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

Abstract

The overarching goal of the proposed project is to increase diagnosis and effective treatment of persons with Familial Hypercholesterolemia (FH). The proposed project aims to improve FH diagnosis by (1) using a validated machine learning tool in a large healthcare system (PennMedicine) to flag individuals at high risk of having FH; (2) employing effective interventions based on implementation science (IS) and behavioral economics (BE) to engage the healthcare system, clinicians, and patients to ensure that the diagnosis of FH is appropriately made; and (3) to improve the uptake of, and adherence to, evidence-based practices (EBP) for these patients, resulting in a reduction in LDL-C and ultimately improved CV outcomes. The project initiated on July 1, 2021 and multiple work streams have been initiated to achieve specific goals of Aim 1 and Aim 2.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 2023
Accession Number
AD1215020

Entities

People

  • Daniel Rader
  • Kevin Volpp

Organizations

  • University of Pennsylvania

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Algorithms
  • Big Data
  • Biomedical Research
  • Covid-19
  • Data Analysis
  • Delivery Of Health Care
  • Economics
  • Employment
  • Health Services
  • Machine Learning
  • Management Personnel
  • Materials
  • Medical Personnel
  • Models
  • Organizational Structure
  • Personnel Management
  • Prototypes
  • Standards
  • Telemedicine
  • Training

Readers

  • Life Cycle Cost Analysis
  • Mental Health of Military Veterans with Posttraumatic Stress Disorder (PTSD): Risk Factors, Prevalence, Symptoms, and Treatment.
  • Molecular and Cellular Biology

Technology Areas

  • AI & ML