Prognostic Nomogram for Gastrointestinal Stromal Tumors after Surgery Based on the SEER Database

Abstract

We aimed to determine prognostic factors and develop an effective and practical nomogram for predicting cancer-specific survival in gastrointestinal stromal tumor (GIST) patients. Postoperative data were obtained from the SEER database (2000-2018). Patients were divided into training and validation cohorts at random (7 : 3). Prognostic factors were screened, and a prognostic nomogram was established using log-rank testing and Cox regression. We used DCA, ROC curves, C-index, and calibration curves to evaluate our model’s predictive performance. The clinical value of the nomogram and the modified National Institute of Health (M-NIH) classification were compared using the NRI and IDI. The Kaplan-Meier method was applied to examine survival by risk group, and log-rank tests were applied to compare variations in survival curves. Independent prognostic risk factors associated with cancer-specific survival on multivariate Cox proportional hazards regression analysis were age, race, and tumor location, size, grade, and stage. Clinically relevant variables need to be considered in addition to statistically significant variables when developing prognostic models to aid clinical decision-making. We included two additional variables (mitotic rate and chemotherapy) when constructing the prognostic model. The C-index was 0.766 (95% confidence interval (CI): 0.737-0.794) in the training cohort and 0.795 (95% CI: 0.754-0.836) in the internal validation group suggesting robustness. The areas under the ROC curve for three-year and five-year survival were >0.700, indicating satisfactory discrimination. The calibration curves showed good agreement between the predictions of the nomogram and the actual results. The NRI (0.346 for 3-year and 0.265 for 5-year cancer-specific survival for patients with GIST (GSS) prediction; validation cohort: 0.356 for 3-year and 0.246 for 5-year GSS prediction) and IDI values (0.047 for 3-year and 0.060 for 5-year GSS prediction; validation cohort: 0.071 for 3-year and 0.084 for 5-year GSS prediction) suggested that the established nomogram performed significantly better than the M-NIH classification. The DCA indicated that the nomogram was clinically useful and had a high discriminative ability in identifying patients who were at high risk of poor outcomes. According to nomogram findings, patients were divided into three groups (high, moderate, and low risk), with significantly different prognoses in both cohorts. Our nomogram satisfactorily predicted survival in postsurgical GIST patients, which may assist clinicians to evaluate the postoperative status and guide subsequent treatments.

Evaluating nomogram models for predicting survival outcomes in gastric gastrointestinal stromal tumors with SEER database analysis

“…Nevertheless, previous research has indicated that the Mitotic rate did not display any significant variations in survival outcomes when undergoing multifactor feature selection. The observed disparity is incongruous with the clinical guidelines indicated earlier 7 , 8 , 10 , 11 . The veracity is found within the survival Cox nomograms, which incorporate the independent clinical factor Mitotic rate and the comprehensive index AJCC stage as simultaneous variables in the nomogram.…”

“…However, the existing literature oversimplifies the treatment of missing data classified as 'unknown' in the development of nomograms. Several research 7 , 8 , 10 , 11 consider the classification of 'unknown' as a distinct category. The validity of this assumption is frequently disregarded, as it is contingent upon the proportions of categories inside the 'unknown' group being similar to the overall proportions.…”

“…Previous research has indicated that nomograms are increasingly being seen as prospective substitutes for the National Institute of Health (NIH) criteria, SEER staging, and TNM staging systems. These nomograms have the www.nature.com/scientificreports/ capacity to potentially establish a novel clinical standard 7,8,10,12 . However, the existing literature oversimplifies the treatment of missing data classified as 'unknown' in the development of nomograms.…”

“…Due to the rarity of GISTs, big datasets such as the Surveillance, Epidemiology, and End Results (SEER) Program can serve as a global real-world cohort database for researching GISTs 7 – 11 . Since data missingness is a typical occurrence in real-world data gathering, some studies 7 , 8 , 10 , 11 have categorized missing data as 'unknown' as one of the values for multi-category variables in subsequent study. However, such a basic method requires that the missingness of the 'unknown' is balanced across different categories, which is difficult to satisfy.…”

“…Directly adding them may lead to model non-convergence and instability. The traditional design of the cox nomogram normally involves a two-stage process of single-factor and multi-factor selection before nomogram construction 7 – 11 . However, with the widespread usage of Least Absolute Shrinkage and Selection Operator (LASSO) in clinical research as a feature selection and standalone model, Penalized Models have steadily developed as a unique clinical modeling strategy to replace the old two-stage method 14 – 17 .…”