Text mining investigation of scale assessment within clinical trials

Many diagnostic assessments use scales to quantify patients' status. Text mining was used to obtain information from outside the assessment capability of scales.; SAS EM was used to investigate the words written by physicians during a course of clinical trials. The concepts within the texts were extracted and classified based on value assignment within domains outlined by clinicians. The text classification was correlated to scales at each visit to investigate the relationship.; The classification of a random subset of documents was given to two clinical experts and four non-experts. The experts and majority of non-experts agreed with the program assignment similarly. The correspondence between groups was lowest with experts for concept assignment. The experts had a higher agreement than non-experts in value assignment.; Since the experts had a lower agreement in concept classification than majority of four non-experts, this process offers objective insight into the assessment of patients' status.