Machine Learning to Understand Genetic and Clinical Factors Associated With the Pulse Waveform Dicrotic Notch - Abstract & Methods Summary

Aug 5, 2026

Upload by Eliana

Absence of a dicrotic notch on finger photoplethysmography (PPG) is an inexpensive trait linked to age and prevalent cardiovascular disease, yet its biological basis and predictive value across the trait continuum remain unclear. Using 169,787 UK Biobank participants, researchers modeled notch smoothness with machine learning to capture continuum variation. They then assessed heritability, genetic architecture, polygenic risk, and clinical associations for both absent-notch status and the derived continuous measure, linking the phenotype to vascular stiffness pathways.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Abstract

Background

Methods

Results

Conclusion

Introduction

UCSF UC San Francisco Previously Published Works Title Machine Learning to Understand Genetic and Clinical Factors Associated With the Pulse Waveform Dicrotic Notch. Permalink [https://escholarship.org/uc/item/1p3647x4](https://escholarship.org/uc/item/1p3647x4) Journal Circulation: Genomic and Precision Medicine, 16(1) Authors Cunningham, Jonathan Di Achille, Paolo Morrill, Valerie et al. Publication Date 2023-02-01 DOI 10.1161/CIRCGEN.121.003676 Peer reviewed [eScholarship.org](eScholarship.org) Powered by the California Digital Library University of California Author Manuscr ipt Author Manuscr ipt Author Manuscr ipt Author Manuscript | | HHS Public Access
Author manuscript
Circ Genom Precis Med. Author manuscript; available in PMC 2024 February 01. | | --- | --- | Published in final edited form as: Circ Genom Precis Med. 2023 February ; 16(1): e003676 . doi:10.1161/CIRCGEN.121.003676 . Machine Learning to Understand Genetic and Clinical Factors Associated with the Pulse Waveform Dicrotic Notch Jonathan W. Cunningham, MD, MPH 1,2,* , Paolo Di Achille, PhD3,* , Valerie N. Morrill, MS2 , Lu-Chen Weng, PhD2,4 , Seung Hoan Choi, PhD2 , Shaan Khurshid, MD, MPH2,5 , Victor Nauffal, MD 1,2 , James P Pirruccello, MD2,6 , Scott D. Solomon, MD 1 , Puneet Batra, PhD3 , Jennifer E. Ho, MD2,7 , Anthony A. Philippakis, MD, PhD3 , Patrick T. Ellinor, MD, PhD2,4,5 , Steven A. Lubitz, MD, MPH2,4,5 1Cardiovascular Division, Brigham & Women’s Hospital, Boston; 2Cardiovascular Disease Initiative, The Broad Institute of MIT & Harvard, Cambridge; 3 Data Sciences Platform, The Broad Institute of MIT & Harvard, Cambridge; 4Cardiovascular Research Center, Massachusetts General Hospital; 5 Demoulas Center for Cardiac Arrhythmias, Massachusetts General Hospital; 6 Division of Cardiology, Massachusetts General Hospital; 7CardioVascular Institute and Division of Cardiology, Department of Medicine, Beth Israel Deaconess Medical Center, Boston, MA Abstract Background: Absence of a dicrotic notch on finger photoplethysmography (PPG) is an easily ascertainable and inexpensive trait that has been associated with age and prevalent cardiovascular disease (CVD) . However, the trait exists along a continuum, and little is known about its genetic underpinnings or prognostic value for incident CVD. Methods: In 169,787 participants in the UK Biobank, we identified absent dicrotic notch on PPG and created a novel continuous trait reflecting notch smoothness using machine learning. Next, we determined the heritability, genetic basis, polygenic risk, and clinical relations for the binary absent notch trait and the newly derived continuous notch smoothness trait. Results: Heritability of the continuous notch smoothness trait was 7 .5%, compared with 5.6% for the binary absent notch trait. A genome-wide association study of notch smoothness identified 15 significant loci, implicating genes including NT5C2 (P=1 .2×10−26), IGFBP3 (P=4 . 8×10−18), Correspondence: Steven A. Lubitz, MD, MPH, Demoulas Center for Cardiac Arrhythmias & Cardiovascular Research Center, Massachusetts General Hospital, 55 Fruit Street, GRB 109, Boston, MA 02114, P:617-643-7339, F:617-726-3852, itzntri@mbuteghde.hqarvauallry[d.edu](d.edu). Supplemental Materials Supplemental Methods Supplemental Tables I–XIII Supplemental Figures I–VIII References20–38 Author Manuscr ipt Author Manuscr ipt Author Manuscr ipt Author Manuscript Cunningham et al. Page 2 and PHACTR1 (P=1 .4×10−13), compared with 6 loci for the binary absent notch trait. Notch smoothness stratified risk of incident myocardial infarction or coronary artery disease, stroke, heart failure, and aortic stenosis. A polygenic risk score for notch smoothness was associated with incident CVD and all-cause death in UK Biobank participants without available PPG data. Conclusion: We found that a machine learning derived continuous trait reflecting dicrotic not

FAQs

Why is the dicrotic notch on PPG clinically relevant?

Absence of the dicrotic notch on finger photoplethysmography is an easily measured, low-cost trait associated with age and prevalent cardiovascular disease. It is considered an indicator of arterial stiffness and coronary disease risk, though its underlying biology and event prediction require clarification.

How did the study use machine learning for PPG data?

The researchers trained a machine learning predictor on PPG waveforms to derive a continuous trait reflecting notch smoothness. Waveforms with absent or small notches received higher smoothness-trait values, while waveforms with larger notches received lower values.

What genetic findings were reported for notch smoothness?

Heritability for the continuous notch smoothness trait was 7.5%, higher than 5.6% for the binary absent-notch trait. A genome-wide association analysis for notch smoothness identified 15 significant loci, implicating genes including NT5C2, IGFBP3, and PHACTR1.

Aug 5, 2026

Upload by Eliana