Aggregating Personal Health Messages for Scalable Comparative Effectiveness Research

Abstract

Comparative Effectiveness Research (CER) is defined as the generation and synthesis of evidence that compares the benefits and harms of different prevention and treatment methods. This is becoming an important field in informing health care providers about the best treatment for individual patients. Currently, the two major approaches in conducting CER are observational studies and randomized clinical trials. These approaches, however, often suffer from either scalability or cost issues.In this paper, we propose a third approach of conducting CER by utilizing online personal health messages, e.g., comments on online medical forums. The approach is effective in resolving the scalability and cost issues, enabling rapid deployment of system to identify treatments of interests, and developing hypotheses for formal CER studies. Moreover, by utilizing the demographic information of the patients, this approach may provide valuable results on the preferences of different demographic groups. Demographic information is extracted using our high precision automated demographic extraction algorithm. This approach is capable of extracting more than 30% of users' age and gender information.We conducted CER by utilizing personal health messages on breast cancer and heart disease. We were able to generate statiatically valid results, many of which have already been validated by clinical trials. Others could become hypothesis to be tested in future CER research.

Understanding user intents in online health forums

“…Had they had access to thread intents, they could have simply conducted the search on threads with "treatment" intent from their corpus of documents. Similarly, Cho et al [12] conducted Comparative Effectiveness Research (CER), defined as how well patients respond to treatments, by extracting treatment sentiments from over 130K online health forum posts to model treatment effectiveness. With knowledge of intents, they could instead run their algorithm only on posts from threads with"treatment" and "adverse effects of treatment" intent which would dramatically reduce the search space and arguably improve the quality of the results obtained.…”

Connecting the Dots

“…There are a lot of online healthcare forums available, such as PatientsLikeMe 1 , WebMD 2 , Healthboards message boards 3 , MedHelp 4 , and the Epilepsy forum 5 . The user population of such forums are rapidly growing.…”

“…In contrast, we propose to connect information in healthcare forums via a semantic unit, a patient. Opinion mining and sentiment analysis are also used for knowledge discovery in online healthcare forums [5,9]. [9] discovers patient drug outcomes by clustering the topics and opinions in online health forums.…”

“…[9] discovers patient drug outcomes by clustering the topics and opinions in online health forums. [5] compares the effectiveness of different treatments with sentiment analysis. The user's demographic information is also used in [5] to differentiate the treatment effectiveness for different populations.…”

“…[5] compares the effectiveness of different treatments with sentiment analysis. The user's demographic information is also used in [5] to differentiate the treatment effectiveness for different populations. Different from our work, they do not connect the medical information within a patient semantic unit.…”