Integrated Machine Learning Approach for High Cholesterol

(BEAT FH Trial)

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: University of Pennsylvania

Disqualifiers: Diagnosed FH, Lipid specialist, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

750 Participants Needed

Trial Summary

What is the purpose of this trial?

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

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

What data supports the effectiveness of this treatment for high cholesterol?

Research shows that using decision-support tools in electronic medical records can improve the management of high cholesterol by helping doctors follow guidelines more effectively. Additionally, interventions that involve patient activation and physician support have been shown to improve cholesterol screening and treatment adherence. ^{1 2 3 4 5}

Is the Integrated Machine Learning Approach for High Cholesterol safe for humans?

The research articles do not provide specific safety data for the Integrated Machine Learning Approach for High Cholesterol. However, they discuss the safety of statins, a common cholesterol-lowering medication, noting that most primary care providers believe statins can cause muscle pain and a minority believe they can cause diabetes. These side effects are often discussed with patients. ^{1 5 6 7 8}

How does this treatment for high cholesterol differ from other treatments?

This treatment uses an integrated machine learning approach to improve the detection and management of high cholesterol by incorporating clinical decision support tools into electronic health records, which helps clinicians identify and manage patients more efficiently compared to traditional methods. ^{9 10 11 12 13}

Eligibility Criteria

This trial is for patients at Penn Medicine who are identified by the FIND FH tool as likely having Familial Hypercholesterolemia (FH), but have not been clinically diagnosed with it. It's aimed at those who may be at high risk of this condition, which involves very high cholesterol levels.

Inclusion Criteria

You have been identified as having a high chance of having familial hypercholesterolemia (FH) by a special screening tool.

Must be a patient at Penn Medicine

Exclusion Criteria

Already have been clinically diagnosed with FH using the proper ICD-10 code

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Phase 1: Data Gathering

Applying the FIND FH tool to the health system EHR and gathering data for pilot development

8 weeks

Phase 2: Pilot Development and Implementation

Co-design and pilot implementation strategies using behavioral economics with an enrollment goal of 80 patients

12 weeks

Phase 3: Large-scale Pragmatic Trial

Conduct a large-scale pragmatic trial consistent with recommendations and learnings from the pilots in Phase 2

24 weeks

Follow-up

Participants are monitored for safety and effectiveness after treatment

4 weeks

Treatment Details

Interventions

• Testing centralized referral mechanisms for PCPs
• Testing out patient outreach methods

Trial Overview The study tests new ways to find and manage FH using a machine learning tool within electronic health records. It includes refining referral processes for primary care providers and exploring patient outreach methods across three phases: data gathering, pilot development, and a large-scale pragmatic trial.

Participant Groups

Group I: Patients without a primary care physician within the UPHS health system Experimental Treatment 1 Intervention

Patients without a primary care physician within the UPHS health system will receive direct outreach from the study team to invite them to schedule a visit with a lipid specialist for a formal evaluation of FH.

Group II: Patients with a primary care physician within the UPHS health system Experimental Treatment 2 Interventions

For patients with a primary care physician within the UPHS health system, their primary care physicians will be asked to review and sign physician referrals to a lipid specialist and invite patients to schedule a visit with a lipid specialist for a formal evaluation of FH.

Who Is Running the Clinical Trial?

University of Pennsylvania

Lead Sponsor

Trials

2,118

Recruited

45,270,000+

Family Heart Foundation

Collaborator

Trials

3

Recruited

1,600+

Northwestern University

Collaborator

Trials

1,674

Recruited

989,000+

Findings from Research

The pharmacist-led SMASH intervention significantly reduced potentially hazardous prescribing rates by 40.7% after 12 months in 43 general practices serving over 235,000 people, demonstrating its efficacy in improving medication safety.

While the intervention also led to a 22.0% reduction in inadequate blood-test monitoring at 24 weeks, this improvement was not sustained at 12 months, indicating a need for ongoing monitoring in this area.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Evaluation of a pharmacist-led actionable audit and feedback intervention for improving medication safety in UK primary care: An interrupted time series analysis. Peek, N., Gude, WT., Keers, RN., et al.[2023]

References

1. United States pubmed.ncbi.nlm.nih.gov

Improving adherence to dyslipidemia medication guidelines in hospitalized diabetic patients using a technology-assisted pharmacist intervention. [2016]

2. England pubmed.ncbi.nlm.nih.gov

Optimisation of lipids for prevention of cardiovascular disease in a primary care. [2019]

3. United States pubmed.ncbi.nlm.nih.gov

Management of high blood cholesterol by primary care physicians: diffusion of the National Cholesterol Education Program Adult Treatment Panel guidelines. [2019]

4. United States pubmed.ncbi.nlm.nih.gov

Impact of decision support in electronic medical records on lipid management in primary care. [2016]

5. United States pubmed.ncbi.nlm.nih.gov

Translating cholesterol guidelines into primary care practice: a multimodal cluster randomized trial. [2021]

6. United States pubmed.ncbi.nlm.nih.gov

Evaluation of a pharmacist-led actionable audit and feedback intervention for improving medication safety in UK primary care: An interrupted time series analysis. [2023]

7. England pubmed.ncbi.nlm.nih.gov

Association of Primary Care Providers' Beliefs of Statins for Primary Prevention and Statin Prescription. [2021]

8. England pubmed.ncbi.nlm.nih.gov

Shared Decisions: A Qualitative Study on Clinician and Patient Perspectives on Statin Therapy and Statin-Associated Side Effects. [2023]

9. Switzerland pubmed.ncbi.nlm.nih.gov

Clinician Perspectives on Clinical Decision Support for Familial Hypercholesterolemia. [2023]

10. Germany pubmed.ncbi.nlm.nih.gov

Barriers to the identification of familial hypercholesterolemia among primary care providers. [2020]

11. Switzerland pubmed.ncbi.nlm.nih.gov

An Implementation Science Framework to Develop a Clinical Decision Support Tool for Familial Hypercholesterolemia. [2020]

12. Germany pubmed.ncbi.nlm.nih.gov

Effect of a Novel Clinical Decision Support Tool on the Efficiency and Accuracy of Treatment Recommendations for Cholesterol Management. [2022]

13. United States pubmed.ncbi.nlm.nih.gov

Dyslipidemia treatment guidelines and management systems in Kaiser Permanente. [2019]