Prediction of ovarian cancer with deep machine-learning and alternative splicing (2167)

Early detection of high-grade serous ovarian cancer (HGSOC) would improve the survival rate of women with ovarian cancer. Currently, there is a lack of effective screening strategies for early-stage disease. Machine learning (ML) may impact the performance of models that predict HGSOC, which could lead to earlier detection of disease. We hypothesized that processing alternative splicing data from HGSOC patients with ML would discriminate HGSOC from normal fallopian tube (FT) samples.