Automatic information timeliness assessment of diabetes web sites by evidence based medicine

• Published in: Computer methods and programs in biomedicine Vol. 117; no. 2; pp. 104 - 113
• Main Authors: SAGLAM, Rahime Belen, TEMIZEL, Tuğba Taşkaya
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ireland Ltd 01.11.2014; Elsevier
• Subjects: Applied sciences; Biological and medical sciences; Clinical Trials as Topic - classification; Clinical Trials as Topic - statistics & numerical data; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Computerized medical documentation; Computerized, statistical medical data processing and models in biomedicine; Content-based retrieval; Data Curation - classification; Data Curation - statistics & numerical data; Data Mining - methods; Diabetes; Diabetes Mellitus; Diabetes. Impaired glucose tolerance; Endocrine pancreas. Apud cells (diseases); Endocrinopathies; Evidence-Based Medicine; Exact sciences and technology; Humans; Information systems. Data bases; Internal Medicine; Medical information systems; Medical sciences; Memory organisation. Data processing; Natural Language Processing; Other; Periodicals as Topic - classification; Periodicals as Topic - statistics & numerical data; Social Media - classification; Social Media - statistics & numerical data; Software; Time Factors; Timeliness analysis; Medical information systems; Content-based retrieval; Timeliness analysis; Diabetes; Endocrinopathy; Archive; Health; Evidence-based practice; Metabolic diseases; Updating; Information retrieval; Glucose; Evidence-based medicine; Recommendation; Relevance; Relevance feedback; Imperfect information; Time interval; Automatic recognition; Web site
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2014.07.014

Highlights • The proposed method predicts the time period that a given content belongs to. • The archives of high quality diabetes web sites between 2006 and 2013 were utilized. • The method's accuracy is 65% in detecting the timeliness according to years. • The accuracy increases when detecting timeliness according to time intervals.