Related Experiment Video
Updated: Sep 10, 2025
Targeted Next-generation Sequencing and Bioinformatics Pipeline to Evaluate Genetic Determinants of Constitutional Disease
Published on: April 4, 2018
Electronic health records-based algorithms to screen for U.S. Centers for Disease Control and Prevention tier 1
William R Harris1, Marianna S Hernandez2, Khanh N H Ngo3
1Harvard Medical School, Boston, MA, 02115, United States.
Insights
Electronic health record (EHR) algorithms show promise for identifying genetic conditions like familial hypercholesterolemia (FH). Machine learning models outperform rule-based ones, but more research is needed for hereditary breast and ovarian cancer (HBOC) and Lynch syndrome.
Area of Science:
- Genomic Medicine
- Clinical Informatics
- Public Health Genomics
Background:
- Missed diagnoses of genetic conditions, including familial hypercholesterolemia (FH), hereditary breast and ovarian cancer (HBOC), and Lynch syndrome, pose a significant clinical challenge.
- These conditions are designated as Tier 1 genomic applications by the U.S. Centers for Disease Control and Prevention (CDC), highlighting their public health importance.
Purpose of the Study:
- To conduct a scoping review of evidence on the utilization of electronic health record (EHR)-based algorithms for identifying individuals with FH, HBOC, and Lynch syndrome.
- To summarize the performance and implementation outcomes of these EHR-based algorithms.
Main Methods:
- A comprehensive scoping review was performed following the JBI Manual for Evidence Synthesis and PRISMA-ScR guidelines.
- Searches were conducted in Ovid MEDLINE, Embase, and Web of Science up to October 2024 for studies evaluating EHR algorithms for FH, HBOC, or Lynch syndrome detection.
- Eligible studies focused on algorithm performance in detecting confirmed cases or on implementation outcomes in unselected populations.
Main Results:
- Twenty-two studies met the inclusion criteria, with the majority (20/22) focusing on FH.
- Machine learning algorithms demonstrated superior performance compared to rule-based algorithms for FH detection (AUROC range 0.78-0.95).
- Implementation studies for FH reported positive predictive values between 11% and 67%. Limited evidence (two studies) existed for HBOC and Lynch syndrome, utilizing rule-based algorithms with low sensitivity.
Conclusions:
- Machine learning models show consistent superiority over rule-based algorithms for identifying genetic conditions based on clinical criteria.
- While EHR-based screening holds potential for early identification of CDC Tier 1 genetic conditions, advancements in both technical aspects and implementation strategies are crucial for improving patient care.
- Further research is urgently needed to develop and validate effective EHR algorithms for HBOC and Lynch syndrome.
Objective:
Missed diagnosis of genetic conditions is a persistent challenge in clinical care, particularly for familial hypercholesterolemia (FH), hereditary breast and ovarian cancer (HBOC), and Lynch syndrome-conditions designated by the U.S. Centers for Disease Control and Prevention (CDC) as Tier 1 genomic applications. This scoping review summarizes evidence on the use of electronic health record (EHR)-based algorithms to identify individuals with these conditions.
Materials And Methods:
We conducted a scoping review using the JBI Manual for Evidence Synthesis and reported results according to PRISMA-ScR guidelines. We searched Ovid MEDLINE, Embase, and Web of Science through October 2024 for studies evaluating EHR-based algorithms to identify individuals with FH, HBOC, or Lynch syndrome. Eligible studies addressed (1) performance of algorithms in detecting clinically or genetically confirmed cases or (2) outcomes from the implementation of algorithms in unselected populations with follow-up to identify new diagnoses.
Results:
Of 598 articles screened, 22 met inclusion criteria. Most studies (20/22) focused on FH. Fourteen FH studies assessed algorithm performance, and 7 reported prospective implementation. FH algorithm performance varied widely (AUROC range 0.78-0.95), with machine learning models outperforming rule-based approaches. Implementation studies reported positive predictive values ranging from 11% to 67%. Only two studies addressed HBOC or Lynch syndrome, both using rules-based algorithms with limited sensitivity.
Discussion:
Machine learning models consistently outperform rules-based algorithms relying on clinical criteria, but limited evidence exists for HBOC and Lynch syndrome.
Conclusions:
Early identification of CDC Tier 1 genetic conditions through EHR-based screening algorithms holds promise but will require both technical and implementation advances to realize improved patient care and outcomes.
More Related Videos
11:35Screening for Functional Non-coding Genetic Variants Using Electrophoretic Mobility Shift Assay EMSA and DNA-affinity Precipitation Assay DAPA
Published on: August 21, 2016
09:30Pre-Implantation Genetic Testing for Aneuploidy on a Semiconductor Based Next-Generation Sequencing Platform
Published on: August 17, 2022
Related Concept Videos
01:12Statistical Software for Data Analysis and Clinical Trials
01:11Genome-wide Association Studies-GWAS
GWAS does not require the identification of the target gene involved in...