Development and Validation of a Personalized Survival Prediction Model for Uterine Adenosarcoma: A Population-Based Deep Learning Study

Abstract

BackgroundThe aim was to develop a personalized survival prediction deep learning model for adenosarcoma patients using the surveillance, epidemiology and end results (SEER) database.MethodsA total of 797 uterine adenosarcoma patients were enrolled in this study. Duplicated and useless variables were excluded, and 15 variables were selected for further analyses, including age, grade, positive lymph nodes or not, marital status, race, tumor extension, stage, and surgery or not. We created our deep survival learning (DSL) model to manipulate the data, which was randomly split into a training set (n = 519, 65%), validation set (n = 143, 18%) and testing set (n = 143, 18%). The Cox proportional hazard (CPH) model was also included comparatively. Finally, personalized survival curves were plotted for randomly selected patients.ResultsThe c-index for the CPH model was 0.726, and the Brier score was 0.17. For our deep survival learning model, we achieved a c-index of 0.774 and a Brier score of 0.14 in the external testing set. In addition, the limitations of the traditional staging system were revealed, and a personalized survival prediction system based on our risk scoring grouping was developed.ConclusionsOur study developed a deep neural network model for adenosarcoma. The performance of this model was superior to that of the traditional Cox proportional hazard model. In addition, a personalized survival prediction system was developed based on our deep survival learning model, which provided more accurate prognostic information for adenosarcoma patients.

Case Report: Uterine Adenosarcoma With Sarcomatous Overgrowth and Malignant Heterologous Elements

“…It has been proven to be greatly effective for various clinical tasks, including image identification, pathological diagnoses, genomic analysis, metabolomics, and immunology studies. Qu et al developed and validated a personalized survival prediction model for UA, combining the SEER database with a neural network model called “neural multitask logistic regression model” (N-MTLR), comparing it with the traditional model (CPH model), demonstrating survival time predictions that are much more accurate than the other model ( 19 ). It is possible that the extension of this model in an online program, in case of obtaining data from cases around the world, could offer more information about this rare tumor.…”

Next-Generation Sequencing Analysis of 3 Uterine Adenosarcomas with Heterogeneously Differentiated Genomic Mutations

“…Uterine adenosarcoma (UA) is an uncommon mixed tumor containing a benign to at most mildly atypical epithelial component and a sarcoma-like stroma and accounts for approximately 5% of uterine sarcomas [ 1 ]. The epithelial component is Müllerian-derived, mainly endometrioid epithelium and a few visible tubal epithelium and squamous epithelium; the glandular epithelium may be accompanied by different atypical degrees.…”

A novel risk classification system based on the eighth edition of TNM frameworks for esophageal adenocarcinoma patients: A deep learning approach

“…With the rapid progress in artificial intelligence (AI) recently, deep learning is a promising solution to this problem ( 15 ). As the state-of-the-art algorithm, deep learning allows a prognostic network to automatically discover the potentially non-linear relationships with the use of multiple neural layers ( 16 ).…”