Abstract 262MO
Background
There are nearly half patients with Ras wild-type metastatic colorectal cancer (mCRC) do not response to Anti-EGFR therapy. Identification of patients who are sensitive to anti-EGFR therapy may increase the response rate and reduce the adverse effect. Therefore, there is a pressing need for predicting the efficacy and the clinical benefit in RAS wild type patients. In this study, we aimed to develop and validate a multi-omics deep learning model to predict cetuximab efficacy in RAS wild type mCRC patients.
Methods
In this study, we retrospectively analyzed 213 Ras wild type mCRC patients. Patients in the Arm A (FOLFOX + cetuximab) of CHINESE study (J Clin Oncol 2013, NCT01564810) make up the training set and patients in CHINESE follow-up study (PMID: 30305811) make up the validation set. External multi-omics testing set was derived from an independent cohort and the Arm B (FOLFOX) of the CHINESE study. Based on the deep learning framework Pytorch, we first built the radiomic and genetic signature. Next, we passed the CT images and gene data into the trained ResNet18 and Random Forest and then we sum the output probabilities of two models with a weight of 3:7 to obtain the classification probability of the fusion model.
Results
The signature (area under the ROC curve) successfully predict sensitivity to anti-EGFR therapy (The radiomic signature: 0.63; the genetic signature: 0.72; the fusion signature: 0.81) but failed with chemotherapy (The fusion signature: 0.55). In cetuximab-containing sets, the fusion signature outperformed existing biomarkers for detection of treatment sensitivity and was strongly associated with progression free survival (P<.005).
Conclusions
The multi-omic signature can serve as an intermediate surrogate marker of anti-EGFR treatment sensitivity and survival. The signature outperformed known biomarkers in providing an early prediction of treatment sensitivity and could be used to Ras wild type mCRC treatment decisions.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
256MO - Decoding the cryptic stroma: Molecular cancer associated fibroblast 1 & 4 imaging allied with mesenchymal stroma to tumor content as a radiation dose bio-predictive signature to augur the future in locally advanced esophageal cancer
Presenter: G Lohith
Session: Mini Oral session: Developmental and precision medicine
Resources:
Abstract
Slides
Webcast
257MO - Integrating AI and ML with lung cancer diagnostics: A step ahead
Presenter: Shrinidhi Nathany
Session: Mini Oral session: Developmental and precision medicine
Resources:
Abstract
Slides
Webcast
258MO - Discovery of synergistic effect for triple-negative breast cancer immunotherapy using tumor-microenvironment-on-chip
Presenter: Hsuan Yu Mu
Session: Mini Oral session: Developmental and precision medicine
Resources:
Abstract
Slides
Webcast
259MO - A predictive score of cancer immunotherapy responses based on ecological analysis of gut microbiota
Presenter: Lisa Derosa
Session: Mini Oral session: Developmental and precision medicine
Resources:
Abstract
Slides
Webcast
Invited Discussant 256MO, 257MO, 258MO and 259MO
Presenter: Christophe Massard
Session: Mini Oral session: Developmental and precision medicine
Resources:
Webcast
Q&A and discussion
Presenter: Christophe Massard
Session: Mini Oral session: Developmental and precision medicine
Resources:
Slides
Webcast
260MO - Liquid biopsy NGS test identifies actionable DNA mutations from CSF specimens of lung cancer patients
Presenter: John Chia
Session: Mini Oral session: Developmental and precision medicine
Resources:
Abstract
Slides
Webcast
261MO - Real-world data on prevalence of MSI-H/dMMR across 6 solid tumor types in Asia
Presenter: David SP Tan
Session: Mini Oral session: Developmental and precision medicine
Resources:
Abstract
Slides
Webcast
263MO - Variant allele frequency and copy number gain in EGFR mutated lung cancer: A menace or a boon?
Presenter: Ullas Batra
Session: Mini Oral session: Developmental and precision medicine
Resources:
Abstract
Slides
Webcast
Invited Discussant 260MO, 261MO, 262MO and 263MO
Presenter: Kaname Nosaki
Session: Mini Oral session: Developmental and precision medicine
Resources:
Slides
Webcast