryWeight, product of:
               1.3543988 = boost
               4.8262353 = idf(docFreq=967, maxDocs=44421)
               0.014141949 = queryNorm
             0.3016397 = fieldWeight in 763, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.8262353 = idf(docFreq=967, maxDocs=44421)
               0.0625 = fieldNorm(doc=763)
         0.67082584 = weight(abstract_txt:clinical in 763) [ClassicSimilarity], result of:
           0.67082584 = score(doc=763,freq=8.0), product of:
             0.52278 = queryWeight, product of:
               5.092651 = boost
               7.2588162 = idf(docFreq=84, maxDocs=44421)
               0.014141949 = queryNorm
             1.2831895 = fieldWeight in 763, product of:
               2.828427 = tf(freq=8.0), with freq of:
                 8.0 = termFreq=8.0
               7.2588162 = idf(docFreq=84, maxDocs=44421)
               0.0625 = fieldNorm(doc=763)
       0.16 = coord(4/25)
   

3. Cruz Díaz, N.P.; Maña López, M.J.; Mata Vázquez, J.; Pachón Álvarez, V.: ¬A machine-learning approach to negation and speculation detection in clinical texts (2012) 0.12

   0.11718626 = sum of:
     0.11718626 = product of:
       0.5859313 = sum of:
         0.044892434 = weight(abstract_txt:biomedical in 1283) [ClassicSimilarity], result of:
           0.044892434 = score(doc=1283,freq=1.0), product of:
             0.10078623 = queryWeight, product of:
               7.1267567 = idf(docFreq=96, maxDocs=44421)
               0.014141949 = queryNorm
             0.4454223 = fieldWeight in 1283, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.1267567 = idf(docFreq=96, maxDocs=44421)
               0.0625 = fieldNorm(doc=1283)
         0.024270717 = weight(abstract_txt:proposed in 1283) [ClassicSimilarity], result of:
           0.024270717 = score(doc=1283,freq=1.0), product of:
             0.08427217 = queryWeight, product of:
               1.2931726 = boost
               4.608063 = idf(docFreq=1203, maxDocs=44421)
               0.014141949 = queryNorm
             0.28800395 = fieldWeight in 1283, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.608063 = idf(docFreq=1203, maxDocs=44421)
               0.0625 = fieldNorm(doc=1283)
         0.048642535 = weight(abstract_txt:medical in 1283) [ClassicSimilarity], result of:
           0.048642535 = score(doc=1283,freq=1.0), product of:
             0.13395941 = queryWeight, product of:
               1.6304257 = boost
               5.8098235 = idf(docFreq=361, maxDocs=44421)
               0.014141949 = queryNorm
             0.36311397 = fieldWeight in 1283, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.8098235 = idf(docFreq=361, maxDocs=44421)
               0.0625 = fieldNorm(doc=1283)
         0.057330336 = weight(abstract_txt:previously in 1283) [ClassicSimilarity], result of:
           0.057330336 = score(doc=1283,freq=1.0), product of:
             0.14946933 = queryWeight, product of:
               1.7222272 = boost
               6.136947 = idf(docFreq=260, maxDocs=44421)
               0.014141949 = queryNorm
             0.3835592 = fieldWeight in 1283, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.136947 = idf(docFreq=260, maxDocs=44421)
               0.0625 = fieldNorm(doc=1283)
         0.41079524 = weight(abstract_txt:clinical in 1283) [ClassicSimilarity], result of:
           0.41079524 = score(doc=1283,freq=3.0), product of:
             0.52278 = queryWeight, product of:
               5.092651 = boost
               7.2588162 = idf(docFreq=84, maxDocs=44421)
               0.014141949 = queryNorm
             0.7857899 = fieldWeight in 1283, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               7.2588162 = idf(docFreq=84, maxDocs=44421)
               0.0625 = fieldNorm(doc=1283)
       0.2 = coord(5/25)
   

4. Thelwall, M.; Maflahi, N.: Guideline references and academic citations as evidence of the clinical value of health research (2016) 0.11

   0.11257464 = sum of:
     0.11257464 = product of:
       0.5628732 = sum of:
         0.0130573725 = weight(abstract_txt:they in 3856) [ClassicSimilarity], result of:
           0.0130573725 = score(doc=3856,freq=1.0), product of:
             0.055744193 = queryWeight, product of:
               1.0517541 = boost
               3.7477977 = idf(docFreq=2845, maxDocs=44421)
               0.014141949 = queryNorm
             0.23423736 = fieldWeight in 3856, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.7477977 = idf(docFreq=2845, maxDocs=44421)
               0.0625 = fieldNorm(doc=3856)
         0.027883856 = weight(abstract_txt:practice in 3856) [ClassicSimilarity], result of:
           0.027883856 = score(doc=3856,freq=1.0), product of:
             0.09244093 = queryWeight, product of:
               1.3543988 = boost
               4.8262353 = idf(docFreq=967, maxDocs=44421)
               0.014141949 = queryNorm
             0.3016397 = fieldWeight in 3856, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.8262353 = idf(docFreq=967, maxDocs=44421)
               0.0625 = fieldNorm(doc=3856)
         0.068790935 = weight(abstract_txt:medical in 3856) [ClassicSimilarity], result of:
           0.068790935 = score(doc=3856,freq=2.0), product of:
             0.13395941 = queryWeight, product of:
               1.6304257 = boost
               5.8098235 = idf(docFreq=361, maxDocs=44421)
               0.014141949 = queryNorm
             0.5135207 = fieldWeight in 3856, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.8098235 = idf(docFreq=361, maxDocs=44421)
               0.0625 = fieldNorm(doc=3856)
         0.042345762 = weight(abstract_txt:literature in 3856) [ClassicSimilarity], result of:
           0.042345762 = score(doc=3856,freq=1.0), product of:
             0.1538789 = queryWeight, product of:
               2.471263 = boost
               4.4030223 = idf(docFreq=1477, maxDocs=44421)
               0.014141949 = queryNorm
             0.2751889 = fieldWeight in 3856, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.4030223 = idf(docFreq=1477, maxDocs=44421)
               0.0625 = fieldNorm(doc=3856)
         0.41079524 = weight(abstract_txt:clinical in 3856) [ClassicSimilarity], result of:
           0.41079524 = score(doc=3856,freq=3.0), product of:
             0.52278 = queryWeight, product of:
               5.092651 = boost
               7.2588162 = idf(docFreq=84, maxDocs=44421)
               0.014141949 = queryNorm
             0.7857899 = fieldWeight in 3856, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               7.2588162 = idf(docFreq=84, maxDocs=44421)
               0.0625 = fieldNorm(doc=3856)
       0.2 = coord(5/25)
   

5. Aloteibi, S.; Sanderson, M.: Analyzing geographic query reformulation : an exploratory study (2014) 0.11

   0.10721326 = sum of:
     0.10721326 = product of:
       0.5360663 = sum of:
         0.06741123 = weight(abstract_txt:filter in 2177) [ClassicSimilarity], result of:
           0.06741123 = score(doc=2177,freq=2.0), product of:
             0.10489721 = queryWeight, product of:
               1.0201907 = boost
               7.270651 = idf(docFreq=83, maxDocs=44421)
               0.014141949 = queryNorm
             0.6426408 = fieldWeight in 2177, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               7.270651 = idf(docFreq=83, maxDocs=44421)
               0.0625 = fieldNorm(doc=2177)
         0.0130573725 = weight(abstract_txt:they in 2177) [ClassicSimilarity], result of:
           0.0130573725 = score(doc=2177,freq=1.0), product of:
             0.055744193 = queryWeight, product of:
               1.0517541 = boost
               3.7477977 = idf(docFreq=2845, maxDocs=44421)
               0.014141949 = queryNorm
             0.23423736 = fieldWeight in 2177, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.7477977 = idf(docFreq=2845, maxDocs=44421)
               0.0625 = fieldNorm(doc=2177)
         0.053317487 = weight(abstract_txt:query in 2177) [ClassicSimilarity], result of:
           0.053317487 = score(doc=2177,freq=4.0), product of:
             0.08971304 = queryWeight, product of:
               1.3342652 = boost
               4.754492 = idf(docFreq=1039, maxDocs=44421)
               0.014141949 = queryNorm
             0.5943115 = fieldWeight in 2177, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               4.754492 = idf(docFreq=1039, maxDocs=44421)
               0.0625 = fieldNorm(doc=2177)
         0.042345762 = weight(abstract_txt:literature in 2177) [ClassicSimilarity], result of:
           0.042345762 = score(doc=2177,freq=1.0), product of:
             0.1538789 = queryWeight, product of:
               2.471263 = boost
               4.4030223 = idf(docFreq=1477, maxDocs=44421)
               0.014141949 = queryNorm
             0.2751889 = fieldWeight in 2177, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.4030223 = idf(docFreq=1477, maxDocs=44421)
               0.0625 = fieldNorm(doc=2177)
         0.35993445 = weight(abstract_txt:reformulate in 2177) [ClassicSimilarity], result of:
           0.35993445 = score(doc=2177,freq=2.0), product of:
             0.4621665 = queryWeight, product of:
               3.7090209 = boost
               8.811096 = idf(docFreq=17, maxDocs=44421)
               0.014141949 = queryNorm
             0.7787982 = fieldWeight in 2177, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               8.811096 = idf(docFreq=17, maxDocs=44421)
               0.0625 = fieldNorm(doc=2177)
       0.2 = coord(5/25)