Clinic-based or community-based interventions can improve adherence to guideline-directed medication therapies (GDMTs) among patients with heart failure (HF). However, opportunities for such interventions are frequently missed, as providers may be unable to recognise risk patterns for medication non-adherence. Machine learning algorithms can help in identifying patients with high likelihood of non-adherence. While a number of multilevel factors influence adherence, prior models predicting non-adherence have been limited by data availability. We have established an electronic health record (EHR)-based cohort with comprehensive data elements from multiple sources to improve on existing models. We linked EHR data with pharmacy refill data for real-time incorporation of prescription fills and with social determinants data to incorporate neighbourhood factors.

Patients seen at a large health system in New York City (NYC), who were >18 years old with diagnosis of HF or reduced ejection fraction (

Among 39 963 patients in the cohort, the average age was 73±14 years old, 44% were female and 48% were current/former smokers. The common comorbid conditions were hypertension (77%), cardiac arrhythmias (56%), obesity (33%) and valvular disease (33%). During the study period, 33 606 (84%) patients had an active prescription of beta blocker, 32 626 (82%) had ACEi/ARB/ARNI, 11 611 (29%) MRA and 7472 (19%) SGLT2i. Ninety-nine per cent were from urban metropolitan areas.

We will use the established cohort to develop a machine learning model to predict medication adherence, and to support ancillary studies assessing associates of adherence. For external validation, we will include data from an additional hospital system in NYC.

Determine the prevaccination healthcare impact of COVID-19 in patients with systemic lupus erythematosus (SLE) in England.

Retrospective cohort study of adult patients with SLE from 1 May to 31 October 2020.

Clinical Practice Research Datalink (CPRD) Aurum and Hospital Episode Statistics (HES) databases from general practitioners across England combining primary care and other health-related data.

Overall, 6145 adults with confirmed SLE diagnosis ≥1 year prior to 1 May 2020 were included. Most patients were women (91.0%), white (67.1%), and diagnosed with SLE at age

Demographics and clinical characteristics were compared. COVID-19 severity was determined by patient care required and procedure/diagnosis codes. COVID-19 cumulative incidence, hospitalisation rates, lengths of stay and mortality rates were determined and stratified by SLE and COVID-19 severity.

Of 6145 patients, 3927 had mild, 1288 moderate and 930 severe SLE at baseline. The majority of patients with moderate to severe SLE were on oral corticosteroids and antimalarial treatments. Overall, 54/6145 (0.88%) patients with SLE acquired and were diagnosed with COVID-19, with 45 classified as mild, 6 moderate and 3 severe COVID-19. Cumulative incidence was higher in patients with severe SLE (1.4%) compared with patients classified as mild (0.8%) or moderate (0.8%). Ten COVID-19-specific hospital admissions occurred (n=6 moderate; n=4 severe). Regardless of COVID-19 status, hospital admission rates and length of stay increased with SLE severity. Of 54 patients with SLE diagnosed with COVID-19, 1 (1.9%) COVID-19-related death was recorded in a patient with both severe SLE and severe COVID-19.

SLE severity did not appear to impact COVID-19 outcomes in this study. The COVID-19 pandemic is evolving and follow-up studies are needed to understand the relationship between COVID-19 and SLE.