Farhad Hormozdiari
YOU?
Author Swipe
View article: Deep Learning of Suboptimal Spirometry to Predict Respiratory Outcomes and Mortality
Deep Learning of Suboptimal Spirometry to Predict Respiratory Outcomes and Mortality Open
Importance: Obtaining spirometry requires repeated testing and using the maximal values based on quality control criteria. Whether the suboptimal efforts are useful for the prediction of respiratory outcomes is not clear. Objective: To det…
View article: Applying multimodal AI to physiological waveforms improves genetic prediction of cardiovascular traits
Applying multimodal AI to physiological waveforms improves genetic prediction of cardiovascular traits Open
View article: Applying multimodal AI to physiological waveforms improves genetic prediction of cardiovascular traits
Applying multimodal AI to physiological waveforms improves genetic prediction of cardiovascular traits Open
View article: Advancing Multimodal Medical Capabilities of Gemini
Advancing Multimodal Medical Capabilities of Gemini Open
Many clinical tasks require an understanding of specialized data, such as medical images and genomics, which is not typically found in general-purpose large multimodal models. Building upon Gemini's multimodal models, we develop several mo…
View article: Utilizing multimodal AI to improve genetic analyses of cardiovascular traits
Utilizing multimodal AI to improve genetic analyses of cardiovascular traits Open
Electronic health records, biobanks, and wearable biosensors contain multiple high-dimensional clinical data (HDCD) modalities (e.g., ECG, Photoplethysmography (PPG), and MRI) for each individual. Access to multimodal HDCD provides a uniqu…
View article: Multimodal LLMs for health grounded in individual-specific data
Multimodal LLMs for health grounded in individual-specific data Open
Foundation large language models (LLMs) have shown an impressive ability to solve tasks across a wide range of fields including health. To effectively solve personalized health tasks, LLMs need the ability to ingest a diversity of data mod…
View article: Unsupervised representation learning improves genomic discovery and risk prediction for respiratory and circulatory functions and diseases
Unsupervised representation learning improves genomic discovery and risk prediction for respiratory and circulatory functions and diseases Open
High-dimensional clinical data are becoming more accessible in biobank-scale datasets. However, effectively utilizing high-dimensional clinical data for genetic discovery remains challenging. Here we introduce a general deep learning-based…
View article: Deep Learning Utilizing Suboptimal Spirometry Data to Improve Lung Function and Mortality Prediction in the UK Biobank
Deep Learning Utilizing Suboptimal Spirometry Data to Improve Lung Function and Mortality Prediction in the UK Biobank Open
Background Spirometry measures lung function by selecting the best of multiple efforts meeting pre-specified quality control (QC), and reporting two key metrics: forced expiratory volume in 1 second (FEV 1 ) and forced vital capacity (FVC)…
View article: An Empirical Study of ML-based Phenotyping and Denoising for Improved Genomic Discovery
An Empirical Study of ML-based Phenotyping and Denoising for Improved Genomic Discovery Open
Genome-wide association studies (GWAS) are used to identify genetic variants significantly correlated with a target disease or phenotype as a first step to detect potentially causal genes. The availability of high-dimensional biomedical da…
View article: Leveraging deep-learning on raw spirograms to improve genetic understanding and risk scoring of COPD despite noisy labels
Leveraging deep-learning on raw spirograms to improve genetic understanding and risk scoring of COPD despite noisy labels Open
Chronic obstructive pulmonary disease (COPD), the third leading cause of death worldwide, is highly heritable. While COPD is clinically defined by applying thresholds to summary measures of lung function, a quantitative liability score has…
View article: DeepNull models non-linear covariate effects to improve phenotypic prediction and association power
DeepNull models non-linear covariate effects to improve phenotypic prediction and association power Open
Genome-wide association studies (GWASs) examine the association between genotype and phenotype while adjusting for a set of covariates. Although the covariates may have non-linear or interactive effects, due to the challenge of specifying …
View article: Combining SNP-to-gene linking strategies to pinpoint disease genes and assess disease omnigenicity
Combining SNP-to-gene linking strategies to pinpoint disease genes and assess disease omnigenicity Open
Although genome-wide association studies (GWAS) have identified thousands of disease-associated common SNPs, these SNPs generally do not implicate the underlying target genes, as most disease SNPs are regulatory. Many SNP-to-gene (S2G) lin…
View article: Large-scale machine-learning-based phenotyping significantly improves genomic discovery for optic nerve head morphology
Large-scale machine-learning-based phenotyping significantly improves genomic discovery for optic nerve head morphology Open
View article: DeepNull: Modeling non-linear covariate effects improves phenotype prediction and association power
DeepNull: Modeling non-linear covariate effects improves phenotype prediction and association power Open
Genome-wide association studies (GWAS) examine the association between genotype and phenotype while adjusting for a set of covariates. Although the covariates may have non-linear or interactive effects, due to the challenge of specifying t…
View article: MARS: leveraging allelic heterogeneity to increase power of association testing
MARS: leveraging allelic heterogeneity to increase power of association testing Open
View article: Population-scale tissue transcriptomics maps long non-coding RNAs to complex disease
Population-scale tissue transcriptomics maps long non-coding RNAs to complex disease Open
View article: MARS: leveraging allelic heterogeneity to increase power of association testing
MARS: leveraging allelic heterogeneity to increase power of association testing Open
In standard genome-wide association studies (GWAS) the standard association test is underpowered to detect associations between loci with multiple causal variants with small effect sizes. We propose a statistical method, Model-based Associ…
View article: Additional file 2 of MARS: leveraging allelic heterogeneity to increase power of association testing
Additional file 2 of MARS: leveraging allelic heterogeneity to increase power of association testing Open
Additional file 2 Extra eGenes identified by MARS but not by GTEx v6. have been reported by other studies. We used the Whole Blood data of GTEx v6 and identified 2,043 extra eGenes that were not reported by the GTEx consortium (GTEx v6). W…
View article: Additional file 3 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci
Additional file 3 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci Open
Additional file 3 Presumed causal genes included in the OMIM database
View article: Additional file 2 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci
Additional file 2 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci Open
Additional file 2 The metadata of the full list of 114 GWASs
View article: Additional file 5 of MARS: leveraging allelic heterogeneity to increase power of association testing
Additional file 5 of MARS: leveraging allelic heterogeneity to increase power of association testing Open
Additional file 5 List of loci found by previous studies among the loci identified by MARS but not by the univariate test
View article: Additional file 5 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci
Additional file 5 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci Open
Additional file 5 BioVU table
View article: Additional file 4 of MARS: leveraging allelic heterogeneity to increase power of association testing
Additional file 4 of MARS: leveraging allelic heterogeneity to increase power of association testing Open
Additional file 4 List of genes significantly associated with traits in NFBC data detected by MARS and the univariate test. The first column shows the geneID. Only genes at least one of the method, MARS or the univariate test, is significa…
View article: Additional file 8 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci
Additional file 8 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci Open
Additional file 8 PrediXcan and enloc results for predicted causal genes selected based on OMIM
View article: Additional file 4 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci
Additional file 4 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci Open
Additional file 4 Genes suggested as causal by rare variant association studies
View article: Additional file 7 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci
Additional file 7 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci Open
Additional file 7 Rare variant silver standard genes included in the analysis
View article: Additional file 6 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci
Additional file 6 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci Open
Additional file 6 OMIM genes included in the analysis
View article: Additional file 3 of MARS: leveraging allelic heterogeneity to increase power of association testing
Additional file 3 of MARS: leveraging allelic heterogeneity to increase power of association testing Open
Additional file 3 List of eGenes identified by MARS, the univariate test, and GTEx 23,163 genes from the Whole Blood data were used for the analysis, which contain at least 50 SNPs in their +/- 1Mb of TSS. We generate null distribution of …
View article: Additional file 9 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci
Additional file 9 of Exploiting the GTEx resources to decipher the mechanisms at GWAS loci Open
Additional file 9 PrediXcan and enloc results for presumed causal genes in the rare variant based silver standard
View article: Large-scale machine learning-based phenotyping significantly improves\n genomic discovery for optic nerve head morphology
Large-scale machine learning-based phenotyping significantly improves\n genomic discovery for optic nerve head morphology Open
Genome-wide association studies (GWAS) require accurate cohort phenotyping,\nbut expert labeling can be costly, time-intensive, and variable. Here we\ndevelop a machine learning (ML) model to predict glaucomatous optic nerve head\nfeatures…