Prediction of long-term survival after gastrectomy using random survival forests

Abstract

Background No well validated and contemporaneous tools for personalized prognostication of gastric adenocarcinoma exist. This study aimed to derive and validate a prognostic model for overall survival after surgery for gastric adenocarcinoma using a large national dataset. Methods National audit data from England and Wales were used to identify patients who underwent a potentially curative gastrectomy for adenocarcinoma of the stomach. A total of 2931 patients were included and 29 clinical and pathological variables were considered for their impact on survival. A non-linear random survival forest methodology was then trained and validated internally using bootstrapping with calibration and discrimination (time-dependent area under the receiver operator curve (tAUC)) assessed. Results The median survival of the cohort was 69 months, with a 5-year survival of 53.2 per cent. Ten variables were found to influence survival significantly and were included in the final model, with the most important being lymph node positivity, pT stage and achieving an R0 resection. Patient characteristics including ASA grade and age were also influential. On validation the model achieved excellent performance with a 5-year tAUC of 0.80 (95 per cent c.i. 0.78 to 0.82) and good agreement between observed and predicted survival probabilities. A wide spread of predictions for 3-year (14.8–98.3 (i.q.r. 43.2–84.4) per cent) and 5-year (9.4–96.1 (i.q.r. 31.7–73.8) per cent) survival were seen. Conclusions A prognostic model for survival after a potentially curative resection for gastric adenocarcinoma was derived and exhibited excellent discrimination and calibration of predictions.

Development and validation of a deep learning model to predict survival of patients with esophageal cancer

“…developed a 3D attention autoencoder-based survival prediction network for esophageal cancer using pretreatment CT images ( 28 ). Rahman and his colleges demonstrated that the Random Survival Forest model performed better than TNM stage for survival prediction of patients after esophagectomy ( 29 ). However, these studies generally have the disadvantages of small sample size and lack of external validation.…”

Endoscopic submucosal dissection versus esophagectomy for t1 esophageal squamous cell carcinoma: a propensity score-matched analysis

“…We can observe that age was the common risk factor for OS, RFS, and DSS, which is consistent with the previous study. 36 Since elderly patients tend to have many comorbidities and poor physical status, a comprehensive evaluation should be conducted by clinicians to select the appropriate treatment for them.…”

Multi-omics integration in Esophageal Adenocarcinoma reveals therapeutic targets and EAC-specific regulation of protein abundances

“…The copyright holder for this this version posted November 29, 2022. ; https://doi.org/10.1101/2022.11.24.22281691 doi: medRxiv preprint Running Title: Multi-omics integration in Esophageal Adenocarcinoma reveals new possible biomarkers containing orthogonal RNA/Protein expression 3 change to columnar mucosa, known as Barrett's esophagus, which can progress over time through dysplasia to EAC 4 . If treated by resection at a mucosal-confined, often asymptomatic, early stage the 5-year overall survival approaches 90% 5 . However, despite recent advances in the detection and surveillance of Barrett's esophagus, the majority of patients with EAC still present with symptomatic, advanced disease, and the prognosis remains grave with a five-year overall survival of less than 20% 6,7 .…”