Increasingly educational providers are being challenged to use their data stores to improve teaching and learning outcomes for their students. A common source of such data is learning management systems which enable providers to manage a virtual platform or space where learning materials and activities can be provided for students to engage with. This study investigated whether data from the learning management system Moodle can be used to predict academic performance of students in a blended learning further education setting. This was achieved by constructing measures of student activity from Moodle logs of further education courses. These were used to predict alphabetic student grade and whether a student would pass or fail the course. A key focus was classifiers that could predict likelihood of failure from data available early in the term. The results showed that classifiers built on all course data predicted student grade moderately well (accuracy= 60.5%, kappa = 0.43) and whether a student would pass or fail very well (accuracy= 92.2%, kappa=0.79). However, classifiers built on the first six weeks of data did not predict failing students well. Classifiers trained on the first ten weeks of data improved significantly on a no-information rate (p<0.008) though more than half of failing students were still misclassified. The evidence indicates that measures of Moodle activity on further education courses could be useful as part of on an early-warning system at ten weeks.

Introduction:International reports suggest there have been prehospital delays for time-sensitive emergencies like stroke and TIA during the COVID-19 pandemic. The aim was to investigate the impact of the COVID-19 pandemic on ambulance times and emergency call volume for adults with suspected stroke and TIA in Ireland.Method:We conducted a retrospective cohort study of patients ≥ 18 years with suspected stroke/TIA, based on data from the National Ambulance Service. We included all cases assigned code 28 (suspected stroke/TIA) by the emergency call-taker, from 2018-2021. We compared ambulance times and emergency call volume by week, the four COVID-19 waves (defined by the Health Protection Surveillance Centre) and annually. The COVID-19 period was from March 1, 2020 - December 19, 2021 and the pre-COVID-19 period January 1, 2018 - February 29, 2020. Continuous variables were compared with t-tests and categorical variables with Pearson’s χ2 tests.Results:40,012 cases were included: 20,281 in the pre-COVID-19 period and 19,731 in the COVID-19 period. Mean patient age significantly decreased between the two periods, from 71 years (±16.5) to 69.8 years (±17.1); p<0.001. Mean ambulance response time increased between the two periods from 17 minutes 31 seconds to 18 minutes 59 seconds (p<0.001). The number of cases with symptom onset to emergency call time of >4 hours significantly increased from 5,581 to 6,060 during the COVID-19 period (p<0.001). Mean calls/day increased from 25.1/day to 30.1/day during the COVID-19 period.Conclusion:Early findings from the study suggest an increase in call volume for stroke/TIA between the COVID-19 and pre-COVID-19 periods. An increase in response times during the same periods was also found. We concluded that longer symptom-to-call times indicate a change in healthcare-seeking behavior. Sustaining high levels of compliance with stroke code protocols is crucial during healthcare crises. Future research will involve further analysis including controlling for confounders.

An effective pain management strategy requires understanding of the epidemiology of pain in the population of interest and accurate measurement upon which to base quality improvement plans. The aims of this study were to estimate the incidence of pain in the prehospital setting and to explore features that impact on (1) documentation of pain; (2) severity of pain reported by patients. This retrospective cohort study included 212,401 care episodes attended by National Ambulance Service practitioners during 2020. Descriptive analysis of patient and care episode characteristics and regression analyses for the outcomes pain recorded and severity of pain were performed. We also used text pattern-matching of the notes field to estimate the proportion of patients in pain for whom a pain score assessment had not been documented. Sixty-five percent of all patients had a pain score documented and 29.5% were in pain (11% in severe pain). Likelihood of pain being recorded was most strongly associated with: Glasgow Coma Scale (GCS) Score, working diagnosis of the patient, location of the incident, and patient age. Likelihood of pain severity was most strongly associated with: transport status of patient, GCS score, and patient age. We treated missing data as a separate category and found consistent associations between the outcomes and missing data. We also found that pain was a symptom in approximately 15% of cases where no formal pain score assessment was documented. The data showed associations between routinely collected variables and the likelihood of pain recording and pain severity. Our findings also demonstrate the impact of missing data. To mitigate missing data impact, we suggest that EMS agencies consider making pain score assessment a mandatory requirement of their reporting for every patient. We also recommend that services report the extent and impact of missing data when measuring clinical performance.