recent research HIGHLIGHTS
hierarchical models based on similarity of causal mechanisms
Given a dataset of related tasks, it is often beneficial to pool learning across tasks using techniques such as meta-learning and multi-task learning. Our new preprint studies an important setting where tasks are generated by different causal models, which occurs in medical/biological data. We discuss this problem and present a new probabilistic machine learning technique for predictive modelling in this setting, which utilises the similarity structure of the tasks.
Learn More
Published in
Preprint, Under review
Technical keywords
Bayesian Hierarchical models, causality, out-of-domain generalisation, meta-learning, Bayesian deep learning, robust mL
Modeling family disease risk in EHRs with graph neural networks
Electronic health records (EHRs) for multiple generations present a new way to study health trends in families. In collaboration with the Institute of Molecular Medicine Finland we developed an AI system to analyse a network of over 7 million patients' EHR data. We show that a geometric deep learning approach is beneficial for modeling the shared genetic, environment and lifestyle factors that influence disease risk in families.
Learn More
Published in
Machine Learning for Healthcare Conference (MLHC)
Technical keywords
graph neural networks, geometric deep learning, deep learning for time series data, electronic health records, genetics, familial factors of disease
Synthetic datasets for enabling genetics-based precision medicine
We developed a new software tool that efficiently simulates synthetic data that resembles real genetics data, to aid researchers with developing new methods for determining the genetic risk of disease. This work was carried out with the European-wide INTERVENE consortium. We publicly released a synthetic data resource of 6.8 million common genetic variants and 9 phenotypes for over 1 million individuals.
Learn More
Published in
BIOINFORMATICS
Technical keywords
computational biology, statistical genetics, simulation-based inference, generative modeling, polygenic risk scoring
recent research HIGHLIGHTS
hierarchical models based on similarity of causal mechanisms
Given a dataset of related tasks, it is often beneficial to pool learning across tasks using techniques such as meta-learning and multi-task learning. Our new preprint studies an important setting where tasks are generated by different causal models, which occurs in medical/biological data. We discuss this problem and present a new probabilistic machine learning technique for predictive modelling in this setting, which utilises the similarity structure of the tasks.
Learn More
Published in
Preprint, Under review
Technical keywords
Bayesian Hierarchical models, causality, out-of-domain generalisation, meta-learning, Bayesian deep learning, robust mL
Modeling family disease risk in EHRs with graph neural networks
Electronic health records (EHRs) for multiple generations present a new way to study health trends in families. In collaboration with the Institute of Molecular Medicine Finland we developed an AI system to analyse a network of over 7 million patients' EHR data. We show that a geometric deep learning approach is beneficial for modeling the shared genetic, environment and lifestyle factors that influence disease risk in families.
Learn More
Published in
Machine Learning for Healthcare Conference (MLHC)
Technical keywords
graph neural networks, geometric deep learning, deep learning for time series data, electronic health records, genetics, familial factors of disease
Synthetic datasets for enabling genetics-based precision medicine
We developed a new software tool that efficiently simulates synthetic data that resembles real genetics data, to aid researchers with developing new methods for determining the genetic risk of disease. This work was carried out with the European-wide INTERVENE consortium. We publicly released a synthetic data resource of 6.8 million common genetic variants and 9 phenotypes for over 1 million individuals.
Learn More
Published in
BIOINFORMATICS
Technical keywords
computational biology, statistical genetics, simulation-based inference, generative modeling, polygenic risk scoring
Learn More About My Research
Working in collaboration with
Working in collaboration with
Health AI
Personalised digital health solutions for women’s health
Translating innovations in AI research to real-world impact
Translating innovations in AI research to real-world impact
Learn More About Velmio
© 2024 Sophie wharrie
RECENT Research Highlights
hierarchical models based on similarity of causal mechanisms
Given a dataset of related tasks, it is often beneficial to pool learning across tasks using techniques such as meta-learning and multi-task learning. Our new preprint studies an important setting where tasks are generated by different causal models, which occurs in medical/biological data. We discuss this problem and present a new probabilistic machine learning technique for predictive modelling in this setting, which utilises the similarity structure of the tasks.
Learn More
Published in
Preprint, Under review
Technical keywords
Bayesian Hierarchical models, causality, out-of-domain generalisation, meta-learning, Bayesian deep learning, robust mL
Modeling family disease risk in EHRs with graph neural networks
Electronic health records (EHRs) for multiple generations present a new way to study health trends in families. In collaboration with the Institute of Molecular Medicine Finland we developed an AI system to analyse a network of over 7 million patients' EHR data. We show that a geometric deep learning approach is beneficial for modeling the shared genetic, environment and lifestyle factors that influence disease risk in families.
Learn More
Published in
Machine Learning for Healthcare Conference (MLHC)
Technical keywords
graph neural networks, geometric deep learning, deep learning for time series data, electronic health records, genetics, familial factors of disease
Synthetic datasets for enabling genetics-based precision medicine
We developed a new software tool that efficiently simulates synthetic data that resembles real genetics data, to aid researchers with developing new methods for determining the genetic risk of disease. This work was carried out with the European-wide INTERVENE consortium. We publicly released a synthetic data resource of 6.8 million common genetic variants and 9 phenotypes for over 1 million individuals.
Learn More
Published in
BIOINFORMATICS
Technical keywords
computational biology, statistical genetics, simulation-based inference, generative modeling, polygenic risk scoring
RECENT Research Highlights
hierarchical models based on similarity of causal mechanisms
Given a dataset of related tasks, it is often beneficial to pool learning across tasks using techniques such as meta-learning and multi-task learning. Our new preprint studies an important setting where tasks are generated by different causal models, which occurs in medical/biological data. We discuss this problem and present a new probabilistic machine learning technique for predictive modelling in this setting, which utilises the similarity structure of the tasks.
Learn More
Published in
Preprint, Under review
Technical keywords
Bayesian Hierarchical models, causality, out-of-domain generalisation, meta-learning, Bayesian deep learning, robust mL
Modeling family disease risk in EHRs with graph neural networks
Electronic health records (EHRs) for multiple generations present a new way to study health trends in families. In collaboration with the Institute of Molecular Medicine Finland we developed an AI system to analyse a network of over 7 million patients' EHR data. We show that a geometric deep learning approach is beneficial for modeling the shared genetic, environment and lifestyle factors that influence disease risk in families.
Learn More
Published in
Machine Learning for Healthcare Conference (MLHC)
Technical keywords
graph neural networks, geometric deep learning, deep learning for time series data, electronic health records, genetics, familial factors of disease
Synthetic datasets for enabling genetics-based precision medicine
We developed a new software tool that efficiently simulates synthetic data that resembles real genetics data, to aid researchers with developing new methods for determining the genetic risk of disease. This work was carried out with the European-wide INTERVENE consortium. We publicly released a synthetic data resource of 6.8 million common genetic variants and 9 phenotypes for over 1 million individuals.
Learn More
Published in
BIOINFORMATICS
Technical keywords
computational biology, statistical genetics, simulation-based inference, generative modeling, polygenic risk scoring
RECENT
Research Highlights
hierarchical models based on similarity of causal mechanisms
Given a dataset of related tasks, it is often beneficial to pool learning across tasks using techniques such as meta-learning and multi-task learning. Our new preprint studies an important setting where tasks are generated by different causal models, which occurs in medical/biological data. We discuss this problem and present a new probabilistic machine learning technique for predictive modelling in this setting, which utilises the similarity structure of the tasks.
Learn More
Published in
Preprint, Under review
Technical
keywords
Bayesian Hierarchical models, causality, out-of-domain generalisation, meta-learning, Bayesian deep learning, robust mL
Published in
Machine Learning for Healthcare Conference, PMLR 2023
Technical
keywords
graph neural networks, geometric deep learning, deep learning for time series data, electronic health records, genetics, familial factors of disease
Modeling family disease risk in EHRs with graph neural networks
Electronic health records (EHRs) for multiple generations present a new way to study health trends in families. In collaboration with the Institute of Molecular Medicine Finland we developed an AI system to analyse a network of over 7 million patients' EHR data. We show that a geometric deep learning approach is beneficial for modeling the shared genetic, environment and lifestyle factors that influence disease risk in families.
Learn More
Published in
BIOINFORMATICS
Technical
keywords
computational biology, statistical genetics, simulation-based inference, generative modeling, polygenic risk scoring
Synthetic datasets for enabling genetics-based precision medicine
We developed a new software tool that efficiently simulates synthetic data that resembles real genetics data, to aid researchers with developing new methods for determining the genetic risk of disease. This work was carried out with the European-wide INTERVENE consortium. We publicly released a synthetic data resource of 6.8 million common genetic variants and 9 phenotypes for over 1 million individuals.
Learn More
RECENT
Research Highlights
hierarchical models based on similarity of causal mechanisms
Given a dataset of related tasks, it is often beneficial to pool learning across tasks using techniques such as meta-learning and multi-task learning. Our new preprint studies an important setting where tasks are generated by different causal models, which occurs in medical/biological data. We discuss this problem and present a new probabilistic machine learning technique for predictive modelling in this setting, which utilises the similarity structure of the tasks.
Learn More
Published in
Preprint, Under review
Technical
keywords
Bayesian Hierarchical models, causality, out-of-domain generalisation, meta-learning, Bayesian deep learning, robust mL
Published in
Machine Learning for Healthcare Conference, PMLR 2023
Technical
keywords
graph neural networks, geometric deep learning, deep learning for time series data, electronic health records, genetics, familial factors of disease
Modeling family disease risk in EHRs with graph neural networks
Electronic health records (EHRs) for multiple generations present a new way to study health trends in families. In collaboration with the Institute of Molecular Medicine Finland we developed an AI system to analyse a network of over 7 million patients' EHR data. We show that a geometric deep learning approach is beneficial for modeling the shared genetic, environment and lifestyle factors that influence disease risk in families.
Learn More
Published in
BIOINFORMATICS
Technical
keywords
computational biology, statistical genetics, simulation-based inference, generative modeling, polygenic risk scoring
Synthetic datasets for enabling genetics-based precision medicine
We developed a new software tool that efficiently simulates synthetic data that resembles real genetics data, to aid researchers with developing new methods for determining the genetic risk of disease. This work was carried out with the European-wide INTERVENE consortium. We publicly released a synthetic data resource of 6.8 million common genetic variants and 9 phenotypes for over 1 million individuals.