Improving search filter development: a study of palliative care literature

Background It is difficult to systematically search for literature relevant to palliative care in general medical journals. A previously developed search filter for use on OVID Medline validated using a gold standard set of references identified through hand searching, achieved an unacceptably low sensitivity (45.4%). Retrieving relevant literature is integral to support evidence based practice, and understanding the nature of the incorrectly excluded citations (false negatives) using the filter may lead to improvement in the filter's performance. Methods The objectives were to describe the nature of subjects reflected in the false negative citations and to empirically improve the sensitivity of the search filter. A thematic analysis of MeSH terms by three independent reviewers was used to describe the subject coverage of the missed records. Using a frequency analysis of MeSH terms, those headings which could individually contribute at least 2.5% to sensitivity (occurring 19 or more times) were added to the search filter. All previously run searches were rerun at the same time as the revised filter, and results compared. Results Thematic analysis of MeSH terms identified thirteen themes reflected in the missing records, none of them intrinsically palliative. The addition of six MeSH terms to the existing search filter (physician-patient relations, prognosis, quality of life, survival rate, treatment outcome and attitude to health) led to an increase in sensitivity from 46.3% to 64.7%, offset by a decrease in precision from 72.6% to 21.9%. Conclusion The filter's sensitivity was successfully increased using frequency analysis of MeSH terms, offset by a decrease in precision. A thematic analysis of MeSH terms for the false negative citations confirmed the absence of any intrinsically palliative theme or term, suggesting that future improvements to search filters for palliative care literature will first depend on better identifying how clinicians and researchers conceptualise palliative care. It is suggested that a constellation of parameters: stage of disease (advanced or active), prospect of cure (little or none), and treatment goals (primarily quality of life) may ultimately inform search strategies. This may be similarly true for chronic diseases, which share the inherent passage of time which marks them apart from acute, and therefore more readily identifiable, episodes of care