Meta-Learning, Multimodal, Predictive Models, Triple -Negative Breast Cancertriple
Conditions
Brief summary
Based on the UPGRADE-TNBC study, a high-quality TNBC sample repository was established. By integrating multi-source data-including clinical information, radiomics, pathological images, and molecular sequencing-and innovatively incorporating a meta-learning strategy, a treatment response prediction model based on multimodal small-sample learning was developed. This approach aims to optimize drug combinations and precisely identify patient subgroups likely to benefit from treatment, thereby providing a new paradigm for personalized therapy in early-stage TNBC.
Interventions
OTHERCollect data
Collect multi-source data from patients, including clinical information, radiomics, pathological images, and molecular sequencing
Sponsors
Cancer Institute and Hospital, Chinese Academy of Medical Sciences
Study design
Observational model
OTHER
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
FEMALE
Age
18 Years to 75 Years
Healthy volunteers
No
Inclusion criteria
* The UPGRADE-TNBC Study Population
Exclusion criteria
* Populations outside the UPGRADE-TNBC study
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Model building | 2 years | A predictive model for neoadjuvant therapy in TNBC was successfully established |
Countries
China
Contacts
CONTACTXue Wang
Outcome results
None listed