Ahmadreza Shirdel

This public OSF project contains the reproducibility materials for a systematic review and exploratory contrast-stratified quantitative synthesis of subsequent-line targeted therapies in advanced gastrointestinal stromal tumors (GIST) by secondary KIT mutation locus. The review was prospectively registered before screening at OSF DOI https://doi.org/10.17605/OSF.IO/8VK7W. The final package includes the manuscript and supplementary appendix, screening and eligibility records, source-traceable extraction tables, risk-of-bias assessments, analysis scripts, and publication figures. The final audit contains 34 quantitative outcome rows from 10 included source reports, with independent verification status recorded in the extraction files. Copyrighted article PDFs and patient-level data are not included; third-party publication rights remain with their respective copyright holders.

BACKGROUND: Tumor mutation burden (TMB) serves as a key biomarker guiding immunotherapy in gastrointestinal (GI) cancers, yet its measurement via whole-exome sequencing (WES) is costly and invasive. Machine learning (ML)-based models and radiogenomics provide promising non-invasive alternatives, but their diagnostic performance and methodological consistency remain unclear. OBJECTIVE: To systematically evaluate and meta-analyze the diagnostic performance, methodological rigor, and reporting quality of ML-based models developed for TMB prediction in GI cancers. METHODS: PubMed, Scopus, and Web of Science were searched through January 2025 for studies applying ML or deep learning to predict TMB in human GI cancers. Risk of bias was assessed using the Cochrane QUADAS-2 framework adapted for AI prediction studies. Pooled estimates for area under the curve (AUC) and accuracy were obtained under a restricted maximum-likelihood random-effects model, with heterogeneity quantified by I² and sensitivity analyses exploring threshold effects. Deeks’ funnel asymmetry test was used to assess publication bias. Subgroup analyses examined cancer type and model architecture. RESULTS: Ten studies met inclusion criteria. The pooled AUC was 0.89 (95% CI 0.80–0.97; I² = 92.1%), and pooled accuracy was 0.86 (95% CI 0.79–0.94; I² = 83.9%). Graph neural networks achieved the most stable performance (AUC ≈ 0.97), while classical ML models showed consistent results on smaller datasets. Publication bias was significant for AUC (p = 0.007) but not for accuracy (p = 0.15), indicating outcome-specific reporting tendencies. Only 3/10 studies performed external validation, and calibration metrics were rarely reported. Subgroup findings suggested that heterogeneity stemmed more from model architecture and dataset design than from cancer subtype. CONCLUSION: ML-based and radiogenomic models demonstrate high diagnostic potential for predicting TMB in GI cancers, particularly with graph-based architectures. However, scarce external validation, inconsistent TMB definitions, and selective reporting of AUC limit clinical generalizability. Standardized reporting of discrimination and calibration metrics, alongside external validation, is essential to translate ML-driven TMB prediction into reliable precision oncology tools.