Improving Diagnosis and Clinical Management of Familial Hypercholesterolemia Through Integrated Machine Learning, Implementation Science, and Behavioral Economics (BEAT FH)

Improving Diagnosis and Clinical Management of Familial Hypercholesterolemia Through Integrated Machine Learning, Implementation Science, and Behavioral Economics

Improving Diagnosis and Clinical Management of Familial Hypercholesterolemia Through Integrated Machine Learning, Implementation Science, and Behavioral Economics

The goal of this study is to identify individuals at high risk of FH, and to encourage the appropriate diagnosis and treatment of individuals at high risk of FH through the use of implementation science and behavioral economics principles. Phase 1: Applying the FIND FH tool to the health system EHR and gathering data for pilot development; Phase 2: Pilot development and implementation; Phase 3: Conduct a large-scale pragmatic trial consistent with recommendations and learnings from the pilots in Phase 2

Phase 1: Aim 1: Adjusting and refining the application of the FIND FH tool to the UPHS EHR database Aim 2: Identifying the barriers and facilitators to making a diagnosis of FH and initiating or intensifying therapy for individuals with FH through qualitative interviews with clinicians and patients and creating a behavioral roadmap to inform the implementation approaches to test in the pilots Phase 2: Aim 1: Co-design implementation strategies using behavioral economics in partnership with the Family Heart Foundation Aim 2: Pilot implementation strategies with an enrollment goal of 80 patients total (40 per pilot) who have been flagged by the FIND FH tool as having probable FH to ascertain feasibility, acceptability, and appropriateness Phase 3: Conduct a large-scale pragmatic trial consistent with recommendations and learnings from the pilots in Phase 2

For the pilots, for patients with a PCP within the healthcare system, we are testing 2 different centralized referral models to increase the # of patients that see a lipid specialist (active choice vs default). For patients without a PCP within the health system, we are testing out health system mediated outreach vs Family Heart Foundation mediated outreach in order to increase the number of patients who make an appointment with a lipid specialist.

Pilot 1 is examining ways to get patients without a primary care physician within the UPHS health system to schedule a visit with a lipid specialist for a formal evaluation of FH.

Pilot 2 is examining ways to increase physician referrals to preventive cardiology, and increase patient visits with a lipid specialist for a formal evaluation of FH.

For patients with a Penn PCP, we are testing the two different centralized referral mechanisms to increase the number of referrals to preventive cardiology (active choice vs default/opt out referrals) For active choice: A non-interruptive In Basket alert will be delivered to PCPs that have patients that have been screened as positive with the FIND FH tool and recommends a referral to a lipid specialist. PCPs will have the choice of either accepting the referral or declining the referral. If they do not take action on the In Basket alert, the referral will stay in their In Basket. For default/opt out: A non-interruptive In Basket alert will be delivered to PCPs that have patients that have been screened as positive with the FIND FH tool and recommends a referral to a lipid specialist. Not interacting with the BPA or accepting the BPA will indicate that the referral to a lipid specialist should be placed.

Testing health care system mediated outreach vs Family Heart Foundation mediated outreach to see which type of outreach might be most effective at getting patients to schedule an appointment with a lipid specialist

For patients with a PCP within the UPHS health system, we want to see which centralized referral options leads to a greater rate of referrals to preventive cardiology.

For all patients, we want to increase the # of scheduled appointments and examine the rate of actual patient visits with a lipid specialist for their formal evaluation of FH.

Inclusion Criteria: Must be a patient at Penn Medicine Must have been flagged by the FIND FH tool as having a high probability of FH Exclusion Criteria: Already have been clinically diagnosed with FH using the proper ICD-10 code