Mo1627 - Deep Learning with Big Clinical Data for Prediction of Advanced Neoplasia in Colorectal Cancer Screening of Asymptomatic Adults

346 Background: There is increasing evidence that non-steroidal anti-inflammatory drugs, in particular aspirin, and statins can reduce the incidence and progression of colorectal cancer. However, studies examining this relationship within colorectal cancer screening are limited. Therefore the aim of the present study was to assess the impact of aspirin and statins on an individual’s risk of advanced neoplasia in a colorectal cancer screening programme. Methods: A prospectively maintained database of all patients in the first round of screening (April 2009 to March 2011) in our geographical was analysed. Medication usage was recorded prospectively at pre-colonoscopy assessment. The outcome measure was advanced neoplasia, which was defined as cancer or an intermediate or high risk adenomata (>2 polyps, or > 1 polyp >1cm). Results: 4,631 individuals underwent colonoscopy following a positive FOBt of which complete results were available for 4,188 (90%) pts. Overall, 657 (16%) were on aspirin, 880 (21%) were on statins and 537 (13%) were on both. Colorectal pathology was associated with a positive FOBt in 3,043 (73%) pts. Aspirin usage was associated with a reduced likelihood of colorectal pathology being identified (OR 0.79 (0.66-0.95) p=0.012). In the 3,043 pts in whom colorectal pathology was identified, advanced neoplasia was seen in 1,704 (56%) pts. Patients with advanced neoplasia were more likely to be older (OR 1.38 (1.19-1.59)) and male (OR 1.66 (1.43-1.94)) (both p<0.001). In contrast, those on aspirin (OR 0.68(0.56-0.83)), statins (OR 0.65 (0.55-0.78)) or both (OR 0.69 (0.55-0.86)) were less likely to have advanced neoplasia at colonoscopy (all p<0.001). On multivariate analysis, use of both aspirin and statins (OR 0.60 (0.48-0.75) p<0.001) remained independently associated with less advanced neoplasia. Conclusions: In patients undergoing colonoscopy following a positive FOBt with documented evidence of statin or aspirin usage, advanced neoplasia was less likely to be found. This suggests that usage of these medications may have a chemopreventative effect within the context of screening for colorectal cancer.

Download Full-text

Mo1175 Increment With Age of Proximal Advanced Neoplasia in Three Rounds of a Colorectal Cancer Screening by Immunochemical Fecal Occult Blood Testing

Gastroenterology ◽

10.1016/s0016-5085(13)62208-8 ◽

2013 ◽

Vol 144 (5) ◽

pp. S-598 ◽

Cited By ~ 1

Author(s):

Sergio Crotta ◽

Roberto Lolli ◽

Cristina Cerrato ◽

Francesca Valle ◽

Simona Paganin ◽

...

Keyword(s):

Colorectal Cancer ◽

Cancer Screening ◽

Colorectal Cancer Screening ◽

Occult Blood ◽

Fecal Occult Blood Testing ◽

Fecal Occult Blood ◽

Blood Testing ◽

Advanced Neoplasia ◽

Fecal Occult

Download Full-text

Intelligent recognition of colorectal cancer combining application of computer-assisted diagnosis with deep learning approaches

International Journal of Electrical and Computer Engineering (IJECE) ◽

10.11591/ijece.v12i1.pp738-747 ◽

2022 ◽

Vol 12 (1) ◽

pp. 738

Author(s):

Akella S. Narasimha Raju ◽

Kayalvizhi Jayavel ◽

Tulasi Rajalakshmi

Keyword(s):

Colorectal Cancer ◽

Deep Learning ◽

Cancer Screening ◽

Colorectal Cancer Screening ◽

Premalignant Lesions ◽

Computer Assisted ◽

Screening Methods ◽

Learning Approaches ◽

Computer Assisted Diagnosis ◽

Assisted Diagnosis

<span>The malignancy of the colorectal testing methods has been exposed triumph to decrease the occurrence and death rate; this cancer is the relatively sluggish rising and has an extremely peculiar to develop the premalignant lesions. Now, many patients are not going to colorectal cancer screening, and people who do, are able to diagnose existing tests and screening methods. The most important concept of this motivation for this research idea is to evaluate the recognized data from the immediately available colorectal cancer screening methods. The data provided to laboratory technologists is important in the formulation of appropriate recommendations that will reduce colorectal cancer. With all standard colon cancer tests can be recognized agitatedly, the treatment of colorectal cancer is more efficient. The intelligent computer assisted diagnosis (CAD) is the most powerful technique for recognition of colorectal cancer in recent advances. It is a lot to reduce the level of interference nature has contributed considerably to the advancement of the quality of cancer treatment. To enhance diagnostic accuracy intelligent CAD has a research always active, ongoing with the deep learning and machine learning approaches with the associated convolutional neural network (CNN) scheme.</span>

Download Full-text