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
382P - Oral health disparities in privileged and underprivileged tribes of south India: A study of the prevalence of precancerous oral lesions
Presenter: Shanavas Palliyal
Session: Poster Display
Resources:
Abstract
383P - Pre-treatment body mass index and neutrophil lymphocyte ratio predict 3-years progression free survival in locally advanced stage nasopharyngeal carcinoma
Presenter: Ni Putu Pusvita Dewi
Session: Poster Display
Resources:
Abstract
384P - Sequential multi-modality strategies for locally advanced betel-nuts related hypopharyngeal cancer in Taiwan
Presenter: Wei-Chen Lu
Session: Poster Display
Resources:
Abstract
385P - The prognostic factors of induction chemotherapy followed by concurrent chemoradiotherapy in patients with HPV associated with oropharyngeal cancer
Presenter: Hyun Jin Bang
Session: Poster Display
Resources:
Abstract
386P - FOLR1 stabilized beta-catenin promotes laryngeal carcinoma progression through EGFR signal
Presenter: Huawei Tuo
Session: Poster Display
Resources:
Abstract
387P - A comprehensive analysis of the oral health status, tobacco use, and cancer prevalence among the tribal communities in India
Presenter: Delfin Lovelina Francis
Session: Poster Display
Resources:
Abstract
388P - Clinicopathological correlation of P53 expression in oral cancers
Presenter: Venkata Madhavi Bellala
Session: Poster Display
Resources:
Abstract
389P - Lack of cross-resistance to erlotinib in human head and neck cancer cells with acquired resistance to cetuximab
Presenter: James A. Bonner
Session: Poster Display
Resources:
Abstract
390P - Epidemiological aspects of the development of oral cancer in the Republic of Uzbekistan
Presenter: Akhrorbek Yusupbekov
Session: Poster Display
Resources:
Abstract
391P - Lip cancer: Racial disparities, treatment modalities and long-term survival outcome in young and adults versus older age patients
Presenter: FathAlrahman Ibrahim
Session: Poster Display
Resources:
Abstract