Implementation of a Machine-Learning Algorithm in the Electronic Health Record for Targeted Screening for Familial Hypercholesterolemia: A Quality Improvement Study

Abstract

GOALS AND VISION OF THE PROGRAMFamilial hypercholesterolemia (FH) is a lipid disorder that results in elevated serum LDL (low-density lipoprotein) cholesterol and markedly increased cardiovascular risk. 1,2 Classical observational data suggest that prevalence of heterozygous FH is ≈1:250, and it is estimated that only 10% of patients with FH in the United States have been diagnosed. 1,2 Early and timely diagnosis of FH reduces cardiovascular risk, which heightens the need for targeted screening. 2,3 To increase the detection rates of FH, several population and targeted screening strategies have been recommended and implemented. For example, mass genetic testing in the workplace and cascade genetic screening have been used in a few settings in the United States. Machine learning models trained on electronic medical record (EMR) data represent another promising approach to identify high-risk populations enriched with FH patients, but deployment of machine learning algorithms in cardiovascular medicine has been a historically challenging process. 4 Recently, The Familial Hypercholesterolemia Foundation developed the flag, identify, network, deliver FH (FIND FH) machine learning algorithm to identify yet-to-be diagnosed FH within millions of individual EMRs. 5 FIND FH is a random forest-based algorithm trained on deidentified, structured EMR data from 939 individuals who were diagnosed with FH at specialty lipid clinics. The model selects 75 features ranging from patient demographics to prescriptions and laboratory data to predict the probability of a patient having FH. In the original study, the model demonstrated robust performance in predicting patients with higher risk of FH at both national (170 416 201 patients) and single health care system (173 733 patients from Oregon Health & Science University) levels, identifying 87% and 77% of patients in 2 independent cohorts as having a high enough suspicion of FH to warrant further evaluation and treatment (likely FH). 5 At the University of Pennsylvania Healthcare System (UPHS), an internal validation of 414 patients flagged by FIND FH revealed that 29% of patients with FIND FH score >0.2 had probable or definite FH (unpublished data). However, no prior studies involving FIND FH had developed an implementation framework, complete with an outreach process, to integrate the algorithm into clinical care.The purpose of this study was to implement an observational trial of a HIPAAcompliant, IRB-approved screening and outreach program based on FIND FH as a case study of how machine learning algorithms could be deployed and utilized in a large health care system. Through this initiative, we assessed (1) the diagnostic rate of FH among clinical results from patients flagged by the algorithm, (2) the treatment of flagged patients in a preventive cardiology setting, and (3) barriers in implementation of the algorithm to inform future quality improvement initiatives.

Soft Tissue Feature Tracking Based on Deep Matching Network

“…The algorithm based on data learning can not only learn the feature detector like Quarknetworks, but also learn the feature descriptor. With the improvement of machine learning [20][21][22][23][24], Simoserra et al proposed Deepdesc [25] for key point descriptor learning. This method uses a convolutional neural network to learn the discriminant representation of image blocks (patches), trains a Siamese network with paired inputs, and processes a large number of paired image blocks by combining the random extraction of training sets and the mining strategy for patch pairs that are difficult to classify.…”

Applications of machine learning in familial hypercholesterolemia

“…They found that 87% and 77% of the individuals were classified as probable or definite FH, respectively, demonstrating the accuracy and efficiency of the model. In an observational study, Sheth et al prospectively implemented the FIND FH model to screen for FH ( 21 ). Based on EHRs from the University of Pennsylvania Healthcare System ( n = 1,607,606), there were 8,614 patients with a FIND FH score >0.2, suggesting possible FH.…”

Developing Patient-Centered Real-World Evidence: Emerging Methods Recommendations From a Consensus Process

“…51,52 The study findings were also part of a larger research plan to deploy the algorithm to directly improve patient care in a large healthcare system. 53…”