Publications

BACKGROUND

It is difficult to synthesize the vast amount of textual data available from social media websites. Capturing real-world discussions via social media could provide insights into individuals' opinions and the decision-making process.

OBJECTIVE

We conducted a sequential mixed methods study to determine the utility of sparse machine learning techniques in summarizing Twitter dialogues. We chose a narrowly defined topic for this approach: cervical cancer discussions over a 6-month time period surrounding a change in Pap smear screening guidelines.

METHODS

We applied statistical methodologies, known as sparse machine learning algorithms, to summarize Twitter messages about cervical cancer before and after the 2012 change in Pap smear screening guidelines by the US Preventive Services Task Force (USPSTF). All messages containing the search terms "cervical cancer," "Pap smear," and "Pap test" were analyzed during: (1) January 1-March 13, 2012, and (2) March 14-June 30, 2012. Topic modeling was used to discern the most common topics from each time period, and determine the singular value criterion for each topic. The results were then qualitatively coded from top 10 relevant topics to determine the efficiency of clustering method in grouping distinct ideas, and how the discussion differed before vs. after the change in guidelines .

RESULTS

This machine learning method was effective in grouping the relevant discussion topics about cervical cancer during the respective time periods (~20% overall irrelevant content in both time periods). Qualitative analysis determined that a significant portion of the top discussion topics in the second time period directly reflected the USPSTF guideline change (eg, "New Screening Guidelines for Cervical Cancer"), and many topics in both time periods were addressing basic screening promotion and education (eg, "It is Cervical Cancer Awareness Month! Click the link to see where you can receive a free or low cost Pap test.")

CONCLUSIONS

It was demonstrated that machine learning tools can be useful in cervical cancer prevention and screening discussions on Twitter. This method allowed us to prove that there is publicly available significant information about cervical cancer screening on social media sites. Moreover, we observed a direct impact of the guideline change within the Twitter messages.

BACKGROUND

Canine intervertebral disc πherniation causes a naturally-occurring spinal cord injury (SCI) that bears critical similarities to human SCI with respect to both injury pathomechanisms and treatment. As such, it has tremendous potential to enhance our understanding of injury biology and the preclinical evaluation of novel therapies. Currently, there is limited understanding of the role of arachidonic acid metabolites in canine SCI.

RESULTS

The CSF concentrations of PLA2 and PGE2 were higher in SCI dogs compared to control dogs (p = 0.0370 and 0.0273, respectively), but CSF LCT4 concentration in SCI dogs was significantly lower than that in control dogs (p < 0.0001). Prostaglandin E2 concentration in the CSF was significantly and positively associated with increased severity of SCI at the time of sampling (p = 0.041) and recovery 42 days post-injury (p = 0.006), as measured by ordinal behavioral scores.

CONCLUSION

Arachidonic acid metabolism is altered in dogs with SCI, and these data suggest that these AA metabolites reflect injury severity and recovery, paralleling data from other model systems.

Randomized controlled trials in CKD lag in number behind those of other chronic diseases, despite the high morbidity and mortality experienced by patients with kidney disease and the exorbitant costs of their health care. Observational studies of CKD frequently yield seemingly paradoxic associations of traditional risk factors with outcomes, making it difficult to extrapolate the results of trials conducted in people with normal kidney function to patients with CKD. However, many completed trials in CKD have been limited by intermediate outcomes of unclear clinical significance or narrow eligibility criteria that limit external validity, and implementation of proven therapies remains a challenge. It is therefore imperative that the nephrology community capitalize on recent interest in novel approaches to trial design, such as pragmatic clinical trials. These trials are meant to promote research within real world settings to yield clinically relevant results with greater applicability than those of traditional trials, while maintaining many advantages, such as controlling for potential sources of bias. We provide a description of pragmatic clinical trials and a discussion of advantages, disadvantages, and practical challenges inherent to this study design, in the context of specific scientific questions relevant to patients with CKD.