Logo

American Heart Association

  72
  1


Final ID: Mo030

Deep learning based multi-omics model for prediction of outcomes in HFpEF and HFmrEF'

Abstract Body: Introduction:
Heart failure with preserved ejection fraction (HFpEF) presents a unique challenge in cardiology due to its diverse etiology and clinical presentation. Our study introduces a cutting-edge integrated deep learning model that combines multi-dimensional datasets, encompassing genetic variants from GWAS, cardiac structural and functional assessments from MRI, and electrophysiological data from ECGs, along with comorbidity profiles including CKD and LFT.
Research Questions:
Can a deep learning model that integrates multi-dimensional datasets accurately predict HFpEF risk?
How does the inclusion of different types of data (genetic, MRI, comorbidity) affect the model's predictive accuracy?
Goals:
To develop a deep learning model that accurately predicts HFpEF risk
To assess the impact of different types of data on the model's predictive accuracy.
Methods:
The model employs a graph convolutional multi-model deep learning approach to dissect the intricate interplay between genetic variants from GWAS, cardiac structural and functional assessments from MRI, electrophysiological data from ECGs, and comorbidity profiles including CKD and LFT.
Results:
The baseline genetic model achieved a PRS of 2.04 and an outcome accuracy of 81%. The incorporation of MRI features improved the outcome accuracy to 85.91%. The inclusion of comorbidities such as CKD and T2D resulted in the highest outcome accuracy of 88.57%.
Discussion: The results suggest that the inclusion of MRI features and comorbidities improves the model's predictive accuracy. This model holds significant promise for clinical adoption and the advancement of personalized treatment strategies.
  • Fisch, Sudeshna  ( Pfizer , Cambridge , Massachusetts , United States )
  • Jha, Alokkumar  ( Weill Cornell Medicine , New York , New York , United States )
  • Author Disclosures:
    Sudeshna Fisch: DO have relevant financial relationships ; Employee:Pfizer:Active (exists now) | Alokkumar Jha: DO NOT have relevant financial relationships
Meeting Info:

Basic Cardiovascular Sciences

2024

Chicago, Illinois

Session Info:

Poster Session and Reception I

Monday, 07/22/2024 , 04:30PM - 07:00PM

Poster Session and Reception

More abstracts on this topic:
Association between Alcohol Consumption and the Risk of Cardiovascular Events by Renal Function Status in Japanese Community Dwellers

Hirata Aya, Sugiyama Daisuke, Okamura Tomonori, Takebayashi Toru, Harada Sei, Iida Miho, Miyagawa Naoko, Matsumoto Minako, Shibuki Takuma, Toki Ryota, Edagawa Shun, Kuwabara Kazuyo

A Multi-Tier, Natural-Language Processing Framework to Automate Labeling of Acute Cerebrovascular Events From Radiology Reports and Diagnosis Codes

Erekat Asala, Stein Laura, Delman Bradley, Karp Adam, Kupersmith Mark, Kummer Benjamin

More abstracts from these authors:
Treatment of Human Engineered Heart Tissue with Serum from Cancer Patients with Clonal Hematopoiesis of Indeterminate Potential Cytokine Leads to Impaired Function

Kaur Harleen, Park Jinkyu, Qyang Yibing, Ibrahim Eiman, Halene Stephanie, Hwa John, Campbell Stuart, Jha Alokkumar, Kwan Jennifer, Halder Saiti, Espinoza Jeacy, Chen Nathan, Vanoudenhove Jennifer, Biancon Giulia, Gu Sean, Chakraborty Raja, Jain Kanika

You have to be authorized to contact abstract author. Please, Login
Not Available