Better identifying late health problems in adult survivors of childhood cancer
Mach-LETSGO: Machine-LEarning of Treatment, Survey, and Genetics towards Obtaining Correct Classification of Chronic Conditions in Adult Survivors in the Childhood Cancer Survivor Study - CCSS Suppl
This project uses computer learning with clinic exams, medical records, genetics, and survey answers to more accurately find conditions like diabetes, high blood pressure, and heart problems in adults who survived childhood cancer.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | St. Jude Children's Research Hospital NIH-funded |
| Lab location | 1 site (Memphis, United States) |
| Project ID | NIH-11471611 on NIH RePORTER |
What this research studies
This team combines detailed clinic assessments from the St. Jude Lifetime Cohort with CCSS survey data, treatment records, and whole-genome information to teach computer models to spot chronic conditions in adult childhood cancer survivors. They will train models on about 2,000 survivors who have both clinic exams and CCSS responses and then test the models on another 436 survivors to check accuracy. Models will use treatment exposures, genetic risk scores, demographic factors, and patterns among survey answers while using techniques to avoid overfitting and to explain predictions. The goal is to correct misreported conditions like diabetes, hypertension, and cardiomyopathy across the larger CCSS group of over 25,000 participants.
Who could benefit from this research
Good fit: Ideal candidates are adult survivors of childhood cancer who are enrolled in CCSS or who have completed clinic-based assessments like SJLIFE and have available medical records and genetic data.
Not a fit: People without a history of childhood cancer or those who cannot provide medical records or genetic information are unlikely to benefit directly from this project.
Why it matters
Potential benefit: If successful, this work could give survivors and their doctors more accurate information about late health conditions, helping guide better follow-up and care.
How similar studies have performed: Machine-learning methods have improved disease classification in other medical datasets, and applying them to linked SJLIFE and CCSS data is a promising but relatively new approach for survivor late-effect classification.
Where this research is happening
Memphis, United States
- St. Jude Children's Research Hospital — Memphis, United States (Active)
Researchers
- Principal investigator: Armstrong, Gregory — St. Jude Children's Research Hospital
- Study coordinator: Armstrong, Gregory
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.