Prediction models for patients with esophageal or gastric cancer: A systematic review and meta-analysis

Abstract

Background: Clinical prediction models are increasingly used to predict outcomes such as survival in cancer patients. The aim of this study was threefold. First, to perform a systematic review to identify available clinical prediction models for patients with esophageal and/or gastric cancer. Second, to evaluate sources of bias in the included studies. Third, to investigate the predictive performance of the prediction models using meta-analysis.

Methods: MEDLINE, EMBASE, PsycINFO, CINAHL, and The Cochrane Library were searched for publications from the year 2000 onwards. Studies describing models predicting survival, adverse events and/or health-related quality of life (HRQoL) for esophageal or gastric cancer patients were included. Potential sources of bias were assessed and a meta-analysis, pooled per prediction model, was performed on the discriminative abilities (c-indices).

Results: A total of 61 studies were included (45 development and 16 validation studies), describing 47 prediction models. Most models predicted survival after a curative resection. Nearly 75% of the studies exhibited bias in at least 3 areas and model calibration was rarely reported. The meta-analysis showed that the averaged c-index of the models is fair (0.75) and ranges from 0.65 to 0.85.

Conclusion: Most available prediction models only focus on survival after a curative resection, which is only relevant to a limited patient population. Few models predicted adverse events after resection, and none focused on patient's HRQoL, despite its relevance. Generally, the quality of reporting is poor and external model validation is limited. We conclude that there is a need for prediction models that better meet patients' information needs, and provide information on both the benefits and harms of the various treatment options in terms of survival, adverse events and HRQoL.

Fig 1. Overview of study selection according to the “Preferred Reporting Items for Systematic Reviews and Meta-Analyses” (PRISMA) statement[21].

Fig 2. Overview of included prediction models.

The shape indicates the type of study and the size of shapes indicate the pooled c-index. Larger sizes of shapes indicate higher c-indices. AE = adverse event; Reilly-Evans = levels of evidence on the discriminatory accuracy of the prediction model described by Reilly and Evans[14], which indicate how extensively a prediction model has been validated and to what extent a model is ready for clinical use.

Fig 3. Random effects meta analyses of the discriminative abilities (c-indices) of the identified prediction models.

DSS: disease-specific survival, POM: post-operative mortality, OS: overall survival, AE: adverse events, DFS: disease-free survival, REC: cancer recurrence, dev: development c-index, int: internal validation, ext: external validation.