SAFE-AI ONCO-TRACK: Multimodal GenAI for Early Detection of Minimal Residual Disease and Recurrence in Gastrointestinal Oncology
试验速览
- 阶段
- 不适用
- 状态
- 尚未招募
- 发起方
- 入组人数
- 700
- 主要终点
- Primary outcomes
研究概览
简要总结
Current decision tools (TNM, MRI/PET, CEA, and other serum markers, as well as single-marker genomics) are insufficiently predictive of responders, fail to detect early MRD in many cases, and rarely connect molecular biology to dynamic perioperative data. SAFE-AI will build and validate multimodal, explainable GenAI models that fuse liquid/tissue multi-omics with radiology and clinical trajectories to:
(i) detect MRD earlier, (ii) improve recurrence-risk calibration, and (iii) support non-invasive "virtual biopsy"-inferring tissue-level features from blood profiles, and vice-versa, to mitigate missing-modality gaps. This is grounded in the strong mechanistic premise that integrating heterogeneous molecular signals with imaging captures tumour-host biology more completely than single-modality assays, enabling actionable, calibrated risk estimates for rectal and oesophageal cancer.
The clinical hypothesis is that such integrated models can improve recurrence prediction by at least 20% over guideline baselines, with transparent uncertainty and bias monitoring to meet EU AI Act/MDR expectations.
详细描述
Current decision tools (TNM, MRI/PET, CEA, and other serum markers, as well as single-marker genomics) are insufficiently predictive of responders, fail to detect early MRD in many cases, and rarely connect molecular biology to dynamic perioperative data. SAFE-AI will build and validate multimodal, explainable GenAI models that fuse liquid/tissue multi-omics with radiology and clinical trajectories to:
(i) detect MRD earlier, (ii) improve recurrence-risk calibration, and (iii) support non-invasive "virtual biopsy"-inferring tissue-level features from blood profiles, and vice-versa, to mitigate missing-modality gaps. This is grounded in the strong mechanistic premise that integrating heterogeneous molecular signals with imaging captures tumour-host biology more completely than single-modality assays, enabling actionable, calibrated risk estimates for rectal and oesophageal cancer.
The clinical hypothesis is that such integrated models can improve recurrence prediction by at least 20% over guideline baselines, with transparent uncertainty and bias monitoring to meet EU AI Act/MDR expectations.
研究设计
- 研究类型
- Observational
- 观察模型
- Cohort
- 时间视角
- Prospective
入排标准
- 年龄范围
- 18 Years 至 —（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- 未提供
排除标准
- •Diagnosis of non-resectable or metastatic disease at enrollment (Excludes non-curative settings where the longitudinal biomarker protocol may not be feasible.)
- •Emergency surgeries or treatment plans that deviate from standard protocols (To maintain data comparability.)
- •Inability or refusal to provide informed consent (Essential for ethical compliance.)
- •Failure to complete biospecimen donation or key follow-up timepoints (Maintains data integrity and model reliability.)
结局指标
主要结局
Primary outcomes
时间窗: 24 months
Primary Objective A: Establish a generative AI-powered simulation ecosystem (SAFE-AI) for biomarker discovery, risk stratification, and safety testing in oncology through integration of synthetic data, 3D tumour models, and multi-omics datasets. (Threshold: AUC ≥0.80 (95% CI ±0.05) for 12-mo recurrence prediction; Model calibration slope ≥0.90)
次要结局
未报告次要终点
研究者
Monica Ortenzi
Assistant Professor
Università Politecnica delle Marche