| CTRI Number |
CTRI/2025/07/089931 [Registered on: 01/07/2025] Trial Registered Prospectively |
| Last Modified On: |
26/06/2025 |
| Post Graduate Thesis |
No |
| Type of Trial |
Observational |
|
Type of Study
|
Retrospective |
| Study Design |
Other |
|
Public Title of Study
|
A Study Using AI and H&E Tissue Images with Omics Data to Predict Genetic Changes and Clinical Outcomes in Cancer Patients. |
|
Scientific Title of Study
|
AI-Driven Model for Predicting Genomic Alterations and Clinical Outcomes Using H and E Imaging with Omics Data Integration |
| Trial Acronym |
NIL |
|
Secondary IDs if Any
|
| Secondary ID |
Identifier |
| NIL |
NIL |
|
|
Details of Principal Investigator or overall Trial Coordinator (multi-center study)
|
| Name |
Dr Ashok Kumar Vaid |
| Designation |
Chairman- Medanta Cancer Institute |
| Affiliation |
Medanta- The Medicity |
| Address |
Sector 38, Gurugram, Haryana, India- 122001
Gurgaon
HARYANA
122001
India |
| Phone |
9810212235 |
| Fax |
|
| Email |
ashok.vaidmier@medanta.org |
|
Details of Contact Person
Scientific Query
|
| Name |
Dr Ashok Kumar Vaid |
| Designation |
Chairman- Medanta Cancer Institute |
| Affiliation |
Medanta- The Medicity |
| Address |
Sector 38, Gurugram, Haryana, India- 122001
HARYANA
122001
India |
| Phone |
9810212235 |
| Fax |
|
| Email |
ashok.vaidmier@medanta.org |
|
Details of Contact Person
Public Query
|
| Name |
Dr Ashok Kumar Vaid |
| Designation |
Chairman- Medanta Cancer Institute |
| Affiliation |
Medanta- The Medicity |
| Address |
Sector 38, Gurugram, Haryana, India- 122001
HARYANA
122001
India |
| Phone |
9810212235 |
| Fax |
|
| Email |
ashok.vaidmier@medanta.org |
|
|
Source of Monetary or Material Support
|
| Canary Oncoceutics India Private Limited |
|
|
Primary Sponsor
|
| Name |
Canary Oncoceutics India Private Limited |
| Address |
RMZ,MILLENIA BUSINESS PARK ,CAMPUS 1A ,NO 143, DR. M.G.R. RO, AD NORTH VEERANAM SALAI SHOLIGANALLUR Pe, Saidapet, Kanchipuram, Tamil Nadu - 600096 |
| Type of Sponsor |
Other [cancer diagnostics company] |
|
|
Details of Secondary Sponsor
|
|
|
Countries of Recruitment
|
India |
|
Sites of Study
|
| No of Sites = 1 |
| Name of Principal
Investigator |
Name of Site |
Site Address |
Phone/Fax/Email |
| Dr Ashok Kumar Vaid |
Medanta-The Medicity |
Room No. 21, Medanta Cancer Institute, Sector- 38, Gurugram, Haryana, India-122001
Gurgaon
HARYANA |
9810212235
ashok.vaidmier@medanta.org |
|
|
Details of Ethics Committee
|
| No of Ethics Committees= 1 |
| Name of Committee |
Approval Status |
| Medanta Institutional Ethics Committee |
Approved |
|
|
Regulatory Clearance Status from DCGI
|
|
|
Health Condition / Problems Studied
|
| Health Type |
Condition |
| Patients |
(1) ICD-10 Condition: C509||Malignant neoplasm of breast of unspecified site, (2) ICD-10 Condition: C189||Malignant neoplasm of colon, unspecified, (3) ICD-10 Condition: C760||Malignant neoplasm of head, face and neck, (4) ICD-10 Condition: C228||Malignant neoplasm of liver, primary, unspecified as to type, (5) ICD-10 Condition: C399||Malignant neoplasm of lower respiratory tract, part unspecified, (6) ICD-10 Condition: C508||Malignant neoplasm of overlappingsites of breast, (7) ICD-10 Condition: C61||Malignant neoplasm of prostate, (8) ICD-10 Condition: C20||Malignant neoplasm of rectum, (9) ICD-10 Condition: C390||Malignant neoplasm of upper respiratory tract, part unspecified, |
|
|
Intervention / Comparator Agent
|
| Type |
Name |
Details |
| Intervention |
Nil |
Nil |
|
|
Inclusion Criteria
|
| Age From |
18.00 Year(s) |
| Age To |
90.00 Year(s) |
| Gender |
Both |
| Details |
1. To be eligible for the study, participants must have a confirmed diagnosis of cancer based on histopathological assessment.
2. They must also have archival FFPE tumor tissue available for multi-omics and AI-based analysis, with a minimum tumor nuclei content of 50% to ensure reliable genomic profiling.
3. Clinical data, including demographics, treatment history, and survival outcomes, must be available for retrospective analysis.
4. In case of prospective recruitment, newly diagnosed patients must provide written informed consent for genomic profiling and AI-assisted predictions. |
|
| ExclusionCriteria |
| Details |
1. Patients will be excluded if their tumor samples are of insufficient quality or quantity for sequencing and AI-based histopathology analysis.
2. Those who have undergone neoadjuvant chemotherapy or radiotherapy before sample collection will be excluded to avoid confounding genomic alterations.
3. Additionally, samples with artifacts, excessive necrosis, or poor resolution in H&E slides will be removed from analysis.
4. Lastly, genomic samples found to be contaminated or of poor sequencing quality during bioinformatics QC assessments will not be included in the study. |
|
|
Method of Generating Random Sequence
|
Not Applicable |
|
Method of Concealment
|
Not Applicable |
|
Blinding/Masking
|
Not Applicable |
|
Primary Outcome
|
| Outcome |
TimePoints |
| The primary outcomes include AI model accuracy in classifying tumors and predicting genomic alterations, metastasis, and survival. |
In the first phase, a retrospective analysis will be performed on 50,000 cancer tissue samples across multiple tumor types, where multi-omics profiling and histopathological imaging will be used to discover novel biomarkers. |
|
|
Secondary Outcome
|
| Outcome |
TimePoints |
| Secondary outcomes include assessing the AI model’s ability to predict patient response to chemotherapy, immunotherapy, and targeted therapy. The effectiveness of AI-driven risk stratification will be validated against treatment response rates, progression-free survival, and overall survival. |
In the second phase, AI model will be trained using data from these retrospective cohorts, allowing for precise classification of tumor subtypes based on their genomic and histological features. The final phase will involve validation using an independent cohort of patients, where AI-driven predictions will be tested against molecular and clinical outcomes. |
|
|
Target Sample Size
|
Total Sample Size="50000"
Sample Size from India="50000"
Final Enrollment numbers achieved (Total)= "Applicable only for Completed/Terminated trials"
Final Enrollment numbers achieved (India)="Applicable only for Completed/Terminated trials" |
|
Phase of Trial
|
N/A |
|
Date of First Enrollment (India)
|
10/07/2025 |
| Date of Study Completion (India) |
Applicable only for Completed/Terminated trials |
| Date of First Enrollment (Global) |
Date Missing |
| Date of Study Completion (Global) |
Applicable only for Completed/Terminated trials |
|
Estimated Duration of Trial
|
Years="0"
Months="0"
Days="0" |
|
Recruitment Status of Trial (Global)
|
Not Applicable |
| Recruitment Status of Trial (India) |
Not Yet Recruiting |
|
Publication Details
|
N/A |
|
Individual Participant Data (IPD) Sharing Statement
|
Will individual participant data (IPD) be shared publicly (including data dictionaries)?
Response - NO
|
|
Brief Summary
|
This study aims to create an advanced computer model using artificial intelligence (AI) to help doctors better understand and treat cancer. By analyzing tissue samples from 50,000 cancer patients, the model will learn to recognize patterns in microscope images of tumors (called H&E images) and match them with important genetic information. The goal is to predict how aggressive a cancer is, whether it’s likely to spread, how long a patient might survive, and how well they may respond to certain treatments like chemotherapy or immunotherapy. This could help doctors make faster, more accurate decisions about personalized treatment—without always needing expensive and time-consuming genetic tests. In short, this AI tool could help bring more precise, faster, and cost-effective cancer care to patients by using information that’s already routinely collected during diagnosis |