This study is a multi-center, case-control study aiming at developing and blinded testing machine learning-based multiple cancers early detection model by prospectively collecting blood samples from newly diagnosed cancer patients and individuals without confirmed cancer diagnosis.
Blood samples from newly diagnosed cancer patients and individuals without confirmed cancer diagnosis will be prospectively collected to identify cancer-specific circulating signals through integrative multi-omic analysis. Based on the comprehensive molecular profiling, a machine learning-driven model will be trained and blinded validated independent through a two-stage approach in clinically annotated individuals. Approximately 10327 cancer patients will be enrolled in this study and early-stage cancer patients will be enriched to improve the model sensitivity on distinguishing cancers with favorable prognosis. Approximately 6339 age and sex matched controls will be included in model development, which are volunteers without a cancer diagnosis after routine cancer screening tests.
Study Type
OBSERVATIONAL
Enrollment
16,666
Peking University People's Hospital
Beijing, Beijing Municipality, China
RECRUITINGPeking University Cancer Hospital and Institute
Beijing, Beijing Municipality, China
NOT_YET_RECRUITINGThe performance of cfDNA methylation-based multiple cancers early detection model in case-control study
The sensitivity, specificity and tissue origin accuracy of cfDNA methylation-based multiple cancers early detection model in detecting cancer or non-cancer at 95% confidence interval.
Time frame: 12 months
The performance of cfDNA methylation-based multiple cancers early detection model in early stage cancer cases
The sensitivity and tissue origin accuracy of cfDNA methylation-based multiple cancers early detection model in detecting stage I to II cancer at 95% confidence interval.
Time frame: 12 months
The performance of multi-omic-based multiple cancers early detection model in case-control study
The sensitivity, specificity and tissue origin accuracy of multi-omic-based multiple cancers early detection model in detecting cancer or non-cancer at 95% confidence interval.
Time frame: 12 months
The performance of different multi-cancer early detection models in different subgroups
The sensitivity and specificity of cfDNA methylation-based or multi-omic-based multiple cancers early detection model in different subgroups of the population (such as age, gender, cancer pathological classification, and clinical stage) at 95% confidence interval.
Time frame: 12 months
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.