Development of a Novel Deep Learning-Based Prediction Model for the Prognosis of Operable Cervical Cancer

Figure 2

Correlation matrix of 15 selected features. Values in this matrix indicate the correlation coefficient of two corresponding variables. Color indicates strength of correlation, in which dark blue and dark red indicate strong positive and strong negative relationships, respectively. Diag: the year when the patient was diagnosed; Diff: differentiation; Hist: histology; Lymmeta: lymph node metastasis; Lymno: numbers of resected lymph nodes; Lympo: number of positive lymph nodes; Primasite: primary tumor sites.