The CCANED-CIPHER Study: Early Cancer Detection and Treatment Response Monitoring Using AI-Based Platelet and Immune Cell Transcriptomic Profiling

Not yet recruiting

• Conditions: Brest Cancer; Lung Cancer (NSCLC); Pancreatic Cancer, Adult; Prostate Cancers; Ovarian Cancer; Colorectal Cancer; Glioblastoma (GBM); Liver Carcinoma

• Registration Number: NCT06717295
• Lead Sponsor: Javier Toledo

Brief Summary

The purpose of the CCANED-CIPHER study is to develop and validate an AI-based blood test for early cancer detection and to monitor treatment effectiveness in cancer patients. This two-phase, multi-center observational study aims to identify specific transcriptomic biomarkers in platelets and immune cells that distinguish cancer patients from healthy individuals and correlate with treatment outcomes. By analysing blood samples using artificial intelligence, the study seeks to create a safe, non-invasive method to enhance cancer diagnosis and monitor treatment responses over time.

Detailed Description

Detailed Description The CCANED-CIPHER study aims to revolutionise cancer diagnostics and treatment monitoring by developing and evaluating an AI-based early cancer detection tool that profiles RNA biomarkers from platelets and immune cells in blood samples. This non-invasive approach leverages liquid biopsy methods to enhance early cancer detection and provide insights into therapeutic responses.

Phase 1 (CCANED): Early Cancer Detection

Objective:

To identify specific platelet-derived RNA biomarkers that can distinguish individuals with common cancers from healthy controls using AI-driven transcriptomic analysis.

Methodology:

Participant Recruitment: Enroll 3,500 patients with confirmed diagnoses of various common cancers and 1,500 cancer-free controls matched by age and sex.

Sample Collection: Obtain a single blood sample from each participant at baseline.

Laboratory Analysis:

Platelet Isolation: Extract platelets from blood samples. RNA Sequencing: Perform transcriptomic profiling to identify RNA expression patterns.

Data Analysis:

AI Integration: Use machine learning algorithms to analyze RNA data and identify biomarkers indicative of cancer presence.

Statistical Evaluation: Assess sensitivity and specificity of the diagnostic tool, and evaluate its ability to differentiate between cancer types.

Expected Outcomes:

Identification of reliable RNA biomarkers for early cancer detection. Validation of the AI-based diagnostic tool's accuracy and feasibility in a clinical setting.

Phase 2 (CIPHER): Therapeutic Response Monitoring

Objective:

To evaluate how RNA biomarkers from immune cells and platelets correlate with therapeutic responses, providing insights into treatment efficacy and potential relapse.

Methodology:

Participant Recruitment: Enroll 1,000 cancer patients diagnosed with HCC or NSCLC across stages I to IV.

Sample Collection:

Baseline: Collect blood samples before therapy initiation. Follow-Up: Additional samples at 6 weeks and 6 months post-therapy initiation.

Laboratory Analysis:

Isolation of Immune Cells and Platelets: Extract these components from blood samples.

Transcriptomic Profiling: Analyse RNA expression changes over time.

Data Analysis:

Correlation Studies: Evaluate associations between RNA biomarkers and clinical treatment responses.

Predictive Modelling: Develop models integrating platelet and immune cell RNA profiles to predict outcomes.

Expected Outcomes:

Identification of biomarkers that correlate with treatment responses and progression-free survival.

Development of predictive models for relapse and drug resistance.

Significance of the Study

The CCANED-CIPHER study addresses critical needs in oncology by providing:

Non-Invasive Diagnostics: A blood test that reduces the need for invasive tissue biopsies.

Early Detection: Potential for identifying cancers at an earlier, more treatable stage.

Personalised Medicine: Tailored treatment strategies based on individual biomarker profiles.

Improved Monitoring: Enhanced ability to monitor treatment effectiveness and adjust therapies accordingly.

Predictive Insights: Early detection of relapse or drug resistance, enabling prompt clinical interventions.

Expected Impact and Future Applications By integrating advanced AI technologies with innovative liquid biopsy methods, the CCANED-CIPHER study aims to significantly improve cancer detection and patient outcomes. The identification of specific RNA biomarkers from platelets and immune cells has the potential to transform current practices in oncology, offering a more efficient, accurate, and patient-friendly approach to cancer care.

Basic Information
|
Recruitment & Eligibility
|
Study & Design
|
Trial Locations

Study Timeline

• Study First Submitted: 2024-11-28
• Status Verified: 2024-12
• Study First Submitted QC: 2024-12-03
• Study First Posted: 2024-12-05
• Last Update Submitted: 2024-12-11
• Last Update Posted: 2024-12-13
• Study Start: 2025-03-01
• Primary Completion: 2027-03-01
• Study Completion: 2028-03-01

Recruitment & Eligibility

• Status: NOT_YET_RECRUITING
• Sex: All
• Target Recruitment: 6000

Inclusion Criteria

• Age: Adults aged 40 years or older.
• Confirmed diagnosis of one of the following common cancers: Non-Small Cell Lung Cancer (NSCLC), Glioblastoma Multiforme (GBM), Colorectal Cancer, Hepatocellular Carcinoma (HCC), Breast Cancer, Prostate Cancer, Ovarian Cancer, Pancreatic Cancer.

Read More

Exclusion Criteria

• Currently pregnant.
• Presence of any active infectious diseases.
• Use of anticoagulant or antiplatelet drugs within the past 2 weeks.
• Any medical or psychological conditions that may affect the participant's ability to comply with study procedures.

Phase 2 (CIPHER)

Inclusion Criteria:

• Adults aged 40 years or older.
• Confirmed diagnosis of: Hepatocellular Carcinoma (HCC), Non-Small Cell Lung Cancer (NSCLC)
• Willingness to provide blood samples at the specified intervals (baseline, 6 weeks, and 6 months post-therapy initiation).

Exclusion Criteria:

• Presence of another malignancy unless it has been in remission for at least 5 years.
• Significant uncontrolled co-morbid conditions that may interfere with study participation or outcomes.

Read More

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
Identification of Platelet RNA Biomarkers Distinguishing Cancer Patients from Controls	Baseline (single time point)	Utilise AI-based transcriptomic analysis of platelet RNA to identify biomarkers that differentiate between cancer patients and cancer-free controls.
Identification of RNA Biomarkers Correlating with Therapeutic Response (Phase 2)	Baseline to 6 months post-therapy initiation	Identify RNA biomarkers from immune cells and platelets that correlate with clinical treatment response, as measured by standard criteria (e.g., RECIST)
Association Between Immune Cell Transcriptomes and AI-Based Platelet Signals	Baseline to 6 months post-therapy initiation	Evaluate how changes in immune cell transcriptomes are associated with signals detected by the AI-based platelet profiling tool.

Secondary Outcome Measures

Name	Time	Method
Sensitivity and Specificity of the AI-Based Diagnostic Tool (Phase 1)	Baseline	Calculate the diagnostic accuracy of the AI-based tool in detecting cancer among participants.
Feasibility of Platelet Transcriptomic Profiling Implementation	Phase 1 - 2 years	Assess the practicality of sample collection, processing, and analysis in a clinical setting.
Development of Predictive Models for Treatment Outcomes (Phase 2)	Phase 2 - Two years	Create and validate predictive models that integrate platelet and immune cell RNA profiles to predict treatment response and progression-free survival.
Identification of Biomarkers Predictive of Relapse and Drug Resistance (Phase 2)	Baseline to 6 months post-therapy initiation	Identify RNA biomarkers predictive of relapse and drug resistance at the 6-month follow-up.

Trial Locations

Locations (3)

Various Cancer Centres; 🇦🇷 Rosario, Argentina

NSIA- Lagos University Teaching Hospital Cancer Centre; 🇳🇬 Lagos, Nigeria

Dysplasia Diagnostics Limited; 🇬🇧 London, United Kingdom