Research Paper: Ad Hoc Classification of Radiology Reports

OBJECTIVE The task of ad hoc classification is to automatically place a large number of text documents into nonstandard categories that are determined by a user. The authors examine the use of statistical information retrieval techniques for ad hoc classification of dictated mammography reports. DESIGN The authors' approach is the automated generation of a classification algorithm based on positive and negative evidence that is extracted from relevance-judged documents. Test documents are sorted into three conceptual bins: membership in a user-defined class, exclusion from the user-defined class, and uncertain. Documentation of absent findings through the use of negation and conjunction, a hallmark of interpretive test results, is managed by expansion and tokenization of these phrases. MEASUREMENTS Classifier performance is evaluated using a single measure, the F measure, which provides a weighted combination of recall and precision of document sorting into true positive and true negative bins. RESULTS Single terms are the most effective text feature in the classification profile, with some improvement provided by the addition of pairs of unordered terms to the profile. Excessive iterations of automated classifier enhancement degrade performance because of overtraining. Performance is best when the proportions of relevant and irrelevant documents in the training collection are close to equal. Special handling of negation phrases improves performance when the number of terms in the classification profile is limited. CONCLUSIONS The ad hoc classifier system is a promising approach for the classification of large collections of medical documents. NegExpander can distinguish positive evidence from negative evidence when the negative evidence plays an important role in the classification.

[1]  Jinxi Xu,et al.  The Design and Implementation of a Part of Speech Tagger for English , 1994 .

[2]  W. Bruce Croft,et al.  Automated classification of encounter notes in a computer based medical record. , 1995, Medinfo. MEDINFO.

[3]  W. Bruce Croft,et al.  Inference networks for document retrieval , 1989, SIGIR '90.

[4]  Carol Friedman,et al.  Identification of findings suspicious for breast cancer based on natural language processing of mammogram reports , 1997, AMIA.

[5]  James Allan,et al.  INQUERY at TREC-5 , 1996, TREC.

[6]  Eugene Charniak,et al.  Bayesian Networks without Tears , 1991, AI Mag..

[7]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[8]  William A. Gale,et al.  A sequential algorithm for training text classifiers , 1994, SIGIR '94.

[9]  W. Bruce Croft,et al.  Efficient probabilistic Inference for text retrieval , 1991, RIAO.

[10]  W. Bruce Croft,et al.  Evaluation of an inference network-based retrieval model , 1991, TOIS.

[11]  G. Octo Barnett,et al.  Puya: a method of attracting attention to relevant physical findings , 1997, AMIA.

[12]  N L Jain,et al.  Identification of suspected tuberculosis patients based on natural language processing of chest radiograph reports. , 1996, Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium.

[13]  W. DuMouchel,et al.  Unlocking Clinical Data from Narrative Reports: A Study of Natural Language Processing , 1995, Annals of Internal Medicine.

[14]  W. Bruce Croft,et al.  Combining classifiers in text categorization , 1996, SIGIR '96.

[15]  James Allan,et al.  The effect of adding relevance information in a relevance feedback environment , 1994, SIGIR '94.

[16]  William R. Hersh,et al.  Automatic Prediction of Trauma Registry Procedure Codes from Emergency Room Dictations , 1998, MedInfo.

[17]  S. Robertson.  The probability ranking principle in IR , 1997 .

[18]  Randolph A. Miller,et al.  Research Paper: An Experiment Comparing Lexical and Statistical Methods for Extracting MeSH Terms from Clinical Free Text , 1998, J. Am. Medical Informatics Assoc..

[19]  Lambert Schomaker,et al.  Proceedings of the 22rd International Conference on Research and Development in Information Retrieval , 1999 .

[20]  C G Chute,et al.  An application of Expert Network to clinical classification and MEDLINE indexing. , 1994, Proceedings. Symposium on Computer Applications in Medical Care.

[21]  B. Silverman,et al.  Some Aspects of the Spline Smoothing Approach to Non‐Parametric Regression Curve Fitting , 1985 .

[22]  W. Bruce Croft,et al.  The INQUERY Retrieval System , 1992, DEXA.

[23]  Wendy G. Lehnert,et al.  Inductive text classification for medical applications , 1995, J. Exp. Theor. Artif. Intell..

[24]  James P. Callan,et al.  Training algorithms for linear text classifiers , 1996, SIGIR '96.

[25]  Fangfang Feng,et al.  Ad-Hoc Classification of Electronic Clinical Documents , 1997, D Lib Mag..

[26]  W. Bruce Croft,et al.  An Association Thesaurus for Information Retrieval , 1994, RIAO.

[27]  James Allan,et al.  Recent Experiments with INQUERY , 1995, TREC.

[28]  Gerard Salton,et al.  Research and Development in Information Retrieval , 1982, Lecture Notes in Computer Science.

[29]  I. W. Wright.  Splines in Statistics , 1983 .

[30]  D B Aronow,et al.  Automated identification of episodes of asthma exacerbation for quality measurement in a computer-based medical record. , 1995, Proceedings. Symposium on Computer Applications in Medical Care.

[31]  J. J. Rocchio,et al.  Relevance feedback in information retrieval , 1971 .

[32]  W. Bruce Croft,et al.  Relevance feedback and inference networks , 1993, SIGIR.

[33]  George Hripcsak,et al.  Research Paper: A Reliability Study for Evaluating Information Extraction from Radiology Reports , 1999, J. Am. Medical Informatics Assoc..