Technique / Bioinformatics / Data mining / Text mining biomedical literatures

Text mining, sometimes alternately referred to as text data mining, refers generally to the process of deriving high quality information from text. High quality information is typically derived through the dividing of patterns and trends through means such as statistical pattern learning.

It is now almost 15 years since the publication of the first paper on text mining in the genomics domain, and decades since the first paper on text mining in the medical domain. Enormous progress has been made in the areas of information retrieval, evaluation methodologies and resource construction. Some problems, such as abbreviation-handling, can essentially be considered solved problems, and others, such as identification of gene mentions in text, seem likely to be solved soon. However, a number of problems at the frontiers of biomedical text mining continue to present interesting challenges and opportunities for great improvements and interesting research. In this article we review the current state of the art in biomedical text mining or 'BioNLP' in general, focusing primarily on papers published within the past year.

OBJECTIVE: This study aims to clarify characteristics of the contents of life review in reminiscence therapies in cancer patients by age, gender, and stage of disease. METHODS: Sixteen patients who were terminally ill and were receiving anticancer treatments participated in life review therapy. Patients reviewed there lives according to their developmental stage, and they mainly reviewed impressive achievements. A clinical psychologist interviewed each patient four times and the total number of sessions was 64. The contents of each life review were transcribed, and a correspondence analysis and a significance test were conducted on these data to choose characteristic words or phrases. RESULTS: The main concern of 40-year-olds was "about children." For 50-year-olds, it was "how to confront death" and for 60-year-olds, "death-related anxiety" and "new discoveries". For 70-year-olds, "resignation about death" and "evaluative reminiscence of their lives" were most important, and for 80-year-olds the main concern was "relationships with others." When analyzing the data according to disease stage and gender, "transcendence to children", "reflection on their past behavior", and "gratitude for my family" were characteristic words for males receiving treatment, "work," "worries about children," "side effects," "homecare," and "reflection on their past behavior" were characteristic words for females receiving treatment. "Physical condition", "desire for death" and "how to confront death" were common phrase for males in the terminal stages of the disease process, while "resignation to life" was characteristic reaction for females. SIGNIFICANCE OF RESULTS: There appear to be considerable differences in the focus of life review interviews by age, disease age, disease stage, and gender. Clinicians should consider these differences when using life-review therapy in order to tailor it to the individual.