Ignite Creation Date:
2025-12-25 @ 4:13 AM
Ignite Modification Date:
2025-12-26 @ 3:11 AM
Study NCT ID:
NCT07189520
Status:
NOT_YET_RECRUITING
Last Update Posted:
2025-09-24
First Post:
2025-09-16
Is NOT Gene Therapy:
False
Has Adverse Events:
False
Brief Title:
1. SAFE-AI ONCO-TRACK: Multimodal GenAI for Early Detection of Minimal Residual Disease and Recurrence in Gastrointestinal Oncology
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}, 'conditionBrowseModule': {'meshes': [{'id': 'D012004', 'term': 'Rectal Neoplasms'}], 'ancestors': [{'id': 'D015179', 'term': 'Colorectal Neoplasms'}, {'id': 'D007414', 'term': 'Intestinal Neoplasms'}, {'id': 'D005770', 'term': 'Gastrointestinal Neoplasms'}, {'id': 'D004067', 'term': 'Digestive System Neoplasms'}, {'id': 'D009371', 'term': 'Neoplasms by Site'}, {'id': 'D009369', 'term': 'Neoplasms'}, {'id': 'D004066', 'term': 'Digestive System Diseases'}, {'id': 'D005767', 'term': 'Gastrointestinal Diseases'}, {'id': 'D007410', 'term': 'Intestinal Diseases'}, {'id': 'D012002', 'term': 'Rectal Diseases'}]}, 'interventionBrowseModule': {'meshes': [{'id': 'D001185', 'term': 'Artificial Intelligence'}], 'ancestors': [{'id': 'D000465', 'term': 'Algorithms'}, {'id': 'D055641', 'term': 'Mathematical Concepts'}]}}, 'protocolSection': {'designModule': {'bioSpec': {'retention': 'SAMPLES_WITH_DNA', 'description': 'consistent prognostic value for minimal residual disease (MRD) and recurrence risk. However, most available studies are heterogeneous in assays, sampling timepoints, and outcome definitions, and are predominantly retrospective or single-centre, which limits their generalizability and clinical utility.'}, 'studyType': 'OBSERVATIONAL', 'designInfo': {'timePerspective': 'PROSPECTIVE', 'observationalModel': 'COHORT'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 700}, 'patientRegistry': False}, 'statusModule': {'overallStatus': 'NOT_YET_RECRUITING', 'startDateStruct': {'date': '2026-06-01', 'type': 'ESTIMATED'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2025-09', 'completionDateStruct': {'date': '2030-06-01', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2025-09-16', 'studyFirstSubmitDate': '2025-09-16', 'studyFirstSubmitQcDate': '2025-09-16', 'lastUpdatePostDateStruct': {'date': '2025-09-24', 'type': 'ESTIMATED'}, 'studyFirstPostDateStruct': {'date': '2025-09-24', 'type': 'ESTIMATED'}, 'primaryCompletionDateStruct': {'date': '2028-06-01', 'type': 'ESTIMATED'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'Primary outcomes', 'timeFrame': '24 months', 'description': '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)'}]}, 'oversightModule': {'oversightHasDmc': True, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'conditions': ['Rectal Cancer']}, 'descriptionModule': {'briefSummary': '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:\n\n(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.\n\nThe 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.', 'detailedDescription': '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:\n\n(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.\n\nThe 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.'}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['ADULT', 'OLDER_ADULT'], 'minimumAge': '18 Years', 'samplingMethod': 'NON_PROBABILITY_SAMPLE', 'studyPopulation': 'Cancer patients', 'healthyVolunteers': False, 'eligibilityCriteria': 'Inclusion Criteria (Justification in parenthesis):\n\n* Age ≥18 years (RC and EC are primarily adult-onset cancers, and adult inclusion aligns with ethical biospecimen collection and consent processes.)\n* Histologically confirmed diagnosis of rectal or esophageal cancer (Confirms clinical relevance and eligibility for standard treatment pathways.)\n* Treatment plan includes surgical resection with curative intent (Ensures applicability to MRD and outcome prediction tasks.)\n* Undergoing standard-of-care neo-adjuvant or perioperative therapy (Ensures data consistency and relevance to response modelling.)\n* Ability and willingness to provide informed consent for biospecimen and clinical data use (Meets ethical requirements for participation.)\n* Availability for longitudinal blood sampling at T0 (baseline), T1 (3 months post-treatment), and T2 (6 months post-treatment) (Critical for temporal biomarker analysis.)\n* Optional Inclusion: Access to tumor tissue (archival or fresh) for multi-omic profiling (Supports deep integrative biomarker discovery.)\n\nExclusion Criteria:\n\n* Diagnosis of non-resectable or metastatic disease at enrollment (Excludes non-curative settings where the longitudinal biomarker protocol may not be feasible.)\n* Emergency surgeries or treatment plans that deviate from standard protocols (To maintain data comparability.)\n* Inability or refusal to provide informed consent (Essential for ethical compliance.)\n* Failure to complete biospecimen donation or key follow-up timepoints (Maintains data integrity and model reliability.)'}, 'identificationModule': {'nctId': 'NCT07189520', 'acronym': 'ONCO-TRACK', 'briefTitle': '1. SAFE-AI ONCO-TRACK: Multimodal GenAI for Early Detection of Minimal Residual Disease and Recurrence in Gastrointestinal Oncology', 'organization': {'class': 'OTHER', 'fullName': 'Università Politecnica delle Marche'}, 'officialTitle': 'SAFE-AI ONCO-TRACK: Multimodal GenAI for Early Detection of Minimal Residual Disease and Recurrence in Gastrointestinal Oncology', 'orgStudyIdInfo': {'id': 'SAFE-AI ONCO-TRACK'}, 'secondaryIdInfos': [{'id': '2025-TOOL-01-03', 'type': 'OTHER', 'domain': 'Università Politecnica delle Marche'}]}, 'armsInterventionsModule': {'armGroups': [{'label': 'AI cohort', 'description': 'Benchmark AI scoring vs expert raters (GEARS/OCHRA κ ≥0.75)• Assess performance gains after GenAI feedback (≥15% improvement)• Measure usability, cognitive load, and ecological footprint reduction', 'interventionNames': ['Other: Artificial Intelligence']}], 'interventions': [{'name': 'Artificial Intelligence', 'type': 'OTHER', 'description': 'Benchmark AI scoring vs expert raters (GEARS/OCHRA κ ≥0.75)• Assess performance gains after GenAI feedback (≥15% improvement)• Measure usability, cognitive load, and ecological footprint reduction', 'armGroupLabels': ['AI cohort']}]}, 'contactsLocationsModule': {'centralContacts': [{'name': 'Monica Ortenzi, PhD', 'role': 'CONTACT', 'email': 'monica.ortenzi@gmail.com', 'phone': '+393924770853'}]}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Università Politecnica delle Marche', 'class': 'OTHER'}, 'responsibleParty': {'type': 'PRINCIPAL_INVESTIGATOR', 'investigatorTitle': 'Assistant Professor', 'investigatorFullName': 'Monica Ortenzi', 'investigatorAffiliation': 'Università Politecnica delle Marche'}}}}