Discretization: An Enabling Technique
Data Mining and Knowledge Discovery
Financial distress prediction based on OR-CBR in the principle of k-nearest neighbors
Expert Systems with Applications: An International Journal
Global optimization of case-based reasoning for breast cytology diagnosis
Expert Systems with Applications: An International Journal
Review: Dimensionality reduction based on rough set theory: A review
Applied Soft Computing
Knowledge-based system for text classification using ID6NB algorithm
Knowledge-Based Systems
Computer Methods and Programs in Biomedicine
Hi-index | 0.00 |
Nowadays, a wide range of serum tumor markers can be applied in the diagnosis of colorectal cancer. There exists a wide variability in the type and number of routinely used markers so that, sometimes, patients may receive redundant or insufficient checks. Furthermore, the traditional single cutoff point also hinders the efficient utilization of the continuous check value of a tumor marker. In order to improve the diagnostic accuracy (DA) and decrease the cost, it is necessary to optimize the check combinations and exploit the check values fully. To this end, focusing on colorectal cancer (CRC), an artificial intelligent algorithm entitled DS-STM (diagnosis strategy of serum tumor makers) is developed in this paper. DS-STM can provide decision support for physicians on the usage of different tumor markers and diagnosis of colorectal cancer (CRC). The study demonstrates that, instead of five or more tumor markers, two markers are already enough for diagnosis for most CRC patients. The experimental study shows, compared to the traditional serial test, DS-STM can improve DA from 67.53% to 73.87% for the same validation dataset. In addition, a significant cost reduction can be achieved with the new developed diagnosis strategy.