Mining causal associations from geriatric literature

Anand Krishnan, Purdue University

Abstract

Literature pertaining to geriatric care contains rich information regarding the best practices related to geriatric health care issues. The publication domain of geriatric care is small as compared to other health related areas, however, there are over a million articles pertaining to different cases and case interventions capturing best practice outcomes. If the data found in these articles could be harvested and processed effectively, such knowledge could then be translated from research to practice in a quicker and more efficient manner. Geriatric literature contains multiple domains or practice areas and within these domains is a wealth of information such as interventions, information on care for elderly, case studies, and real life scenarios. These articles are comprised of a variety of causal relationships such as the relationship between interventions and disorders. The goal of this study is to identify these causal relations from published abstracts. Natural language processing and statistical method were adopted to identify and extract these causal relations. Using the developed methods, causal relations were extracted with precision of 79.54%, recall of 81% while only having a false positive rate 8%.

Degree

M.S.

Advisors

Palakal, Purdue University.

Subject Area

Gerontology|Information science|Computer science

COinS