ABSTRACT
Recent advancements in speech recognition technology in combination with increased access to smart speaker devices are expanding conversational interactions to ever-new areas of our lives - including our health and wellbeing. Prior human-computer interaction research suggests that Conversational Agents (CAs) have the potential to support a variety of health-related outcomes, due in part to their intuitive and engaging nature. Realizing this potential requires however developing a rich understanding of users' needs and experiences in relation to these still-emerging technologies. To inform the design of CAs for health and wellbeing, we analyze 2741 critical reviews of 485 Alexa health and fitness Skills using an automated topic modeling approach; identifying 15 subjects of criticism across four key areas of design (functionality, reliability, usability, pleasurability). Based on these findings, we discuss implications for the design of engaging CAs to support health and wellbeing.
ABSTRACT
BACKGROUND: The cause of ischemic stroke or transient ischemic attack (TIA) remains unclear after initial cardiac monitoring in approximately one-third of patients. Randomized controlled trials (RCTs) showed that the prolonged cardiac monitoring of patients with cryptogenic stroke or TIA increased detection of atrial fibrillation (AF). We aimed to perform a meta-analysis of all RCTs that evaluated the prolonged monitoring ≥7 days in patients with cryptogenic stroke or TIA. METHODS: We searched PubMed, EMBASE, Cochrane CENTRAL, and relevant references for RCTs without language restriction (inception through December 2014) and performed meta-analysis using random effects model. Detection of AF, use of anticoagulation at follow-up, recurrent stroke or TIA, and mortality were major outcomes. RESULTS: Four RCTs with 1149 total patients were included in the meta-analysis. Prolonged cardiac monitoring ≥7 days compared to shorter cardiac monitoring of ≤48 hours duration increased the detection of AF (≥30 seconds duration) in patients after cryptogenic stroke or TIA (13.8% vs. 2.5%; odds ratio [OR], 6.4; 95% confidence interval [CI], 3.50-11.73; P < 0.00001; I(2) , 0%]. It also increased the odds of AF detection of any duration (22.6% vs. 5.2%; 5.68[3.3-9.77]; P < 0.00001; I(2) , 0%). The patients who underwent prolonged monitoring were more likely to be on anticoagulation at follow-up (2.21[1.52-3.21]; P < 0.0001; I(2) , 0%). No differences in recurrent stroke or TIA (0.78[0.40-1.55]; P = 0.48; I(2) , 0%) and mortality (1.33[0.29-6.00]; P = 0.71; I(2) , 0%] were observed between two strategies. CONCLUSION: Prolonged cardiac monitoring improves detection of atrial fibrillation and anti-coagulation use after cryptogenic stroke or TIA and therefore should be considered instead of shorter duration of cardiac monitoring.
