The FDA offered a limited amount of bamlanivimab to ChristianaCare, but the organization anticipated high demand for monoclonal antibody therapy. Depending upon the organization’s success in adhering to eligibility criteria and the effectiveness of its distribution efforts, the FDA would make additional doses available.
ChristianaCare was challenged to rapidly identify and reach out to high-risk patients who were COVID-19 positive, met the strict FDA criteria, and qualified for the therapy outlined in the emergency use authorization. The organization also desired monoclonal antibody therapy distribution be equitable. ChristianaCare wanted to ensure that it was able to identify all patients who met the criteria and wanted to avoid inadvertently developing processes that offered the therapy to a privileged few or only to the well insured.
ChristianaCare leveraged the Health Catalyst® Data Operating System (DOS™) platform and a robust suite of analytics applications, including data science tools and predictive analytics, to identify patients who meet the requirements for authorized use of bamlanivimab. The organization developed a machine learning model to stratify the risk of hospitalization in outpatients with mild-to-moderate COVID-19 who meet eligibility requirements.
Each day, the machine learning model identifies patients with an increased likelihood of hospital admission. The model assigns a risk score to each patient, identifies the symptomatic patients at the highest risk of admission, and automates bamlanivimab eligibility, efficiently identifying outpatients who:
The prioritized patient list is then sent to care coordinators. Care coordinators contact eligible patients, perform the initial screening to assess the patients’ symptoms, and confirm if they have an immunosuppressive disease, which requires additional eligibility criteria and provider input. Eligible patients who express interest in treatment are referred to ChristianaCare’s virtual practice. The organization uses secure text messaging to communicate with team members when an eligible patient desires treatment. Two providers independently review the eligibility criteria, review the patient data, and confirm if the patient meets the requirements defined by the FDA emergency use authorization.
Care coordinators then reach back out to the patient and schedule them for their bamlanivimab infusion. ChristianaCare reconfigured space to create an infusion center for patients receiving bamlanivimab, ensuring patients with COVID-19 are kept separate from patients receiving chemotherapy or other infusions. ChristianaCare uses the data platform to track the number of patients receiving monoclonal antibodies for COVID-19 and the impact of treatment on outcomes, including COVID-19 related hospitalizations and emergency room visits within 28 days of treatment.
ChristianaCare was able to rapidly identify high-risk patients with COVID-19 who qualified for therapy, achieving the following results:
“Leveraging the Health Catalyst data science tools to stratify the risk and automate the identification of eligible patients allowed us to distribute monoclonal antibody therapy to our patients with COVID-19 efficiently and equitably. It is available to anyone who meets the criteria, often within hours of their positive COVID-19 test.”
Ed Ewen, MD, Director, Clinical Data and Analytics, Center for Strategic Information Management
ChristianaCare’s outcomes data for patients receiving bamlanivimab will inform future therapeutics that can be used in the battle against COVID-19.