Artificial Intelligence in Colorectal Cancer Diagnosis Using Clinical Data: Non-Invasive Approach

• Published in: Diagnostics (Basel) Vol. 11; no. 3; p. 514
• Main Authors: Lorenzovici, Noémi, Dulf, Eva-H., Mocan, Teodora, Mocan, Lucian
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 14.03.2021; MDPI
• Subjects: Accuracy; Algorithms; Antigens; Artificial intelligence; Biomarkers; clinical data; Colonoscopy; Colorectal cancer; computer aided diagnostic system; Datasets; Deep learning; deep neural networks; Efficiency; Epigenetics; Glycoproteins; Machine learning; Medical diagnosis; Medical research; Patients; Plasma; Surgical outcomes; Tumors; colorectal cancer; computer aided diagnostic system; artificial intelligence; deep neural networks; clinical data
• ISSN: 2075-4418; 2075-4418
• DOI: 10.3390/diagnostics11030514

Colorectal cancer is the third most common and second most lethal tumor globally, causing 900,000 deaths annually. In this research, a computer aided diagnosis system was designed that detects colorectal cancer, using an innovative dataset composing of both numeric (blood and urine analysis) and qualitative data (living environment of the patient, tumor position, T, N, M, Dukes classification, associated pathology, technical approach, complications, incidents, ultrasonography-dimensions as well as localization). The intelligent computer aided colorectal cancer diagnosis system was designed using different machine learning techniques, such as classification and shallow and deep neural networks. The maximum accuracy obtained from solving the binary classification problem with traditional machine learning algorithms was 77.8%. However, the regression problem solved with deep neural networks yielded with significantly better performance in terms of mean squared error minimization, reaching the value of 0.0000529.