The FuSion Program: A Prospective and Multicenter Cohort Study of Pan-Cancer Screening in Chinese Population

To develop a multi-omics model for pan-cancer screening integrating the markers of ctDNA mutation, DNA fragmentation and methylation et al.

To construct a multi-dimensional ensembled stacked machine learning approach, employing several different base models on ctDNA mutation, DNA fragmentation and mehylation, to provide an effective model for cancer early detection.

Time frame: assessed up to 36 months

To evaluate sensitivity,specificity,positive/negative predictive value of the screening model in participants taking routine annual physicals

Sensitivity: the ability of a test to correctly identify patients with a disease. Specificity: the ability of a test to correctly identify people without the disease. Positive predictive value refers to the probability of the person having the disease when the test is positive. Negative predictive value refers to the probability of the person not having the disease when the test is negative.

Time frame: assessed up to 24 months

To validate model's efficacy and clinical value in the diagnosis of cancers in Taizhou cohort.

Cancer early detection could increase detection of cancer at early stages, when survival outcomes are better and treatment costs are lower. we will explore whether this model with high specificity could potentially improve long-term health outcomes and reduce cancer treatment costs.

Time frame: assessed up to 12 months