A clinical decision support system using decision tree and expert opinion in rectal cancer treatment

Since there are several criteria regarding the disease in treatment of colorectal cancer which is one of the important health problems in world; choosing the most appropriate treatment option concerning a patient is of great importance for the physician. While cancer of the colon and rectum is also called colorectal cancer, in the present study it was focused on the rectal part. It was aimed to create a system to support the decisions of the physician in order to determine the most appropriate treatment method for rectum cancer patients. A decision model was developed by combining the analytic hierarchy process method which is one of the multi criteria decision making techniques in operations research, and decision tree method. The treatment decision for a patient may be made with the use of priorities that obtained from analytic hierarchy process method by investigating criteria from the most prior to the least. The model that built by the use of a decision tree used previous patient data and expert opinions to suggest a treatment method, and showed survivals that obtained from patient data regarding the suggested treatment and literature review. Thus, the physician may make decision by taking survivals into account when there are various treatment suggestions for a particular patient. The real patient data application of decision model that built by combining analytic hierarchy process method and decision tree method was presented to the user by using a web-based application. The consistency of the clinical decision support system was evaluated by the experts. Due to the fact that this study supports a stepwise decision making process using patient data and disease criteria as well as expert knowledge, it is expected that the system may support the decision making process of the physician.