USE OF TEXT-MINING TOOLS FOR SYSTEMATIC REVIEWS
Author(s)
Paynter RA1, Bañez LL2, Berliner E2, Erinoff E3, Lege-Matsuura JM3, Potter S4
1AHRQ Effective Health Care Program, Portland, OR, USA, 2Agency for Healthcare Research and Quality, Rockville, MD, USA, 3ECRI Institute, Plymouth Meeting, PA, USA, 4Vanderbilt University, Nashville, TN, USA
OBJECTIVES: To provide a preliminary review of text-mining tools as an emerging methodology to support systematic review processes. METHODS: We conducted a literature search to identify and summarize research on the use of text-mining tools within the systematic review context. We conducted telephone interviews with Key Informants using a semi-structured instrument, and subsequent qualitative analysis to explore issues surrounding implementation and use of text-mining tools. Lastly, we compiled a list of text-mining tools to support systematic review methods and evaluated the tools using an informal descriptive appraisal tool. RESULTS: The literature review identified 670 articles, 122 of which met inclusion criteria. Support for the use of text mining was strong amongst the Key Informants overall, though most noted performance caveats or areas requiring further research. We describe 111 text-mining tools identified from the literature review and KI interviews. CONCLUSIONS: Text-mining tools are currently being used in a wide range of applications, including support for systematic review searching, screening, appraisal, and synthesis. The literature-base is growing, although likely not as quickly as ongoing innovation. Additional research is needed to address the reliability, validity, and practicality of these emerging technologies in the context of the systematic literature review.
Conference/Value in Health Info
2016-05, ISPOR 2016, Washington DC, USA
Value in Health, Vol. 19, No. 3 (May 2016)
Code
PRM211
Topic
Methodological & Statistical Research
Topic Subcategory
Confounding, Selection Bias Correction, Causal Inference
Disease
Multiple Diseases