Electronic health records (EHRs) are an important source of data for detection of adverse drug reactions (ADRs). However, adverse events are frequently due not to medications but to the patients’ underlying conditions. Mining to detect ADRs from EHR data must account for confounders. We developed an automated method using natural-language processing (NLP) and a knowledge source to differentiate cases in which the patient’s disease is responsible for the event rather than a drug. Our method was applied to 199,920 hospitalization records, concentrating on two serious ADRs: rhabdomyolysis (n = 687) and agranulocytosis (n = 772). Our method automatically identified 75% of the cases, those with disease etiology. The sensitivity and specificity were 93.8% (confidence interval: 88.9-96.7%) and 91.8% (confidence interval: 84.0-96.2%), respectively. The method resulted in considerable saving of time: for every 1 h spent in development, there was a saving of at least 20 h in manual review. The review of the remaining 25% of the cases therefore became more feasible, allowing us to identify the medications that had caused the ADRs.

A725anxiety/depression). Univariate regression analysis was used to determine whether covariates should be included in the multivariate model using an a priori specified criterion (p≤ 0.2). Correlation coefficients were estimated to detect the presence of significant correlations between these covariates. Multivariate linear regression models were estimated using robust (Huber-White) standard errors. Results: A total of 595 people completed the survey in full and of these 541 completed the detailed EQ-5D-5L questionnaire. The mean age of the sample was 47.0 (SD: 12.0) years and 71% were female. The median duration of disease was 6 (IQR: 4-8) years. Of the sample, 57.7%, 35.5%, and 6.8% reported being in a 'mild', 'moderate', and 'severe' disease state, respectively. The mean EQ-5D-5L score among the sample was 0.69 (SD: 0.24). In the multivariate regression analysis, increasing disease severity, being unemployed, being male, and older age were all statistically significantly associated with a reduction in quality of life (all p< 0.05). ConClusions: Multiple Sclerosis is associated with a significant decrease in HRQoL. In particular, employment status and disease severity were statistically significantly associated with EQ-5D scores, which may provide for useful information for clinicians and/ or policy-makers.

More research is needed to identify the direct, and indirect, relationships between IPF events and the costs they generate. This would help to further evaluate the area of need for future health technologies and to understand what events should be targeted to reduce the global economic burden of IPF.

Evolving standards of care will lead to increased interest by stakeholders, on the methods used to measure QOL in infants and children across all types of SMA. Generic tools may not adequately capture QOL changes in SMA, especially given the age group affected by the disease. Further research is required to explore the scope for a disease-focused approach.