Identifying potential adverse effects using the web: A new approach to medical hypothesis generation

Abstract

Medical message boards are online resources where users with a particular condition exchange information, some of which they might not otherwise share with medical providers. Many of these boards contain a large number of posts and contain patient opinions and experiences that would be potentially useful to clinicians and researchers. We present an approach that is able to collect a corpus of medical message board posts, de-identify the corpus, and extract information on potential adverse drug effects discussed by users. Using a corpus of posts to breast cancer message boards, we identified drug event pairs using co-occurrence statistics. We then compared the identified drug event pairs with adverse effects listed on the package labels of tamoxifen, anastrozole, exemestane, and letrozole. Of the pairs identified by our system, 75–80% were documented on the drug labels. Some of the undocumented pairs may represent previously unidentified adverse drug effects.

Open Issues in Intelligent Personal Health Record – An Updated Status Report for 2012

“…For each listed side effect, its incidence statistics reflecting the likelihood of developing it could be displayed. To compile side effects of SCAs, we can adopt a method similar to those used for compiling drug side/adverse effects from various resources, such as electronic health knowledge resources [27,68,89], historical data in electronic health records [148], and medical message board posts [15]. To obtain incidence statistics of side effects of SCAs, we can adopt a method similar to those used for estimating incidence statistics of drug adverse effects from various resources [36,50,68].…”

“…Each approach will extract some candidate, potentially novel SCA contraindication information. Controlled studies then need to be conducted to verify the correctness of the extracted, candidate SCA contraindication information [15]. Following, we describe two potential approaches for automatically extracting potentially novel SCA contraindication information from other electronic data resources.…”

“…As mentioned in Benton et al [15], many medical message boards contain a large number of candid messages and have moderators to remove spam messages, resulting in an inexpensive and relatively trustworthy way to learn more about a given population. Benton et al used text mining and statistical techniques to detect potentially novel adverse drug events from medical message board posts [15].…”

“…Benton et al used text mining and statistical techniques to detect potentially novel adverse drug events from medical message board posts [15]. Contraindication is one type of harm, whereas harm is often discussed on medical message boards.…”

“…Contraindication is one type of harm, whereas harm is often discussed on medical message boards. Hence, an approach similar to that in Benton et al [15] can be used to extract potentially novel SCA contraindication information from medical message board posts. For example, consider a particular SCA and a specific health issue.…”