Abstract 623P
Background
Cancer ranks second globally in causes of death, accounting for 21% of all fatalities. However, many types of cancer can be cured if diagnosed and treated during early stages. We propose a liquid biopsy cancer analysis method that uses deep learning and a methylation-sensitive restriction enzyme digestion followed by sequencing method to detect and classify the most common cancers worldwide at early stages.
Methods
We developed a selective methylation sensitive restriction enzyme sequencing (MRE-Seq) method combined with a prediction model based on deep neural network (DNN) learning on data from 63,266 CpG sites to identify global hypomethylation patterns. The methylation dataset was made from 96 colon cancer samples, 95 lung cancer samples, 122 gastric cancer samples, 136 breast cancer samples, and 183 control samples. To eliminate batch bias, the ANOVA test was performed during feature selection. A DNN was adopted as a classifier, and 5-fold cross validation was performed to verify the classification performance.
Results
Across four cancer types, colorectal cancer had the highest predictive performance at 0.98, followed by breast cancer at 0.97, gastric cancer at 0.96, and lung cancer at 0.93. At 95% specificity, the sensitivity for detecting early-stage cancers varied widely, with lung cancer at 50% and breast cancer at 83%. Two different metrics were used to evaluate the model's performance. The cancer classifier (performance in detecting cancer) had a sensitivity of 95.1% and a specificity of 66.7%, indicating better performance in correctly identifying cancer samples. The cancer type classifier (performance in classifying the cancer type) utilized the precision metric to evaluate the accuracy of cancer classification. Notably, breast cancer achieved the highest precision at 95.8%, followed by lung cancer at 83.3%, gastric cancer at 79.1%, and colon cancer at 69.0%.
Conclusions
The proposed classification model based on the MRE-Seq method can reliably identify cancer and normal samples and differentiate between different cancer types using only methylation information obtained from patient's blood. This approach could be used in clinical practices to help medical experts diagnose cancer earlier and at the individual level.
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
484P - Treatment (tx) patterns and outcomes in resectable early-stage EGFR-mutated (EGFRm) NSCLC in South Korea: Subgroup analysis of a global real-world (rw) study
Presenter: Myung-Ju Ahn
Session: Poster Display
Resources:
Abstract
485P - LDCT lung cancer screening of never-smokers meta-analysis subgroup analysis: Adenocarcinoma is the highly predictive histology identified in never-smokers
Presenter: Sai-Hong Ou
Session: Poster Display
Resources:
Abstract
486P - Fiscal feasibility and implications of integrating lung cancer screening into Hong Kong’s healthcare system
Presenter: Herbert Ho Fung Loong
Session: Poster Display
Resources:
Abstract
487P - Evaluating the performance of the USPSTF lung cancer screening guidelines in an Asian population of lung cancer patients
Presenter: Jian Wei Tan
Session: Poster Display
Resources:
Abstract
488P - Pulmonary ground glass opacity lesions: Immune ecosystem and its clinical relevances of early-stage lung adenocarcinoma
Presenter: Shensi Shen
Session: Poster Display
Resources:
Abstract
489TiP - BGB-LC-202 (NCT05577702): Phase II Umbrella study of tislelizumab (TIS) monotherapy and TIS-based immunotherapy combinations +/- chemotherapy (CT) as neoadjuvant treatment in Chinese patients (pts) with resectable stage II to IIIA non-small cell lung cancer (NSCLC)
Presenter: Wentao Yu
Session: Poster Display
Resources:
Abstract
491P - Furmonertinib as adjuvant therapy for elderly patients in resected EGFR-mutated non-small cell lung cancer: A double-center, real-world experience
Presenter: Ziheng Wu
Session: Poster Display
Resources:
Abstract
492P - Penpulimab-based combination neoadjuvant/adjuvant therapy for patients with resectable locally advanced non-small cell lung cancer: Preliminary results from a phase II study (ALTER-L043)
Presenter: Changli Wang
Session: Poster Display
Resources:
Abstract
493P - The prognostic value of 4L lymph node dissection in left-sided operable non-small cell lung cancer: A systematic review and meta-analysis
Presenter: Lei Peng
Session: Poster Display
Resources:
Abstract
495P - Intrinsic STING of CD8+T cells regulates self-metabolic reprogramming and exerts anti-tumor effects
Presenter: Qiuli Xu
Session: Poster Display
Resources:
Abstract