⚡ Quick Summary
This systematic review and meta-analysis evaluated the role of radiomics and artificial intelligence (AI) in predicting tumor response in gastrointestinal (GI) neoplasms, highlighting their potential in enhancing diagnostic and prognostic accuracy. The findings revealed significant odds ratios (OR) for various applications, indicating a promising future for AI in oncology.
🔍 Key Details
- 📊 Studies Reviewed: 120 ongoing studies from 2016 to 2025
- 🧩 Applications Covered: Endoscopy, colonoscopy, capsule endoscopy, intraoperative guidance, CT/MRI radiomics, molecular/histopathology AI models
- ⚙️ Methodology: Meta-analysis using random-effects modeling
- 🏆 Performance Metrics: Various odds ratios (OR) indicating effectiveness across applications
🔑 Key Takeaways
- 📊 AI significantly enhances detection and diagnosis in upper GI tract endoscopy (OR = 16.12).
- 💡 Colonoscopy for colorectal polyps shows an impressive OR of 12.0.
- 👩🔬 Capsule endoscopy demonstrates effectiveness with an OR of 10.16.
- 🏥 Intraoperative guidance aids surgical decision-making (OR = 8.12).
- 🤖 AI-based patient risk assessment predicts lymph node metastasis and survival (OR = 9.62).
- 📈 Radiomic models forecast tumor responses in various cancers with ORs ranging from 10.48 to 11.62.
- 🌍 Methodological quality assessed as moderate-to-high via Radiomics Quality Score (RQS).
- 🆔 Low-to-moderate risk of bias indicated by PROBAST evaluation.
📚 Background
The integration of radiomics and artificial intelligence in oncology is a rapidly evolving field, particularly in the context of gastrointestinal tumors. These technologies aim to enhance the accuracy of tumor response predictions, recurrence assessments, and overall prognosis, thereby improving patient outcomes and guiding treatment strategies.
🗒️ Study
This systematic review focused on analyzing data from 120 ongoing studies between 2016 and 2025, covering various applications of AI and radiomics in the GI tract. The researchers employed a meta-analysis approach, utilizing random-effects modeling to assess the performance of these technologies across different diagnostic and prognostic scenarios.
📈 Results
The results of the meta-analysis were compelling, showcasing the effectiveness of AI in multiple applications. For instance, the odds ratio for AI-assisted endoscopy in the upper GI tract was a remarkable 16.12, while colonoscopy for colorectal polyps yielded an OR of 12.0. Additionally, radiomic models demonstrated strong predictive capabilities for tumor responses across various cancer types, with ORs ranging from 10.48 to 11.62.
🌍 Impact and Implications
The implications of this study are profound, suggesting that the incorporation of AI and radiomics can significantly enhance the precision of diagnostics and prognostics in oncology. As these technologies continue to evolve, they hold the potential to transform clinical practices, leading to more personalized treatment approaches and improved patient outcomes in gastrointestinal cancers.
🔮 Conclusion
This systematic review underscores the transformative potential of AI and radiomics in predicting tumor responses in gastrointestinal neoplasms. The findings advocate for further validation through prospective multicenter studies and standardized reporting to enhance clinical reliability and support the implementation of precision oncology. The future of cancer care looks promising with these advancements!
💬 Your comments
What are your thoughts on the integration of AI and radiomics in oncology? We would love to hear your insights! 💬 Share your comments below or connect with us on social media:
Radiomics and artificial intelligence-based prediction of tumor response in digestive system neoplasm: a systematic review and meta-analysis.
Abstract
BACKGROUND: Radiomics and artificial intelligence (AI) are progressively gaining recognition for predicting tumor response, recurrence, and prognosis in gastrointestinal tumors. The current review singled out the diagnostic and prognostic potential of AI and radiomics in the whole GI tract.
METHODS: Out of 120 ongoing studies from the year 2016 to 2025, the following applications were covered: endoscopy, colonoscopy, capsule endoscopy, intraoperative guidance, CT/MRI radiomics, and molecular/histopathology AI models. The performance across studies was assessed by meta-analysis using random-effects modeling that incorporated inverse variance methods. Results from the analysis of heterogeneity (I 2), publication bias (funnel plots, Egger’s test), methodological quality (Radiomics Quality Score, RQS), and risk of bias (PROBAST) were reported.
RESULTS: The use of AI in detection and diagnosis assisted with the endoscopy of the upper gastrointestinal tract (OR = 16.12, 95% CI: 7.72-33.65), colonoscopies for colorectal polyps (OR = 12.0, 95% CI: 10.26-14.03), and capsule endoscopy (OR = 10.16, 95% CI: 8.32-12.4) and was proven to be very effective. Intraoperative guidance also was proven to be an effective surgical decision-making tool (OR = 8.12, 95% CI: 7.12-9.26), whereas an AI-based strategy for patient risk assessment predicted the occurrence of lymph node metastasis, molecular tumor types, and patient survival (OR = 9.62, 95% CI: 7.93-11.66). Radiomic models forecasted tumor responses and relapses in rectal/colorectal (OR = 10.48, 95% CI: 9.66-11.36), gastric/esophagogastric/esophageal cancers (OR = 10.81, 95% CI: 9.89-11.82), molecular/histopathology datasets (OR = 11.62, 95% CI: 10.42-12.95), and CT/MRI recurrence/prognosis models (OR = 10.59, 95% CI: 9.52-11.79). The RQS assessment indicated moderate-to-high methodological quality, and the PROBAST evaluation revealed a low-to-moderate risk of bias.
CONCLUSION: Validation through prospective multicenter studies and reporting that has been standardized is the key to clinical reliability enhancement and backed-up precision oncology implementation.
Author: [‘Yu S’, ‘Gong M’, ‘Wang H’, ‘Liu H’, ‘Deng M’]
Journal: Front Med (Lausanne)
Citation: Yu S, et al. Radiomics and artificial intelligence-based prediction of tumor response in digestive system neoplasm: a systematic review and meta-analysis. Radiomics and artificial intelligence-based prediction of tumor response in digestive system neoplasm: a systematic review and meta-analysis. 2026; 13:1795060. doi: 10.3389/fmed.2026.1795060