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
26P - Subcutaneous trastuzumab versus intravenous trastuzumab for treatment of patients with HER2-positive breast cancer: A time, motion and cost-benefit assessment in a day care oncology unit in China
Presenter: Bei Sun
Session: Poster Display
Resources:
Abstract
27P - The biological characteristics of HER2-low in TNBC using mRNA profiling and molecular subtypes
Presenter: Asako Tsuruga
Session: Poster Display
Resources:
Abstract
28P - One-week ultra-hypofractionated partial breast RT in early breast cancer: 3DCRT vs IMRT
Presenter: Nurilla Zaynutdinov
Session: Poster Display
Resources:
Abstract
30P - Stereotactic body radiotherapy using cyberknife versus interstitial brachytherapy in accelerated partial breast irradiation on left-sided breast: A comparison of preliminary clinical result and dosimetric characteristics
Presenter: Ting-Na Wei
Session: Poster Display
Resources:
Abstract
31P - Prognostic implication of breast edema on preoperative breast MRI in breast cancer
Presenter: Ki-tae Hwang
Session: Poster Display
Resources:
Abstract
32P - Efficacy of olanzapine in the prophylaxis of delayed chemotherapy-induced nausea and vomiting in breast cancer patients receiving dose-dense AC with a steroid-sparing regimen: A single-center pilot study
Presenter: Manami Tada
Session: Poster Display
Resources:
Abstract
34P - Social support as the mediator of the association between unmet needs and happiness among women with early breast cancer
Presenter: Nithiya Sinarajoo
Session: Poster Display
Resources:
Abstract
35P - Prospective study assessing the efficacy and safety of a scalp cooling device for the prevention of alopecia in breast cancer patients undergoing (neo)adjuvant chemotherapy
Presenter: Winnie Yeo
Session: Poster Display
Resources:
Abstract
37P - To excise or not to excise: Preventive management of early breast cancer in atypical ductal hyperplasia patients
Presenter: Clarisse Hing
Session: Poster Display
Resources:
Abstract
38P - Exploring prognostic factors in patients achieving PCR after neoadjuvant therapy for triple-negative breast cancer: A retrospective study based on SEER data
Presenter: Lv Wenjie
Session: Poster Display
Resources:
Abstract