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) 4.07

   4.0712194 = sum of:
     4.0712194 = sum of:
       1.7681984 = weight(author_txt:yates in 3930) [ClassicSimilarity], result of:
         1.7681984 = score(doc=3930,freq=1.0), product of:
           0.6425055 = queryWeight, product of:
             8.806516 = idf(docFreq=17, maxDocs=44218)
             0.07295797 = queryNorm
           2.752036 = fieldWeight in 3930, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             8.806516 = idf(docFreq=17, maxDocs=44218)
             0.3125 = fieldNorm(doc=3930)
       2.3030212 = weight(author_txt:goharian in 3930) [ClassicSimilarity], result of:
         2.3030212 = score(doc=3930,freq=1.0), product of:
           0.7662811 = queryWeight, product of:
             1.092083 = boost
             9.617446 = idf(docFreq=7, maxDocs=44218)
             0.07295797 = queryNorm
           3.005452 = fieldWeight in 3930, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             9.617446 = idf(docFreq=7, maxDocs=44218)
             0.3125 = fieldNorm(doc=3930)
   

2. Mengle, S.; Goharian, N.: Passage detection using text classification (2009) 1.84

   1.8424169 = sum of:
     1.8424169 = product of:
       3.6848338 = sum of:
         3.6848338 = weight(author_txt:goharian in 2765) [ClassicSimilarity], result of:
           3.6848338 = score(doc=2765,freq=1.0), product of:
             0.7662811 = queryWeight, product of:
               1.092083 = boost
               9.617446 = idf(docFreq=7, maxDocs=44218)
               0.07295797 = queryNorm
             4.808723 = fieldWeight in 2765, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.617446 = idf(docFreq=7, maxDocs=44218)
               0.5 = fieldNorm(doc=2765)
       0.5 = coord(1/2)
   

3. Mengle, S.S.R.; Goharian, N.: Ambiguity measure feature-selection algorithm (2009) 1.84

   1.8424169 = sum of:
     1.8424169 = product of:
       3.6848338 = sum of:
         3.6848338 = weight(author_txt:goharian in 2804) [ClassicSimilarity], result of:
           3.6848338 = score(doc=2804,freq=1.0), product of:
             0.7662811 = queryWeight, product of:
               1.092083 = boost
               9.617446 = idf(docFreq=7, maxDocs=44218)
               0.07295797 = queryNorm
             4.808723 = fieldWeight in 2804, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.617446 = idf(docFreq=7, maxDocs=44218)
               0.5 = fieldNorm(doc=2804)
       0.5 = coord(1/2)
   

4. Mengle, S.S.R.; Goharian, N.: Detecting relationships among categories using text classification (2010) 1.84

   1.8424169 = sum of:
     1.8424169 = product of:
       3.6848338 = sum of:
         3.6848338 = weight(author_txt:goharian in 3462) [ClassicSimilarity], result of:
           3.6848338 = score(doc=3462,freq=1.0), product of:
             0.7662811 = queryWeight, product of:
               1.092083 = boost
               9.617446 = idf(docFreq=7, maxDocs=44218)
               0.07295797 = queryNorm
             4.808723 = fieldWeight in 3462, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.617446 = idf(docFreq=7, maxDocs=44218)
               0.5 = fieldNorm(doc=3462)
       0.5 = coord(1/2)
   

5. Baeza-Yates, R.A.: Introduction to data structures and algorithms related to information retrieval (1992) 1.41

   1.4145588 = sum of:
     1.4145588 = product of:
       2.8291175 = sum of:
         2.8291175 = weight(author_txt:yates in 3082) [ClassicSimilarity], result of:
           2.8291175 = score(doc=3082,freq=1.0), product of:
             0.6425055 = queryWeight, product of:
               8.806516 = idf(docFreq=17, maxDocs=44218)
               0.07295797 = queryNorm
             4.403258 = fieldWeight in 3082, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.806516 = idf(docFreq=17, maxDocs=44218)
               0.5 = fieldNorm(doc=3082)
       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

   0.13116491 = sum of:
     0.13116491 = product of:
       0.65582454 = sum of:
         0.018521192 = weight(abstract_txt:they in 534) [ClassicSimilarity], result of:
           0.018521192 = score(doc=534,freq=2.0), product of:
             0.05584784 = queryWeight, product of:
               1.0520912 = boost
               3.7520406 = idf(docFreq=2820, maxDocs=44218)
               0.014147687 = queryNorm
             0.33163667 = fieldWeight in 534, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.7520406 = idf(docFreq=2820, maxDocs=44218)
               0.0625 = fieldNorm(doc=534)
         0.022608086 = weight(abstract_txt:method in 534) [ClassicSimilarity], result of:
           0.022608086 = score(doc=534,freq=1.0), product of:
             0.08036734 = queryWeight, product of:
               1.2620891 = boost
               4.50095 = idf(docFreq=1333, maxDocs=44218)
               0.014147687 = queryNorm
             0.28130937 = fieldWeight in 534, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.50095 = idf(docFreq=1333, maxDocs=44218)
               0.0625 = fieldNorm(doc=534)
         0.034338005 = weight(abstract_txt:proposed in 534) [ClassicSimilarity], result of:
           0.034338005 = score(doc=534,freq=2.0), product of:
             0.08428374 = queryWeight, product of:
               1.2924749 = boost
               4.6093135 = idf(docFreq=1196, maxDocs=44218)
               0.014147687 = queryNorm
             0.4074096 = fieldWeight in 534, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.6093135 = idf(docFreq=1196, maxDocs=44218)
               0.0625 = fieldNorm(doc=534)
         0.04864692 = weight(abstract_txt:medical in 534) [ClassicSimilarity], result of:
           0.04864692 = score(doc=534,freq=1.0), product of:
             0.13394935 = queryWeight, product of:
               1.6293731 = boost
               5.8107834 = idf(docFreq=359, maxDocs=44218)
               0.014147687 = queryNorm
             0.36317396 = fieldWeight in 534, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.8107834 = idf(docFreq=359, maxDocs=44218)
               0.0625 = fieldNorm(doc=534)
         0.5317103 = weight(abstract_txt:clinical in 534) [ClassicSimilarity], result of:
           0.5317103 = score(doc=534,freq=5.0), product of:
             0.5236131 = queryWeight, product of:
               5.0936074 = boost
               7.2660704 = idf(docFreq=83, maxDocs=44218)
               0.014147687 = queryNorm
             1.0154642 = fieldWeight in 534, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               7.2660704 = idf(docFreq=83, maxDocs=44218)
               0.0625 = fieldNorm(doc=534)
       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

   0.1226448 = sum of:
     0.1226448 = product of:
       0.76653 = sum of:
         0.020810481 = weight(abstract_txt:support in 4763) [ClassicSimilarity], result of:
           0.020810481 = score(doc=4763,freq=1.0), product of:
             0.07604871 = queryWeight, product of:
               1.227711 = boost
               4.378348 = idf(docFreq=1507, maxDocs=44218)
               0.014147687 = queryNorm
             0.27364674 = fieldWeight in 4763, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.378348 = idf(docFreq=1507, maxDocs=44218)
               0.0625 = fieldNorm(doc=4763)
         0.045216173 = weight(abstract_txt:method in 4763) [ClassicSimilarity], result of:
           0.045216173 = score(doc=4763,freq=4.0), product of:
             0.08036734 = queryWeight, product of:
               1.2620891 = boost
               4.50095 = idf(docFreq=1333, maxDocs=44218)
               0.014147687 = queryNorm
             0.56261873 = fieldWeight in 4763, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               4.50095 = idf(docFreq=1333, maxDocs=44218)
               0.0625 = fieldNorm(doc=4763)
         0.027937036 = weight(abstract_txt:practice in 4763) [ClassicSimilarity], result of:
           0.027937036 = score(doc=4763,freq=1.0), product of:
             0.09254593 = queryWeight, product of:
               1.3543437 = boost
               4.829954 = idf(docFreq=959, maxDocs=44218)
               0.014147687 = queryNorm
             0.30187213 = fieldWeight in 4763, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.829954 = idf(docFreq=959, maxDocs=44218)
               0.0625 = fieldNorm(doc=4763)
         0.6725663 = weight(abstract_txt:clinical in 4763) [ClassicSimilarity], result of:
           0.6725663 = score(doc=4763,freq=8.0), product of:
             0.5236131 = queryWeight, product of:
               5.0936074 = boost
               7.2660704 = idf(docFreq=83, maxDocs=44218)
               0.014147687 = queryNorm
             1.2844719 = fieldWeight in 4763, product of:
               2.828427 = tf(freq=8.0), with freq of:
                 8.0 = termFreq=8.0
               7.2660704 = idf(docFreq=83, maxDocs=44218)
               0.0625 = fieldNorm(doc=4763)
       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

   0.11741171 = sum of:
     0.11741171 = product of:
       0.58705854 = sum of:
         0.04498355 = weight(abstract_txt:biomedical in 283) [ClassicSimilarity], result of:
           0.04498355 = score(doc=283,freq=1.0), product of:
             0.10090893 = queryWeight, product of:
               7.132539 = idf(docFreq=95, maxDocs=44218)
               0.014147687 = queryNorm
             0.44578367 = fieldWeight in 283, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.132539 = idf(docFreq=95, maxDocs=44218)
               0.0625 = fieldNorm(doc=283)
         0.024280636 = weight(abstract_txt:proposed in 283) [ClassicSimilarity], result of:
           0.024280636 = score(doc=283,freq=1.0), product of:
             0.08428374 = queryWeight, product of:
               1.2924749 = boost
               4.6093135 = idf(docFreq=1196, maxDocs=44218)
               0.014147687 = queryNorm
             0.2880821 = fieldWeight in 283, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.6093135 = idf(docFreq=1196, maxDocs=44218)
               0.0625 = fieldNorm(doc=283)
         0.04864692 = weight(abstract_txt:medical in 283) [ClassicSimilarity], result of:
           0.04864692 = score(doc=283,freq=1.0), product of:
             0.13394935 = queryWeight, product of:
               1.6293731 = boost
               5.8107834 = idf(docFreq=359, maxDocs=44218)
               0.014147687 = queryNorm
             0.36317396 = fieldWeight in 283, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.8107834 = idf(docFreq=359, maxDocs=44218)
               0.0625 = fieldNorm(doc=283)
         0.057286337 = weight(abstract_txt:previously in 283) [ClassicSimilarity], result of:
           0.057286337 = score(doc=283,freq=1.0), product of:
             0.14937267 = queryWeight, product of:
               1.7206231 = boost
               6.1362057 = idf(docFreq=259, maxDocs=44218)
               0.014147687 = queryNorm
             0.38351285 = fieldWeight in 283, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.1362057 = idf(docFreq=259, maxDocs=44218)
               0.0625 = fieldNorm(doc=283)
         0.41186106 = weight(abstract_txt:clinical in 283) [ClassicSimilarity], result of:
           0.41186106 = score(doc=283,freq=3.0), product of:
             0.5236131 = queryWeight, product of:
               5.0936074 = boost
               7.2660704 = idf(docFreq=83, maxDocs=44218)
               0.014147687 = queryNorm
             0.7865752 = fieldWeight in 283, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               7.2660704 = idf(docFreq=83, maxDocs=44218)
               0.0625 = fieldNorm(doc=283)
       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

   0.11286428 = sum of:
     0.11286428 = product of:
       0.5643214 = sum of:
         0.01309646 = weight(abstract_txt:they in 2856) [ClassicSimilarity], result of:
           0.01309646 = score(doc=2856,freq=1.0), product of:
             0.05584784 = queryWeight, product of:
               1.0520912 = boost
               3.7520406 = idf(docFreq=2820, maxDocs=44218)
               0.014147687 = queryNorm
             0.23450254 = fieldWeight in 2856, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.7520406 = idf(docFreq=2820, maxDocs=44218)
               0.0625 = fieldNorm(doc=2856)
         0.027937036 = weight(abstract_txt:practice in 2856) [ClassicSimilarity], result of:
           0.027937036 = score(doc=2856,freq=1.0), product of:
             0.09254593 = queryWeight, product of:
               1.3543437 = boost
               4.829954 = idf(docFreq=959, maxDocs=44218)
               0.014147687 = queryNorm
             0.30187213 = fieldWeight in 2856, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.829954 = idf(docFreq=959, maxDocs=44218)
               0.0625 = fieldNorm(doc=2856)
         0.06879713 = weight(abstract_txt:medical in 2856) [ClassicSimilarity], result of:
           0.06879713 = score(doc=2856,freq=2.0), product of:
             0.13394935 = queryWeight, product of:
               1.6293731 = boost
               5.8107834 = idf(docFreq=359, maxDocs=44218)
               0.014147687 = queryNorm
             0.51360554 = fieldWeight in 2856, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.8107834 = idf(docFreq=359, maxDocs=44218)
               0.0625 = fieldNorm(doc=2856)
         0.042629737 = weight(abstract_txt:literature in 2856) [ClassicSimilarity], result of:
           0.042629737 = score(doc=2856,freq=1.0), product of:
             0.1545452 = queryWeight, product of:
               2.4751012 = boost
               4.413439 = idf(docFreq=1455, maxDocs=44218)
               0.014147687 = queryNorm
             0.27583992 = fieldWeight in 2856, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.413439 = idf(docFreq=1455, maxDocs=44218)
               0.0625 = fieldNorm(doc=2856)
         0.41186106 = weight(abstract_txt:clinical in 2856) [ClassicSimilarity], result of:
           0.41186106 = score(doc=2856,freq=3.0), product of:
             0.5236131 = queryWeight, product of:
               5.0936074 = boost
               7.2660704 = idf(docFreq=83, maxDocs=44218)
               0.014147687 = queryNorm
             0.7865752 = fieldWeight in 2856, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               7.2660704 = idf(docFreq=83, maxDocs=44218)
               0.0625 = fieldNorm(doc=2856)
       0.2 = coord(5/25)
   

5. Cimino, J.J.: Distributed cognition and knowledge-based controlled medical terminologies (1998) 0.11

   0.1072494 = sum of:
     0.1072494 = product of:
       0.67030877 = sum of:
         0.032412086 = weight(abstract_txt:they in 3223) [ClassicSimilarity], result of:
           0.032412086 = score(doc=3223,freq=2.0), product of:
             0.05584784 = queryWeight, product of:
               1.0520912 = boost
               3.7520406 = idf(docFreq=2820, maxDocs=44218)
               0.014147687 = queryNorm
             0.58036417 = fieldWeight in 3223, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.7520406 = idf(docFreq=2820, maxDocs=44218)
               0.109375 = fieldNorm(doc=3223)
         0.051503316 = weight(abstract_txt:support in 3223) [ClassicSimilarity], result of:
           0.051503316 = score(doc=3223,freq=2.0), product of:
             0.07604871 = queryWeight, product of:
               1.227711 = boost
               4.378348 = idf(docFreq=1507, maxDocs=44218)
               0.014147687 = queryNorm
             0.67724115 = fieldWeight in 3223, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.378348 = idf(docFreq=1507, maxDocs=44218)
               0.109375 = fieldNorm(doc=3223)
         0.17026421 = weight(abstract_txt:medical in 3223) [ClassicSimilarity], result of:
           0.17026421 = score(doc=3223,freq=4.0), product of:
             0.13394935 = queryWeight, product of:
               1.6293731 = boost
               5.8107834 = idf(docFreq=359, maxDocs=44218)
               0.014147687 = queryNorm
             1.2711089 = fieldWeight in 3223, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               5.8107834 = idf(docFreq=359, maxDocs=44218)
               0.109375 = fieldNorm(doc=3223)
         0.41612917 = weight(abstract_txt:clinical in 3223) [ClassicSimilarity], result of:
           0.41612917 = score(doc=3223,freq=1.0), product of:
             0.5236131 = queryWeight, product of:
               5.0936074 = boost
               7.2660704 = idf(docFreq=83, maxDocs=44218)
               0.014147687 = queryNorm
             0.79472643 = fieldWeight in 3223, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.2660704 = idf(docFreq=83, maxDocs=44218)
               0.109375 = fieldNorm(doc=3223)
       0.16 = coord(4/25)