Opening book details…
Can I read Antiracist Ai: A Machine Learning Model Using Electrocardiograms And Echocardiograms Can Detect Transthyretin Cardiac Amyloidosis And Decrease Racial Bias In Diagnostic Testing on EtoBox?
Antiracist Ai: A Machine Learning Model Using Electrocardiograms And Echocardiograms Can Detect Transthyretin Cardiac Amyloidosis And Decrease Racial Bias In Diagnostic Testing by Sneha S. Jain; Tony Sun; Kathleen Brown; Vijendra Ramlall; Nicholas Tatonetti; Noémie Elhadad; Fatima Rodriguez; Ronald Witteles; Mathew S. Maurer; Timothy Poterucha; Pierre Elias is a Medicine article available to read on EtoBox.
What is Antiracist Ai: A Machine Learning Model Using Electrocardiograms And Echocardiograms Can Detect Transthyretin Cardiac Amyloidosis And Decrease Racial Bias In Diagnostic Testing about?
Background: Transthyretin cardiac amyloidosis (ATTR-CA) disproportionately affects Black pts, who are diagnosed with more advanced phenotypes and experience worse outcomes than non-Black pts. Methods: Electrocardiogram (ECG), transthoracic echocardiography (TTE), and pyrophosphate (PYP) scanning utilization by race and ethnicity at a New York center was abstracted (2010)(2011)(2012)(2013)(2014)(2015)(2016)(2017)(2018)(2019)(2020)(2021). A machine learning (ML) model, ATTRACTnet, was trained using ECG waveforms and TTE measurements to detect ATTR-CA (as diagnosed by a positive PYP scan) using Equalized Odds to ensure equivalent accuracy in Black/non-Black pts. The model was assessed using 5-fold cross validation (Train: 6894 ECGs/351 pts, Validation: 1943 ECGs/123 pts). ATTRACTnetʼs performance was compared to a traditional (non-ML) risk calculator, the Mayo ATTR-CA Score (TCAS), then run on pts at risk of ATTR-CA (TCAS≥6) but who had not undergone PYP scan (13598 pts). Results: Pts undergoing PYP scan were 80% Non-Hispanic White (NHW) compared to 43% for ECG and 52% for TTE (Figure). Among pts with PYP scans, ATTRACTnet could detect ATTR-CA (AUROC 0.90) with similar accuracy in Bla
Who reads Antiracist Ai: A Machine Learning Model Using Electrocardiograms And Echocardiograms Can Detect Transthyretin Cardiac Amyloidosis And Decrease Racial Bias In Diagnostic Testing?
It is typically read by researchers, students, and practitioners in Medicine.
- Author
- Sneha S. Jain; Tony Sun; Kathleen Brown; Vijendra Ramlall; Nicholas Tatonetti; Noémie Elhadad; Fatima Rodriguez; Ronald Witteles; Mathew S. Maurer; Timothy Poterucha; Pierre Elias
- Publisher
- Elsevier BV
- Published
- 2023
- Language
- EN
- Field
- Medicine (Health Sciences)