Decision Trees for Predicting Brain Tumors: A Case Study in Health Care
With the wide expansion of unstructured health data records, there is a need to organize in an effective manner and easy data access. The top-down approach can automatically assign the unstructured health records into a hierarchy with prior domain knowledge. Decision trees are reliable providing high classification accuracy with a simple representation of collected knowledge and effective decision-making technique that can be used in medical care. Decision trees can handle huge datasets with simple and fast integration. It is easy to predict the classification of unseen records using decision tree.
KeywordsDecision trees Health care Machine learning Supervised learning
We express our gratitude to our research guide Dr. I. V. Murali Krishna for his constant and excellent help with the innovative ideas. We also express our gratitude to Dr. Jacqueline Williams (Dean of Commerce, Loyola Academy, Secunderabad, India) for her efforts in carefully reading and giving valuable comments on the paper.
The performance of decision trees can be further increased by applying any criteria on the attributes. Prediction as well as classification of the brain anomalies can be done so that the tumor can be predicted as benign or malignant and further glioma or meningioma.
Conflicts of Interest
The authors declare that there are no conflicts of interest regarding the publication of this paper.
- 1.Huang et al (2017) Biomedical informatics with optimization and machine learning. J Bioinform Syst BiolGoogle Scholar
- 4.Hall LO et al. Decision tree learning on very large data setsGoogle Scholar
- 5.Ross Quinlan J (1994) C4.5: programs for machine learning. Morgan Kaufmann Publishers, Machine Learning, vol 16, Kluwer Academic Publishers, Boston (1994)Google Scholar
- 6.Podgorelec V et al (2002) Decision trees: an overview and their use in medicine. J Med SystGoogle Scholar