Skip to main content
. 2022 Oct 25;11:e80150. doi: 10.7554/eLife.80150

Figure 3. Survival analysis and predictive performance evaluation of artificial intelligence-derived prognostic signature (AIDPS).

(A, B) Kaplan–Meier survival analysis for overall survival (OS) (A) and relapse-free survival (RFS) (B) between the high and low AIDPS groups in the PACA-AU-Array. (C, D) Kaplan–Meier survival analysis for OS (C) and RFS (D) between the high and low AIDPS groups in the Meta-Cohort. (E, F) Multivariate Cox regression analysis of OS (E) and RFS (F) in the PACA-AU-Array. (G, H) Multivariate Cox regression analysis of OS (G) and RFS (H) in the Meta-Cohort. (I, J) Calibration curve for predicting 1-, 2-, and 3-year OS in the PACA-AU-Array (I), and Meta-Cohort (J). (K, L) Time-dependent receiver-operator characteristic (ROC) analysis for predicting 1-, 2-, and 3-year OS in the PACA-AU-Array (K), and Meta-Cohort (L).

Figure 3.

Figure 3—figure supplement 1. Survival analysis of artificial intelligence-derived prognostic signature (AIDPS) in the nine testing cohorts.

Figure 3—figure supplement 1.

(A–I) Kaplan–Meier survival analysis for overall survival (OS) between the high and low AIDPS groups in the TCGA-PAAD (A), PACA-AU-Seq (B), PACA-CA-Seq (C), E-MTAB-6134 (D), GSE62452 (E), GSE28735 (F), GSE78229 (G), GSE79668 (H), and GSE85916 (I). (J–M) Kaplan–Meier survival analysis for relapse-free survival (RFS) between the high and low AIDPS groups in the TCGA-PAAD (J), PACA-AU-Seq (K), PACA-CA-Seq (L), and E-MTAB-6134 (M). (N) Multivariate Cox regression analysis of OS in the TCGA-PAAD.
Figure 3—figure supplement 2. Survival analysis of artificial intelligence-derived prognostic signature (AIDPS) in the nine testing cohorts.

Figure 3—figure supplement 2.

(A–F) Multivariate Cox regression analysis of overall survival (OS) in the PACA-AU-Seq (A), PACA-CA-Seq (B), E-MTAB-6134 (C), GSE79668 (D), GSE62452 (E), and GSE78229 (F). (G–J) Multivariate Cox regression analysis of relapse-free survival (RFS) in the TCGA-PAAD (G), E-MTAB-6134 (H), PACA-CA-Seq (I), and PACA-AU-Seq (J).
Figure 3—figure supplement 3. Predictive performance of artificial intelligence-derived prognostic signature (AIDPS) in the nine testing cohorts.

Figure 3—figure supplement 3.

Time-dependent receiver-operator characteristic (ROC) analysis for predicting 1-, 2-, and 3-year overall survival (OS) in the TCGA-PAAD (A), PACA-AU-Seq (B), PACA-CA-Seq (C), E-MTAB-6134 (D), GSE62452 (E), GSE28735 (F), GSE78229 (G), GSE79668 (H), and GSE85916 (I).
Figure 3—figure supplement 4. Survival analysis and predictive performance of artificial intelligence-derived prognostic signature (AIDPS) in the three external validation cohorts.

Figure 3—figure supplement 4.

(A) Univariate Cox regression analysis of AIDPS and 86 published signatures of pancreatic cancer (PACA) in three external validation cohorts. (B–D) Kaplan–Meier survival analysis for overall survival (OS) in the GSE21501 (B), GSE57495 (C), and GSE71729 (D) cohorts. (E–G) Time-dependent receiver-operator characteristic (ROC) analysis for predicting 1-, 2-, and 3-year OS in the GSE21501 (E), GSE57495 (F), and GSE71729 (G). (H–J) Calibration curve for predicting 1-, 2-, and 3-year OS in the GSE21501 (H), GSE57495 (I), and GSE71729 (J).