Biomarkers unrelated to myocardial necrosis, such as cystatin C, copeptin, and mid-regional pro-adrenomedullin (MR-proADM), showed promise for cardiovascular risk prediction. Knowing whether they are comparable to cardiac biomarkers such as high-sensitive cardiac-troponin T (hs-cTnT) or N-terminal pro-Brain natriuretic peptide (NT-proBNP) in elderly patients with acute non-massive pulmonary embolism (NMPE) remains elusive. This study aims at comparing the prognostic accuracy of cardiac and non-cardiac biomarkers in patients with NMPE aged ≥65 years over time. In the context of the SWITCO65+ cohort, we evaluated 227 elderly patients with an available blood sample taken within one day from diagnosis. The primary study endpoint was defined as PE-related mortality and the secondary endpoint as PE-related complications. The biomarkers’ predictive ability at 1, 3, 12 and 24 months was determined using C-statistics and Cox regression. For both study endpoints, C-statistics (95% confidence interval) were stable over time for all biomarkers, with the highest value for hs-cTnT, ranging between 0.84 (0.68–1.00) and 0.80 (0.70–0.90) for the primary endpoint, and between 0.74 (0.63–0.86) and 0.65 (0.57–0.73) for the secondary endpoint. For both study endpoints, cardiac biomarkers were found to be independently associated with risk, NT-proBNP displaying a negative predictive value of 100%. Among non-cardiac biomarkers, only copeptin and MR-proADM were independent predictors of PE-related mortality but they were not independent predictors of PE-related complications, and displayed lower negative predictive values. In elderly NMPE patients, cardiac biomarkers appear to be valuable prognostic to identify very low-risk individuals.Trial Registration: ClinicalTrials.gov NCT00973596

No abstract

Pharmacovigilance improves patient safety by detecting and preventing adverse drug events. However, challenges exist that limit adverse drug event detection, resulting in many adverse drug events being underreported or inaccurately reported. One challenge includes having access to large data sets from various sources including electronic health records and wearable medical devices. Artificial intelligence, including machine learning methods, such as natural language processing and deep learning, can detect and extract information about adverse drug events, thus automating the pharmacovigilance process and improving the surveillance of known and documented adverse drug events. In addition, with the increased demand for telehealth services, for managing both acute and chronic diseases, artificial intelligence methods can play a role in detecting and preventing adverse drug events. In this review, we discuss two use cases of how artificial intelligence methods may be useful to improve the quality of pharmacovigilance and the role of artificial intelligence in telehealth practices.