BackgroundTwitter is a microblogging service where users can send and read short 140-character messages called “tweets.” There are several unstructured, free-text tweets relating to health care being shared on Twitter, which is becoming a popular area for health care research. Sentiment is a metric commonly used to investigate the positive or negative opinion within these messages. Exploring the methods used for sentiment analysis in Twitter health care research may allow us to better understand the options available for future research in this growing field.ObjectiveThe first objective of this study was to understand which tools would be available for sentiment analysis of Twitter health care research, by reviewing existing studies in this area and the methods they used. The second objective was to determine which method would work best in the health care settings, by analyzing how the methods were used to answer specific health care questions, their production, and how their accuracy was analyzed.MethodsA review of the literature was conducted pertaining to Twitter and health care research, which used a quantitative method of sentiment analysis for the free-text messages (tweets). The study compared the types of tools used in each case and examined methods for tool production, tool training, and analysis of accuracy.ResultsA total of 12 papers studying the quantitative measurement of sentiment in the health care setting were found. More than half of these studies produced tools specifically for their research, 4 used open source tools available freely, and 2 used commercially available software. Moreover, 4 out of the 12 tools were trained using a smaller sample of the study’s final data. The sentiment method was trained against, on an average, 0.45% (2816/627,024) of the total sample data. One of the 12 papers commented on the analysis of accuracy of the tool used.ConclusionsMultiple methods are used for sentiment analysis of tweets in the health care setting. These range from self-produced basic categorizations to more complex and expensive commercial software. The open source and commercial methods are developed on product reviews and generic social media messages. None of these methods have been extensively tested against a corpus of health care messages to check their accuracy. This study suggests that there is a need for an accurate and tested tool for sentiment analysis of tweets trained using a health care setting–specific corpus of manually annotated tweets first.

We conclude that off-pump endarterectomy of the LAD is a viable option for patients with diffuse LAD disease.

BACKGROUND Engagement strategies used within the NHS, to reach out to the public and internal stakeholders, have continuously changed over time. Communication with each other is happening through more user-generated information being shared through social media (SM). The advent of SM has shifted the information-seeking behaviour of society, including healthcare. The ability of SM to engage people in the community and overcome traditional separation barriers gives SM the invaluable power of helping in the transition towards a more community and prevention focused health care delivery involving multiple stakeholders. OBJECTIVE A systematic literature review (SLR) was conducted to explore how SM is currently being used in the NHS using current literature. This was under the general theme of use of SM in the NHS, and strategies to engage the public in the NHS. METHODS Literature searches were performed in PubMed, MEDLINE and EMBASE between 2004-2017. The relevance of articles were screening using a pre decided inclusion and exclusion criteria. The papers included were critically appraised using the PRISMA Statement. Two separate search strings were created to cover both SM use in the NHS and engagement strategies in the NHS. RESULTS The search string yielded 3145 papers in total. After screening by initial limits, de-duplicating, screening by title, abstract and inclusion/exclusion criteria, a total of 55 papers were reached. These were all critically appraised and were divided based on the theme they covered. The themes found amongst these 55 papers were use of SM in: the NHS, nursing, healthcare research, conferences, gaining insights to patient perspectives and trends, recruitment, patient and medical education, successful Twitter campaigns and engaging patients. CONCLUSIONS Literature has shown two main views apparent on the use of SM in the NHS. The effectiveness of SM use in the NHS is uncertain, but SM specific uses acknowledges the potential of SM in engaging with the public and therefore helping to achieve the ambitious Five Year Forward View. Whilst limited, the literature has shown that SM in NHS has been used in research, conferences, and education of other doctors and patients. Engagement strategies in the NHS have mostly taken the form of awareness campaigns in key areas, such as lung cancer, nutrition and antibiotics use. 22% (12/55 papers) shows that the use of SM in the NHS has still far to go before it achieves full implementation and utilization.

BACKGROUND The number of social media users in the UK is rapidly rising. However, there is a lack on primary research as to how the National Health Service (NHS) is using social media to engage patients and the public. OBJECTIVE To understand the current methodology, implementation and strategy of social media use within NHS Trusts. METHODS A qualitative grounded theory approach was taken through semi-structured interviews with NHS Trusts. Selection was based on the Trusts quality ratings by the Care Quality Commission (CQC) in 2017, selecting the highest 15 and lowest 15 ranked trusts. Telephone interviews were conducted with a member of the communication teams and were audio recorded then transcribed. Three independent researchers thematically analysed the transcripts, to draw themes that emerged from the transcripts. RESULTS Following a pilot study, we conducted interviews with the communications team of 27 NHS trusts across the UK. Six main themes arose from the interviews: 1) The social media and communications teams; 2)The Trust; 3) The Trusts’ use of social media; 4)The Trusts’ management of their social media ; 5)The future of social media; 6)The use of social media within the NHS). These six higher themes consisted of a total of 26 subthemes. CONCLUSIONS The themes allow us to understand how social media is currently used within the NHS, as well as its potential future scope. Recognising the main areas of importance to Trusts and current difficulties they are facing, allow us to explore ways of increasing social media use by NHS Trusts. We have proposed a set of guidelines, known as the ENGAGED framework, which trusts can use to enhance social media use and enagagement. CLINICALTRIAL Nil

BACKGROUND Twitter is a microblogging service where users can send and read short 140-character messages called “tweets.” There are several unstructured, free-text tweets relating to health care being shared on Twitter, which is becoming a popular area for health care research. Sentiment is a metric commonly used to investigate the positive or negative opinion within these messages. Exploring the methods used for sentiment analysis in Twitter health care research may allow us to better understand the options available for future research in this growing field. OBJECTIVE The first objective of this study was to understand which tools would be available for sentiment analysis of Twitter health care research, by reviewing existing studies in this area and the methods they used. The second objective was to determine which method would work best in the health care settings, by analyzing how the methods were used to answer specific health care questions, their production, and how their accuracy was analyzed. METHODS A review of the literature was conducted pertaining to Twitter and health care research, which used a quantitative method of sentiment analysis for the free-text messages (tweets). The study compared the types of tools used in each case and examined methods for tool production, tool training, and analysis of accuracy. RESULTS A total of 12 papers studying the quantitative measurement of sentiment in the health care setting were found. More than half of these studies produced tools specifically for their research, 4 used open source tools available freely, and 2 used commercially available software. Moreover, 4 out of the 12 tools were trained using a smaller sample of the study’s final data. The sentiment method was trained against, on an average, 0.45% (2816/627,024) of the total sample data. One of the 12 papers commented on the analysis of accuracy of the tool used. CONCLUSIONS Multiple methods are used for sentiment analysis of tweets in the health care setting. These range from self-produced basic categorizations to more complex and expensive commercial software. The open source and commercial methods are developed on product reviews and generic social media messages. None of these methods have been extensively tested against a corpus of health care messages to check their accuracy. This study suggests that there is a need for an accurate and tested tool for sentiment analysis of tweets trained using a health care setting–specific corpus of manually annotated tweets first.