Crowdsourcing Treatments for Low Back Pain

Abstract

Low back pain (LBP) is a globally common condition with no silver bullet solutions. Further, the lack of therapeutic consensus causes challenges in choosing suitable solutions to try. In this work, we crowdsourced knowledge bases on LBP treatments. The knowledge bases were used to rank and offer best-matching LBP treatments to end users. We collected two knowledge bases: one from clinical professionals and one from non-professionals. Our quantitative analysis revealed that non-professional end users perceived the best treatments by both groups as equally good. However, the worst treatments by nonprofessionals were clearly seen as inferior to the lowest ranking treatments by professionals. Certain treatments by professionals were also perceived significantly differently by non-professionals and professionals themselves. Professionals found our system handy for self-reflection and for educating new patients, while non-professionals appreciated the reliable decision support that also respected the non-professional opinion.

Search Support for Exploratory Writing

“…Figure 2 compares a search on GAS and Google for cheap but efficient treatments for low back pain, as an example. This exact case with the original system was discussed in-depth in [21].…”

“…In doing so, the system applies wisdom of the crowd [45]. We direct the reader to the original article on the system and the newer account for a detailed overview [19,21].…”

“…The knowledge bases in AnswerBot are collected dynamically over time to answer topic-specific information needs: they are are not transferable between different problem domains. For this paper, we obtained and reused three knowledge bases collected by the AnswerBot platform and documented in [8,21]. The three data collection campaigns are summarised in Table 2.…”

“…To support such writing, we modified the AnswerBot system by Hosio et al [19]. Our solution, GAS, ranks open-ended content across multiple criteria simultaneously -an approach versatile for provisioning decision support for real-world problems [21] but also for discovering ideas that best fulfil a set of search criteria. Thus, it affords a straightforward approach to solving complex search tasks [1] that the online search engines have been shown to struggle with [34].…”

“…Yet, there is an identified need for supporting multidimensional search and discovery of unpopular information [35]. For instance, people suffering from back pain may want to discover fast, cheap and long-lasting ways of treating back pain -a real-world information need for which online search engines are not well-equipped [21].…”