Summary
Recurrent miscarriage (RM) affects 1% of couples trying to conceive and has a wide range of negative physical and mental impacts yet still has few evidence-based, preventative treatments. RM is used as a catch-all term for an event with diverse underlying causes. Broad categorisation hampers research targeting specific causes that could identify potential therapeutic avenues. This generalisation compounds trauma for patients and the path to successful pregnancy is unclear.
As a MSCA fellow at the University of Copenhagen, I will generate deeper understanding of RM aetiology by identifying granular subgroups of RM and elucidating their underlying biology. To do so I will: 1) Establish novel phenotypes derived from clinical data in electronic health records, including ultrasound images, and use these phenotypes to identify clinical phenotypes driving current miscarriage classification systems. 2) Apply hypothesis-free unsupervised machine learning to clinical data to disentangle complex phenotypes of RM into clinically relevant subgroups. 3) Employ genetic analyses to characterise biological pathways underlying these RM subgroups and identify potential therapeutic avenues.
This fellowship will allow me to apply my skills and expertise in large-scale biomedical data analysis and genetics to a new field in which I will pursue a long-term career. In particular it will provide training in field specific scientific knowledge (obstetrics and gynaecology), cutting edge techniques (machine learning) and transferable skills towards scientific leadership (research management).
Taken together the outcomes of this interdisciplinary research will have ramifications for researchers, clinicians and patients. For researchers, a granular understanding of RM and its causes will enable discovery of novel therapeutic avenues. For clinicians, it would assist clinical decision making towards personalised treatments. For patients, alleviation of trauma through empowerment with information.
As a MSCA fellow at the University of Copenhagen, I will generate deeper understanding of RM aetiology by identifying granular subgroups of RM and elucidating their underlying biology. To do so I will: 1) Establish novel phenotypes derived from clinical data in electronic health records, including ultrasound images, and use these phenotypes to identify clinical phenotypes driving current miscarriage classification systems. 2) Apply hypothesis-free unsupervised machine learning to clinical data to disentangle complex phenotypes of RM into clinically relevant subgroups. 3) Employ genetic analyses to characterise biological pathways underlying these RM subgroups and identify potential therapeutic avenues.
This fellowship will allow me to apply my skills and expertise in large-scale biomedical data analysis and genetics to a new field in which I will pursue a long-term career. In particular it will provide training in field specific scientific knowledge (obstetrics and gynaecology), cutting edge techniques (machine learning) and transferable skills towards scientific leadership (research management).
Taken together the outcomes of this interdisciplinary research will have ramifications for researchers, clinicians and patients. For researchers, a granular understanding of RM and its causes will enable discovery of novel therapeutic avenues. For clinicians, it would assist clinical decision making towards personalised treatments. For patients, alleviation of trauma through empowerment with information.
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/101064250 |
| Start date: | 01-07-2022 |
| End date: | 31-12-2023 |
| Total budget - Public funding: | - 173 080,00 Euro |
Cordis data
Original description
Recurrent miscarriage (RM) affects 1% of couples trying to conceive and has a wide range of negative physical and mental impacts yet still has few evidence-based, preventative treatments. RM is used as a catch-all term for an event with diverse underlying causes. Broad categorisation hampers research targeting specific causes that could identify potential therapeutic avenues. This generalisation compounds trauma for patients and the path to successful pregnancy is unclear.As a MSCA fellow at the University of Copenhagen, I will generate deeper understanding of RM aetiology by identifying granular subgroups of RM and elucidating their underlying biology. To do so I will: 1) Establish novel phenotypes derived from clinical data in electronic health records, including ultrasound images, and use these phenotypes to identify clinical phenotypes driving current miscarriage classification systems. 2) Apply hypothesis-free unsupervised machine learning to clinical data to disentangle complex phenotypes of RM into clinically relevant subgroups. 3) Employ genetic analyses to characterise biological pathways underlying these RM subgroups and identify potential therapeutic avenues.
This fellowship will allow me to apply my skills and expertise in large-scale biomedical data analysis and genetics to a new field in which I will pursue a long-term career. In particular it will provide training in field specific scientific knowledge (obstetrics and gynaecology), cutting edge techniques (machine learning) and transferable skills towards scientific leadership (research management).
Taken together the outcomes of this interdisciplinary research will have ramifications for researchers, clinicians and patients. For researchers, a granular understanding of RM and its causes will enable discovery of novel therapeutic avenues. For clinicians, it would assist clinical decision making towards personalised treatments. For patients, alleviation of trauma through empowerment with information.
Status
SIGNEDCall topic
HORIZON-MSCA-2021-PF-01-01Update Date
09-02-2023
Images
No images available.
Geographical location(s)
