Search

We investigate the use of Twitter data to deliver signals for syndromic surveillance in order to assess its ability to augment existing syndromic surveillance efforts and give a better understanding of symptomatic people who do not seek healthcare advice directly. We focus on a specific syndrome—asthma/difficulty breathing. We outline data collection using the Twitter streaming API as well as analysis and pre-processing of the collected data. Even with keyword-based data collection, many of the tweets collected are not be relevant because they represent chatter, or talk of awareness instead of an individual suffering a particular condition. In light of this, we set out to identify relevant tweets to collect a strong and reliable signal. For this, we investigate text classification techniques, and in particular we focus on semi-supervised classification techniques since they enable us to use more of the Twitter data collected while only doing very minimal labelling. In this paper, we propose a semi-supervised approach to symptomatic tweet classification and relevance filtering. We also propose alternative techniques to popular deep learning approaches. Additionally, we highlight the use of emojis and other special features capturing the tweet’s tone to improve the classification performance. Our results show that negative emojis and those that denote laughter provide the best classification performance in conjunction with a simple word-level n-gram approach. We obtain good performance in classifying symptomatic tweets with both supervised and semi-supervised algorithms and found that the proposed semi-supervised algorithms preserve more of the relevant tweets and may be advantageous in the context of a weak signal. Finally, we found some correlation (r = 0.414, p = 0.0004) between the Twitter signal generated with the semi-supervised system and data from consultations for related health conditions. [ABSTRACT FROM AUTHOR]

Background. Orthostatic hypotension (OH) is common amongst the older population and is associated with morbidity and mortality. We sought to investigate predictors of OH to assist the clinician in identifying patients at risk. Methods and results. Database of 2696 patients attending a transient ischaemic attack (TIA) clinic between January 2006 and May 2009 was examined. Logistic regression models were constructed to determine clinical associates of OH. Demographics, co-morbidities, cardiovascular risk factors and medications were included in the multivariate models. Simple data mining models in the form of rule sets were developed for each component and they were assessed for predictive accuracy. The best models were validated on a smaller sample. Prevalence of OH was 22.3% in the TIA clinic population (50.6% men, mean 72 years; 49.4% women, mean 75 years). A significant postural drop in systolic blood pressure (BP) (≥ 20 mmHg) was more prevalent than a significant diastolic BP drop (≥ 10 mmHg). Isolated systolic hypertension was common (52.4%). Common factors predicting a significant systolic and diastolic BP fall were older age, previous TIA, being a current smoker, having diabetes and the use of beta-blockers. Both mean arterial and pulse pressure (MAP and PP) derived from supine BP were significantly associated with OH. Conclusions. OH should be assessed routinely in TIA clinics. MAP and PP may provide information on the predictability of OH. [ABSTRACT FROM AUTHOR]