Background: Colorectal cancer (CRC) is one of the most common malignancies, and early detection plays a crucial role in enhancing curative outcomes. While colonoscopy is considered the gold standard for CRC diagnosis, noninvasive screening methods of DNA methylation biomarkers can improve the early detection of CRC and precancerous lesions.
Methods: Bioinformatics and machine learning methods were used to evaluate CRC-related genes within the TCGA database. By identifying the overlapped genes, potential biomarkers were selected for further validation. Methylation-specific PCR (MSP) was utilized to identify the associated genes as biomarkers. Subsequently, a real-time PCR assay for detecting the presence of neoplasia or cancer of the colon or rectum was established. This screening approach involved the recruitment of 978 participants from five cohorts.
Results: The genes with the highest specificity and sensitivity were Septin9, AXL4, and SDC2. A total of 940 participants were involved in the establishment of the final PCR system and the subsequent performance evaluation test. A multiplex TaqMan real-time PCR system has been illustrated to greatly enhance the ability to detect precancerous lesions and achieved an accuracy of 87.8% (95% CI 82.9-91.5), a sensitivity of 82.7% (95% CI 71.8-90.1), and a specificity of 90.1% (95% CI 84.3-93.9). Moreover, the detection rate of precancerous lesions of this assay reached 55.0% (95% CI 38.7-70.4).
Conclusion: The combined detection of the methylation status of SEPT9, SDC2, and ALX4 in plasma holds the potential to further enhance the sensitivity of CRC detection.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10660402 | PMC |
http://dx.doi.org/10.1002/cam4.6511 | DOI Listing |
BMJ Open
January 2025
Global Health Working Group, Institute of Medical Epidemiology, Biometrics and Informatics, Martin Luther University Halle Wittenberg, Halle, Germany.
Introduction: The follow-up adherence after treatment for a positive screening test is critical for preventing the development of screen-detected abnormalities in cervical cancer. Yet, this poses a major challenge in developing countries like Ethiopia, emphasising the urgency for intervention strategies. Our trial aims to assess which strategies would be effective in improving adherence to follow-up after suspicious cervical lesion treatment in Ethiopia.
View Article and Find Full Text PDFChin Med
January 2025
School of Pharmacy, Hangzhou Normal University, Hangzhou, China.
Background: The individualized prediction and discrimination of precancerous lesions of gastric cancer (PLGC) is critical for the early prevention of gastric cancer (GC). However, accurate non-invasive methods for distinguishing between PLGC and GC are currently lacking. This study therefore aimed to develop a risk prediction model by machine learning and deep learning techniques to aid the early diagnosis of GC.
View Article and Find Full Text PDFInt J Mol Sci
December 2024
National Medical Research Center for Obstetrics, Gynecology and Perinatology Named After Academician V.I. Kulakov, Ministry of Healthcare of the Russian Federation, Moscow 117997, Russia.
Despite prevention strategies, cervical cancer remains a significant public health issue. Human papillomavirus plays a critical role in its development, and early detection is vital to improve patient outcomes. The incidence of cervical cancer is projected to rise, necessitating better diagnostic tools.
View Article and Find Full Text PDFLife (Basel)
November 2024
Clinical Omics Institute, Kyungpook National University, Daegu 41405, Republic of Korea.
Cervical cancer is a significant health challenge, yet it can be effectively prevented through early detection. Cytology-based screening is critical for identifying cancerous and precancerous lesions; however, the process is labor-intensive and reliant on trained experts to scan through hundreds of thousands of mostly normal cells. To address these challenges, we propose a novel distribution-augmented approach using contrastive self-supervised learning for detecting abnormal squamous cervical cells from cytological images.
View Article and Find Full Text PDFCancers (Basel)
December 2024
Machine and Hybrid Intelligence Lab, Feinberg School of Medicine, Northwestern University, Chicago, IL 60611, USA.
Pancreatic cystic lesions (PCLs) represent a spectrum of non-neoplasms and neoplasms with varying malignant potential, posing significant challenges in diagnosis and management. While some PCLs are precursors to pancreatic cancer, others remain benign, necessitating accurate differentiation for optimal patient care. Conventional approaches to PCL management rely heavily on radiographic imaging, and endoscopic ultrasound (EUS) guided fine-needle aspiration (FNA), coupled with clinical and biochemical data.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!